diff --git a/README.md b/README.md index 0a46256..da9b7a8 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,4 @@ -## Searching for A Robust Neural Architecture in Four GPU Hours +## [Searching for A Robust Neural Architecture in Four GPU Hours](http://xuanyidong.com/publication/gradient-based-diff-sampler/) We propose A Gradient-based neural architecture search approach using Differentiable Architecture Sampler (GDAS). diff --git a/data/decompress.py b/data/decompress.py index 032cb0e..f2b6c43 100644 --- a/data/decompress.py +++ b/data/decompress.py @@ -16,10 +16,21 @@ def execute(cmds, idx, num): def command(prefix, cmd): #print ('{:}{:}'.format(prefix, cmd)) #if execute: os.system(cmd) + #xcmd = '(echo {:} $(date +\"%Y-%h-%d--%T\") \"PID:\"$$; {:}; sleep 0.1s)'.format(prefix, cmd) + #xcmd = '(echo {:} $(date +\"%Y-%h-%d--%T\") \"PID:\"$$; {:}; sleep 0.1s; pmap $$; echo \"\")'.format(prefix, cmd) + #xcmd = '(echo {:} $(date +\"%Y-%h-%d--%T\") \"PID:\"$$; {:}; sleep 0.1s; pmap $$; echo \"\")'.format(prefix, cmd) xcmd = '(echo {:} $(date +\"%Y-%h-%d--%T\") \"PID:\"$$; {:}; sleep 0.1s)'.format(prefix, cmd) return xcmd +def mkILSVRC2012(destination): + destination = destination.resolve() + destination.mkdir(parents=True, exist_ok=True) + os.system('rm -rf {:}'.format(destination)) + destination.mkdir(parents=True, exist_ok=True) + (destination/'train').mkdir(parents=True, exist_ok=True) + + def main(source, destination, xtype): assert source.exists(), '{:} does not exist'.format(source) assert (source/'train' ).exists(), '{:}/train does not exist'.format(source) @@ -28,25 +39,21 @@ def main(source, destination, xtype): else : raise ValueError('invalid unzip type : {:}'.format(xtype)) #assert num_process > 0, 'invalid num_process : {:}'.format(num_process) source = source.resolve() - destination = destination.resolve() - destination.mkdir(parents=True, exist_ok=True) - os.system('rm -rf {:}'.format(destination)) - destination.mkdir(parents=True, exist_ok=True) - (destination/'train').mkdir(parents=True, exist_ok=True) + mkILSVRC2012(destination) subdirs = list( (source / 'train').glob('n*') ) all_commands = [] assert len(subdirs) == 1000, 'ILSVRC2012 should contain 1000 classes instead of {:}.'.format( len(subdirs) ) - if xtype == 'tar' : cmd = command('', 'tar -xf {:} -C {:}'.format(source/'val.tar', destination)) - elif xtype == 'zip': cmd = command('', 'unzip -qd {:} {:}'.format(destination, source/'val.zip')) - else : raise ValueError('invalid unzip type : {:}'.format(xtype)) - all_commands.append( cmd ) for idx, subdir in enumerate(subdirs): name = subdir.name if xtype == 'tar' : cmd = command('{:03d}/{:03d}-th: '.format(idx, len(subdirs)), 'tar -xf {:} -C {:}'.format(source/'train'/'{:}'.format(name), destination / 'train')) elif xtype == 'zip': cmd = command('{:03d}/{:03d}-th: '.format(idx, len(subdirs)), 'unzip -qd {:} {:}'.format(destination / 'train', source/'train'/'{:}'.format(name))) else : raise ValueError('invalid unzip type : {:}'.format(xtype)) all_commands.append( cmd ) + if xtype == 'tar' : cmd = command('', 'tar -xf {:} -C {:}'.format(source/'val.tar', destination)) + elif xtype == 'zip': cmd = command('', 'unzip -qd {:} {:}'.format(destination, source/'val.zip')) + else : raise ValueError('invalid unzip type : {:}'.format(xtype)) + all_commands.append( cmd ) #print ('Collect all commands done : {:} lines'.format( len(all_commands) )) for i, cmd in enumerate(all_commands): @@ -70,4 +77,18 @@ if __name__ == '__main__': assert len(sys.argv) == 4, 'invalid argv : {:}'.format(sys.argv) source, destination = Path(sys.argv[1]), Path(sys.argv[2]) #num_process = int(sys.argv[3]) - main(source, destination, sys.argv[3]) + if sys.argv[3] == 'wget': + with open(source) as f: + content = f.readlines() + content = [x.strip() for x in content] + assert len(content) == 1000, 'invalid lines={:} from {:}'.format( len(content), source ) + mkILSVRC2012(destination) + all_commands = [] + cmd = command('make-val', 'wget -q http://10.127.2.44:8000/ILSVRC2012-TAR/val.tar --directory-prefix={:} ; tar -xf {:} -C {:} ; rm {:}'.format(destination, destination / 'val.tar', destination, destination / 'val.tar')) + all_commands.append(cmd) + for idx, name in enumerate(content): + cmd = command('{:03d}/{:03d}-th: '.format(idx, len(content)), 'wget -q http://10.127.2.44:8000/ILSVRC2012-TAR/train/{:}.tar --directory-prefix={:} ; tar -xf {:}.tar -C {:} ; rm {:}.tar'.format(name, destination / 'train', destination / 'train' / name, destination / 'train', destination / 'train' / name)) + all_commands.append(cmd) + for i, cmd in enumerate(all_commands): print(cmd) + else: + main(source, destination, sys.argv[3]) diff --git a/data/load_data_CUHK-PEDES.py b/data/load_data_CUHK-PEDES.py new file mode 100755 index 0000000..3a74878 --- /dev/null +++ b/data/load_data_CUHK-PEDES.py @@ -0,0 +1,15 @@ +import json + +def main(): + xpath = 'caption_all.json' + with open(xpath, 'r') as cfile: + cap_data = json.load(cfile) + print ('There are {:} images'.format( len(cap_data) )) + IDs = set() + for idx, data in enumerate( cap_data ): + IDs.add( data['id'] ) + assert len( data['captions'] ) > 0, 'invalid {:}-th caption length : {:} {:}'.format(idx, data['captions'], len(data['captions'])) + print ('IDs :: min={:}, max={:}, num={:}'.format(min(IDs), max(IDs), len(IDs))) + +if __name__ == '__main__': + main() diff --git a/data/logs/GDAS_V1-imagenet-seed-3993.txt b/data/logs/GDAS_V1-imagenet-seed-3993.txt new file mode 100755 index 0000000..2f8f8e1 --- /dev/null +++ b/data/logs/GDAS_V1-imagenet-seed-3993.txt @@ -0,0 +1,15895 @@ +save path : ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993 +{'arch': 'DMS_V1', 'data_path': '/home/dxy/.torch/ILSVRC2012', 'dataset': 'imagenet', 'grad_clip': 5.0, 'init_channels': 50, 'layers': 14, 'manualSeed': 3993, 'model_config': './configs/nas-imagenet.config', 'print_freq': 200, 'save_path': './snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993', 'workers': 20} +Random Seed: 3993 +Python version : 3.6.5 |Anaconda, Inc.| (default, Apr 29 2018, 16:14:56) [GCC 7.2.0] +Torch version : 0.4.1 +CUDA version : 9.0.176 +cuDNN version : 7102 +Num of GPUs : 1 +configuration : Configure(type='steplr', batch_size=128, epochs=250, decay_period=1, gamma=0.97, momentum=0.9, decay=3e-05, LR=0.1, label_smooth=0.1, auxiliary=True, auxiliary_weight=0.4, grad_clip=5.0, drop_path_prob=0.0) +genotype : Genotype(normal=[('skip_connect', 0, 0.13017432391643524), ('skip_connect', 1, 0.12947972118854523), ('skip_connect', 0, 0.13062666356563568), ('sep_conv_5x5', 2, 0.12980839610099792), ('sep_conv_3x3', 3, 0.12923765182495117), ('skip_connect', 0, 0.12901571393013), ('sep_conv_5x5', 4, 0.12938997149467468), ('sep_conv_3x3', 3, 0.1289220005273819)], normal_concat=range(2, 6), reduce=[('sep_conv_5x5', 0, 0.12862831354141235), ('sep_conv_3x3', 1, 0.12783904373645782), ('sep_conv_5x5', 2, 0.12725995481014252), ('sep_conv_5x5', 1, 0.12705285847187042), ('dil_conv_5x5', 2, 0.12797553837299347), ('sep_conv_3x3', 1, 0.12737272679805756), ('sep_conv_5x5', 0, 0.12833961844444275), ('sep_conv_5x5', 1, 0.12758426368236542)], reduce_concat=range(2, 6)) +-------------------------------------- main-procedure +config : Configure(type='steplr', batch_size=128, epochs=250, decay_period=1, gamma=0.97, momentum=0.9, decay=3e-05, LR=0.1, label_smooth=0.1, auxiliary=True, auxiliary_weight=0.4, grad_clip=5.0, drop_path_prob=0.0) +genotype : Genotype(normal=[('skip_connect', 0, 0.13017432391643524), ('skip_connect', 1, 0.12947972118854523), ('skip_connect', 0, 0.13062666356563568), ('sep_conv_5x5', 2, 0.12980839610099792), ('sep_conv_3x3', 3, 0.12923765182495117), ('skip_connect', 0, 0.12901571393013), ('sep_conv_5x5', 4, 0.12938997149467468), ('sep_conv_3x3', 3, 0.1289220005273819)], normal_concat=range(2, 6), reduce=[('sep_conv_5x5', 0, 0.12862831354141235), ('sep_conv_3x3', 1, 0.12783904373645782), ('sep_conv_5x5', 2, 0.12725995481014252), ('sep_conv_5x5', 1, 0.12705285847187042), ('dil_conv_5x5', 2, 0.12797553837299347), ('sep_conv_3x3', 1, 0.12737272679805756), ('sep_conv_5x5', 0, 0.12833961844444275), ('sep_conv_5x5', 1, 0.12758426368236542)], reduce_concat=range(2, 6)) +init_channels : 50 +layers : 14 +class_num : 1000 +Network => +NetworkImageNet( + (stem0): Sequential( + (0): Conv2d(3, 25, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) + (1): BatchNorm2d(25, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (2): ReLU(inplace) + (3): Conv2d(25, 50, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) + (4): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + (stem1): Sequential( + (0): ReLU(inplace) + (1): Conv2d(50, 50, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) + (2): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + (cells): ModuleList( + (0): Cell( + (preprocess0): FactorizedReduce( + (relu): ReLU() + (conv_1): Conv2d(50, 25, kernel_size=(1, 1), stride=(2, 2), bias=False) + (conv_2): Conv2d(50, 25, kernel_size=(1, 1), stride=(2, 2), bias=False) + (bn): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (pad): ConstantPad2d(padding=(0, 1, 0, 1), value=0) + ) + (preprocess1): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (_ops): ModuleList( + (0): Identity() + (1): Identity() + (2): Identity() + (3): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(50, 50, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=50, bias=False) + (2): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(50, 50, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=50, bias=False) + (6): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (4): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(50, 50, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=50, bias=False) + (2): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(50, 50, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=50, bias=False) + (6): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (5): Identity() + (6): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(50, 50, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=50, bias=False) + (2): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(50, 50, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=50, bias=False) + (6): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (7): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(50, 50, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=50, bias=False) + (2): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(50, 50, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=50, bias=False) + (6): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + ) + ) + (1): Cell( + (preprocess0): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (preprocess1): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (_ops): ModuleList( + (0): Identity() + (1): Identity() + (2): Identity() + (3): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(50, 50, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=50, bias=False) + (2): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(50, 50, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=50, bias=False) + (6): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (4): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(50, 50, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=50, bias=False) + (2): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(50, 50, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=50, bias=False) + (6): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (5): Identity() + (6): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(50, 50, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=50, bias=False) + (2): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(50, 50, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=50, bias=False) + (6): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (7): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(50, 50, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=50, bias=False) + (2): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(50, 50, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=50, bias=False) + (6): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + ) + ) + (2): Cell( + (preprocess0): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (preprocess1): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (_ops): ModuleList( + (0): Identity() + (1): Identity() + (2): Identity() + (3): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(50, 50, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=50, bias=False) + (2): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(50, 50, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=50, bias=False) + (6): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (4): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(50, 50, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=50, bias=False) + (2): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(50, 50, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=50, bias=False) + (6): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (5): Identity() + (6): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(50, 50, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=50, bias=False) + (2): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(50, 50, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=50, bias=False) + (6): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (7): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(50, 50, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=50, bias=False) + (2): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(50, 50, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=50, bias=False) + (6): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + ) + ) + (3): Cell( + (preprocess0): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (preprocess1): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (_ops): ModuleList( + (0): Identity() + (1): Identity() + (2): Identity() + (3): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(50, 50, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=50, bias=False) + (2): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(50, 50, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=50, bias=False) + (6): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (4): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(50, 50, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=50, bias=False) + (2): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(50, 50, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=50, bias=False) + (6): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (5): Identity() + (6): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(50, 50, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=50, bias=False) + (2): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(50, 50, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=50, bias=False) + (6): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (7): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(50, 50, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=50, bias=False) + (2): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(50, 50, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=50, bias=False) + (6): Conv2d(50, 50, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + ) + ) + (4): Cell( + (preprocess0): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (preprocess1): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (_ops): ModuleList( + (0): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (1): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (2): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (3): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (4): DilConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(4, 4), dilation=(2, 2), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (5): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (6): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (7): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + ) + ) + (5): Cell( + (preprocess0): FactorizedReduce( + (relu): ReLU() + (conv_1): Conv2d(200, 50, kernel_size=(1, 1), stride=(2, 2), bias=False) + (conv_2): Conv2d(200, 50, kernel_size=(1, 1), stride=(2, 2), bias=False) + (bn): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (pad): ConstantPad2d(padding=(0, 1, 0, 1), value=0) + ) + (preprocess1): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(400, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (_ops): ModuleList( + (0): Identity() + (1): Identity() + (2): Identity() + (3): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (4): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (5): Identity() + (6): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (7): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + ) + ) + (6): Cell( + (preprocess0): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(400, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (preprocess1): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(400, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (_ops): ModuleList( + (0): Identity() + (1): Identity() + (2): Identity() + (3): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (4): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (5): Identity() + (6): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (7): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + ) + ) + (7): Cell( + (preprocess0): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(400, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (preprocess1): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(400, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (_ops): ModuleList( + (0): Identity() + (1): Identity() + (2): Identity() + (3): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (4): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (5): Identity() + (6): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (7): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + ) + ) + (8): Cell( + (preprocess0): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(400, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (preprocess1): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(400, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (_ops): ModuleList( + (0): Identity() + (1): Identity() + (2): Identity() + (3): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (4): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (5): Identity() + (6): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (7): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(100, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=100, bias=False) + (2): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(100, 100, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=100, bias=False) + (6): Conv2d(100, 100, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + ) + ) + (9): Cell( + (preprocess0): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(400, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (preprocess1): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(400, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (_ops): ModuleList( + (0): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (1): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (2): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (3): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (4): DilConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(4, 4), dilation=(2, 2), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (5): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (6): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (7): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + ) + ) + (10): Cell( + (preprocess0): FactorizedReduce( + (relu): ReLU() + (conv_1): Conv2d(400, 100, kernel_size=(1, 1), stride=(2, 2), bias=False) + (conv_2): Conv2d(400, 100, kernel_size=(1, 1), stride=(2, 2), bias=False) + (bn): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (pad): ConstantPad2d(padding=(0, 1, 0, 1), value=0) + ) + (preprocess1): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(800, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (_ops): ModuleList( + (0): Identity() + (1): Identity() + (2): Identity() + (3): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (4): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (5): Identity() + (6): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (7): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + ) + ) + (11): Cell( + (preprocess0): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(800, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (preprocess1): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(800, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (_ops): ModuleList( + (0): Identity() + (1): Identity() + (2): Identity() + (3): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (4): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (5): Identity() + (6): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (7): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + ) + ) + (12): Cell( + (preprocess0): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(800, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (preprocess1): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(800, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (_ops): ModuleList( + (0): Identity() + (1): Identity() + (2): Identity() + (3): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (4): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (5): Identity() + (6): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (7): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + ) + ) + (13): Cell( + (preprocess0): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(800, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (preprocess1): ReLUConvBN( + (op): Sequential( + (0): ReLU() + (1): Conv2d(800, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (2): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (_ops): ModuleList( + (0): Identity() + (1): Identity() + (2): Identity() + (3): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (4): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (5): Identity() + (6): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + (7): SepConv( + (op): Sequential( + (0): ReLU() + (1): Conv2d(200, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=200, bias=False) + (2): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU() + (5): Conv2d(200, 200, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=200, bias=False) + (6): Conv2d(200, 200, kernel_size=(1, 1), stride=(1, 1), bias=False) + (7): BatchNorm2d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + ) + ) + ) + ) + ) + (auxiliary_head): AuxiliaryHeadImageNet( + (features): Sequential( + (0): ReLU(inplace) + (1): AvgPool2d(kernel_size=5, stride=2, padding=0) + (2): Conv2d(800, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) + (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) + (4): ReLU(inplace) + (5): Conv2d(128, 768, kernel_size=(2, 2), stride=(1, 1), bias=False) + (6): ReLU(inplace) + ) + (classifier): Linear(in_features=768, out_features=1000, bias=True) + ) + (global_pooling): AvgPool2d(kernel_size=7, stride=7, padding=0) + (classifier): Linear(in_features=800, out_features=1000, bias=True) +) +Parameters : 6.609947 - 1.264872 = 5.345 MB +config : Configure(type='steplr', batch_size=128, epochs=250, decay_period=1, gamma=0.97, momentum=0.9, decay=3e-05, LR=0.1, label_smooth=0.1, auxiliary=True, auxiliary_weight=0.4, grad_clip=5.0, drop_path_prob=0.0) +genotype : Genotype(normal=[('skip_connect', 0, 0.13017432391643524), ('skip_connect', 1, 0.12947972118854523), ('skip_connect', 0, 0.13062666356563568), ('sep_conv_5x5', 2, 0.12980839610099792), ('sep_conv_3x3', 3, 0.12923765182495117), ('skip_connect', 0, 0.12901571393013), ('sep_conv_5x5', 4, 0.12938997149467468), ('sep_conv_3x3', 3, 0.1289220005273819)], normal_concat=range(2, 6), reduce=[('sep_conv_5x5', 0, 0.12862831354141235), ('sep_conv_3x3', 1, 0.12783904373645782), ('sep_conv_5x5', 2, 0.12725995481014252), ('sep_conv_5x5', 1, 0.12705285847187042), ('dil_conv_5x5', 2, 0.12797553837299347), ('sep_conv_3x3', 1, 0.12737272679805756), ('sep_conv_5x5', 0, 0.12833961844444275), ('sep_conv_5x5', 1, 0.12758426368236542)], reduce_concat=range(2, 6)) +Train-Dataset : Dataset ImageFolder + Number of datapoints: 1281167 + Root Location: /home/dxy/.torch/ILSVRC2012/train + Transforms (if any): Compose( + RandomResizedCrop(size=(224, 224), scale=(0.08, 1.0), ratio=(0.75, 1.3333), interpolation=PIL.Image.BILINEAR) + RandomHorizontalFlip(p=0.5) + ColorJitter(brightness=0.4, contrast=0.4, saturation=0.4, hue=0.2) + ToTensor() + Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) + ) + Target Transforms (if any): None +Valid--Dataset : Dataset ImageFolder + Number of datapoints: 50000 + Root Location: /home/dxy/.torch/ILSVRC2012/val + Transforms (if any): Compose( + Resize(size=256, interpolation=PIL.Image.BILINEAR) + CenterCrop(size=(224, 224)) + ToTensor() + Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) + ) + Target Transforms (if any): None +Args : Namespace(arch='DMS_V1', data_path='/home/dxy/.torch/ILSVRC2012', dataset='imagenet', grad_clip=5.0, init_channels=50, layers=14, manualSeed=3993, model_config='./configs/nas-imagenet.config', print_freq=200, save_path='./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993', workers=20) +Load checkpoint from ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth with start-epoch = 8 + +==>>[2018-10-11-03:34:36] [Epoch=008/250] [Need: 00:00:00] LR=0.0784 ~ 0.0784, Batch=128 + train[2018-10-11-03:34:44] Epoch: [008][000/10010] Time 7.89 (7.89) Data 4.54 (4.54) Loss 4.907 (4.907) Prec@1 42.97 (42.97) Prec@5 65.62 (65.62) + train[2018-10-11-03:36:29] Epoch: [008][200/10010] Time 0.54 (0.56) Data 0.00 (0.02) Loss 4.856 (4.716) Prec@1 41.41 (45.79) Prec@5 66.41 (69.76) + train[2018-10-11-03:38:13] Epoch: [008][400/10010] Time 0.53 (0.54) Data 0.00 (0.01) Loss 4.507 (4.687) Prec@1 49.22 (46.17) Prec@5 74.22 (70.38) + train[2018-10-11-03:39:56] Epoch: [008][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 4.980 (4.689) Prec@1 43.75 (46.10) Prec@5 71.09 (70.37) + train[2018-10-11-03:41:41] Epoch: [008][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 4.767 (4.687) Prec@1 42.19 (46.21) Prec@5 66.41 (70.42) + train[2018-10-11-03:43:24] Epoch: [008][1000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 4.294 (4.688) Prec@1 51.56 (46.19) Prec@5 74.22 (70.34) + train[2018-10-11-03:45:09] Epoch: [008][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 4.390 (4.687) Prec@1 48.44 (46.18) Prec@5 75.78 (70.37) + train[2018-10-11-03:46:53] Epoch: [008][1400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 4.939 (4.692) Prec@1 39.06 (46.06) Prec@5 66.41 (70.27) + train[2018-10-11-03:48:36] Epoch: [008][1600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 5.031 (4.693) Prec@1 37.50 (46.00) Prec@5 69.53 (70.28) + train[2018-10-11-03:50:20] Epoch: [008][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.683 (4.695) Prec@1 43.75 (45.96) Prec@5 68.75 (70.23) + train[2018-10-11-03:52:04] Epoch: [008][2000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.866 (4.697) Prec@1 42.97 (45.92) Prec@5 68.75 (70.18) + train[2018-10-11-03:53:48] Epoch: [008][2200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.292 (4.698) Prec@1 51.56 (45.92) Prec@5 74.22 (70.18) + train[2018-10-11-03:55:31] Epoch: [008][2400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.507 (4.699) Prec@1 50.78 (45.87) Prec@5 75.78 (70.17) + train[2018-10-11-03:57:14] Epoch: [008][2600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.583 (4.701) Prec@1 47.66 (45.85) Prec@5 72.66 (70.14) + train[2018-10-11-03:58:59] Epoch: [008][2800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.594 (4.701) Prec@1 50.00 (45.82) Prec@5 71.88 (70.14) + train[2018-10-11-04:00:42] Epoch: [008][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.341 (4.700) Prec@1 52.34 (45.82) Prec@5 74.22 (70.15) + train[2018-10-11-04:02:27] Epoch: [008][3200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.636 (4.698) Prec@1 42.97 (45.82) Prec@5 69.53 (70.16) + train[2018-10-11-04:04:10] Epoch: [008][3400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.668 (4.699) Prec@1 46.09 (45.81) Prec@5 71.88 (70.15) + train[2018-10-11-04:05:54] Epoch: [008][3600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.728 (4.700) Prec@1 42.97 (45.80) Prec@5 67.19 (70.13) + train[2018-10-11-04:07:38] Epoch: [008][3800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.709 (4.701) Prec@1 46.09 (45.78) Prec@5 71.88 (70.11) + train[2018-10-11-04:09:22] Epoch: [008][4000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.700 (4.699) Prec@1 48.44 (45.81) Prec@5 71.09 (70.16) + train[2018-10-11-04:11:06] Epoch: [008][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.523 (4.698) Prec@1 51.56 (45.81) Prec@5 74.22 (70.16) + train[2018-10-11-04:12:50] Epoch: [008][4400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.759 (4.700) Prec@1 43.75 (45.78) Prec@5 68.75 (70.13) + train[2018-10-11-04:14:33] Epoch: [008][4600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.456 (4.700) Prec@1 47.66 (45.77) Prec@5 78.12 (70.13) + train[2018-10-11-04:16:17] Epoch: [008][4800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.965 (4.700) Prec@1 42.19 (45.76) Prec@5 65.62 (70.14) + train[2018-10-11-04:18:01] Epoch: [008][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.760 (4.701) Prec@1 42.97 (45.75) Prec@5 67.19 (70.13) + train[2018-10-11-04:19:46] Epoch: [008][5200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.880 (4.702) Prec@1 38.28 (45.74) Prec@5 66.41 (70.11) + train[2018-10-11-04:21:30] Epoch: [008][5400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.519 (4.702) Prec@1 47.66 (45.73) Prec@5 75.00 (70.11) + train[2018-10-11-04:23:14] Epoch: [008][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.686 (4.703) Prec@1 43.75 (45.72) Prec@5 70.31 (70.10) + train[2018-10-11-04:24:58] Epoch: [008][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.367 (4.703) Prec@1 47.66 (45.72) Prec@5 78.12 (70.10) + train[2018-10-11-04:26:42] Epoch: [008][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.972 (4.702) Prec@1 42.19 (45.72) Prec@5 64.06 (70.11) + train[2018-10-11-04:28:26] Epoch: [008][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.793 (4.703) Prec@1 47.66 (45.71) Prec@5 71.09 (70.11) + train[2018-10-11-04:30:09] Epoch: [008][6400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.441 (4.702) Prec@1 49.22 (45.72) Prec@5 71.09 (70.11) + train[2018-10-11-04:31:53] Epoch: [008][6600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.551 (4.702) Prec@1 49.22 (45.74) Prec@5 71.88 (70.12) + train[2018-10-11-04:33:37] Epoch: [008][6800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.533 (4.702) Prec@1 48.44 (45.72) Prec@5 67.97 (70.12) + train[2018-10-11-04:35:20] Epoch: [008][7000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.213 (4.701) Prec@1 51.56 (45.74) Prec@5 78.91 (70.11) + train[2018-10-11-04:37:05] Epoch: [008][7200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 5.034 (4.701) Prec@1 44.53 (45.74) Prec@5 67.97 (70.11) + train[2018-10-11-04:38:49] Epoch: [008][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.492 (4.700) Prec@1 48.44 (45.74) Prec@5 71.88 (70.12) + train[2018-10-11-04:40:33] Epoch: [008][7600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.420 (4.700) Prec@1 48.44 (45.74) Prec@5 70.31 (70.12) + train[2018-10-11-04:42:17] Epoch: [008][7800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.859 (4.700) Prec@1 44.53 (45.75) Prec@5 69.53 (70.13) + train[2018-10-11-04:44:01] Epoch: [008][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.676 (4.700) Prec@1 39.84 (45.75) Prec@5 67.19 (70.12) + train[2018-10-11-04:45:45] Epoch: [008][8200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.694 (4.700) Prec@1 44.53 (45.76) Prec@5 68.75 (70.14) + train[2018-10-11-04:47:28] Epoch: [008][8400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.665 (4.699) Prec@1 49.22 (45.76) Prec@5 71.88 (70.14) + train[2018-10-11-04:49:12] Epoch: [008][8600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.783 (4.699) Prec@1 44.53 (45.76) Prec@5 74.22 (70.14) + train[2018-10-11-04:50:56] Epoch: [008][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 5.039 (4.699) Prec@1 37.50 (45.77) Prec@5 66.41 (70.15) + train[2018-10-11-04:52:40] Epoch: [008][9000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.557 (4.698) Prec@1 47.66 (45.76) Prec@5 74.22 (70.15) + train[2018-10-11-04:54:23] Epoch: [008][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 5.003 (4.698) Prec@1 32.81 (45.76) Prec@5 62.50 (70.15) + train[2018-10-11-04:56:07] Epoch: [008][9400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.599 (4.698) Prec@1 48.44 (45.75) Prec@5 70.31 (70.15) + train[2018-10-11-04:57:51] Epoch: [008][9600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.609 (4.698) Prec@1 43.75 (45.76) Prec@5 71.09 (70.16) + train[2018-10-11-04:59:35] Epoch: [008][9800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 5.066 (4.697) Prec@1 42.97 (45.76) Prec@5 62.50 (70.17) + train[2018-10-11-05:01:19] Epoch: [008][10000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.747 (4.697) Prec@1 46.09 (45.77) Prec@5 68.75 (70.18) + train[2018-10-11-05:01:24] Epoch: [008][10009/10010] Time 1.04 (0.52) Data 0.00 (0.00) Loss 4.733 (4.697) Prec@1 53.33 (45.77) Prec@5 73.33 (70.18) +[2018-10-11-05:01:24] **train** Prec@1 45.77 Prec@5 70.18 Error@1 54.23 Error@5 29.82 Loss:4.697 + test [2018-10-11-05:01:29] Epoch: [008][000/391] Time 4.76 (4.76) Data 4.61 (4.61) Loss 1.339 (1.339) Prec@1 74.22 (74.22) Prec@5 88.28 (88.28) + test [2018-10-11-05:01:56] Epoch: [008][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 2.775 (1.973) Prec@1 39.84 (54.42) Prec@5 66.41 (80.42) + test [2018-10-11-05:02:21] Epoch: [008][390/391] Time 0.32 (0.15) Data 0.00 (0.01) Loss 3.668 (2.177) Prec@1 32.50 (51.26) Prec@5 51.25 (76.80) +[2018-10-11-05:02:21] **test** Prec@1 51.26 Prec@5 76.80 Error@1 48.74 Error@5 23.20 Loss:2.177 +----> Best Accuracy : Acc@1=51.26, Acc@5=76.80, Error@1=48.74, Error@5=23.20 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-11-05:02:21] [Epoch=009/250] [Need: 352:28:11] LR=0.0760 ~ 0.0760, Batch=128 + train[2018-10-11-05:02:27] Epoch: [009][000/10010] Time 5.58 (5.58) Data 4.48 (4.48) Loss 4.504 (4.504) Prec@1 48.44 (48.44) Prec@5 73.44 (73.44) + train[2018-10-11-05:04:11] Epoch: [009][200/10010] Time 0.55 (0.55) Data 0.00 (0.02) Loss 4.718 (4.635) Prec@1 45.31 (46.84) Prec@5 70.31 (71.18) + train[2018-10-11-05:05:55] Epoch: [009][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 4.634 (4.626) Prec@1 44.53 (46.85) Prec@5 71.88 (71.20) + train[2018-10-11-05:07:39] Epoch: [009][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 4.232 (4.617) Prec@1 53.12 (46.97) Prec@5 76.56 (71.34) + train[2018-10-11-05:09:24] Epoch: [009][800/10010] Time 0.56 (0.53) Data 0.00 (0.01) Loss 4.518 (4.623) Prec@1 51.56 (46.90) Prec@5 72.66 (71.27) + train[2018-10-11-05:11:07] Epoch: [009][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 4.687 (4.629) Prec@1 43.75 (46.74) Prec@5 75.00 (71.19) + train[2018-10-11-05:12:51] Epoch: [009][1200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.758 (4.630) Prec@1 42.19 (46.68) Prec@5 70.31 (71.14) + train[2018-10-11-05:14:34] Epoch: [009][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.836 (4.630) Prec@1 40.62 (46.68) Prec@5 69.53 (71.10) + train[2018-10-11-05:16:18] Epoch: [009][1600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.411 (4.629) Prec@1 49.22 (46.74) Prec@5 71.88 (71.12) + train[2018-10-11-05:18:02] Epoch: [009][1800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.941 (4.628) Prec@1 38.28 (46.72) Prec@5 63.28 (71.12) + train[2018-10-11-05:19:46] Epoch: [009][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.489 (4.627) Prec@1 51.56 (46.74) Prec@5 71.88 (71.15) + train[2018-10-11-05:21:30] Epoch: [009][2200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.921 (4.626) Prec@1 40.62 (46.80) Prec@5 64.84 (71.15) + train[2018-10-11-05:23:14] Epoch: [009][2400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.481 (4.623) Prec@1 49.22 (46.83) Prec@5 73.44 (71.19) + train[2018-10-11-05:24:58] Epoch: [009][2600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.264 (4.622) Prec@1 51.56 (46.87) Prec@5 79.69 (71.23) + train[2018-10-11-05:26:41] Epoch: [009][2800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.453 (4.623) Prec@1 50.78 (46.81) Prec@5 70.31 (71.21) + train[2018-10-11-05:28:25] Epoch: [009][3000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 5.171 (4.623) Prec@1 42.97 (46.80) Prec@5 69.53 (71.23) + train[2018-10-11-05:30:09] Epoch: [009][3200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 5.058 (4.623) Prec@1 41.41 (46.80) Prec@5 65.62 (71.24) + train[2018-10-11-05:31:52] Epoch: [009][3400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.384 (4.623) Prec@1 48.44 (46.78) Prec@5 71.88 (71.22) + train[2018-10-11-05:33:35] Epoch: [009][3600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.724 (4.624) Prec@1 47.66 (46.75) Prec@5 68.75 (71.21) + train[2018-10-11-05:35:19] Epoch: [009][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.778 (4.623) Prec@1 48.44 (46.77) Prec@5 68.75 (71.20) + train[2018-10-11-05:37:03] Epoch: [009][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.969 (4.625) Prec@1 42.19 (46.74) Prec@5 71.09 (71.16) + train[2018-10-11-05:38:48] Epoch: [009][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.419 (4.626) Prec@1 49.22 (46.73) Prec@5 72.66 (71.15) + train[2018-10-11-05:40:31] Epoch: [009][4400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.538 (4.626) Prec@1 47.66 (46.75) Prec@5 72.66 (71.16) + train[2018-10-11-05:42:15] Epoch: [009][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.159 (4.628) Prec@1 53.91 (46.73) Prec@5 77.34 (71.15) + train[2018-10-11-05:43:59] Epoch: [009][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 5.011 (4.628) Prec@1 39.06 (46.73) Prec@5 64.06 (71.13) + train[2018-10-11-05:45:43] Epoch: [009][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.587 (4.628) Prec@1 45.31 (46.73) Prec@5 71.09 (71.14) + train[2018-10-11-05:47:27] Epoch: [009][5200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.534 (4.628) Prec@1 52.34 (46.74) Prec@5 75.00 (71.14) + train[2018-10-11-05:49:11] Epoch: [009][5400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.699 (4.628) Prec@1 42.19 (46.73) Prec@5 70.31 (71.14) + train[2018-10-11-05:50:56] Epoch: [009][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.264 (4.628) Prec@1 50.00 (46.74) Prec@5 78.12 (71.16) + train[2018-10-11-05:52:39] Epoch: [009][5800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.820 (4.629) Prec@1 42.97 (46.71) Prec@5 68.75 (71.14) + train[2018-10-11-05:54:23] Epoch: [009][6000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.774 (4.628) Prec@1 42.97 (46.72) Prec@5 68.75 (71.16) + train[2018-10-11-05:56:07] Epoch: [009][6200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.769 (4.629) Prec@1 46.88 (46.73) Prec@5 69.53 (71.16) + train[2018-10-11-05:57:51] Epoch: [009][6400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.575 (4.629) Prec@1 47.66 (46.74) Prec@5 71.09 (71.14) + train[2018-10-11-05:59:35] Epoch: [009][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.821 (4.629) Prec@1 46.09 (46.73) Prec@5 67.19 (71.14) + train[2018-10-11-06:01:19] Epoch: [009][6800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.417 (4.629) Prec@1 50.78 (46.75) Prec@5 75.78 (71.14) + train[2018-10-11-06:03:03] Epoch: [009][7000/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 4.655 (4.629) Prec@1 46.88 (46.75) Prec@5 70.31 (71.14) + train[2018-10-11-06:04:47] Epoch: [009][7200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.796 (4.628) Prec@1 42.97 (46.76) Prec@5 67.97 (71.15) + train[2018-10-11-06:06:30] Epoch: [009][7400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.814 (4.628) Prec@1 39.84 (46.76) Prec@5 70.31 (71.15) + train[2018-10-11-06:08:14] Epoch: [009][7600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.665 (4.629) Prec@1 47.66 (46.76) Prec@5 68.75 (71.15) + train[2018-10-11-06:09:57] Epoch: [009][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.783 (4.628) Prec@1 46.88 (46.78) Prec@5 64.84 (71.16) + train[2018-10-11-06:11:41] Epoch: [009][8000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.478 (4.628) Prec@1 43.75 (46.79) Prec@5 71.09 (71.16) + train[2018-10-11-06:13:25] Epoch: [009][8200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.313 (4.627) Prec@1 50.00 (46.80) Prec@5 82.03 (71.16) + train[2018-10-11-06:15:09] Epoch: [009][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.776 (4.628) Prec@1 50.78 (46.79) Prec@5 68.75 (71.15) + train[2018-10-11-06:16:52] Epoch: [009][8600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.661 (4.627) Prec@1 46.88 (46.80) Prec@5 68.75 (71.16) + train[2018-10-11-06:18:36] Epoch: [009][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 5.124 (4.627) Prec@1 37.50 (46.81) Prec@5 65.62 (71.16) + train[2018-10-11-06:20:19] Epoch: [009][9000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.340 (4.627) Prec@1 49.22 (46.82) Prec@5 76.56 (71.16) + train[2018-10-11-06:22:03] Epoch: [009][9200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.830 (4.627) Prec@1 43.75 (46.82) Prec@5 67.97 (71.16) + train[2018-10-11-06:23:47] Epoch: [009][9400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.758 (4.627) Prec@1 45.31 (46.82) Prec@5 70.31 (71.15) + train[2018-10-11-06:25:31] Epoch: [009][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.778 (4.627) Prec@1 48.44 (46.82) Prec@5 68.75 (71.16) + train[2018-10-11-06:27:15] Epoch: [009][9800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.914 (4.627) Prec@1 45.31 (46.82) Prec@5 64.06 (71.15) + train[2018-10-11-06:28:58] Epoch: [009][10000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.400 (4.627) Prec@1 47.66 (46.81) Prec@5 74.22 (71.15) + train[2018-10-11-06:29:02] Epoch: [009][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 5.647 (4.627) Prec@1 40.00 (46.81) Prec@5 60.00 (71.14) +[2018-10-11-06:29:02] **train** Prec@1 46.81 Prec@5 71.14 Error@1 53.19 Error@5 28.86 Loss:4.627 + test [2018-10-11-06:29:06] Epoch: [009][000/391] Time 3.57 (3.57) Data 3.43 (3.43) Loss 1.257 (1.257) Prec@1 76.56 (76.56) Prec@5 90.62 (90.62) + test [2018-10-11-06:29:34] Epoch: [009][200/391] Time 0.14 (0.16) Data 0.00 (0.02) Loss 3.122 (1.863) Prec@1 34.38 (56.50) Prec@5 62.50 (82.01) + test [2018-10-11-06:29:59] Epoch: [009][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 3.208 (2.117) Prec@1 36.25 (52.55) Prec@5 57.50 (77.71) +[2018-10-11-06:29:59] **test** Prec@1 52.55 Prec@5 77.71 Error@1 47.45 Error@5 22.29 Loss:2.117 +----> Best Accuracy : Acc@1=52.55, Acc@5=77.71, Error@1=47.45, Error@5=22.29 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-11-06:29:59] [Epoch=010/250] [Need: 350:30:29] LR=0.0737 ~ 0.0737, Batch=128 + train[2018-10-11-06:30:03] Epoch: [010][000/10010] Time 4.34 (4.34) Data 3.72 (3.72) Loss 4.785 (4.785) Prec@1 42.19 (42.19) Prec@5 71.09 (71.09) + train[2018-10-11-06:31:47] Epoch: [010][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 4.826 (4.556) Prec@1 43.75 (47.97) Prec@5 67.19 (72.24) + train[2018-10-11-06:33:32] Epoch: [010][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 4.799 (4.550) Prec@1 46.88 (48.06) Prec@5 66.41 (72.21) + train[2018-10-11-06:35:15] Epoch: [010][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 4.664 (4.554) Prec@1 50.78 (48.07) Prec@5 71.88 (72.13) + train[2018-10-11-06:36:59] Epoch: [010][800/10010] Time 0.52 (0.52) Data 0.00 (0.01) Loss 4.230 (4.548) Prec@1 50.00 (48.06) Prec@5 74.22 (72.22) + train[2018-10-11-06:38:44] Epoch: [010][1000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.598 (4.559) Prec@1 48.44 (47.95) Prec@5 69.53 (72.08) + train[2018-10-11-06:40:28] Epoch: [010][1200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.771 (4.561) Prec@1 43.75 (47.91) Prec@5 67.19 (72.01) + train[2018-10-11-06:42:12] Epoch: [010][1400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.664 (4.562) Prec@1 46.09 (47.89) Prec@5 70.31 (71.97) + train[2018-10-11-06:43:56] Epoch: [010][1600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 5.097 (4.562) Prec@1 42.97 (47.89) Prec@5 61.72 (71.98) + train[2018-10-11-06:45:40] Epoch: [010][1800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.588 (4.564) Prec@1 44.53 (47.84) Prec@5 68.75 (71.95) + train[2018-10-11-06:47:24] Epoch: [010][2000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.540 (4.566) Prec@1 40.62 (47.79) Prec@5 75.78 (71.93) + train[2018-10-11-06:49:07] Epoch: [010][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.631 (4.565) Prec@1 40.62 (47.79) Prec@5 73.44 (71.93) + train[2018-10-11-06:50:51] Epoch: [010][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.589 (4.566) Prec@1 51.56 (47.76) Prec@5 74.22 (71.91) + train[2018-10-11-06:52:35] Epoch: [010][2600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.107 (4.566) Prec@1 56.25 (47.75) Prec@5 78.12 (71.92) + train[2018-10-11-06:54:19] Epoch: [010][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.729 (4.568) Prec@1 50.78 (47.75) Prec@5 65.62 (71.89) + train[2018-10-11-06:56:03] Epoch: [010][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.776 (4.569) Prec@1 39.84 (47.72) Prec@5 71.09 (71.87) + train[2018-10-11-06:57:47] Epoch: [010][3200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.217 (4.569) Prec@1 53.12 (47.71) Prec@5 78.91 (71.86) + train[2018-10-11-06:59:31] Epoch: [010][3400/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 4.766 (4.569) Prec@1 46.09 (47.73) Prec@5 66.41 (71.89) + train[2018-10-11-07:01:15] Epoch: [010][3600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.874 (4.568) Prec@1 45.31 (47.73) Prec@5 71.09 (71.89) + train[2018-10-11-07:02:59] Epoch: [010][3800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.489 (4.569) Prec@1 48.44 (47.72) Prec@5 71.88 (71.89) + train[2018-10-11-07:04:43] Epoch: [010][4000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.957 (4.568) Prec@1 46.09 (47.72) Prec@5 70.31 (71.90) + train[2018-10-11-07:06:28] Epoch: [010][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.333 (4.568) Prec@1 48.44 (47.72) Prec@5 76.56 (71.90) + train[2018-10-11-07:08:12] Epoch: [010][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.210 (4.568) Prec@1 51.56 (47.71) Prec@5 78.12 (71.89) + train[2018-10-11-07:09:56] Epoch: [010][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.760 (4.569) Prec@1 44.53 (47.70) Prec@5 72.66 (71.90) + train[2018-10-11-07:11:40] Epoch: [010][4800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.843 (4.569) Prec@1 42.97 (47.70) Prec@5 67.97 (71.89) + train[2018-10-11-07:13:24] Epoch: [010][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.623 (4.569) Prec@1 49.22 (47.71) Prec@5 71.88 (71.89) + train[2018-10-11-07:15:08] Epoch: [010][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.710 (4.569) Prec@1 42.97 (47.68) Prec@5 72.66 (71.89) + train[2018-10-11-07:16:53] Epoch: [010][5400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.311 (4.570) Prec@1 53.91 (47.68) Prec@5 77.34 (71.88) + train[2018-10-11-07:18:37] Epoch: [010][5600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.670 (4.570) Prec@1 43.75 (47.68) Prec@5 67.97 (71.87) + train[2018-10-11-07:20:21] Epoch: [010][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.410 (4.571) Prec@1 48.44 (47.66) Prec@5 75.78 (71.86) + train[2018-10-11-07:22:04] Epoch: [010][6000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.430 (4.572) Prec@1 51.56 (47.63) Prec@5 72.66 (71.84) + train[2018-10-11-07:23:49] Epoch: [010][6200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.518 (4.573) Prec@1 48.44 (47.60) Prec@5 72.66 (71.82) + train[2018-10-11-07:25:32] Epoch: [010][6400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.662 (4.574) Prec@1 46.88 (47.60) Prec@5 74.22 (71.82) + train[2018-10-11-07:27:16] Epoch: [010][6600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.313 (4.574) Prec@1 50.78 (47.60) Prec@5 75.78 (71.81) + train[2018-10-11-07:29:01] Epoch: [010][6800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.898 (4.574) Prec@1 42.97 (47.60) Prec@5 66.41 (71.82) + train[2018-10-11-07:30:44] Epoch: [010][7000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.549 (4.575) Prec@1 46.88 (47.59) Prec@5 74.22 (71.81) + train[2018-10-11-07:32:27] Epoch: [010][7200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.622 (4.574) Prec@1 50.00 (47.60) Prec@5 67.97 (71.82) + train[2018-10-11-07:34:11] Epoch: [010][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.608 (4.574) Prec@1 39.06 (47.60) Prec@5 68.75 (71.82) + train[2018-10-11-07:35:55] Epoch: [010][7600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.462 (4.574) Prec@1 49.22 (47.61) Prec@5 75.00 (71.83) + train[2018-10-11-07:37:39] Epoch: [010][7800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.429 (4.574) Prec@1 53.12 (47.61) Prec@5 75.00 (71.83) + train[2018-10-11-07:39:22] Epoch: [010][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.977 (4.573) Prec@1 47.66 (47.62) Prec@5 60.94 (71.84) + train[2018-10-11-07:41:06] Epoch: [010][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.852 (4.572) Prec@1 46.09 (47.63) Prec@5 67.97 (71.85) + train[2018-10-11-07:42:50] Epoch: [010][8400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.687 (4.573) Prec@1 47.66 (47.63) Prec@5 72.66 (71.86) + train[2018-10-11-07:44:34] Epoch: [010][8600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.484 (4.572) Prec@1 53.12 (47.63) Prec@5 74.22 (71.86) + train[2018-10-11-07:46:18] Epoch: [010][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.561 (4.572) Prec@1 51.56 (47.65) Prec@5 68.75 (71.86) + train[2018-10-11-07:48:02] Epoch: [010][9000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.872 (4.572) Prec@1 46.09 (47.64) Prec@5 67.19 (71.85) + train[2018-10-11-07:49:46] Epoch: [010][9200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.860 (4.572) Prec@1 46.09 (47.64) Prec@5 70.31 (71.85) + train[2018-10-11-07:51:30] Epoch: [010][9400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.839 (4.572) Prec@1 41.41 (47.64) Prec@5 71.09 (71.85) + train[2018-10-11-07:53:13] Epoch: [010][9600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.359 (4.572) Prec@1 47.66 (47.63) Prec@5 75.78 (71.85) + train[2018-10-11-07:54:57] Epoch: [010][9800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.604 (4.572) Prec@1 49.22 (47.63) Prec@5 75.00 (71.86) + train[2018-10-11-07:56:41] Epoch: [010][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.157 (4.572) Prec@1 53.91 (47.64) Prec@5 77.34 (71.86) + train[2018-10-11-07:56:46] Epoch: [010][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.333 (4.572) Prec@1 66.67 (47.64) Prec@5 73.33 (71.86) +[2018-10-11-07:56:46] **train** Prec@1 47.64 Prec@5 71.86 Error@1 52.36 Error@5 28.14 Loss:4.572 + test [2018-10-11-07:56:49] Epoch: [010][000/391] Time 3.70 (3.70) Data 3.55 (3.55) Loss 1.603 (1.603) Prec@1 67.19 (67.19) Prec@5 86.72 (86.72) + test [2018-10-11-07:57:17] Epoch: [010][200/391] Time 0.13 (0.16) Data 0.00 (0.02) Loss 2.402 (1.871) Prec@1 45.31 (57.58) Prec@5 79.69 (82.50) + test [2018-10-11-07:57:42] Epoch: [010][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 3.373 (2.085) Prec@1 30.00 (53.81) Prec@5 58.75 (78.69) +[2018-10-11-07:57:42] **test** Prec@1 53.81 Prec@5 78.69 Error@1 46.19 Error@5 21.31 Loss:2.085 +----> Best Accuracy : Acc@1=53.81, Acc@5=78.69, Error@1=46.19, Error@5=21.31 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-11-07:57:42] [Epoch=011/250] [Need: 349:25:17] LR=0.0715 ~ 0.0715, Batch=128 + train[2018-10-11-07:57:47] Epoch: [011][000/10010] Time 4.35 (4.35) Data 3.77 (3.77) Loss 4.186 (4.186) Prec@1 59.38 (59.38) Prec@5 76.56 (76.56) + train[2018-10-11-07:59:31] Epoch: [011][200/10010] Time 0.54 (0.54) Data 0.00 (0.02) Loss 4.618 (4.536) Prec@1 50.78 (48.13) Prec@5 70.31 (72.16) + train[2018-10-11-08:01:15] Epoch: [011][400/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 4.174 (4.503) Prec@1 58.59 (48.80) Prec@5 76.56 (72.56) + train[2018-10-11-08:03:00] Epoch: [011][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 4.358 (4.502) Prec@1 52.34 (48.74) Prec@5 75.78 (72.56) + train[2018-10-11-08:04:43] Epoch: [011][800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.407 (4.506) Prec@1 53.91 (48.64) Prec@5 75.78 (72.63) + train[2018-10-11-08:06:26] Epoch: [011][1000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.824 (4.503) Prec@1 48.44 (48.70) Prec@5 64.06 (72.73) + train[2018-10-11-08:08:10] Epoch: [011][1200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.392 (4.506) Prec@1 50.00 (48.64) Prec@5 71.88 (72.72) + train[2018-10-11-08:09:54] Epoch: [011][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.194 (4.508) Prec@1 51.56 (48.65) Prec@5 78.12 (72.69) + train[2018-10-11-08:11:38] Epoch: [011][1600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.849 (4.510) Prec@1 41.41 (48.59) Prec@5 69.53 (72.69) + train[2018-10-11-08:13:21] Epoch: [011][1800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.617 (4.511) Prec@1 52.34 (48.57) Prec@5 66.41 (72.70) + train[2018-10-11-08:15:05] Epoch: [011][2000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.311 (4.509) Prec@1 52.34 (48.62) Prec@5 73.44 (72.73) + train[2018-10-11-08:16:49] Epoch: [011][2200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.645 (4.509) Prec@1 46.09 (48.65) Prec@5 71.09 (72.73) + train[2018-10-11-08:18:32] Epoch: [011][2400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.579 (4.509) Prec@1 51.56 (48.66) Prec@5 74.22 (72.71) + train[2018-10-11-08:20:14] Epoch: [011][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.215 (4.511) Prec@1 54.69 (48.63) Prec@5 76.56 (72.68) + train[2018-10-11-08:21:58] Epoch: [011][2800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.373 (4.512) Prec@1 50.00 (48.59) Prec@5 71.09 (72.67) + train[2018-10-11-08:23:42] Epoch: [011][3000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.436 (4.512) Prec@1 55.47 (48.61) Prec@5 78.91 (72.69) + train[2018-10-11-08:25:25] Epoch: [011][3200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.693 (4.513) Prec@1 46.09 (48.58) Prec@5 71.09 (72.68) + train[2018-10-11-08:27:09] Epoch: [011][3400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.156 (4.514) Prec@1 55.47 (48.55) Prec@5 78.12 (72.68) + train[2018-10-11-08:28:54] Epoch: [011][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.616 (4.515) Prec@1 45.31 (48.53) Prec@5 72.66 (72.65) + train[2018-10-11-08:30:38] Epoch: [011][3800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.449 (4.516) Prec@1 42.97 (48.52) Prec@5 72.66 (72.63) + train[2018-10-11-08:32:21] Epoch: [011][4000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.457 (4.516) Prec@1 53.12 (48.53) Prec@5 74.22 (72.63) + train[2018-10-11-08:34:05] Epoch: [011][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.325 (4.516) Prec@1 51.56 (48.54) Prec@5 75.00 (72.63) + train[2018-10-11-08:35:50] Epoch: [011][4400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.396 (4.517) Prec@1 50.00 (48.52) Prec@5 71.88 (72.61) + train[2018-10-11-08:37:34] Epoch: [011][4600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.443 (4.517) Prec@1 46.88 (48.51) Prec@5 70.31 (72.61) + train[2018-10-11-08:39:18] Epoch: [011][4800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.661 (4.518) Prec@1 42.97 (48.50) Prec@5 66.41 (72.59) + train[2018-10-11-08:41:02] Epoch: [011][5000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.603 (4.518) Prec@1 45.31 (48.50) Prec@5 73.44 (72.58) + train[2018-10-11-08:42:47] Epoch: [011][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.429 (4.519) Prec@1 50.00 (48.49) Prec@5 71.09 (72.58) + train[2018-10-11-08:44:31] Epoch: [011][5400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.383 (4.519) Prec@1 50.00 (48.47) Prec@5 78.12 (72.59) + train[2018-10-11-08:46:15] Epoch: [011][5600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.274 (4.519) Prec@1 46.09 (48.47) Prec@5 77.34 (72.59) + train[2018-10-11-08:47:59] Epoch: [011][5800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.481 (4.520) Prec@1 49.22 (48.46) Prec@5 75.00 (72.58) + train[2018-10-11-08:49:42] Epoch: [011][6000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.529 (4.520) Prec@1 45.31 (48.46) Prec@5 71.09 (72.57) + train[2018-10-11-08:51:25] Epoch: [011][6200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.418 (4.520) Prec@1 47.66 (48.46) Prec@5 78.91 (72.56) + train[2018-10-11-08:53:09] Epoch: [011][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.379 (4.520) Prec@1 54.69 (48.46) Prec@5 71.09 (72.55) + train[2018-10-11-08:54:53] Epoch: [011][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.579 (4.519) Prec@1 50.78 (48.46) Prec@5 69.53 (72.56) + train[2018-10-11-08:56:36] Epoch: [011][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.723 (4.520) Prec@1 49.22 (48.46) Prec@5 67.19 (72.55) + train[2018-10-11-08:58:20] Epoch: [011][7000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.409 (4.519) Prec@1 50.78 (48.48) Prec@5 75.00 (72.54) + train[2018-10-11-09:00:04] Epoch: [011][7200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.715 (4.521) Prec@1 46.09 (48.45) Prec@5 65.62 (72.52) + train[2018-10-11-09:01:47] Epoch: [011][7400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.444 (4.521) Prec@1 50.00 (48.44) Prec@5 75.00 (72.51) + train[2018-10-11-09:03:31] Epoch: [011][7600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.587 (4.521) Prec@1 48.44 (48.45) Prec@5 71.09 (72.51) + train[2018-10-11-09:05:15] Epoch: [011][7800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.224 (4.520) Prec@1 46.09 (48.46) Prec@5 77.34 (72.53) + train[2018-10-11-09:06:59] Epoch: [011][8000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.445 (4.520) Prec@1 51.56 (48.46) Prec@5 72.66 (72.53) + train[2018-10-11-09:08:42] Epoch: [011][8200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.494 (4.520) Prec@1 51.56 (48.48) Prec@5 73.44 (72.53) + train[2018-10-11-09:10:26] Epoch: [011][8400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.731 (4.520) Prec@1 42.97 (48.48) Prec@5 71.88 (72.53) + train[2018-10-11-09:12:09] Epoch: [011][8600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.328 (4.520) Prec@1 51.56 (48.47) Prec@5 76.56 (72.53) + train[2018-10-11-09:13:53] Epoch: [011][8800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.495 (4.520) Prec@1 50.00 (48.48) Prec@5 70.31 (72.54) + train[2018-10-11-09:15:36] Epoch: [011][9000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.392 (4.520) Prec@1 47.66 (48.48) Prec@5 74.22 (72.54) + train[2018-10-11-09:17:20] Epoch: [011][9200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.562 (4.520) Prec@1 50.78 (48.48) Prec@5 71.88 (72.53) + train[2018-10-11-09:19:04] Epoch: [011][9400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.427 (4.520) Prec@1 47.66 (48.47) Prec@5 75.00 (72.53) + train[2018-10-11-09:20:48] Epoch: [011][9600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.518 (4.520) Prec@1 50.78 (48.47) Prec@5 76.56 (72.53) + train[2018-10-11-09:22:32] Epoch: [011][9800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.658 (4.520) Prec@1 39.06 (48.46) Prec@5 77.34 (72.53) + train[2018-10-11-09:24:15] Epoch: [011][10000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.367 (4.520) Prec@1 51.56 (48.47) Prec@5 75.00 (72.53) + train[2018-10-11-09:24:20] Epoch: [011][10009/10010] Time 0.21 (0.52) Data 0.00 (0.00) Loss 5.211 (4.520) Prec@1 40.00 (48.47) Prec@5 46.67 (72.53) +[2018-10-11-09:24:20] **train** Prec@1 48.47 Prec@5 72.53 Error@1 51.53 Error@5 27.47 Loss:4.520 + test [2018-10-11-09:24:24] Epoch: [011][000/391] Time 4.39 (4.39) Data 4.25 (4.25) Loss 1.206 (1.206) Prec@1 75.78 (75.78) Prec@5 89.84 (89.84) + test [2018-10-11-09:24:51] Epoch: [011][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 2.174 (1.844) Prec@1 44.53 (57.42) Prec@5 75.00 (82.42) + test [2018-10-11-09:25:16] Epoch: [011][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 3.425 (2.054) Prec@1 21.25 (53.92) Prec@5 53.75 (78.61) +[2018-10-11-09:25:16] **test** Prec@1 53.92 Prec@5 78.61 Error@1 46.08 Error@5 21.39 Loss:2.054 +----> Best Accuracy : Acc@1=53.92, Acc@5=78.61, Error@1=46.08, Error@5=21.39 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-11-09:25:16] [Epoch=012/250] [Need: 347:21:25] LR=0.0694 ~ 0.0694, Batch=128 + train[2018-10-11-09:25:22] Epoch: [012][000/10010] Time 5.65 (5.65) Data 5.04 (5.04) Loss 4.513 (4.513) Prec@1 50.00 (50.00) Prec@5 72.66 (72.66) + train[2018-10-11-09:27:06] Epoch: [012][200/10010] Time 0.50 (0.55) Data 0.00 (0.03) Loss 4.138 (4.483) Prec@1 52.34 (49.22) Prec@5 82.81 (72.91) + train[2018-10-11-09:28:49] Epoch: [012][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 4.220 (4.468) Prec@1 53.91 (49.22) Prec@5 72.66 (73.10) + train[2018-10-11-09:30:33] Epoch: [012][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 4.422 (4.460) Prec@1 51.56 (49.30) Prec@5 74.22 (73.17) + train[2018-10-11-09:32:17] Epoch: [012][800/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 4.532 (4.465) Prec@1 53.12 (49.26) Prec@5 71.88 (73.12) + train[2018-10-11-09:34:01] Epoch: [012][1000/10010] Time 0.51 (0.52) Data 0.00 (0.01) Loss 4.550 (4.465) Prec@1 45.31 (49.24) Prec@5 68.75 (73.18) + train[2018-10-11-09:35:44] Epoch: [012][1200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.271 (4.466) Prec@1 48.44 (49.20) Prec@5 77.34 (73.15) + train[2018-10-11-09:37:28] Epoch: [012][1400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.690 (4.465) Prec@1 45.31 (49.23) Prec@5 68.75 (73.21) + train[2018-10-11-09:39:12] Epoch: [012][1600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.419 (4.470) Prec@1 51.56 (49.18) Prec@5 71.88 (73.13) + train[2018-10-11-09:40:56] Epoch: [012][1800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.474 (4.468) Prec@1 51.56 (49.23) Prec@5 75.78 (73.15) + train[2018-10-11-09:42:41] Epoch: [012][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.357 (4.470) Prec@1 49.22 (49.17) Prec@5 70.31 (73.15) + train[2018-10-11-09:44:25] Epoch: [012][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.550 (4.471) Prec@1 47.66 (49.14) Prec@5 72.66 (73.15) + train[2018-10-11-09:46:09] Epoch: [012][2400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.462 (4.470) Prec@1 45.31 (49.16) Prec@5 74.22 (73.20) + train[2018-10-11-09:47:53] Epoch: [012][2600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.335 (4.470) Prec@1 45.31 (49.18) Prec@5 78.91 (73.22) + train[2018-10-11-09:49:36] Epoch: [012][2800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.291 (4.470) Prec@1 49.22 (49.18) Prec@5 74.22 (73.20) + train[2018-10-11-09:51:20] Epoch: [012][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.316 (4.472) Prec@1 50.78 (49.18) Prec@5 75.00 (73.18) + train[2018-10-11-09:53:04] Epoch: [012][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.921 (4.471) Prec@1 60.94 (49.18) Prec@5 79.69 (73.18) + train[2018-10-11-09:54:48] Epoch: [012][3400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.678 (4.471) Prec@1 46.09 (49.20) Prec@5 72.66 (73.18) + train[2018-10-11-09:56:32] Epoch: [012][3600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.365 (4.469) Prec@1 53.91 (49.22) Prec@5 75.00 (73.21) + train[2018-10-11-09:58:15] Epoch: [012][3800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.637 (4.468) Prec@1 42.19 (49.24) Prec@5 71.88 (73.23) + train[2018-10-11-09:59:59] Epoch: [012][4000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.267 (4.466) Prec@1 50.00 (49.25) Prec@5 77.34 (73.25) + train[2018-10-11-10:01:42] Epoch: [012][4200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.415 (4.466) Prec@1 48.44 (49.27) Prec@5 73.44 (73.25) + train[2018-10-11-10:03:26] Epoch: [012][4400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.622 (4.468) Prec@1 47.66 (49.25) Prec@5 69.53 (73.23) + train[2018-10-11-10:05:11] Epoch: [012][4600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.643 (4.468) Prec@1 44.53 (49.25) Prec@5 69.53 (73.23) + train[2018-10-11-10:06:54] Epoch: [012][4800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.983 (4.468) Prec@1 46.09 (49.25) Prec@5 65.62 (73.24) + train[2018-10-11-10:08:39] Epoch: [012][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.448 (4.469) Prec@1 51.56 (49.25) Prec@5 73.44 (73.24) + train[2018-10-11-10:10:22] Epoch: [012][5200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.099 (4.469) Prec@1 56.25 (49.23) Prec@5 75.78 (73.23) + train[2018-10-11-10:12:07] Epoch: [012][5400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.370 (4.469) Prec@1 53.12 (49.23) Prec@5 74.22 (73.25) + train[2018-10-11-10:13:51] Epoch: [012][5600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.860 (4.469) Prec@1 42.97 (49.23) Prec@5 66.41 (73.23) + train[2018-10-11-10:15:35] Epoch: [012][5800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.269 (4.470) Prec@1 54.69 (49.23) Prec@5 76.56 (73.22) + train[2018-10-11-10:17:19] Epoch: [012][6000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.360 (4.470) Prec@1 54.69 (49.23) Prec@5 76.56 (73.22) + train[2018-10-11-10:19:03] Epoch: [012][6200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.492 (4.469) Prec@1 46.09 (49.24) Prec@5 69.53 (73.22) + train[2018-10-11-10:20:47] Epoch: [012][6400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 4.724 (4.470) Prec@1 46.09 (49.22) Prec@5 69.53 (73.21) + train[2018-10-11-10:22:31] Epoch: [012][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.584 (4.470) Prec@1 48.44 (49.23) Prec@5 76.56 (73.21) + train[2018-10-11-10:24:15] Epoch: [012][6800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.155 (4.470) Prec@1 50.00 (49.23) Prec@5 78.12 (73.20) + train[2018-10-11-10:25:59] Epoch: [012][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.314 (4.471) Prec@1 57.03 (49.21) Prec@5 75.00 (73.19) + train[2018-10-11-10:27:44] Epoch: [012][7200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.638 (4.471) Prec@1 47.66 (49.20) Prec@5 74.22 (73.19) + train[2018-10-11-10:29:28] Epoch: [012][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.390 (4.472) Prec@1 49.22 (49.19) Prec@5 80.47 (73.18) + train[2018-10-11-10:31:11] Epoch: [012][7600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.278 (4.472) Prec@1 53.91 (49.18) Prec@5 80.47 (73.18) + train[2018-10-11-10:32:55] Epoch: [012][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.223 (4.473) Prec@1 50.78 (49.16) Prec@5 75.00 (73.16) + train[2018-10-11-10:34:38] Epoch: [012][8000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.648 (4.475) Prec@1 44.53 (49.13) Prec@5 67.97 (73.14) + train[2018-10-11-10:36:23] Epoch: [012][8200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.441 (4.475) Prec@1 47.66 (49.13) Prec@5 71.88 (73.13) + train[2018-10-11-10:38:07] Epoch: [012][8400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.959 (4.475) Prec@1 57.81 (49.13) Prec@5 81.25 (73.13) + train[2018-10-11-10:39:50] Epoch: [012][8600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.738 (4.475) Prec@1 46.09 (49.13) Prec@5 68.75 (73.12) + train[2018-10-11-10:41:34] Epoch: [012][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.253 (4.475) Prec@1 56.25 (49.13) Prec@5 75.00 (73.12) + train[2018-10-11-10:43:17] Epoch: [012][9000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.335 (4.476) Prec@1 50.00 (49.11) Prec@5 73.44 (73.11) + train[2018-10-11-10:45:01] Epoch: [012][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.949 (4.476) Prec@1 42.97 (49.12) Prec@5 66.41 (73.10) + train[2018-10-11-10:46:45] Epoch: [012][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.578 (4.475) Prec@1 50.00 (49.11) Prec@5 71.88 (73.11) + train[2018-10-11-10:48:28] Epoch: [012][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.520 (4.476) Prec@1 46.88 (49.12) Prec@5 72.66 (73.10) + train[2018-10-11-10:50:12] Epoch: [012][9800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.661 (4.476) Prec@1 49.22 (49.11) Prec@5 71.09 (73.10) + train[2018-10-11-10:51:56] Epoch: [012][10000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.364 (4.476) Prec@1 46.88 (49.10) Prec@5 75.00 (73.10) + train[2018-10-11-10:52:00] Epoch: [012][10009/10010] Time 0.14 (0.52) Data 0.00 (0.00) Loss 4.881 (4.476) Prec@1 46.67 (49.10) Prec@5 73.33 (73.10) +[2018-10-11-10:52:00] **train** Prec@1 49.10 Prec@5 73.10 Error@1 50.90 Error@5 26.90 Loss:4.476 + test [2018-10-11-10:52:05] Epoch: [012][000/391] Time 4.56 (4.56) Data 4.41 (4.41) Loss 1.226 (1.226) Prec@1 79.69 (79.69) Prec@5 89.06 (89.06) + test [2018-10-11-10:52:31] Epoch: [012][200/391] Time 0.12 (0.16) Data 0.00 (0.02) Loss 2.688 (1.804) Prec@1 43.75 (58.60) Prec@5 69.53 (83.24) + test [2018-10-11-10:52:57] Epoch: [012][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 3.281 (2.012) Prec@1 23.75 (54.93) Prec@5 58.75 (79.67) +[2018-10-11-10:52:57] **test** Prec@1 54.93 Prec@5 79.67 Error@1 45.07 Error@5 20.33 Loss:2.012 +----> Best Accuracy : Acc@1=54.93, Acc@5=79.67, Error@1=45.07, Error@5=20.33 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-11-10:52:57] [Epoch=013/250] [Need: 346:19:07] LR=0.0673 ~ 0.0673, Batch=128 + train[2018-10-11-10:53:01] Epoch: [013][000/10010] Time 4.36 (4.36) Data 3.75 (3.75) Loss 4.102 (4.102) Prec@1 49.22 (49.22) Prec@5 80.47 (80.47) + train[2018-10-11-10:54:46] Epoch: [013][200/10010] Time 0.51 (0.54) Data 0.00 (0.02) Loss 4.721 (4.406) Prec@1 43.75 (50.04) Prec@5 67.97 (74.28) + train[2018-10-11-10:56:30] Epoch: [013][400/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 4.470 (4.395) Prec@1 50.78 (50.27) Prec@5 75.00 (74.33) + train[2018-10-11-10:58:14] Epoch: [013][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 4.507 (4.396) Prec@1 46.88 (50.15) Prec@5 72.66 (74.36) + train[2018-10-11-10:59:57] Epoch: [013][800/10010] Time 0.50 (0.52) Data 0.00 (0.01) Loss 4.208 (4.398) Prec@1 54.69 (50.25) Prec@5 73.44 (74.16) + train[2018-10-11-11:01:41] Epoch: [013][1000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.481 (4.401) Prec@1 47.66 (50.20) Prec@5 74.22 (74.10) + train[2018-10-11-11:03:25] Epoch: [013][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.013 (4.408) Prec@1 56.25 (50.10) Prec@5 78.12 (74.04) + train[2018-10-11-11:05:09] Epoch: [013][1400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.646 (4.411) Prec@1 45.31 (50.07) Prec@5 71.88 (73.99) + train[2018-10-11-11:06:53] Epoch: [013][1600/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 4.475 (4.417) Prec@1 45.31 (50.02) Prec@5 72.66 (73.94) + train[2018-10-11-11:08:37] Epoch: [013][1800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.196 (4.418) Prec@1 55.47 (50.02) Prec@5 78.91 (73.92) + train[2018-10-11-11:10:20] Epoch: [013][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.995 (4.416) Prec@1 54.69 (50.05) Prec@5 79.69 (73.95) + train[2018-10-11-11:12:05] Epoch: [013][2200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.008 (4.415) Prec@1 55.47 (50.07) Prec@5 78.12 (73.96) + train[2018-10-11-11:13:49] Epoch: [013][2400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.713 (4.415) Prec@1 41.41 (50.08) Prec@5 70.31 (73.97) + train[2018-10-11-11:15:32] Epoch: [013][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.698 (4.416) Prec@1 42.97 (50.04) Prec@5 69.53 (73.95) + train[2018-10-11-11:17:16] Epoch: [013][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.812 (4.419) Prec@1 46.09 (50.01) Prec@5 67.97 (73.90) + train[2018-10-11-11:19:00] Epoch: [013][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.290 (4.422) Prec@1 52.34 (49.96) Prec@5 77.34 (73.85) + train[2018-10-11-11:20:44] Epoch: [013][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.420 (4.423) Prec@1 53.91 (49.93) Prec@5 72.66 (73.83) + train[2018-10-11-11:22:28] Epoch: [013][3400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.344 (4.423) Prec@1 51.56 (49.91) Prec@5 71.09 (73.83) + train[2018-10-11-11:24:12] Epoch: [013][3600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.344 (4.424) Prec@1 47.66 (49.89) Prec@5 71.09 (73.81) + train[2018-10-11-11:25:56] Epoch: [013][3800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.193 (4.424) Prec@1 57.81 (49.88) Prec@5 74.22 (73.79) + train[2018-10-11-11:27:41] Epoch: [013][4000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.250 (4.424) Prec@1 49.22 (49.88) Prec@5 74.22 (73.79) + train[2018-10-11-11:29:25] Epoch: [013][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.319 (4.425) Prec@1 53.12 (49.84) Prec@5 73.44 (73.78) + train[2018-10-11-11:31:08] Epoch: [013][4400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.236 (4.425) Prec@1 50.78 (49.83) Prec@5 81.25 (73.79) + train[2018-10-11-11:32:52] Epoch: [013][4600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.481 (4.427) Prec@1 46.09 (49.79) Prec@5 76.56 (73.77) + train[2018-10-11-11:34:36] Epoch: [013][4800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.339 (4.427) Prec@1 48.44 (49.80) Prec@5 74.22 (73.78) + train[2018-10-11-11:36:20] Epoch: [013][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.664 (4.427) Prec@1 46.88 (49.80) Prec@5 67.97 (73.77) + train[2018-10-11-11:38:04] Epoch: [013][5200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.829 (4.428) Prec@1 33.59 (49.80) Prec@5 71.09 (73.76) + train[2018-10-11-11:39:48] Epoch: [013][5400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.420 (4.428) Prec@1 51.56 (49.80) Prec@5 74.22 (73.75) + train[2018-10-11-11:41:32] Epoch: [013][5600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.492 (4.427) Prec@1 50.78 (49.82) Prec@5 73.44 (73.76) + train[2018-10-11-11:43:16] Epoch: [013][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.380 (4.427) Prec@1 57.03 (49.81) Prec@5 75.00 (73.77) + train[2018-10-11-11:45:00] Epoch: [013][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.427 (4.427) Prec@1 56.25 (49.82) Prec@5 78.12 (73.78) + train[2018-10-11-11:46:44] Epoch: [013][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.463 (4.427) Prec@1 51.56 (49.82) Prec@5 78.12 (73.78) + train[2018-10-11-11:48:29] Epoch: [013][6400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.449 (4.428) Prec@1 53.12 (49.81) Prec@5 72.66 (73.77) + train[2018-10-11-11:50:13] Epoch: [013][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 5.309 (4.429) Prec@1 40.62 (49.81) Prec@5 57.81 (73.75) + train[2018-10-11-11:51:57] Epoch: [013][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.320 (4.429) Prec@1 51.56 (49.80) Prec@5 78.12 (73.75) + train[2018-10-11-11:53:40] Epoch: [013][7000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.647 (4.430) Prec@1 50.78 (49.79) Prec@5 69.53 (73.74) + train[2018-10-11-11:55:25] Epoch: [013][7200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.236 (4.431) Prec@1 50.00 (49.79) Prec@5 80.47 (73.73) + train[2018-10-11-11:57:08] Epoch: [013][7400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.284 (4.431) Prec@1 52.34 (49.80) Prec@5 75.00 (73.72) + train[2018-10-11-11:58:52] Epoch: [013][7600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 5.036 (4.431) Prec@1 38.28 (49.79) Prec@5 64.06 (73.71) + train[2018-10-11-12:00:36] Epoch: [013][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.050 (4.431) Prec@1 55.47 (49.79) Prec@5 78.91 (73.71) + train[2018-10-11-12:02:20] Epoch: [013][8000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.332 (4.432) Prec@1 49.22 (49.79) Prec@5 77.34 (73.70) + train[2018-10-11-12:04:04] Epoch: [013][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.422 (4.433) Prec@1 50.78 (49.77) Prec@5 75.78 (73.70) + train[2018-10-11-12:05:48] Epoch: [013][8400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.337 (4.433) Prec@1 48.44 (49.78) Prec@5 75.78 (73.70) + train[2018-10-11-12:07:32] Epoch: [013][8600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.310 (4.433) Prec@1 50.78 (49.77) Prec@5 77.34 (73.69) + train[2018-10-11-12:09:16] Epoch: [013][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.170 (4.433) Prec@1 53.91 (49.77) Prec@5 79.69 (73.69) + train[2018-10-11-12:11:00] Epoch: [013][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.137 (4.434) Prec@1 58.59 (49.76) Prec@5 74.22 (73.68) + train[2018-10-11-12:12:45] Epoch: [013][9200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.318 (4.434) Prec@1 53.12 (49.76) Prec@5 75.78 (73.68) + train[2018-10-11-12:14:29] Epoch: [013][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.749 (4.434) Prec@1 48.44 (49.75) Prec@5 72.66 (73.68) + train[2018-10-11-12:16:13] Epoch: [013][9600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.309 (4.434) Prec@1 49.22 (49.74) Prec@5 75.00 (73.68) + train[2018-10-11-12:17:57] Epoch: [013][9800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.410 (4.434) Prec@1 51.56 (49.75) Prec@5 75.78 (73.68) + train[2018-10-11-12:19:40] Epoch: [013][10000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.416 (4.435) Prec@1 46.09 (49.74) Prec@5 70.31 (73.67) + train[2018-10-11-12:19:44] Epoch: [013][10009/10010] Time 0.14 (0.52) Data 0.00 (0.00) Loss 5.502 (4.435) Prec@1 40.00 (49.74) Prec@5 66.67 (73.67) +[2018-10-11-12:19:44] **train** Prec@1 49.74 Prec@5 73.67 Error@1 50.26 Error@5 26.33 Loss:4.435 + test [2018-10-11-12:19:48] Epoch: [013][000/391] Time 3.74 (3.74) Data 3.60 (3.60) Loss 1.027 (1.027) Prec@1 77.34 (77.34) Prec@5 90.62 (90.62) + test [2018-10-11-12:20:16] Epoch: [013][200/391] Time 0.14 (0.16) Data 0.00 (0.02) Loss 2.723 (1.780) Prec@1 35.16 (58.78) Prec@5 67.97 (83.00) + test [2018-10-11-12:20:41] Epoch: [013][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 4.024 (2.010) Prec@1 16.25 (55.02) Prec@5 47.50 (79.24) +[2018-10-11-12:20:41] **test** Prec@1 55.02 Prec@5 79.24 Error@1 44.98 Error@5 20.76 Loss:2.010 +----> Best Accuracy : Acc@1=55.02, Acc@5=79.24, Error@1=44.98, Error@5=20.76 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-11-12:20:41] [Epoch=014/250] [Need: 345:06:07] LR=0.0653 ~ 0.0653, Batch=128 + train[2018-10-11-12:20:45] Epoch: [014][000/10010] Time 4.22 (4.22) Data 3.64 (3.64) Loss 4.143 (4.143) Prec@1 50.00 (50.00) Prec@5 79.69 (79.69) + train[2018-10-11-12:22:31] Epoch: [014][200/10010] Time 0.56 (0.54) Data 0.00 (0.02) Loss 4.331 (4.362) Prec@1 50.00 (50.77) Prec@5 74.22 (74.76) + train[2018-10-11-12:24:14] Epoch: [014][400/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 4.540 (4.367) Prec@1 46.09 (50.78) Prec@5 69.53 (74.59) + train[2018-10-11-12:25:58] Epoch: [014][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 4.466 (4.370) Prec@1 44.53 (50.79) Prec@5 78.12 (74.55) + train[2018-10-11-12:27:42] Epoch: [014][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 4.841 (4.367) Prec@1 46.09 (50.81) Prec@5 67.19 (74.67) + train[2018-10-11-12:29:26] Epoch: [014][1000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.409 (4.366) Prec@1 52.34 (50.85) Prec@5 73.44 (74.63) + train[2018-10-11-12:31:10] Epoch: [014][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.525 (4.366) Prec@1 44.53 (50.79) Prec@5 70.31 (74.61) + train[2018-10-11-12:32:53] Epoch: [014][1400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.373 (4.362) Prec@1 51.56 (50.87) Prec@5 76.56 (74.66) + train[2018-10-11-12:34:37] Epoch: [014][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.136 (4.364) Prec@1 52.34 (50.82) Prec@5 79.69 (74.61) + train[2018-10-11-12:36:21] Epoch: [014][1800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.424 (4.368) Prec@1 53.91 (50.77) Prec@5 75.00 (74.56) + train[2018-10-11-12:38:05] Epoch: [014][2000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.475 (4.370) Prec@1 44.53 (50.72) Prec@5 70.31 (74.55) + train[2018-10-11-12:39:49] Epoch: [014][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.193 (4.373) Prec@1 58.59 (50.63) Prec@5 79.69 (74.50) + train[2018-10-11-12:41:32] Epoch: [014][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.597 (4.376) Prec@1 42.97 (50.56) Prec@5 71.88 (74.43) + train[2018-10-11-12:43:17] Epoch: [014][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.412 (4.376) Prec@1 49.22 (50.55) Prec@5 73.44 (74.43) + train[2018-10-11-12:45:01] Epoch: [014][2800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.166 (4.379) Prec@1 51.56 (50.53) Prec@5 78.12 (74.41) + train[2018-10-11-12:46:45] Epoch: [014][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.496 (4.381) Prec@1 46.88 (50.49) Prec@5 73.44 (74.38) + train[2018-10-11-12:48:29] Epoch: [014][3200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.404 (4.382) Prec@1 49.22 (50.50) Prec@5 71.88 (74.37) + train[2018-10-11-12:50:13] Epoch: [014][3400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.110 (4.381) Prec@1 52.34 (50.52) Prec@5 82.81 (74.36) + train[2018-10-11-12:51:57] Epoch: [014][3600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.204 (4.382) Prec@1 50.78 (50.51) Prec@5 78.91 (74.36) + train[2018-10-11-12:53:41] Epoch: [014][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.431 (4.382) Prec@1 50.78 (50.51) Prec@5 75.00 (74.37) + train[2018-10-11-12:55:25] Epoch: [014][4000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.814 (4.384) Prec@1 41.41 (50.48) Prec@5 64.84 (74.34) + train[2018-10-11-12:57:09] Epoch: [014][4200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.333 (4.385) Prec@1 45.31 (50.47) Prec@5 78.91 (74.31) + train[2018-10-11-12:58:51] Epoch: [014][4400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.516 (4.386) Prec@1 50.00 (50.44) Prec@5 73.44 (74.29) + train[2018-10-11-13:00:35] Epoch: [014][4600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.256 (4.386) Prec@1 45.31 (50.43) Prec@5 76.56 (74.30) + train[2018-10-11-13:02:19] Epoch: [014][4800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.219 (4.387) Prec@1 52.34 (50.42) Prec@5 78.91 (74.29) + train[2018-10-11-13:04:03] Epoch: [014][5000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.360 (4.388) Prec@1 50.00 (50.42) Prec@5 74.22 (74.29) + train[2018-10-11-13:05:46] Epoch: [014][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.298 (4.388) Prec@1 53.12 (50.41) Prec@5 74.22 (74.30) + train[2018-10-11-13:07:30] Epoch: [014][5400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.207 (4.389) Prec@1 53.12 (50.40) Prec@5 78.91 (74.30) + train[2018-10-11-13:09:15] Epoch: [014][5600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.424 (4.389) Prec@1 53.91 (50.41) Prec@5 75.00 (74.31) + train[2018-10-11-13:10:59] Epoch: [014][5800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.527 (4.389) Prec@1 48.44 (50.39) Prec@5 74.22 (74.30) + train[2018-10-11-13:12:42] Epoch: [014][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.203 (4.390) Prec@1 52.34 (50.39) Prec@5 75.78 (74.29) + train[2018-10-11-13:14:26] Epoch: [014][6200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.574 (4.390) Prec@1 47.66 (50.37) Prec@5 69.53 (74.28) + train[2018-10-11-13:16:09] Epoch: [014][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.395 (4.390) Prec@1 51.56 (50.37) Prec@5 74.22 (74.27) + train[2018-10-11-13:17:54] Epoch: [014][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.240 (4.390) Prec@1 57.81 (50.37) Prec@5 75.00 (74.27) + train[2018-10-11-13:19:38] Epoch: [014][6800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.656 (4.391) Prec@1 45.31 (50.36) Prec@5 70.31 (74.26) + train[2018-10-11-13:21:22] Epoch: [014][7000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.099 (4.392) Prec@1 56.25 (50.35) Prec@5 76.56 (74.25) + train[2018-10-11-13:23:06] Epoch: [014][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.947 (4.392) Prec@1 57.03 (50.35) Prec@5 80.47 (74.24) + train[2018-10-11-13:24:50] Epoch: [014][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.213 (4.393) Prec@1 51.56 (50.33) Prec@5 74.22 (74.22) + train[2018-10-11-13:26:34] Epoch: [014][7600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.470 (4.393) Prec@1 50.78 (50.34) Prec@5 72.66 (74.22) + train[2018-10-11-13:28:18] Epoch: [014][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.544 (4.394) Prec@1 46.88 (50.33) Prec@5 72.66 (74.22) + train[2018-10-11-13:30:02] Epoch: [014][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.324 (4.393) Prec@1 53.12 (50.33) Prec@5 75.00 (74.22) + train[2018-10-11-13:31:46] Epoch: [014][8200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.144 (4.394) Prec@1 46.09 (50.32) Prec@5 80.47 (74.21) + train[2018-10-11-13:33:29] Epoch: [014][8400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.470 (4.394) Prec@1 50.78 (50.32) Prec@5 72.66 (74.21) + train[2018-10-11-13:35:14] Epoch: [014][8600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.336 (4.394) Prec@1 53.12 (50.33) Prec@5 75.78 (74.21) + train[2018-10-11-13:36:58] Epoch: [014][8800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.439 (4.394) Prec@1 53.12 (50.33) Prec@5 71.09 (74.21) + train[2018-10-11-13:38:42] Epoch: [014][9000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.492 (4.394) Prec@1 50.00 (50.32) Prec@5 69.53 (74.21) + train[2018-10-11-13:40:25] Epoch: [014][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.979 (4.395) Prec@1 56.25 (50.31) Prec@5 82.03 (74.20) + train[2018-10-11-13:42:09] Epoch: [014][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.355 (4.395) Prec@1 47.66 (50.31) Prec@5 77.34 (74.19) + train[2018-10-11-13:43:53] Epoch: [014][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.374 (4.396) Prec@1 51.56 (50.30) Prec@5 74.22 (74.17) + train[2018-10-11-13:45:38] Epoch: [014][9800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.636 (4.396) Prec@1 46.09 (50.30) Prec@5 74.22 (74.17) + train[2018-10-11-13:47:21] Epoch: [014][10000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.719 (4.396) Prec@1 48.44 (50.29) Prec@5 72.66 (74.17) + train[2018-10-11-13:47:26] Epoch: [014][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 6.183 (4.396) Prec@1 26.67 (50.29) Prec@5 53.33 (74.17) +[2018-10-11-13:47:26] **train** Prec@1 50.29 Prec@5 74.17 Error@1 49.71 Error@5 25.83 Loss:4.396 + test [2018-10-11-13:47:30] Epoch: [014][000/391] Time 4.01 (4.01) Data 3.87 (3.87) Loss 1.023 (1.023) Prec@1 77.34 (77.34) Prec@5 91.41 (91.41) + test [2018-10-11-13:47:57] Epoch: [014][200/391] Time 0.14 (0.16) Data 0.00 (0.03) Loss 2.193 (1.695) Prec@1 46.09 (60.44) Prec@5 79.69 (85.00) + test [2018-10-11-13:48:22] Epoch: [014][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 3.903 (1.935) Prec@1 27.50 (56.44) Prec@5 46.25 (80.86) +[2018-10-11-13:48:22] **test** Prec@1 56.44 Prec@5 80.86 Error@1 43.56 Error@5 19.14 Loss:1.935 +----> Best Accuracy : Acc@1=56.44, Acc@5=80.86, Error@1=43.56, Error@5=19.14 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-11-13:48:22] [Epoch=015/250] [Need: 343:25:05] LR=0.0633 ~ 0.0633, Batch=128 + train[2018-10-11-13:48:28] Epoch: [015][000/10010] Time 5.65 (5.65) Data 4.99 (4.99) Loss 4.544 (4.544) Prec@1 47.66 (47.66) Prec@5 69.53 (69.53) + train[2018-10-11-13:50:13] Epoch: [015][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.998 (4.333) Prec@1 60.94 (51.47) Prec@5 75.78 (74.79) + train[2018-10-11-13:51:56] Epoch: [015][400/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 4.226 (4.325) Prec@1 53.12 (51.21) Prec@5 73.44 (75.08) + train[2018-10-11-13:53:41] Epoch: [015][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 4.367 (4.341) Prec@1 51.56 (51.07) Prec@5 70.31 (74.85) + train[2018-10-11-13:55:25] Epoch: [015][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 4.224 (4.340) Prec@1 52.34 (51.05) Prec@5 77.34 (74.91) + train[2018-10-11-13:57:09] Epoch: [015][1000/10010] Time 0.49 (0.53) Data 0.00 (0.01) Loss 4.571 (4.343) Prec@1 50.78 (51.03) Prec@5 73.44 (74.92) + train[2018-10-11-13:58:53] Epoch: [015][1200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 4.768 (4.343) Prec@1 46.09 (51.08) Prec@5 68.75 (74.94) + train[2018-10-11-14:00:37] Epoch: [015][1400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.471 (4.344) Prec@1 46.09 (51.00) Prec@5 72.66 (74.88) + train[2018-10-11-14:02:22] Epoch: [015][1600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.305 (4.346) Prec@1 46.88 (50.97) Prec@5 72.66 (74.88) + train[2018-10-11-14:04:05] Epoch: [015][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.318 (4.342) Prec@1 47.66 (51.02) Prec@5 75.78 (74.91) + train[2018-10-11-14:05:49] Epoch: [015][2000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.100 (4.342) Prec@1 54.69 (51.09) Prec@5 78.91 (74.94) + train[2018-10-11-14:07:33] Epoch: [015][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.307 (4.346) Prec@1 46.88 (51.03) Prec@5 78.91 (74.87) + train[2018-10-11-14:09:17] Epoch: [015][2400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.234 (4.346) Prec@1 53.12 (51.04) Prec@5 75.78 (74.86) + train[2018-10-11-14:11:01] Epoch: [015][2600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.224 (4.343) Prec@1 57.03 (51.10) Prec@5 77.34 (74.91) + train[2018-10-11-14:12:45] Epoch: [015][2800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.462 (4.342) Prec@1 49.22 (51.13) Prec@5 71.88 (74.93) + train[2018-10-11-14:14:30] Epoch: [015][3000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.275 (4.341) Prec@1 52.34 (51.16) Prec@5 78.12 (74.94) + train[2018-10-11-14:16:14] Epoch: [015][3200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.528 (4.341) Prec@1 46.88 (51.15) Prec@5 74.22 (74.94) + train[2018-10-11-14:17:59] Epoch: [015][3400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.276 (4.341) Prec@1 47.66 (51.16) Prec@5 74.22 (74.93) + train[2018-10-11-14:19:42] Epoch: [015][3600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.111 (4.342) Prec@1 54.69 (51.14) Prec@5 75.00 (74.91) + train[2018-10-11-14:21:26] Epoch: [015][3800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.104 (4.345) Prec@1 60.94 (51.11) Prec@5 78.91 (74.87) + train[2018-10-11-14:23:11] Epoch: [015][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.425 (4.346) Prec@1 48.44 (51.07) Prec@5 71.88 (74.84) + train[2018-10-11-14:24:55] Epoch: [015][4200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.364 (4.346) Prec@1 46.09 (51.07) Prec@5 72.66 (74.83) + train[2018-10-11-14:26:39] Epoch: [015][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.517 (4.349) Prec@1 53.12 (51.03) Prec@5 74.22 (74.80) + train[2018-10-11-14:28:23] Epoch: [015][4600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.484 (4.349) Prec@1 47.66 (51.03) Prec@5 74.22 (74.81) + train[2018-10-11-14:30:07] Epoch: [015][4800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.894 (4.350) Prec@1 58.59 (51.02) Prec@5 81.25 (74.78) + train[2018-10-11-14:31:51] Epoch: [015][5000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.123 (4.350) Prec@1 57.03 (51.01) Prec@5 77.34 (74.78) + train[2018-10-11-14:33:35] Epoch: [015][5200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.491 (4.351) Prec@1 49.22 (50.99) Prec@5 71.09 (74.76) + train[2018-10-11-14:35:19] Epoch: [015][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.166 (4.352) Prec@1 54.69 (50.97) Prec@5 78.91 (74.73) + train[2018-10-11-14:37:03] Epoch: [015][5600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.485 (4.353) Prec@1 42.97 (50.95) Prec@5 73.44 (74.72) + train[2018-10-11-14:38:48] Epoch: [015][5800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.164 (4.354) Prec@1 55.47 (50.93) Prec@5 76.56 (74.71) + train[2018-10-11-14:40:31] Epoch: [015][6000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.374 (4.354) Prec@1 52.34 (50.93) Prec@5 77.34 (74.70) + train[2018-10-11-14:42:15] Epoch: [015][6200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.278 (4.354) Prec@1 51.56 (50.92) Prec@5 74.22 (74.70) + train[2018-10-11-14:43:59] Epoch: [015][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.658 (4.355) Prec@1 44.53 (50.92) Prec@5 71.09 (74.69) + train[2018-10-11-14:45:43] Epoch: [015][6600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.528 (4.355) Prec@1 48.44 (50.91) Prec@5 73.44 (74.69) + train[2018-10-11-14:47:27] Epoch: [015][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.425 (4.355) Prec@1 46.88 (50.91) Prec@5 75.78 (74.69) + train[2018-10-11-14:49:11] Epoch: [015][7000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.277 (4.355) Prec@1 53.12 (50.91) Prec@5 78.12 (74.69) + train[2018-10-11-14:50:54] Epoch: [015][7200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.334 (4.354) Prec@1 51.56 (50.93) Prec@5 78.91 (74.71) + train[2018-10-11-14:52:38] Epoch: [015][7400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.912 (4.355) Prec@1 41.41 (50.91) Prec@5 66.41 (74.69) + train[2018-10-11-14:54:21] Epoch: [015][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.029 (4.356) Prec@1 55.47 (50.90) Prec@5 78.12 (74.69) + train[2018-10-11-14:56:05] Epoch: [015][7800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.227 (4.356) Prec@1 50.00 (50.90) Prec@5 76.56 (74.69) + train[2018-10-11-14:57:50] Epoch: [015][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.255 (4.357) Prec@1 53.12 (50.89) Prec@5 75.00 (74.68) + train[2018-10-11-14:59:33] Epoch: [015][8200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.254 (4.357) Prec@1 53.91 (50.89) Prec@5 78.12 (74.68) + train[2018-10-11-15:01:17] Epoch: [015][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.491 (4.356) Prec@1 51.56 (50.90) Prec@5 75.78 (74.69) + train[2018-10-11-15:03:01] Epoch: [015][8600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.113 (4.357) Prec@1 57.81 (50.88) Prec@5 75.78 (74.68) + train[2018-10-11-15:04:45] Epoch: [015][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.679 (4.358) Prec@1 46.88 (50.87) Prec@5 74.22 (74.67) + train[2018-10-11-15:06:29] Epoch: [015][9000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.384 (4.358) Prec@1 47.66 (50.87) Prec@5 74.22 (74.67) + train[2018-10-11-15:08:13] Epoch: [015][9200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.112 (4.357) Prec@1 50.00 (50.88) Prec@5 81.25 (74.68) + train[2018-10-11-15:09:56] Epoch: [015][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.189 (4.358) Prec@1 53.12 (50.87) Prec@5 78.12 (74.67) + train[2018-10-11-15:11:40] Epoch: [015][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.079 (4.358) Prec@1 53.91 (50.87) Prec@5 79.69 (74.68) + train[2018-10-11-15:13:24] Epoch: [015][9800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.061 (4.358) Prec@1 51.56 (50.87) Prec@5 79.69 (74.68) + train[2018-10-11-15:15:08] Epoch: [015][10000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.529 (4.358) Prec@1 50.78 (50.86) Prec@5 69.53 (74.67) + train[2018-10-11-15:15:12] Epoch: [015][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.333 (4.358) Prec@1 46.67 (50.86) Prec@5 73.33 (74.67) +[2018-10-11-15:15:12] **train** Prec@1 50.86 Prec@5 74.67 Error@1 49.14 Error@5 25.33 Loss:4.358 + test [2018-10-11-15:15:16] Epoch: [015][000/391] Time 3.55 (3.55) Data 3.41 (3.41) Loss 1.095 (1.095) Prec@1 77.34 (77.34) Prec@5 89.84 (89.84) + test [2018-10-11-15:15:44] Epoch: [015][200/391] Time 0.15 (0.16) Data 0.00 (0.02) Loss 2.189 (1.718) Prec@1 46.09 (60.10) Prec@5 75.78 (84.47) + test [2018-10-11-15:16:09] Epoch: [015][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 3.353 (1.933) Prec@1 25.00 (56.42) Prec@5 57.50 (80.93) +[2018-10-11-15:16:09] **test** Prec@1 56.42 Prec@5 80.93 Error@1 43.58 Error@5 19.07 Loss:1.933 +----> Best Accuracy : Acc@1=56.44, Acc@5=80.86, Error@1=43.56, Error@5=19.14 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-11-15:16:09] [Epoch=016/250] [Need: 342:21:20] LR=0.0614 ~ 0.0614, Batch=128 + train[2018-10-11-15:16:14] Epoch: [016][000/10010] Time 4.83 (4.83) Data 4.22 (4.22) Loss 4.682 (4.682) Prec@1 46.09 (46.09) Prec@5 69.53 (69.53) + train[2018-10-11-15:17:58] Epoch: [016][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 4.282 (4.331) Prec@1 57.81 (51.78) Prec@5 74.22 (75.35) + train[2018-10-11-15:19:43] Epoch: [016][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 4.347 (4.302) Prec@1 52.34 (52.08) Prec@5 75.78 (75.60) + train[2018-10-11-15:21:28] Epoch: [016][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 4.896 (4.308) Prec@1 42.19 (52.00) Prec@5 67.97 (75.48) + train[2018-10-11-15:23:12] Epoch: [016][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 4.111 (4.312) Prec@1 53.91 (51.88) Prec@5 75.00 (75.34) + train[2018-10-11-15:24:56] Epoch: [016][1000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 4.351 (4.312) Prec@1 55.47 (51.81) Prec@5 75.00 (75.37) + train[2018-10-11-15:26:40] Epoch: [016][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 4.353 (4.312) Prec@1 45.31 (51.77) Prec@5 78.12 (75.30) + train[2018-10-11-15:28:24] Epoch: [016][1400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.190 (4.313) Prec@1 52.34 (51.70) Prec@5 75.78 (75.26) + train[2018-10-11-15:30:08] Epoch: [016][1600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.601 (4.310) Prec@1 49.22 (51.76) Prec@5 69.53 (75.31) + train[2018-10-11-15:31:52] Epoch: [016][1800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.695 (4.310) Prec@1 50.78 (51.77) Prec@5 71.09 (75.30) + train[2018-10-11-15:33:37] Epoch: [016][2000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.673 (4.310) Prec@1 42.97 (51.77) Prec@5 69.53 (75.27) + train[2018-10-11-15:35:20] Epoch: [016][2200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.932 (4.310) Prec@1 55.47 (51.77) Prec@5 80.47 (75.28) + train[2018-10-11-15:37:04] Epoch: [016][2400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.357 (4.311) Prec@1 53.91 (51.76) Prec@5 75.00 (75.26) + train[2018-10-11-15:38:48] Epoch: [016][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.440 (4.313) Prec@1 50.78 (51.73) Prec@5 72.66 (75.20) + train[2018-10-11-15:40:31] Epoch: [016][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.384 (4.314) Prec@1 50.78 (51.70) Prec@5 75.00 (75.17) + train[2018-10-11-15:42:17] Epoch: [016][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.845 (4.316) Prec@1 43.75 (51.67) Prec@5 71.09 (75.15) + train[2018-10-11-15:44:00] Epoch: [016][3200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.437 (4.317) Prec@1 51.56 (51.64) Prec@5 75.00 (75.13) + train[2018-10-11-15:45:44] Epoch: [016][3400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.214 (4.319) Prec@1 50.00 (51.62) Prec@5 74.22 (75.11) + train[2018-10-11-15:47:28] Epoch: [016][3600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.467 (4.319) Prec@1 49.22 (51.61) Prec@5 69.53 (75.11) + train[2018-10-11-15:49:12] Epoch: [016][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.172 (4.320) Prec@1 53.12 (51.58) Prec@5 78.12 (75.09) + train[2018-10-11-15:50:56] Epoch: [016][4000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.853 (4.321) Prec@1 45.31 (51.56) Prec@5 64.06 (75.09) + train[2018-10-11-15:52:40] Epoch: [016][4200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.152 (4.321) Prec@1 57.81 (51.55) Prec@5 78.91 (75.08) + train[2018-10-11-15:54:25] Epoch: [016][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.161 (4.321) Prec@1 50.00 (51.54) Prec@5 78.12 (75.07) + train[2018-10-11-15:56:09] Epoch: [016][4600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.370 (4.323) Prec@1 52.34 (51.51) Prec@5 75.78 (75.05) + train[2018-10-11-15:57:53] Epoch: [016][4800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.419 (4.325) Prec@1 50.00 (51.48) Prec@5 74.22 (75.03) + train[2018-10-11-15:59:36] Epoch: [016][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.250 (4.326) Prec@1 53.12 (51.47) Prec@5 74.22 (75.03) + train[2018-10-11-16:01:20] Epoch: [016][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.256 (4.326) Prec@1 50.78 (51.47) Prec@5 77.34 (75.03) + train[2018-10-11-16:03:05] Epoch: [016][5400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.977 (4.326) Prec@1 55.47 (51.46) Prec@5 82.03 (75.03) + train[2018-10-11-16:04:49] Epoch: [016][5600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.884 (4.326) Prec@1 59.38 (51.47) Prec@5 78.12 (75.04) + train[2018-10-11-16:06:34] Epoch: [016][5800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.964 (4.325) Prec@1 59.38 (51.47) Prec@5 77.34 (75.05) + train[2018-10-11-16:08:17] Epoch: [016][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.702 (4.326) Prec@1 57.81 (51.46) Prec@5 82.03 (75.04) + train[2018-10-11-16:10:02] Epoch: [016][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.319 (4.326) Prec@1 54.69 (51.46) Prec@5 77.34 (75.04) + train[2018-10-11-16:11:46] Epoch: [016][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.353 (4.327) Prec@1 53.91 (51.45) Prec@5 71.88 (75.03) + train[2018-10-11-16:13:30] Epoch: [016][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.079 (4.328) Prec@1 59.38 (51.44) Prec@5 77.34 (75.02) + train[2018-10-11-16:15:15] Epoch: [016][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.492 (4.328) Prec@1 48.44 (51.43) Prec@5 75.78 (75.01) + train[2018-10-11-16:16:58] Epoch: [016][7000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.169 (4.328) Prec@1 52.34 (51.43) Prec@5 77.34 (75.01) + train[2018-10-11-16:18:42] Epoch: [016][7200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.237 (4.328) Prec@1 56.25 (51.44) Prec@5 79.69 (75.01) + train[2018-10-11-16:20:26] Epoch: [016][7400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.644 (4.328) Prec@1 49.22 (51.43) Prec@5 69.53 (75.02) + train[2018-10-11-16:22:09] Epoch: [016][7600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.065 (4.329) Prec@1 59.38 (51.42) Prec@5 76.56 (75.01) + train[2018-10-11-16:23:53] Epoch: [016][7800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.511 (4.329) Prec@1 46.88 (51.42) Prec@5 71.88 (74.99) + train[2018-10-11-16:25:37] Epoch: [016][8000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.492 (4.330) Prec@1 41.41 (51.41) Prec@5 75.00 (74.99) + train[2018-10-11-16:27:22] Epoch: [016][8200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.989 (4.330) Prec@1 40.62 (51.40) Prec@5 64.84 (74.98) + train[2018-10-11-16:29:05] Epoch: [016][8400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.554 (4.331) Prec@1 50.78 (51.38) Prec@5 69.53 (74.97) + train[2018-10-11-16:30:49] Epoch: [016][8600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.954 (4.331) Prec@1 56.25 (51.37) Prec@5 78.91 (74.97) + train[2018-10-11-16:32:33] Epoch: [016][8800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.190 (4.331) Prec@1 51.56 (51.36) Prec@5 83.59 (74.98) + train[2018-10-11-16:34:16] Epoch: [016][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.486 (4.331) Prec@1 50.78 (51.37) Prec@5 73.44 (74.97) + train[2018-10-11-16:36:00] Epoch: [016][9200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.222 (4.331) Prec@1 54.69 (51.36) Prec@5 76.56 (74.96) + train[2018-10-11-16:37:44] Epoch: [016][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.453 (4.330) Prec@1 51.56 (51.37) Prec@5 71.88 (74.97) + train[2018-10-11-16:39:27] Epoch: [016][9600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.656 (4.331) Prec@1 52.34 (51.36) Prec@5 69.53 (74.97) + train[2018-10-11-16:41:10] Epoch: [016][9800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.338 (4.331) Prec@1 53.91 (51.36) Prec@5 75.00 (74.96) + train[2018-10-11-16:42:54] Epoch: [016][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.110 (4.332) Prec@1 57.03 (51.35) Prec@5 82.03 (74.94) + train[2018-10-11-16:42:58] Epoch: [016][10009/10010] Time 0.14 (0.52) Data 0.00 (0.00) Loss 4.463 (4.332) Prec@1 60.00 (51.35) Prec@5 73.33 (74.94) +[2018-10-11-16:42:58] **train** Prec@1 51.35 Prec@5 74.94 Error@1 48.65 Error@5 25.06 Loss:4.332 + test [2018-10-11-16:43:03] Epoch: [016][000/391] Time 4.58 (4.58) Data 4.45 (4.45) Loss 1.034 (1.034) Prec@1 78.12 (78.12) Prec@5 92.19 (92.19) + test [2018-10-11-16:43:30] Epoch: [016][200/391] Time 0.13 (0.16) Data 0.00 (0.02) Loss 2.195 (1.694) Prec@1 48.44 (60.73) Prec@5 78.12 (84.49) + test [2018-10-11-16:43:55] Epoch: [016][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.855 (1.929) Prec@1 23.75 (56.71) Prec@5 72.50 (80.65) +[2018-10-11-16:43:55] **test** Prec@1 56.71 Prec@5 80.65 Error@1 43.29 Error@5 19.35 Loss:1.929 +----> Best Accuracy : Acc@1=56.71, Acc@5=80.65, Error@1=43.29, Error@5=19.35 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-11-16:43:55] [Epoch=017/250] [Need: 340:50:23] LR=0.0596 ~ 0.0596, Batch=128 + train[2018-10-11-16:44:01] Epoch: [017][000/10010] Time 5.47 (5.47) Data 4.92 (4.92) Loss 4.487 (4.487) Prec@1 50.78 (50.78) Prec@5 74.22 (74.22) + train[2018-10-11-16:45:45] Epoch: [017][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 4.098 (4.276) Prec@1 57.81 (52.09) Prec@5 80.47 (75.82) + train[2018-10-11-16:47:29] Epoch: [017][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 4.472 (4.278) Prec@1 46.88 (52.16) Prec@5 71.88 (75.74) + train[2018-10-11-16:49:13] Epoch: [017][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 4.056 (4.289) Prec@1 59.38 (51.95) Prec@5 81.25 (75.55) + train[2018-10-11-16:50:56] Epoch: [017][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 4.200 (4.283) Prec@1 50.00 (52.02) Prec@5 76.56 (75.63) + train[2018-10-11-16:52:41] Epoch: [017][1000/10010] Time 0.50 (0.52) Data 0.00 (0.01) Loss 4.351 (4.285) Prec@1 57.03 (52.01) Prec@5 74.22 (75.65) + train[2018-10-11-16:54:24] Epoch: [017][1200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.097 (4.283) Prec@1 53.12 (52.02) Prec@5 77.34 (75.66) + train[2018-10-11-16:56:09] Epoch: [017][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.581 (4.285) Prec@1 50.78 (51.95) Prec@5 66.41 (75.63) + train[2018-10-11-16:57:53] Epoch: [017][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.238 (4.282) Prec@1 53.91 (51.98) Prec@5 77.34 (75.67) + train[2018-10-11-16:59:37] Epoch: [017][1800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.059 (4.279) Prec@1 59.38 (52.03) Prec@5 78.91 (75.72) + train[2018-10-11-17:01:21] Epoch: [017][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.429 (4.283) Prec@1 53.12 (51.95) Prec@5 74.22 (75.64) + train[2018-10-11-17:03:05] Epoch: [017][2200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.487 (4.282) Prec@1 49.22 (51.95) Prec@5 71.09 (75.64) + train[2018-10-11-17:04:50] Epoch: [017][2400/10010] Time 0.59 (0.52) Data 0.00 (0.00) Loss 4.116 (4.284) Prec@1 60.94 (51.93) Prec@5 78.12 (75.61) + train[2018-10-11-17:06:34] Epoch: [017][2600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.297 (4.285) Prec@1 56.25 (51.96) Prec@5 75.78 (75.61) + train[2018-10-11-17:08:18] Epoch: [017][2800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.430 (4.285) Prec@1 53.91 (51.96) Prec@5 72.66 (75.60) + train[2018-10-11-17:10:02] Epoch: [017][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.294 (4.285) Prec@1 53.12 (51.96) Prec@5 74.22 (75.60) + train[2018-10-11-17:11:47] Epoch: [017][3200/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 4.652 (4.286) Prec@1 50.78 (51.96) Prec@5 71.09 (75.59) + train[2018-10-11-17:13:31] Epoch: [017][3400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.230 (4.287) Prec@1 53.12 (51.96) Prec@5 78.91 (75.57) + train[2018-10-11-17:15:16] Epoch: [017][3600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.482 (4.288) Prec@1 46.88 (51.95) Prec@5 73.44 (75.57) + train[2018-10-11-17:16:59] Epoch: [017][3800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.522 (4.289) Prec@1 50.78 (51.96) Prec@5 70.31 (75.55) + train[2018-10-11-17:18:43] Epoch: [017][4000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.520 (4.289) Prec@1 47.66 (51.96) Prec@5 75.78 (75.56) + train[2018-10-11-17:20:28] Epoch: [017][4200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.009 (4.289) Prec@1 57.81 (51.95) Prec@5 76.56 (75.55) + train[2018-10-11-17:22:12] Epoch: [017][4400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.255 (4.290) Prec@1 48.44 (51.94) Prec@5 76.56 (75.55) + train[2018-10-11-17:23:57] Epoch: [017][4600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.519 (4.290) Prec@1 48.44 (51.94) Prec@5 71.09 (75.53) + train[2018-10-11-17:25:41] Epoch: [017][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.103 (4.290) Prec@1 53.91 (51.95) Prec@5 80.47 (75.53) + train[2018-10-11-17:27:25] Epoch: [017][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.389 (4.292) Prec@1 44.53 (51.92) Prec@5 71.09 (75.50) + train[2018-10-11-17:29:10] Epoch: [017][5200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.365 (4.291) Prec@1 47.66 (51.92) Prec@5 78.12 (75.52) + train[2018-10-11-17:30:54] Epoch: [017][5400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.282 (4.292) Prec@1 45.31 (51.92) Prec@5 75.78 (75.50) + train[2018-10-11-17:32:38] Epoch: [017][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.201 (4.292) Prec@1 51.56 (51.92) Prec@5 78.91 (75.50) + train[2018-10-11-17:34:23] Epoch: [017][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.365 (4.293) Prec@1 53.91 (51.92) Prec@5 77.34 (75.49) + train[2018-10-11-17:36:08] Epoch: [017][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.405 (4.293) Prec@1 50.00 (51.92) Prec@5 76.56 (75.49) + train[2018-10-11-17:37:52] Epoch: [017][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.480 (4.293) Prec@1 49.22 (51.92) Prec@5 71.88 (75.49) + train[2018-10-11-17:39:36] Epoch: [017][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.536 (4.293) Prec@1 48.44 (51.91) Prec@5 70.31 (75.50) + train[2018-10-11-17:41:20] Epoch: [017][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.639 (4.295) Prec@1 41.41 (51.88) Prec@5 69.53 (75.47) + train[2018-10-11-17:43:05] Epoch: [017][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.175 (4.295) Prec@1 56.25 (51.87) Prec@5 78.12 (75.46) + train[2018-10-11-17:44:49] Epoch: [017][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.918 (4.296) Prec@1 57.03 (51.86) Prec@5 80.47 (75.45) + train[2018-10-11-17:46:33] Epoch: [017][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.285 (4.296) Prec@1 49.22 (51.86) Prec@5 75.78 (75.44) + train[2018-10-11-17:48:18] Epoch: [017][7400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.575 (4.297) Prec@1 45.31 (51.85) Prec@5 70.31 (75.43) + train[2018-10-11-17:50:02] Epoch: [017][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.416 (4.297) Prec@1 50.78 (51.85) Prec@5 71.88 (75.43) + train[2018-10-11-17:51:46] Epoch: [017][7800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.198 (4.296) Prec@1 53.12 (51.86) Prec@5 75.78 (75.44) + train[2018-10-11-17:53:30] Epoch: [017][8000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.347 (4.297) Prec@1 51.56 (51.84) Prec@5 75.00 (75.43) + train[2018-10-11-17:55:14] Epoch: [017][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.199 (4.298) Prec@1 54.69 (51.83) Prec@5 76.56 (75.41) + train[2018-10-11-17:56:58] Epoch: [017][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.296 (4.298) Prec@1 50.00 (51.83) Prec@5 75.78 (75.40) + train[2018-10-11-17:58:42] Epoch: [017][8600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.518 (4.298) Prec@1 50.00 (51.83) Prec@5 70.31 (75.39) + train[2018-10-11-18:00:26] Epoch: [017][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.205 (4.299) Prec@1 56.25 (51.81) Prec@5 74.22 (75.38) + train[2018-10-11-18:02:10] Epoch: [017][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.171 (4.299) Prec@1 53.12 (51.81) Prec@5 77.34 (75.37) + train[2018-10-11-18:03:54] Epoch: [017][9200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.277 (4.300) Prec@1 54.69 (51.80) Prec@5 75.00 (75.36) + train[2018-10-11-18:05:38] Epoch: [017][9400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.899 (4.300) Prec@1 39.06 (51.79) Prec@5 69.53 (75.36) + train[2018-10-11-18:07:22] Epoch: [017][9600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.551 (4.300) Prec@1 47.66 (51.79) Prec@5 71.88 (75.35) + train[2018-10-11-18:09:06] Epoch: [017][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.007 (4.300) Prec@1 52.34 (51.79) Prec@5 81.25 (75.34) + train[2018-10-11-18:10:51] Epoch: [017][10000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.101 (4.301) Prec@1 52.34 (51.77) Prec@5 80.47 (75.33) + train[2018-10-11-18:10:55] Epoch: [017][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 3.926 (4.301) Prec@1 73.33 (51.77) Prec@5 80.00 (75.33) +[2018-10-11-18:10:55] **train** Prec@1 51.77 Prec@5 75.33 Error@1 48.23 Error@5 24.67 Loss:4.301 + test [2018-10-11-18:10:59] Epoch: [017][000/391] Time 3.43 (3.43) Data 3.28 (3.28) Loss 1.115 (1.115) Prec@1 76.56 (76.56) Prec@5 89.84 (89.84) + test [2018-10-11-18:11:27] Epoch: [017][200/391] Time 0.13 (0.16) Data 0.00 (0.02) Loss 2.171 (1.660) Prec@1 51.56 (61.45) Prec@5 78.91 (85.21) + test [2018-10-11-18:11:52] Epoch: [017][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 3.224 (1.882) Prec@1 26.25 (57.53) Prec@5 65.00 (81.41) +[2018-10-11-18:11:52] **test** Prec@1 57.53 Prec@5 81.41 Error@1 42.47 Error@5 18.59 Loss:1.882 +----> Best Accuracy : Acc@1=57.53, Acc@5=81.41, Error@1=42.47, Error@5=18.59 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-11-18:11:52] [Epoch=018/250] [Need: 340:02:36] LR=0.0578 ~ 0.0578, Batch=128 + train[2018-10-11-18:11:57] Epoch: [018][000/10010] Time 4.71 (4.71) Data 4.01 (4.01) Loss 4.555 (4.555) Prec@1 48.44 (48.44) Prec@5 71.09 (71.09) + train[2018-10-11-18:13:40] Epoch: [018][200/10010] Time 0.51 (0.54) Data 0.00 (0.02) Loss 4.245 (4.253) Prec@1 50.00 (52.24) Prec@5 75.78 (76.11) + train[2018-10-11-18:15:24] Epoch: [018][400/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 4.227 (4.240) Prec@1 57.03 (52.60) Prec@5 78.12 (76.21) + train[2018-10-11-18:17:07] Epoch: [018][600/10010] Time 0.50 (0.52) Data 0.00 (0.01) Loss 4.102 (4.236) Prec@1 57.81 (52.83) Prec@5 78.91 (76.24) + train[2018-10-11-18:18:51] Epoch: [018][800/10010] Time 0.50 (0.52) Data 0.00 (0.01) Loss 4.626 (4.240) Prec@1 47.66 (52.74) Prec@5 67.19 (76.12) + train[2018-10-11-18:20:35] Epoch: [018][1000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.049 (4.244) Prec@1 54.69 (52.74) Prec@5 77.34 (76.07) + train[2018-10-11-18:22:18] Epoch: [018][1200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.236 (4.246) Prec@1 52.34 (52.71) Prec@5 77.34 (76.08) + train[2018-10-11-18:24:02] Epoch: [018][1400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.494 (4.249) Prec@1 50.78 (52.66) Prec@5 71.09 (75.99) + train[2018-10-11-18:25:47] Epoch: [018][1600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.474 (4.250) Prec@1 53.91 (52.63) Prec@5 71.09 (76.00) + train[2018-10-11-18:27:30] Epoch: [018][1800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.144 (4.250) Prec@1 48.44 (52.65) Prec@5 74.22 (75.99) + train[2018-10-11-18:29:14] Epoch: [018][2000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.590 (4.251) Prec@1 48.44 (52.61) Prec@5 68.75 (75.95) + train[2018-10-11-18:30:57] Epoch: [018][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.606 (4.252) Prec@1 43.75 (52.58) Prec@5 67.19 (75.93) + train[2018-10-11-18:32:42] Epoch: [018][2400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.582 (4.253) Prec@1 52.34 (52.55) Prec@5 71.88 (75.92) + train[2018-10-11-18:34:26] Epoch: [018][2600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.051 (4.255) Prec@1 53.12 (52.51) Prec@5 80.47 (75.89) + train[2018-10-11-18:36:10] Epoch: [018][2800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.347 (4.256) Prec@1 51.56 (52.51) Prec@5 72.66 (75.86) + train[2018-10-11-18:37:53] Epoch: [018][3000/10010] Time 0.59 (0.52) Data 0.00 (0.00) Loss 4.168 (4.256) Prec@1 50.78 (52.53) Prec@5 75.78 (75.86) + train[2018-10-11-18:39:37] Epoch: [018][3200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.253 (4.258) Prec@1 58.59 (52.49) Prec@5 76.56 (75.86) + train[2018-10-11-18:41:21] Epoch: [018][3400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.694 (4.260) Prec@1 42.97 (52.44) Prec@5 67.19 (75.84) + train[2018-10-11-18:43:05] Epoch: [018][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.354 (4.262) Prec@1 51.56 (52.43) Prec@5 76.56 (75.81) + train[2018-10-11-18:44:48] Epoch: [018][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.379 (4.263) Prec@1 49.22 (52.43) Prec@5 75.00 (75.80) + train[2018-10-11-18:46:32] Epoch: [018][4000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.502 (4.264) Prec@1 48.44 (52.41) Prec@5 70.31 (75.79) + train[2018-10-11-18:48:17] Epoch: [018][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.556 (4.265) Prec@1 42.97 (52.39) Prec@5 74.22 (75.78) + train[2018-10-11-18:50:01] Epoch: [018][4400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.343 (4.265) Prec@1 50.00 (52.38) Prec@5 78.91 (75.78) + train[2018-10-11-18:51:45] Epoch: [018][4600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.903 (4.266) Prec@1 57.03 (52.37) Prec@5 80.47 (75.78) + train[2018-10-11-18:53:29] Epoch: [018][4800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.466 (4.267) Prec@1 50.00 (52.35) Prec@5 71.88 (75.78) + train[2018-10-11-18:55:12] Epoch: [018][5000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.291 (4.268) Prec@1 54.69 (52.33) Prec@5 72.66 (75.78) + train[2018-10-11-18:56:57] Epoch: [018][5200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.863 (4.267) Prec@1 60.94 (52.35) Prec@5 77.34 (75.79) + train[2018-10-11-18:58:41] Epoch: [018][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.273 (4.267) Prec@1 49.22 (52.37) Prec@5 71.88 (75.79) + train[2018-10-11-19:00:26] Epoch: [018][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.540 (4.267) Prec@1 47.66 (52.37) Prec@5 71.09 (75.78) + train[2018-10-11-19:02:09] Epoch: [018][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.954 (4.268) Prec@1 54.69 (52.36) Prec@5 78.12 (75.78) + train[2018-10-11-19:03:53] Epoch: [018][6000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.077 (4.268) Prec@1 57.81 (52.35) Prec@5 78.12 (75.77) + train[2018-10-11-19:05:37] Epoch: [018][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.360 (4.269) Prec@1 50.78 (52.32) Prec@5 82.03 (75.76) + train[2018-10-11-19:07:21] Epoch: [018][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.211 (4.269) Prec@1 56.25 (52.31) Prec@5 75.00 (75.75) + train[2018-10-11-19:09:05] Epoch: [018][6600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.014 (4.269) Prec@1 51.56 (52.30) Prec@5 82.03 (75.75) + train[2018-10-11-19:10:49] Epoch: [018][6800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.906 (4.269) Prec@1 56.25 (52.31) Prec@5 79.69 (75.75) + train[2018-10-11-19:12:33] Epoch: [018][7000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.262 (4.270) Prec@1 50.78 (52.30) Prec@5 80.47 (75.74) + train[2018-10-11-19:14:17] Epoch: [018][7200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.319 (4.271) Prec@1 51.56 (52.29) Prec@5 73.44 (75.72) + train[2018-10-11-19:16:01] Epoch: [018][7400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.655 (4.272) Prec@1 47.66 (52.27) Prec@5 67.97 (75.71) + train[2018-10-11-19:17:45] Epoch: [018][7600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.336 (4.272) Prec@1 50.00 (52.26) Prec@5 74.22 (75.70) + train[2018-10-11-19:19:28] Epoch: [018][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.327 (4.272) Prec@1 49.22 (52.27) Prec@5 75.78 (75.70) + train[2018-10-11-19:21:13] Epoch: [018][8000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.223 (4.272) Prec@1 50.00 (52.27) Prec@5 77.34 (75.70) + train[2018-10-11-19:22:56] Epoch: [018][8200/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 4.131 (4.273) Prec@1 54.69 (52.26) Prec@5 78.91 (75.70) + train[2018-10-11-19:24:41] Epoch: [018][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.874 (4.273) Prec@1 43.75 (52.25) Prec@5 67.97 (75.70) + train[2018-10-11-19:26:25] Epoch: [018][8600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.543 (4.273) Prec@1 50.00 (52.24) Prec@5 70.31 (75.69) + train[2018-10-11-19:28:09] Epoch: [018][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.396 (4.274) Prec@1 48.44 (52.23) Prec@5 73.44 (75.69) + train[2018-10-11-19:29:53] Epoch: [018][9000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.331 (4.274) Prec@1 52.34 (52.22) Prec@5 75.00 (75.69) + train[2018-10-11-19:31:37] Epoch: [018][9200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.332 (4.274) Prec@1 50.00 (52.22) Prec@5 71.88 (75.69) + train[2018-10-11-19:33:21] Epoch: [018][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.190 (4.274) Prec@1 48.44 (52.22) Prec@5 75.78 (75.69) + train[2018-10-11-19:35:04] Epoch: [018][9600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.377 (4.274) Prec@1 44.53 (52.22) Prec@5 81.25 (75.69) + train[2018-10-11-19:36:47] Epoch: [018][9800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.022 (4.274) Prec@1 55.47 (52.21) Prec@5 77.34 (75.69) + train[2018-10-11-19:38:31] Epoch: [018][10000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.980 (4.274) Prec@1 55.47 (52.21) Prec@5 82.03 (75.69) + train[2018-10-11-19:38:35] Epoch: [018][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.753 (4.274) Prec@1 60.00 (52.21) Prec@5 80.00 (75.69) +[2018-10-11-19:38:35] **train** Prec@1 52.21 Prec@5 75.69 Error@1 47.79 Error@5 24.31 Loss:4.274 + test [2018-10-11-19:38:39] Epoch: [018][000/391] Time 3.86 (3.86) Data 3.73 (3.73) Loss 0.994 (0.994) Prec@1 77.34 (77.34) Prec@5 90.62 (90.62) + test [2018-10-11-19:39:07] Epoch: [018][200/391] Time 0.16 (0.16) Data 0.00 (0.02) Loss 2.748 (1.656) Prec@1 39.06 (61.66) Prec@5 66.41 (85.41) + test [2018-10-11-19:39:32] Epoch: [018][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.974 (1.878) Prec@1 31.25 (57.77) Prec@5 66.25 (81.49) +[2018-10-11-19:39:32] **test** Prec@1 57.77 Prec@5 81.49 Error@1 42.23 Error@5 18.51 Loss:1.878 +----> Best Accuracy : Acc@1=57.77, Acc@5=81.49, Error@1=42.23, Error@5=18.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-11-19:39:33] [Epoch=019/250] [Need: 337:34:10] LR=0.0561 ~ 0.0561, Batch=128 + train[2018-10-11-19:39:37] Epoch: [019][000/10010] Time 4.37 (4.37) Data 3.77 (3.77) Loss 3.978 (3.978) Prec@1 52.34 (52.34) Prec@5 81.25 (81.25) + train[2018-10-11-19:41:22] Epoch: [019][200/10010] Time 0.54 (0.54) Data 0.00 (0.02) Loss 3.956 (4.243) Prec@1 53.12 (52.69) Prec@5 80.47 (76.23) + train[2018-10-11-19:43:05] Epoch: [019][400/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 4.397 (4.230) Prec@1 54.69 (53.02) Prec@5 72.66 (76.45) + train[2018-10-11-19:44:48] Epoch: [019][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 4.070 (4.231) Prec@1 54.69 (52.98) Prec@5 79.69 (76.44) + train[2018-10-11-19:46:33] Epoch: [019][800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.298 (4.226) Prec@1 52.34 (53.06) Prec@5 72.66 (76.46) + train[2018-10-11-19:48:17] Epoch: [019][1000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.722 (4.224) Prec@1 42.97 (53.09) Prec@5 67.19 (76.39) + train[2018-10-11-19:50:01] Epoch: [019][1200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.263 (4.224) Prec@1 49.22 (53.15) Prec@5 81.25 (76.38) + train[2018-10-11-19:51:44] Epoch: [019][1400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.459 (4.225) Prec@1 48.44 (53.09) Prec@5 76.56 (76.34) + train[2018-10-11-19:53:27] Epoch: [019][1600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.146 (4.225) Prec@1 52.34 (53.07) Prec@5 80.47 (76.34) + train[2018-10-11-19:55:11] Epoch: [019][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.083 (4.226) Prec@1 52.34 (53.06) Prec@5 77.34 (76.33) + train[2018-10-11-19:56:55] Epoch: [019][2000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.845 (4.226) Prec@1 56.25 (53.00) Prec@5 82.03 (76.32) + train[2018-10-11-19:58:39] Epoch: [019][2200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.469 (4.227) Prec@1 51.56 (52.98) Prec@5 71.09 (76.33) + train[2018-10-11-20:00:23] Epoch: [019][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.307 (4.228) Prec@1 50.00 (52.96) Prec@5 79.69 (76.32) + train[2018-10-11-20:02:07] Epoch: [019][2600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.273 (4.228) Prec@1 50.00 (52.98) Prec@5 75.78 (76.34) + train[2018-10-11-20:03:52] Epoch: [019][2800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.884 (4.227) Prec@1 57.81 (52.97) Prec@5 78.91 (76.35) + train[2018-10-11-20:05:36] Epoch: [019][3000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.232 (4.228) Prec@1 44.53 (52.95) Prec@5 79.69 (76.34) + train[2018-10-11-20:07:20] Epoch: [019][3200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.471 (4.229) Prec@1 48.44 (52.91) Prec@5 71.09 (76.33) + train[2018-10-11-20:09:04] Epoch: [019][3400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.223 (4.230) Prec@1 55.47 (52.91) Prec@5 74.22 (76.32) + train[2018-10-11-20:10:48] Epoch: [019][3600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.931 (4.231) Prec@1 57.81 (52.87) Prec@5 81.25 (76.31) + train[2018-10-11-20:12:32] Epoch: [019][3800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.458 (4.233) Prec@1 50.78 (52.84) Prec@5 70.31 (76.28) + train[2018-10-11-20:14:16] Epoch: [019][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.633 (4.232) Prec@1 47.66 (52.87) Prec@5 74.22 (76.28) + train[2018-10-11-20:15:59] Epoch: [019][4200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.478 (4.234) Prec@1 47.66 (52.83) Prec@5 72.66 (76.26) + train[2018-10-11-20:17:43] Epoch: [019][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.315 (4.235) Prec@1 53.12 (52.80) Prec@5 72.66 (76.24) + train[2018-10-11-20:19:27] Epoch: [019][4600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.198 (4.234) Prec@1 46.88 (52.83) Prec@5 78.91 (76.27) + train[2018-10-11-20:21:11] Epoch: [019][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.351 (4.233) Prec@1 50.78 (52.83) Prec@5 72.66 (76.27) + train[2018-10-11-20:22:55] Epoch: [019][5000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.719 (4.234) Prec@1 46.09 (52.82) Prec@5 67.97 (76.27) + train[2018-10-11-20:24:39] Epoch: [019][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.457 (4.234) Prec@1 46.88 (52.81) Prec@5 71.09 (76.25) + train[2018-10-11-20:26:22] Epoch: [019][5400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.478 (4.235) Prec@1 49.22 (52.80) Prec@5 71.88 (76.24) + train[2018-10-11-20:28:06] Epoch: [019][5600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.400 (4.236) Prec@1 52.34 (52.78) Prec@5 74.22 (76.23) + train[2018-10-11-20:29:50] Epoch: [019][5800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.313 (4.236) Prec@1 54.69 (52.79) Prec@5 72.66 (76.22) + train[2018-10-11-20:31:33] Epoch: [019][6000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.049 (4.236) Prec@1 54.69 (52.79) Prec@5 78.91 (76.21) + train[2018-10-11-20:33:17] Epoch: [019][6200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.288 (4.237) Prec@1 52.34 (52.77) Prec@5 80.47 (76.20) + train[2018-10-11-20:35:00] Epoch: [019][6400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.559 (4.238) Prec@1 49.22 (52.77) Prec@5 67.19 (76.19) + train[2018-10-11-20:36:44] Epoch: [019][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.939 (4.238) Prec@1 60.16 (52.77) Prec@5 80.47 (76.19) + train[2018-10-11-20:38:28] Epoch: [019][6800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.132 (4.239) Prec@1 57.03 (52.76) Prec@5 74.22 (76.17) + train[2018-10-11-20:40:13] Epoch: [019][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.356 (4.240) Prec@1 50.78 (52.74) Prec@5 73.44 (76.15) + train[2018-10-11-20:41:57] Epoch: [019][7200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.181 (4.240) Prec@1 58.59 (52.74) Prec@5 75.78 (76.16) + train[2018-10-11-20:43:41] Epoch: [019][7400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 4.409 (4.241) Prec@1 46.09 (52.73) Prec@5 71.88 (76.14) + train[2018-10-11-20:45:25] Epoch: [019][7600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.580 (4.241) Prec@1 51.56 (52.72) Prec@5 71.88 (76.13) + train[2018-10-11-20:47:09] Epoch: [019][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.215 (4.242) Prec@1 54.69 (52.71) Prec@5 78.12 (76.12) + train[2018-10-11-20:48:53] Epoch: [019][8000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.559 (4.242) Prec@1 50.00 (52.71) Prec@5 71.09 (76.11) + train[2018-10-11-20:50:36] Epoch: [019][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.268 (4.243) Prec@1 53.12 (52.70) Prec@5 75.00 (76.10) + train[2018-10-11-20:52:20] Epoch: [019][8400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.061 (4.243) Prec@1 57.81 (52.70) Prec@5 75.78 (76.10) + train[2018-10-11-20:54:03] Epoch: [019][8600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.199 (4.243) Prec@1 50.00 (52.69) Prec@5 78.12 (76.10) + train[2018-10-11-20:55:47] Epoch: [019][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.137 (4.243) Prec@1 51.56 (52.69) Prec@5 76.56 (76.10) + train[2018-10-11-20:57:30] Epoch: [019][9000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.314 (4.243) Prec@1 48.44 (52.69) Prec@5 70.31 (76.10) + train[2018-10-11-20:59:14] Epoch: [019][9200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.720 (4.243) Prec@1 45.31 (52.69) Prec@5 68.75 (76.10) + train[2018-10-11-21:00:57] Epoch: [019][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.413 (4.244) Prec@1 46.88 (52.68) Prec@5 70.31 (76.09) + train[2018-10-11-21:02:41] Epoch: [019][9600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.099 (4.244) Prec@1 53.91 (52.68) Prec@5 74.22 (76.10) + train[2018-10-11-21:04:24] Epoch: [019][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.571 (4.244) Prec@1 46.09 (52.66) Prec@5 71.09 (76.09) + train[2018-10-11-21:06:08] Epoch: [019][10000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.236 (4.245) Prec@1 54.69 (52.65) Prec@5 71.88 (76.09) + train[2018-10-11-21:06:12] Epoch: [019][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 3.988 (4.245) Prec@1 66.67 (52.65) Prec@5 86.67 (76.09) +[2018-10-11-21:06:13] **train** Prec@1 52.65 Prec@5 76.09 Error@1 47.35 Error@5 23.91 Loss:4.245 + test [2018-10-11-21:06:16] Epoch: [019][000/391] Time 3.91 (3.91) Data 3.77 (3.77) Loss 1.127 (1.127) Prec@1 76.56 (76.56) Prec@5 93.75 (93.75) + test [2018-10-11-21:06:44] Epoch: [019][200/391] Time 0.13 (0.16) Data 0.00 (0.02) Loss 2.984 (1.665) Prec@1 29.69 (61.23) Prec@5 59.38 (85.15) + test [2018-10-11-21:07:10] Epoch: [019][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.835 (1.890) Prec@1 30.00 (57.51) Prec@5 71.25 (81.50) +[2018-10-11-21:07:10] **test** Prec@1 57.51 Prec@5 81.50 Error@1 42.49 Error@5 18.50 Loss:1.890 +----> Best Accuracy : Acc@1=57.77, Acc@5=81.49, Error@1=42.23, Error@5=18.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-11-21:07:10] [Epoch=020/250] [Need: 335:52:52] LR=0.0544 ~ 0.0544, Batch=128 + train[2018-10-11-21:07:15] Epoch: [020][000/10010] Time 4.95 (4.95) Data 4.35 (4.35) Loss 4.011 (4.011) Prec@1 59.38 (59.38) Prec@5 76.56 (76.56) + train[2018-10-11-21:08:59] Epoch: [020][200/10010] Time 0.54 (0.54) Data 0.00 (0.02) Loss 4.332 (4.211) Prec@1 50.00 (53.20) Prec@5 75.78 (76.78) + train[2018-10-11-21:10:43] Epoch: [020][400/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 4.217 (4.202) Prec@1 57.03 (53.37) Prec@5 78.12 (76.77) + train[2018-10-11-21:12:26] Epoch: [020][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 4.400 (4.195) Prec@1 48.44 (53.40) Prec@5 75.78 (76.83) + train[2018-10-11-21:14:10] Epoch: [020][800/10010] Time 0.53 (0.52) Data 0.00 (0.01) Loss 3.865 (4.196) Prec@1 61.72 (53.55) Prec@5 80.47 (76.79) + train[2018-10-11-21:15:53] Epoch: [020][1000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.287 (4.196) Prec@1 53.91 (53.54) Prec@5 75.00 (76.73) + train[2018-10-11-21:17:37] Epoch: [020][1200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.275 (4.196) Prec@1 47.66 (53.48) Prec@5 78.12 (76.71) + train[2018-10-11-21:19:20] Epoch: [020][1400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.164 (4.193) Prec@1 55.47 (53.54) Prec@5 77.34 (76.78) + train[2018-10-11-21:21:04] Epoch: [020][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.171 (4.194) Prec@1 50.00 (53.55) Prec@5 75.78 (76.77) + train[2018-10-11-21:22:48] Epoch: [020][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.152 (4.196) Prec@1 56.25 (53.53) Prec@5 74.22 (76.75) + train[2018-10-11-21:24:32] Epoch: [020][2000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.084 (4.198) Prec@1 62.50 (53.49) Prec@5 77.34 (76.73) + train[2018-10-11-21:26:15] Epoch: [020][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.526 (4.199) Prec@1 48.44 (53.49) Prec@5 69.53 (76.71) + train[2018-10-11-21:27:59] Epoch: [020][2400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.882 (4.200) Prec@1 57.81 (53.46) Prec@5 79.69 (76.68) + train[2018-10-11-21:29:42] Epoch: [020][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.380 (4.202) Prec@1 53.91 (53.42) Prec@5 76.56 (76.66) + train[2018-10-11-21:31:26] Epoch: [020][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.195 (4.199) Prec@1 57.03 (53.45) Prec@5 78.91 (76.71) + train[2018-10-11-21:33:09] Epoch: [020][3000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.563 (4.199) Prec@1 51.56 (53.46) Prec@5 71.09 (76.68) + train[2018-10-11-21:34:53] Epoch: [020][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.340 (4.201) Prec@1 50.00 (53.41) Prec@5 78.12 (76.66) + train[2018-10-11-21:36:36] Epoch: [020][3400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.121 (4.204) Prec@1 52.34 (53.35) Prec@5 76.56 (76.61) + train[2018-10-11-21:38:20] Epoch: [020][3600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.930 (4.203) Prec@1 53.91 (53.37) Prec@5 78.91 (76.61) + train[2018-10-11-21:40:04] Epoch: [020][3800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.843 (4.204) Prec@1 57.81 (53.34) Prec@5 81.25 (76.60) + train[2018-10-11-21:41:48] Epoch: [020][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.703 (4.205) Prec@1 64.06 (53.32) Prec@5 81.25 (76.60) + train[2018-10-11-21:43:32] Epoch: [020][4200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.481 (4.206) Prec@1 49.22 (53.31) Prec@5 70.31 (76.59) + train[2018-10-11-21:45:15] Epoch: [020][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.236 (4.208) Prec@1 57.81 (53.27) Prec@5 75.00 (76.57) + train[2018-10-11-21:46:59] Epoch: [020][4600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.809 (4.208) Prec@1 57.03 (53.27) Prec@5 79.69 (76.56) + train[2018-10-11-21:48:43] Epoch: [020][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.023 (4.210) Prec@1 50.78 (53.23) Prec@5 76.56 (76.53) + train[2018-10-11-21:50:27] Epoch: [020][5000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.240 (4.210) Prec@1 52.34 (53.23) Prec@5 74.22 (76.53) + train[2018-10-11-21:52:12] Epoch: [020][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.945 (4.211) Prec@1 56.25 (53.20) Prec@5 79.69 (76.53) + train[2018-10-11-21:53:56] Epoch: [020][5400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.074 (4.211) Prec@1 57.81 (53.19) Prec@5 77.34 (76.53) + train[2018-10-11-21:55:40] Epoch: [020][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.125 (4.211) Prec@1 56.25 (53.21) Prec@5 76.56 (76.53) + train[2018-10-11-21:57:23] Epoch: [020][5800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.942 (4.211) Prec@1 53.91 (53.21) Prec@5 81.25 (76.52) + train[2018-10-11-21:59:07] Epoch: [020][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.324 (4.213) Prec@1 51.56 (53.18) Prec@5 73.44 (76.50) + train[2018-10-11-22:00:51] Epoch: [020][6200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.254 (4.213) Prec@1 50.78 (53.18) Prec@5 74.22 (76.50) + train[2018-10-11-22:02:35] Epoch: [020][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.264 (4.213) Prec@1 51.56 (53.18) Prec@5 78.91 (76.50) + train[2018-10-11-22:04:18] Epoch: [020][6600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.701 (4.214) Prec@1 46.09 (53.16) Prec@5 71.88 (76.49) + train[2018-10-11-22:06:01] Epoch: [020][6800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.145 (4.214) Prec@1 54.69 (53.16) Prec@5 77.34 (76.49) + train[2018-10-11-22:07:45] Epoch: [020][7000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.996 (4.214) Prec@1 57.03 (53.16) Prec@5 76.56 (76.49) + train[2018-10-11-22:09:28] Epoch: [020][7200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.292 (4.214) Prec@1 55.47 (53.15) Prec@5 75.78 (76.48) + train[2018-10-11-22:11:12] Epoch: [020][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.033 (4.215) Prec@1 57.03 (53.13) Prec@5 76.56 (76.47) + train[2018-10-11-22:12:56] Epoch: [020][7600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.940 (4.215) Prec@1 61.72 (53.13) Prec@5 79.69 (76.48) + train[2018-10-11-22:14:39] Epoch: [020][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.076 (4.215) Prec@1 53.91 (53.13) Prec@5 78.91 (76.48) + train[2018-10-11-22:16:23] Epoch: [020][8000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.055 (4.215) Prec@1 58.59 (53.13) Prec@5 81.25 (76.48) + train[2018-10-11-22:18:07] Epoch: [020][8200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.518 (4.215) Prec@1 47.66 (53.12) Prec@5 72.66 (76.48) + train[2018-10-11-22:19:51] Epoch: [020][8400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.070 (4.215) Prec@1 53.91 (53.12) Prec@5 73.44 (76.48) + train[2018-10-11-22:21:35] Epoch: [020][8600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.328 (4.216) Prec@1 52.34 (53.12) Prec@5 75.00 (76.47) + train[2018-10-11-22:23:19] Epoch: [020][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.035 (4.216) Prec@1 55.47 (53.11) Prec@5 75.00 (76.47) + train[2018-10-11-22:25:02] Epoch: [020][9000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.820 (4.216) Prec@1 58.59 (53.11) Prec@5 82.03 (76.47) + train[2018-10-11-22:26:46] Epoch: [020][9200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.237 (4.216) Prec@1 56.25 (53.10) Prec@5 79.69 (76.46) + train[2018-10-11-22:28:30] Epoch: [020][9400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.125 (4.217) Prec@1 53.12 (53.09) Prec@5 75.78 (76.45) + train[2018-10-11-22:30:13] Epoch: [020][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.275 (4.218) Prec@1 46.09 (53.08) Prec@5 75.00 (76.43) + train[2018-10-11-22:31:57] Epoch: [020][9800/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 4.336 (4.218) Prec@1 50.78 (53.08) Prec@5 71.88 (76.43) + train[2018-10-11-22:33:41] Epoch: [020][10000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.456 (4.219) Prec@1 47.66 (53.07) Prec@5 70.31 (76.42) + train[2018-10-11-22:33:45] Epoch: [020][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.641 (4.219) Prec@1 66.67 (53.06) Prec@5 73.33 (76.42) +[2018-10-11-22:33:45] **train** Prec@1 53.06 Prec@5 76.42 Error@1 46.94 Error@5 23.58 Loss:4.219 + test [2018-10-11-22:33:49] Epoch: [020][000/391] Time 4.07 (4.07) Data 3.94 (3.94) Loss 1.331 (1.331) Prec@1 71.09 (71.09) Prec@5 87.50 (87.50) + test [2018-10-11-22:34:17] Epoch: [020][200/391] Time 0.12 (0.16) Data 0.00 (0.02) Loss 1.943 (1.616) Prec@1 45.31 (62.10) Prec@5 82.81 (85.64) + test [2018-10-11-22:34:42] Epoch: [020][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.823 (1.842) Prec@1 30.00 (58.13) Prec@5 68.75 (81.92) +[2018-10-11-22:34:42] **test** Prec@1 58.13 Prec@5 81.92 Error@1 41.87 Error@5 18.08 Loss:1.842 +----> Best Accuracy : Acc@1=58.13, Acc@5=81.92, Error@1=41.87, Error@5=18.08 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-11-22:34:42] [Epoch=021/250] [Need: 334:05:25] LR=0.0527 ~ 0.0527, Batch=128 + train[2018-10-11-22:34:46] Epoch: [021][000/10010] Time 4.04 (4.04) Data 3.38 (3.38) Loss 4.161 (4.161) Prec@1 53.91 (53.91) Prec@5 78.91 (78.91) + train[2018-10-11-22:36:31] Epoch: [021][200/10010] Time 0.54 (0.54) Data 0.00 (0.02) Loss 4.315 (4.155) Prec@1 51.56 (54.05) Prec@5 75.00 (77.13) + train[2018-10-11-22:38:15] Epoch: [021][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.989 (4.166) Prec@1 60.94 (53.67) Prec@5 79.69 (77.04) + train[2018-10-11-22:39:59] Epoch: [021][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 4.370 (4.169) Prec@1 52.34 (53.73) Prec@5 71.09 (77.04) + train[2018-10-11-22:41:44] Epoch: [021][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 4.079 (4.168) Prec@1 50.78 (53.80) Prec@5 81.25 (77.10) + train[2018-10-11-22:43:27] Epoch: [021][1000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.160 (4.167) Prec@1 53.12 (53.78) Prec@5 75.78 (77.14) + train[2018-10-11-22:45:12] Epoch: [021][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.445 (4.170) Prec@1 50.78 (53.75) Prec@5 72.66 (77.13) + train[2018-10-11-22:46:56] Epoch: [021][1400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.386 (4.171) Prec@1 46.88 (53.76) Prec@5 72.66 (77.10) + train[2018-10-11-22:48:40] Epoch: [021][1600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.390 (4.174) Prec@1 49.22 (53.74) Prec@5 74.22 (77.04) + train[2018-10-11-22:50:23] Epoch: [021][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.727 (4.176) Prec@1 63.28 (53.72) Prec@5 81.25 (77.02) + train[2018-10-11-22:52:07] Epoch: [021][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.995 (4.178) Prec@1 57.81 (53.68) Prec@5 78.12 (76.97) + train[2018-10-11-22:53:51] Epoch: [021][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.327 (4.180) Prec@1 52.34 (53.67) Prec@5 74.22 (76.96) + train[2018-10-11-22:55:34] Epoch: [021][2400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.208 (4.177) Prec@1 53.91 (53.70) Prec@5 75.00 (76.99) + train[2018-10-11-22:57:18] Epoch: [021][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.137 (4.176) Prec@1 52.34 (53.71) Prec@5 81.25 (77.00) + train[2018-10-11-22:59:02] Epoch: [021][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.647 (4.175) Prec@1 51.56 (53.72) Prec@5 74.22 (77.00) + train[2018-10-11-23:00:46] Epoch: [021][3000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.510 (4.176) Prec@1 53.12 (53.70) Prec@5 75.78 (76.99) + train[2018-10-11-23:02:30] Epoch: [021][3200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.015 (4.178) Prec@1 57.81 (53.66) Prec@5 78.12 (76.98) + train[2018-10-11-23:04:14] Epoch: [021][3400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.808 (4.179) Prec@1 60.16 (53.65) Prec@5 79.69 (76.97) + train[2018-10-11-23:05:57] Epoch: [021][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.025 (4.180) Prec@1 57.81 (53.65) Prec@5 80.47 (76.95) + train[2018-10-11-23:07:42] Epoch: [021][3800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.679 (4.181) Prec@1 62.50 (53.64) Prec@5 84.38 (76.94) + train[2018-10-11-23:09:25] Epoch: [021][4000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.830 (4.181) Prec@1 59.38 (53.64) Prec@5 81.25 (76.93) + train[2018-10-11-23:11:08] Epoch: [021][4200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.294 (4.180) Prec@1 53.12 (53.66) Prec@5 77.34 (76.93) + train[2018-10-11-23:12:52] Epoch: [021][4400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.295 (4.181) Prec@1 53.12 (53.65) Prec@5 71.88 (76.92) + train[2018-10-11-23:14:35] Epoch: [021][4600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.159 (4.181) Prec@1 53.12 (53.64) Prec@5 80.47 (76.93) + train[2018-10-11-23:16:19] Epoch: [021][4800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.230 (4.181) Prec@1 48.44 (53.64) Prec@5 78.91 (76.92) + train[2018-10-11-23:18:02] Epoch: [021][5000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.287 (4.181) Prec@1 52.34 (53.64) Prec@5 75.00 (76.92) + train[2018-10-11-23:19:46] Epoch: [021][5200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.227 (4.181) Prec@1 56.25 (53.64) Prec@5 75.78 (76.93) + train[2018-10-11-23:21:29] Epoch: [021][5400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.455 (4.181) Prec@1 44.53 (53.64) Prec@5 72.66 (76.93) + train[2018-10-11-23:23:12] Epoch: [021][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.058 (4.181) Prec@1 58.59 (53.63) Prec@5 78.12 (76.92) + train[2018-10-11-23:24:55] Epoch: [021][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.228 (4.181) Prec@1 50.00 (53.65) Prec@5 75.78 (76.91) + train[2018-10-11-23:26:39] Epoch: [021][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.043 (4.182) Prec@1 54.69 (53.63) Prec@5 79.69 (76.89) + train[2018-10-11-23:28:22] Epoch: [021][6200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.393 (4.181) Prec@1 50.00 (53.61) Prec@5 69.53 (76.90) + train[2018-10-11-23:30:06] Epoch: [021][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.070 (4.181) Prec@1 58.59 (53.61) Prec@5 75.00 (76.89) + train[2018-10-11-23:31:50] Epoch: [021][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.216 (4.182) Prec@1 50.78 (53.61) Prec@5 77.34 (76.88) + train[2018-10-11-23:33:34] Epoch: [021][6800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.203 (4.183) Prec@1 53.91 (53.60) Prec@5 74.22 (76.87) + train[2018-10-11-23:35:17] Epoch: [021][7000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.332 (4.184) Prec@1 52.34 (53.58) Prec@5 75.78 (76.86) + train[2018-10-11-23:37:01] Epoch: [021][7200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.046 (4.184) Prec@1 55.47 (53.57) Prec@5 81.25 (76.85) + train[2018-10-11-23:38:45] Epoch: [021][7400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.409 (4.185) Prec@1 49.22 (53.56) Prec@5 76.56 (76.84) + train[2018-10-11-23:40:28] Epoch: [021][7600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.548 (4.185) Prec@1 44.53 (53.55) Prec@5 71.88 (76.83) + train[2018-10-11-23:42:12] Epoch: [021][7800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.385 (4.186) Prec@1 52.34 (53.54) Prec@5 72.66 (76.82) + train[2018-10-11-23:43:56] Epoch: [021][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.040 (4.186) Prec@1 51.56 (53.53) Prec@5 78.91 (76.81) + train[2018-10-11-23:45:39] Epoch: [021][8200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.172 (4.187) Prec@1 50.00 (53.52) Prec@5 75.00 (76.80) + train[2018-10-11-23:47:23] Epoch: [021][8400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.942 (4.187) Prec@1 57.03 (53.52) Prec@5 78.91 (76.80) + train[2018-10-11-23:49:07] Epoch: [021][8600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.440 (4.187) Prec@1 53.12 (53.52) Prec@5 71.09 (76.79) + train[2018-10-11-23:50:50] Epoch: [021][8800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.015 (4.187) Prec@1 57.03 (53.52) Prec@5 81.25 (76.79) + train[2018-10-11-23:52:33] Epoch: [021][9000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.881 (4.187) Prec@1 57.03 (53.51) Prec@5 81.25 (76.79) + train[2018-10-11-23:54:18] Epoch: [021][9200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.192 (4.188) Prec@1 53.91 (53.51) Prec@5 78.91 (76.79) + train[2018-10-11-23:56:01] Epoch: [021][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.989 (4.188) Prec@1 60.94 (53.50) Prec@5 78.91 (76.78) + train[2018-10-11-23:57:45] Epoch: [021][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.545 (4.189) Prec@1 40.62 (53.49) Prec@5 75.78 (76.77) + train[2018-10-11-23:59:30] Epoch: [021][9800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.144 (4.189) Prec@1 51.56 (53.49) Prec@5 79.69 (76.76) + train[2018-10-12-00:01:14] Epoch: [021][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.379 (4.190) Prec@1 50.00 (53.48) Prec@5 75.00 (76.75) + train[2018-10-12-00:01:18] Epoch: [021][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 5.073 (4.190) Prec@1 46.67 (53.48) Prec@5 66.67 (76.75) +[2018-10-12-00:01:18] **train** Prec@1 53.48 Prec@5 76.75 Error@1 46.52 Error@5 23.25 Loss:4.190 + test [2018-10-12-00:01:21] Epoch: [021][000/391] Time 3.37 (3.37) Data 3.22 (3.22) Loss 1.121 (1.121) Prec@1 74.22 (74.22) Prec@5 90.62 (90.62) + test [2018-10-12-00:01:49] Epoch: [021][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 2.330 (1.634) Prec@1 43.75 (62.36) Prec@5 75.78 (85.63) + test [2018-10-12-00:02:14] Epoch: [021][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 3.226 (1.838) Prec@1 26.25 (58.66) Prec@5 62.50 (82.16) +[2018-10-12-00:02:14] **test** Prec@1 58.66 Prec@5 82.16 Error@1 41.34 Error@5 17.84 Loss:1.838 +----> Best Accuracy : Acc@1=58.66, Acc@5=82.16, Error@1=41.34, Error@5=17.84 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-12-00:02:15] [Epoch=022/250] [Need: 332:39:57] LR=0.0512 ~ 0.0512, Batch=128 + train[2018-10-12-00:02:19] Epoch: [022][000/10010] Time 4.35 (4.35) Data 3.69 (3.69) Loss 3.936 (3.936) Prec@1 53.12 (53.12) Prec@5 82.03 (82.03) + train[2018-10-12-00:04:04] Epoch: [022][200/10010] Time 0.57 (0.54) Data 0.00 (0.02) Loss 4.162 (4.137) Prec@1 53.91 (54.52) Prec@5 76.56 (77.59) + train[2018-10-12-00:05:47] Epoch: [022][400/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 4.153 (4.145) Prec@1 54.69 (54.20) Prec@5 76.56 (77.41) + train[2018-10-12-00:07:31] Epoch: [022][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 4.251 (4.153) Prec@1 55.47 (54.13) Prec@5 77.34 (77.23) + train[2018-10-12-00:09:14] Epoch: [022][800/10010] Time 0.50 (0.52) Data 0.00 (0.01) Loss 4.435 (4.145) Prec@1 44.53 (54.23) Prec@5 72.66 (77.34) + train[2018-10-12-00:10:58] Epoch: [022][1000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.482 (4.149) Prec@1 48.44 (54.19) Prec@5 74.22 (77.24) + train[2018-10-12-00:12:42] Epoch: [022][1200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.108 (4.145) Prec@1 57.03 (54.25) Prec@5 75.00 (77.32) + train[2018-10-12-00:14:26] Epoch: [022][1400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.245 (4.144) Prec@1 52.34 (54.26) Prec@5 77.34 (77.34) + train[2018-10-12-00:16:09] Epoch: [022][1600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.056 (4.147) Prec@1 56.25 (54.24) Prec@5 77.34 (77.30) + train[2018-10-12-00:17:53] Epoch: [022][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.352 (4.147) Prec@1 50.00 (54.23) Prec@5 71.88 (77.29) + train[2018-10-12-00:19:37] Epoch: [022][2000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.941 (4.149) Prec@1 57.81 (54.20) Prec@5 79.69 (77.27) + train[2018-10-12-00:21:21] Epoch: [022][2200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.390 (4.148) Prec@1 57.81 (54.22) Prec@5 74.22 (77.29) + train[2018-10-12-00:23:04] Epoch: [022][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.267 (4.145) Prec@1 54.69 (54.29) Prec@5 71.88 (77.32) + train[2018-10-12-00:24:48] Epoch: [022][2600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.157 (4.145) Prec@1 50.78 (54.27) Prec@5 77.34 (77.31) + train[2018-10-12-00:26:32] Epoch: [022][2800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.141 (4.147) Prec@1 55.47 (54.25) Prec@5 73.44 (77.29) + train[2018-10-12-00:28:16] Epoch: [022][3000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.289 (4.149) Prec@1 57.81 (54.22) Prec@5 73.44 (77.26) + train[2018-10-12-00:30:00] Epoch: [022][3200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.996 (4.150) Prec@1 59.38 (54.18) Prec@5 78.91 (77.24) + train[2018-10-12-00:31:44] Epoch: [022][3400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.106 (4.152) Prec@1 51.56 (54.16) Prec@5 78.91 (77.23) + train[2018-10-12-00:33:28] Epoch: [022][3600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.111 (4.151) Prec@1 50.78 (54.16) Prec@5 77.34 (77.24) + train[2018-10-12-00:35:12] Epoch: [022][3800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.136 (4.152) Prec@1 49.22 (54.13) Prec@5 76.56 (77.23) + train[2018-10-12-00:36:55] Epoch: [022][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.195 (4.152) Prec@1 54.69 (54.11) Prec@5 75.78 (77.24) + train[2018-10-12-00:38:39] Epoch: [022][4200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.458 (4.153) Prec@1 44.53 (54.09) Prec@5 78.12 (77.23) + train[2018-10-12-00:40:23] Epoch: [022][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.039 (4.154) Prec@1 51.56 (54.08) Prec@5 77.34 (77.21) + train[2018-10-12-00:42:06] Epoch: [022][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.285 (4.156) Prec@1 55.47 (54.05) Prec@5 77.34 (77.19) + train[2018-10-12-00:43:49] Epoch: [022][4800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.282 (4.157) Prec@1 49.22 (54.02) Prec@5 74.22 (77.19) + train[2018-10-12-00:45:34] Epoch: [022][5000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.271 (4.157) Prec@1 52.34 (54.01) Prec@5 79.69 (77.19) + train[2018-10-12-00:47:18] Epoch: [022][5200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.982 (4.156) Prec@1 54.69 (54.03) Prec@5 74.22 (77.19) + train[2018-10-12-00:49:02] Epoch: [022][5400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.311 (4.157) Prec@1 54.69 (54.00) Prec@5 71.88 (77.17) + train[2018-10-12-00:50:46] Epoch: [022][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.097 (4.159) Prec@1 49.22 (53.99) Prec@5 78.12 (77.15) + train[2018-10-12-00:52:29] Epoch: [022][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.189 (4.159) Prec@1 55.47 (53.98) Prec@5 80.47 (77.17) + train[2018-10-12-00:54:13] Epoch: [022][6000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.098 (4.159) Prec@1 52.34 (53.99) Prec@5 77.34 (77.16) + train[2018-10-12-00:55:57] Epoch: [022][6200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.228 (4.159) Prec@1 52.34 (53.98) Prec@5 76.56 (77.16) + train[2018-10-12-00:57:40] Epoch: [022][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.755 (4.160) Prec@1 59.38 (53.95) Prec@5 81.25 (77.14) + train[2018-10-12-00:59:24] Epoch: [022][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.031 (4.161) Prec@1 56.25 (53.95) Prec@5 80.47 (77.13) + train[2018-10-12-01:01:07] Epoch: [022][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.899 (4.161) Prec@1 60.94 (53.94) Prec@5 78.91 (77.13) + train[2018-10-12-01:02:51] Epoch: [022][7000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.067 (4.162) Prec@1 53.12 (53.93) Prec@5 77.34 (77.11) + train[2018-10-12-01:04:35] Epoch: [022][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.442 (4.162) Prec@1 47.66 (53.91) Prec@5 75.00 (77.10) + train[2018-10-12-01:06:18] Epoch: [022][7400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.375 (4.163) Prec@1 51.56 (53.91) Prec@5 74.22 (77.10) + train[2018-10-12-01:08:03] Epoch: [022][7600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.490 (4.163) Prec@1 50.00 (53.91) Prec@5 72.66 (77.09) + train[2018-10-12-01:09:47] Epoch: [022][7800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.367 (4.163) Prec@1 49.22 (53.90) Prec@5 75.78 (77.09) + train[2018-10-12-01:11:30] Epoch: [022][8000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.060 (4.163) Prec@1 58.59 (53.90) Prec@5 77.34 (77.09) + train[2018-10-12-01:13:14] Epoch: [022][8200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.967 (4.163) Prec@1 58.59 (53.91) Prec@5 82.03 (77.09) + train[2018-10-12-01:14:58] Epoch: [022][8400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.628 (4.163) Prec@1 58.59 (53.91) Prec@5 84.38 (77.09) + train[2018-10-12-01:16:42] Epoch: [022][8600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.309 (4.164) Prec@1 52.34 (53.91) Prec@5 75.00 (77.08) + train[2018-10-12-01:18:25] Epoch: [022][8800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.246 (4.165) Prec@1 51.56 (53.89) Prec@5 78.12 (77.07) + train[2018-10-12-01:20:09] Epoch: [022][9000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.197 (4.165) Prec@1 50.00 (53.89) Prec@5 80.47 (77.07) + train[2018-10-12-01:21:53] Epoch: [022][9200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.129 (4.165) Prec@1 50.00 (53.89) Prec@5 74.22 (77.07) + train[2018-10-12-01:23:37] Epoch: [022][9400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.171 (4.165) Prec@1 56.25 (53.89) Prec@5 75.00 (77.07) + train[2018-10-12-01:25:20] Epoch: [022][9600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.048 (4.166) Prec@1 58.59 (53.88) Prec@5 78.12 (77.05) + train[2018-10-12-01:27:04] Epoch: [022][9800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.095 (4.166) Prec@1 52.34 (53.88) Prec@5 76.56 (77.05) + train[2018-10-12-01:28:48] Epoch: [022][10000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.108 (4.166) Prec@1 58.59 (53.89) Prec@5 75.00 (77.05) + train[2018-10-12-01:28:52] Epoch: [022][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 5.732 (4.166) Prec@1 33.33 (53.89) Prec@5 53.33 (77.05) +[2018-10-12-01:28:52] **train** Prec@1 53.89 Prec@5 77.05 Error@1 46.11 Error@5 22.95 Loss:4.166 + test [2018-10-12-01:28:56] Epoch: [022][000/391] Time 4.46 (4.46) Data 4.32 (4.32) Loss 1.194 (1.194) Prec@1 72.66 (72.66) Prec@5 89.84 (89.84) + test [2018-10-12-01:29:24] Epoch: [022][200/391] Time 0.12 (0.16) Data 0.00 (0.03) Loss 2.511 (1.610) Prec@1 43.75 (63.05) Prec@5 67.19 (86.28) + test [2018-10-12-01:29:48] Epoch: [022][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.690 (1.804) Prec@1 33.75 (59.57) Prec@5 72.50 (82.93) +[2018-10-12-01:29:49] **test** Prec@1 59.57 Prec@5 82.93 Error@1 40.43 Error@5 17.07 Loss:1.804 +----> Best Accuracy : Acc@1=59.57, Acc@5=82.93, Error@1=40.43, Error@5=17.07 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-12-01:29:49] [Epoch=023/250] [Need: 331:17:44] LR=0.0496 ~ 0.0496, Batch=128 + train[2018-10-12-01:29:54] Epoch: [023][000/10010] Time 5.26 (5.26) Data 4.69 (4.69) Loss 3.749 (3.749) Prec@1 61.72 (61.72) Prec@5 82.81 (82.81) + train[2018-10-12-01:31:38] Epoch: [023][200/10010] Time 0.52 (0.54) Data 0.00 (0.02) Loss 3.936 (4.099) Prec@1 57.03 (54.78) Prec@5 82.03 (77.86) + train[2018-10-12-01:33:22] Epoch: [023][400/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 4.723 (4.105) Prec@1 42.19 (54.83) Prec@5 72.66 (77.82) + train[2018-10-12-01:35:05] Epoch: [023][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 4.401 (4.106) Prec@1 50.78 (54.82) Prec@5 71.88 (77.82) + train[2018-10-12-01:36:49] Epoch: [023][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 4.273 (4.108) Prec@1 51.56 (54.87) Prec@5 76.56 (77.80) + train[2018-10-12-01:38:33] Epoch: [023][1000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.315 (4.113) Prec@1 49.22 (54.76) Prec@5 77.34 (77.71) + train[2018-10-12-01:40:17] Epoch: [023][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.243 (4.114) Prec@1 52.34 (54.74) Prec@5 71.88 (77.70) + train[2018-10-12-01:42:01] Epoch: [023][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.017 (4.113) Prec@1 50.78 (54.75) Prec@5 78.12 (77.70) + train[2018-10-12-01:43:45] Epoch: [023][1600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.880 (4.116) Prec@1 58.59 (54.71) Prec@5 81.25 (77.66) + train[2018-10-12-01:45:28] Epoch: [023][1800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.193 (4.116) Prec@1 57.81 (54.73) Prec@5 78.91 (77.68) + train[2018-10-12-01:47:11] Epoch: [023][2000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.658 (4.116) Prec@1 62.50 (54.74) Prec@5 81.25 (77.69) + train[2018-10-12-01:48:55] Epoch: [023][2200/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 4.147 (4.118) Prec@1 56.25 (54.67) Prec@5 78.91 (77.67) + train[2018-10-12-01:50:39] Epoch: [023][2400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.509 (4.120) Prec@1 51.56 (54.61) Prec@5 70.31 (77.65) + train[2018-10-12-01:52:23] Epoch: [023][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.900 (4.123) Prec@1 54.69 (54.54) Prec@5 81.25 (77.62) + train[2018-10-12-01:54:06] Epoch: [023][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.109 (4.124) Prec@1 52.34 (54.54) Prec@5 76.56 (77.62) + train[2018-10-12-01:55:50] Epoch: [023][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.150 (4.125) Prec@1 53.12 (54.50) Prec@5 75.78 (77.61) + train[2018-10-12-01:57:34] Epoch: [023][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.886 (4.126) Prec@1 56.25 (54.47) Prec@5 80.47 (77.58) + train[2018-10-12-01:59:17] Epoch: [023][3400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.106 (4.127) Prec@1 56.25 (54.45) Prec@5 76.56 (77.56) + train[2018-10-12-02:01:00] Epoch: [023][3600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.295 (4.129) Prec@1 48.44 (54.42) Prec@5 77.34 (77.54) + train[2018-10-12-02:02:44] Epoch: [023][3800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.225 (4.130) Prec@1 46.88 (54.41) Prec@5 75.78 (77.53) + train[2018-10-12-02:04:27] Epoch: [023][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.237 (4.130) Prec@1 55.47 (54.40) Prec@5 75.78 (77.51) + train[2018-10-12-02:06:11] Epoch: [023][4200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.998 (4.130) Prec@1 57.03 (54.39) Prec@5 80.47 (77.51) + train[2018-10-12-02:07:54] Epoch: [023][4400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.903 (4.131) Prec@1 57.03 (54.37) Prec@5 79.69 (77.51) + train[2018-10-12-02:09:38] Epoch: [023][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.842 (4.132) Prec@1 64.84 (54.37) Prec@5 82.03 (77.50) + train[2018-10-12-02:11:21] Epoch: [023][4800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.259 (4.132) Prec@1 50.78 (54.38) Prec@5 75.78 (77.50) + train[2018-10-12-02:13:05] Epoch: [023][5000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.068 (4.133) Prec@1 53.12 (54.38) Prec@5 79.69 (77.48) + train[2018-10-12-02:14:48] Epoch: [023][5200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.329 (4.133) Prec@1 52.34 (54.38) Prec@5 72.66 (77.48) + train[2018-10-12-02:16:32] Epoch: [023][5400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.516 (4.134) Prec@1 47.66 (54.37) Prec@5 73.44 (77.47) + train[2018-10-12-02:18:15] Epoch: [023][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.032 (4.134) Prec@1 54.69 (54.37) Prec@5 79.69 (77.47) + train[2018-10-12-02:19:58] Epoch: [023][5800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.234 (4.135) Prec@1 52.34 (54.36) Prec@5 76.56 (77.46) + train[2018-10-12-02:21:42] Epoch: [023][6000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.184 (4.135) Prec@1 51.56 (54.33) Prec@5 75.00 (77.45) + train[2018-10-12-02:23:26] Epoch: [023][6200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.169 (4.136) Prec@1 51.56 (54.32) Prec@5 76.56 (77.43) + train[2018-10-12-02:25:10] Epoch: [023][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.012 (4.137) Prec@1 57.03 (54.31) Prec@5 82.03 (77.43) + train[2018-10-12-02:26:55] Epoch: [023][6600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.255 (4.137) Prec@1 50.78 (54.31) Prec@5 77.34 (77.42) + train[2018-10-12-02:28:38] Epoch: [023][6800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.220 (4.137) Prec@1 51.56 (54.31) Prec@5 78.91 (77.41) + train[2018-10-12-02:30:22] Epoch: [023][7000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.791 (4.139) Prec@1 53.12 (54.29) Prec@5 85.16 (77.40) + train[2018-10-12-02:32:06] Epoch: [023][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.195 (4.139) Prec@1 55.47 (54.29) Prec@5 77.34 (77.40) + train[2018-10-12-02:33:50] Epoch: [023][7400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.789 (4.138) Prec@1 55.47 (54.29) Prec@5 85.16 (77.41) + train[2018-10-12-02:35:33] Epoch: [023][7600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.927 (4.138) Prec@1 53.91 (54.28) Prec@5 82.81 (77.41) + train[2018-10-12-02:37:16] Epoch: [023][7800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.056 (4.138) Prec@1 52.34 (54.28) Prec@5 78.91 (77.42) + train[2018-10-12-02:39:00] Epoch: [023][8000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.089 (4.139) Prec@1 55.47 (54.28) Prec@5 78.12 (77.41) + train[2018-10-12-02:40:44] Epoch: [023][8200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.765 (4.140) Prec@1 60.94 (54.26) Prec@5 85.94 (77.39) + train[2018-10-12-02:42:28] Epoch: [023][8400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.175 (4.140) Prec@1 58.59 (54.26) Prec@5 75.78 (77.39) + train[2018-10-12-02:44:12] Epoch: [023][8600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.856 (4.140) Prec@1 57.03 (54.26) Prec@5 86.72 (77.39) + train[2018-10-12-02:45:55] Epoch: [023][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.119 (4.141) Prec@1 53.12 (54.25) Prec@5 73.44 (77.38) + train[2018-10-12-02:47:39] Epoch: [023][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.299 (4.141) Prec@1 50.00 (54.23) Prec@5 75.78 (77.37) + train[2018-10-12-02:49:22] Epoch: [023][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.106 (4.141) Prec@1 53.12 (54.23) Prec@5 77.34 (77.37) + train[2018-10-12-02:51:06] Epoch: [023][9400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.199 (4.142) Prec@1 53.91 (54.22) Prec@5 74.22 (77.36) + train[2018-10-12-02:52:49] Epoch: [023][9600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.141 (4.143) Prec@1 53.12 (54.20) Prec@5 75.78 (77.35) + train[2018-10-12-02:54:32] Epoch: [023][9800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.960 (4.143) Prec@1 57.81 (54.20) Prec@5 78.91 (77.34) + train[2018-10-12-02:56:16] Epoch: [023][10000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.198 (4.144) Prec@1 60.94 (54.19) Prec@5 75.78 (77.34) + train[2018-10-12-02:56:20] Epoch: [023][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 3.771 (4.144) Prec@1 53.33 (54.19) Prec@5 93.33 (77.34) +[2018-10-12-02:56:20] **train** Prec@1 54.19 Prec@5 77.34 Error@1 45.81 Error@5 22.66 Loss:4.144 + test [2018-10-12-02:56:25] Epoch: [023][000/391] Time 4.29 (4.29) Data 4.16 (4.16) Loss 1.233 (1.233) Prec@1 75.00 (75.00) Prec@5 90.62 (90.62) + test [2018-10-12-02:56:52] Epoch: [023][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 2.218 (1.561) Prec@1 42.97 (63.70) Prec@5 77.34 (86.59) + test [2018-10-12-02:57:18] Epoch: [023][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.950 (1.767) Prec@1 35.00 (59.82) Prec@5 68.75 (83.08) +[2018-10-12-02:57:18] **test** Prec@1 59.82 Prec@5 83.08 Error@1 40.18 Error@5 16.92 Loss:1.767 +----> Best Accuracy : Acc@1=59.82, Acc@5=83.08, Error@1=40.18, Error@5=16.92 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-12-02:57:18] [Epoch=024/250] [Need: 329:32:42] LR=0.0481 ~ 0.0481, Batch=128 + train[2018-10-12-02:57:24] Epoch: [024][000/10010] Time 5.91 (5.91) Data 5.32 (5.32) Loss 4.230 (4.230) Prec@1 55.47 (55.47) Prec@5 76.56 (76.56) + train[2018-10-12-02:59:08] Epoch: [024][200/10010] Time 0.49 (0.55) Data 0.00 (0.03) Loss 3.703 (4.065) Prec@1 57.03 (55.61) Prec@5 84.38 (78.23) + train[2018-10-12-03:00:52] Epoch: [024][400/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 4.100 (4.077) Prec@1 57.03 (55.24) Prec@5 75.78 (78.20) + train[2018-10-12-03:02:35] Epoch: [024][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 4.138 (4.073) Prec@1 53.91 (55.26) Prec@5 78.12 (78.22) + train[2018-10-12-03:04:19] Epoch: [024][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 4.362 (4.074) Prec@1 51.56 (55.26) Prec@5 72.66 (78.26) + train[2018-10-12-03:06:02] Epoch: [024][1000/10010] Time 0.53 (0.52) Data 0.00 (0.01) Loss 3.702 (4.077) Prec@1 64.06 (55.20) Prec@5 84.38 (78.24) + train[2018-10-12-03:07:46] Epoch: [024][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.115 (4.079) Prec@1 56.25 (55.23) Prec@5 78.12 (78.20) + train[2018-10-12-03:09:30] Epoch: [024][1400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.718 (4.084) Prec@1 60.16 (55.13) Prec@5 85.94 (78.16) + train[2018-10-12-03:11:13] Epoch: [024][1600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.095 (4.087) Prec@1 56.25 (55.06) Prec@5 75.78 (78.09) + train[2018-10-12-03:12:57] Epoch: [024][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.172 (4.090) Prec@1 51.56 (54.99) Prec@5 78.91 (78.07) + train[2018-10-12-03:14:41] Epoch: [024][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.882 (4.092) Prec@1 58.59 (54.95) Prec@5 82.03 (78.02) + train[2018-10-12-03:16:25] Epoch: [024][2200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.574 (4.093) Prec@1 47.66 (54.97) Prec@5 73.44 (77.98) + train[2018-10-12-03:18:08] Epoch: [024][2400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.061 (4.096) Prec@1 59.38 (54.91) Prec@5 75.00 (77.93) + train[2018-10-12-03:19:51] Epoch: [024][2600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.038 (4.096) Prec@1 58.59 (54.92) Prec@5 78.12 (77.93) + train[2018-10-12-03:21:35] Epoch: [024][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.085 (4.099) Prec@1 53.12 (54.86) Prec@5 76.56 (77.89) + train[2018-10-12-03:23:19] Epoch: [024][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.210 (4.098) Prec@1 56.25 (54.89) Prec@5 77.34 (77.89) + train[2018-10-12-03:25:03] Epoch: [024][3200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.127 (4.101) Prec@1 56.25 (54.87) Prec@5 78.91 (77.84) + train[2018-10-12-03:26:47] Epoch: [024][3400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.202 (4.102) Prec@1 54.69 (54.87) Prec@5 71.88 (77.84) + train[2018-10-12-03:28:31] Epoch: [024][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.891 (4.105) Prec@1 60.16 (54.84) Prec@5 82.03 (77.80) + train[2018-10-12-03:30:15] Epoch: [024][3800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.877 (4.106) Prec@1 60.94 (54.81) Prec@5 79.69 (77.77) + train[2018-10-12-03:31:58] Epoch: [024][4000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.822 (4.106) Prec@1 61.72 (54.79) Prec@5 85.16 (77.76) + train[2018-10-12-03:33:42] Epoch: [024][4200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.026 (4.108) Prec@1 56.25 (54.78) Prec@5 78.12 (77.75) + train[2018-10-12-03:35:25] Epoch: [024][4400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.064 (4.108) Prec@1 57.03 (54.78) Prec@5 78.12 (77.74) + train[2018-10-12-03:37:09] Epoch: [024][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.012 (4.108) Prec@1 57.81 (54.77) Prec@5 77.34 (77.74) + train[2018-10-12-03:38:52] Epoch: [024][4800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.277 (4.110) Prec@1 53.12 (54.74) Prec@5 72.66 (77.73) + train[2018-10-12-03:40:36] Epoch: [024][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.139 (4.110) Prec@1 53.12 (54.73) Prec@5 76.56 (77.72) + train[2018-10-12-03:42:20] Epoch: [024][5200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.964 (4.111) Prec@1 61.72 (54.72) Prec@5 78.91 (77.71) + train[2018-10-12-03:44:04] Epoch: [024][5400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.942 (4.112) Prec@1 54.69 (54.71) Prec@5 80.47 (77.70) + train[2018-10-12-03:45:48] Epoch: [024][5600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.908 (4.111) Prec@1 57.03 (54.72) Prec@5 85.16 (77.72) + train[2018-10-12-03:47:32] Epoch: [024][5800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.940 (4.112) Prec@1 53.91 (54.71) Prec@5 78.91 (77.71) + train[2018-10-12-03:49:17] Epoch: [024][6000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.630 (4.112) Prec@1 49.22 (54.69) Prec@5 70.31 (77.71) + train[2018-10-12-03:51:00] Epoch: [024][6200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.126 (4.113) Prec@1 52.34 (54.68) Prec@5 79.69 (77.70) + train[2018-10-12-03:52:44] Epoch: [024][6400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.171 (4.114) Prec@1 54.69 (54.67) Prec@5 76.56 (77.68) + train[2018-10-12-03:54:28] Epoch: [024][6600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.219 (4.115) Prec@1 56.25 (54.65) Prec@5 77.34 (77.67) + train[2018-10-12-03:56:12] Epoch: [024][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.077 (4.116) Prec@1 59.38 (54.64) Prec@5 76.56 (77.66) + train[2018-10-12-03:57:55] Epoch: [024][7000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.180 (4.116) Prec@1 63.28 (54.63) Prec@5 78.12 (77.65) + train[2018-10-12-03:59:39] Epoch: [024][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.079 (4.117) Prec@1 57.81 (54.62) Prec@5 75.00 (77.64) + train[2018-10-12-04:01:23] Epoch: [024][7400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.259 (4.118) Prec@1 51.56 (54.60) Prec@5 75.00 (77.62) + train[2018-10-12-04:03:06] Epoch: [024][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.094 (4.119) Prec@1 52.34 (54.59) Prec@5 77.34 (77.61) + train[2018-10-12-04:04:49] Epoch: [024][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.509 (4.119) Prec@1 61.72 (54.59) Prec@5 89.06 (77.60) + train[2018-10-12-04:06:33] Epoch: [024][8000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.426 (4.120) Prec@1 50.00 (54.57) Prec@5 77.34 (77.59) + train[2018-10-12-04:08:16] Epoch: [024][8200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.185 (4.121) Prec@1 52.34 (54.56) Prec@5 77.34 (77.58) + train[2018-10-12-04:10:01] Epoch: [024][8400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 4.310 (4.122) Prec@1 50.00 (54.54) Prec@5 73.44 (77.57) + train[2018-10-12-04:11:45] Epoch: [024][8600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.081 (4.122) Prec@1 53.91 (54.54) Prec@5 80.47 (77.56) + train[2018-10-12-04:13:29] Epoch: [024][8800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.604 (4.123) Prec@1 42.19 (54.53) Prec@5 72.66 (77.55) + train[2018-10-12-04:15:13] Epoch: [024][9000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.145 (4.122) Prec@1 55.47 (54.54) Prec@5 77.34 (77.56) + train[2018-10-12-04:16:56] Epoch: [024][9200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.991 (4.123) Prec@1 60.16 (54.53) Prec@5 80.47 (77.55) + train[2018-10-12-04:18:40] Epoch: [024][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.230 (4.123) Prec@1 53.91 (54.53) Prec@5 80.47 (77.55) + train[2018-10-12-04:20:24] Epoch: [024][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.796 (4.123) Prec@1 60.16 (54.54) Prec@5 83.59 (77.55) + train[2018-10-12-04:22:08] Epoch: [024][9800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.024 (4.123) Prec@1 55.47 (54.53) Prec@5 80.47 (77.55) + train[2018-10-12-04:23:52] Epoch: [024][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.121 (4.123) Prec@1 54.69 (54.54) Prec@5 77.34 (77.55) + train[2018-10-12-04:23:56] Epoch: [024][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.790 (4.123) Prec@1 40.00 (54.54) Prec@5 80.00 (77.55) +[2018-10-12-04:23:56] **train** Prec@1 54.54 Prec@5 77.55 Error@1 45.46 Error@5 22.45 Loss:4.123 + test [2018-10-12-04:24:00] Epoch: [024][000/391] Time 3.97 (3.97) Data 3.82 (3.82) Loss 1.086 (1.086) Prec@1 77.34 (77.34) Prec@5 92.97 (92.97) + test [2018-10-12-04:24:28] Epoch: [024][200/391] Time 0.12 (0.16) Data 0.00 (0.03) Loss 1.916 (1.524) Prec@1 49.22 (63.72) Prec@5 80.47 (86.88) + test [2018-10-12-04:24:53] Epoch: [024][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 3.099 (1.752) Prec@1 27.50 (59.78) Prec@5 66.25 (83.27) +[2018-10-12-04:24:53] **test** Prec@1 59.78 Prec@5 83.27 Error@1 40.22 Error@5 16.73 Loss:1.752 +----> Best Accuracy : Acc@1=59.82, Acc@5=83.08, Error@1=40.18, Error@5=16.92 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-12-04:24:54] [Epoch=025/250] [Need: 328:28:21] LR=0.0467 ~ 0.0467, Batch=128 + train[2018-10-12-04:24:59] Epoch: [025][000/10010] Time 5.34 (5.34) Data 4.73 (4.73) Loss 3.969 (3.969) Prec@1 57.81 (57.81) Prec@5 81.25 (81.25) + train[2018-10-12-04:26:43] Epoch: [025][200/10010] Time 0.54 (0.54) Data 0.00 (0.02) Loss 4.255 (4.067) Prec@1 50.00 (55.66) Prec@5 75.78 (78.32) + train[2018-10-12-04:28:27] Epoch: [025][400/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.934 (4.072) Prec@1 60.94 (55.42) Prec@5 83.59 (78.25) + train[2018-10-12-04:30:11] Epoch: [025][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 4.082 (4.065) Prec@1 55.47 (55.45) Prec@5 82.03 (78.40) + train[2018-10-12-04:31:54] Epoch: [025][800/10010] Time 0.49 (0.53) Data 0.00 (0.01) Loss 4.374 (4.072) Prec@1 54.69 (55.40) Prec@5 71.88 (78.27) + train[2018-10-12-04:33:38] Epoch: [025][1000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.877 (4.068) Prec@1 62.50 (55.47) Prec@5 82.03 (78.35) + train[2018-10-12-04:35:22] Epoch: [025][1200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.870 (4.067) Prec@1 57.81 (55.49) Prec@5 81.25 (78.35) + train[2018-10-12-04:37:05] Epoch: [025][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.192 (4.070) Prec@1 53.91 (55.43) Prec@5 81.25 (78.27) + train[2018-10-12-04:38:49] Epoch: [025][1600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.907 (4.073) Prec@1 59.38 (55.43) Prec@5 78.91 (78.24) + train[2018-10-12-04:40:33] Epoch: [025][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.112 (4.074) Prec@1 52.34 (55.42) Prec@5 75.00 (78.22) + train[2018-10-12-04:42:16] Epoch: [025][2000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.875 (4.073) Prec@1 58.59 (55.39) Prec@5 79.69 (78.23) + train[2018-10-12-04:44:01] Epoch: [025][2200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.865 (4.074) Prec@1 59.38 (55.38) Prec@5 82.03 (78.21) + train[2018-10-12-04:45:44] Epoch: [025][2400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.701 (4.074) Prec@1 62.50 (55.37) Prec@5 82.81 (78.20) + train[2018-10-12-04:47:28] Epoch: [025][2600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.756 (4.076) Prec@1 46.09 (55.33) Prec@5 66.41 (78.18) + train[2018-10-12-04:49:12] Epoch: [025][2800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.291 (4.077) Prec@1 52.34 (55.33) Prec@5 75.78 (78.16) + train[2018-10-12-04:50:55] Epoch: [025][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.024 (4.078) Prec@1 54.69 (55.31) Prec@5 80.47 (78.15) + train[2018-10-12-04:52:39] Epoch: [025][3200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.196 (4.078) Prec@1 51.56 (55.32) Prec@5 77.34 (78.16) + train[2018-10-12-04:54:23] Epoch: [025][3400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.015 (4.078) Prec@1 54.69 (55.34) Prec@5 82.03 (78.15) + train[2018-10-12-04:56:07] Epoch: [025][3600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.073 (4.078) Prec@1 55.47 (55.33) Prec@5 72.66 (78.17) + train[2018-10-12-04:57:51] Epoch: [025][3800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.102 (4.080) Prec@1 58.59 (55.30) Prec@5 80.47 (78.15) + train[2018-10-12-04:59:35] Epoch: [025][4000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.033 (4.081) Prec@1 53.12 (55.26) Prec@5 82.03 (78.14) + train[2018-10-12-05:01:18] Epoch: [025][4200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.877 (4.083) Prec@1 63.28 (55.23) Prec@5 83.59 (78.11) + train[2018-10-12-05:03:03] Epoch: [025][4400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.208 (4.083) Prec@1 51.56 (55.21) Prec@5 76.56 (78.11) + train[2018-10-12-05:04:46] Epoch: [025][4600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.026 (4.084) Prec@1 57.03 (55.19) Prec@5 82.03 (78.10) + train[2018-10-12-05:06:30] Epoch: [025][4800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.196 (4.085) Prec@1 47.66 (55.18) Prec@5 78.12 (78.08) + train[2018-10-12-05:08:14] Epoch: [025][5000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.308 (4.086) Prec@1 47.66 (55.16) Prec@5 75.78 (78.06) + train[2018-10-12-05:09:58] Epoch: [025][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.151 (4.086) Prec@1 53.12 (55.14) Prec@5 75.78 (78.06) + train[2018-10-12-05:11:41] Epoch: [025][5400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.882 (4.088) Prec@1 61.72 (55.11) Prec@5 78.12 (78.05) + train[2018-10-12-05:13:24] Epoch: [025][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.960 (4.088) Prec@1 57.03 (55.11) Prec@5 80.47 (78.04) + train[2018-10-12-05:15:08] Epoch: [025][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.656 (4.089) Prec@1 44.53 (55.08) Prec@5 73.44 (78.03) + train[2018-10-12-05:16:52] Epoch: [025][6000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.164 (4.091) Prec@1 55.47 (55.07) Prec@5 78.91 (78.00) + train[2018-10-12-05:18:35] Epoch: [025][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.134 (4.092) Prec@1 50.78 (55.05) Prec@5 83.59 (77.99) + train[2018-10-12-05:20:19] Epoch: [025][6400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.204 (4.091) Prec@1 51.56 (55.04) Prec@5 76.56 (77.99) + train[2018-10-12-05:22:02] Epoch: [025][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.946 (4.092) Prec@1 60.16 (55.04) Prec@5 80.47 (77.98) + train[2018-10-12-05:23:46] Epoch: [025][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.210 (4.092) Prec@1 57.03 (55.04) Prec@5 74.22 (77.98) + train[2018-10-12-05:25:30] Epoch: [025][7000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.920 (4.093) Prec@1 53.91 (55.03) Prec@5 82.03 (77.98) + train[2018-10-12-05:27:13] Epoch: [025][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.497 (4.093) Prec@1 47.66 (55.02) Prec@5 69.53 (77.97) + train[2018-10-12-05:28:57] Epoch: [025][7400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.885 (4.094) Prec@1 59.38 (55.01) Prec@5 78.91 (77.96) + train[2018-10-12-05:30:40] Epoch: [025][7600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.417 (4.095) Prec@1 48.44 (54.99) Prec@5 73.44 (77.94) + train[2018-10-12-05:32:25] Epoch: [025][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.699 (4.095) Prec@1 60.94 (54.97) Prec@5 84.38 (77.94) + train[2018-10-12-05:34:08] Epoch: [025][8000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.054 (4.096) Prec@1 52.34 (54.96) Prec@5 78.91 (77.93) + train[2018-10-12-05:35:52] Epoch: [025][8200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.268 (4.096) Prec@1 52.34 (54.96) Prec@5 73.44 (77.92) + train[2018-10-12-05:37:37] Epoch: [025][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.073 (4.096) Prec@1 55.47 (54.96) Prec@5 74.22 (77.92) + train[2018-10-12-05:39:20] Epoch: [025][8600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.938 (4.097) Prec@1 56.25 (54.95) Prec@5 78.12 (77.92) + train[2018-10-12-05:41:04] Epoch: [025][8800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.886 (4.097) Prec@1 61.72 (54.94) Prec@5 82.81 (77.91) + train[2018-10-12-05:42:48] Epoch: [025][9000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.144 (4.097) Prec@1 50.78 (54.93) Prec@5 76.56 (77.90) + train[2018-10-12-05:44:31] Epoch: [025][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.384 (4.098) Prec@1 49.22 (54.93) Prec@5 73.44 (77.90) + train[2018-10-12-05:46:14] Epoch: [025][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.158 (4.098) Prec@1 53.91 (54.92) Prec@5 78.91 (77.89) + train[2018-10-12-05:47:57] Epoch: [025][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.187 (4.098) Prec@1 52.34 (54.92) Prec@5 73.44 (77.89) + train[2018-10-12-05:49:41] Epoch: [025][9800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.132 (4.099) Prec@1 50.00 (54.91) Prec@5 74.22 (77.88) + train[2018-10-12-05:51:25] Epoch: [025][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.014 (4.099) Prec@1 55.47 (54.91) Prec@5 78.12 (77.88) + train[2018-10-12-05:51:29] Epoch: [025][10009/10010] Time 0.18 (0.52) Data 0.00 (0.00) Loss 6.295 (4.099) Prec@1 33.33 (54.91) Prec@5 53.33 (77.87) +[2018-10-12-05:51:29] **train** Prec@1 54.91 Prec@5 77.87 Error@1 45.09 Error@5 22.13 Loss:4.099 + test [2018-10-12-05:51:33] Epoch: [025][000/391] Time 4.43 (4.43) Data 4.28 (4.28) Loss 0.988 (0.988) Prec@1 77.34 (77.34) Prec@5 90.62 (90.62) + test [2018-10-12-05:52:00] Epoch: [025][200/391] Time 0.12 (0.16) Data 0.00 (0.02) Loss 2.064 (1.549) Prec@1 46.88 (64.26) Prec@5 75.78 (87.14) + test [2018-10-12-05:52:25] Epoch: [025][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 3.159 (1.758) Prec@1 32.50 (60.35) Prec@5 60.00 (83.63) +[2018-10-12-05:52:25] **test** Prec@1 60.35 Prec@5 83.63 Error@1 39.65 Error@5 16.37 Loss:1.758 +----> Best Accuracy : Acc@1=60.35, Acc@5=83.63, Error@1=39.65, Error@5=16.37 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-12-05:52:26] [Epoch=026/250] [Need: 326:47:09] LR=0.0453 ~ 0.0453, Batch=128 + train[2018-10-12-05:52:30] Epoch: [026][000/10010] Time 4.12 (4.12) Data 3.51 (3.51) Loss 3.992 (3.992) Prec@1 53.91 (53.91) Prec@5 78.91 (78.91) + train[2018-10-12-05:54:13] Epoch: [026][200/10010] Time 0.55 (0.54) Data 0.00 (0.02) Loss 3.784 (4.032) Prec@1 58.59 (56.09) Prec@5 81.25 (78.71) + train[2018-10-12-05:55:56] Epoch: [026][400/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 4.008 (4.033) Prec@1 55.47 (55.99) Prec@5 81.25 (78.81) + train[2018-10-12-05:57:40] Epoch: [026][600/10010] Time 0.50 (0.52) Data 0.00 (0.01) Loss 3.925 (4.038) Prec@1 58.59 (56.01) Prec@5 82.03 (78.75) + train[2018-10-12-05:59:25] Epoch: [026][800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.025 (4.041) Prec@1 54.69 (55.92) Prec@5 79.69 (78.68) + train[2018-10-12-06:01:08] Epoch: [026][1000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.752 (4.040) Prec@1 57.81 (55.89) Prec@5 84.38 (78.65) + train[2018-10-12-06:02:51] Epoch: [026][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.180 (4.043) Prec@1 50.78 (55.84) Prec@5 77.34 (78.56) + train[2018-10-12-06:04:35] Epoch: [026][1400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.398 (4.044) Prec@1 49.22 (55.78) Prec@5 71.09 (78.60) + train[2018-10-12-06:06:18] Epoch: [026][1600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.007 (4.051) Prec@1 55.47 (55.71) Prec@5 74.22 (78.51) + train[2018-10-12-06:08:03] Epoch: [026][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.208 (4.054) Prec@1 53.91 (55.65) Prec@5 71.88 (78.47) + train[2018-10-12-06:09:46] Epoch: [026][2000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.984 (4.054) Prec@1 53.12 (55.63) Prec@5 78.12 (78.45) + train[2018-10-12-06:11:30] Epoch: [026][2200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.542 (4.055) Prec@1 64.06 (55.60) Prec@5 83.59 (78.43) + train[2018-10-12-06:13:13] Epoch: [026][2400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.808 (4.056) Prec@1 57.81 (55.59) Prec@5 81.25 (78.42) + train[2018-10-12-06:14:57] Epoch: [026][2600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.224 (4.057) Prec@1 51.56 (55.57) Prec@5 74.22 (78.41) + train[2018-10-12-06:16:40] Epoch: [026][2800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.822 (4.057) Prec@1 62.50 (55.54) Prec@5 79.69 (78.42) + train[2018-10-12-06:18:24] Epoch: [026][3000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.055 (4.058) Prec@1 53.91 (55.54) Prec@5 82.03 (78.42) + train[2018-10-12-06:20:07] Epoch: [026][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.138 (4.057) Prec@1 53.91 (55.57) Prec@5 80.47 (78.42) + train[2018-10-12-06:21:51] Epoch: [026][3400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.845 (4.058) Prec@1 60.16 (55.54) Prec@5 78.12 (78.39) + train[2018-10-12-06:23:34] Epoch: [026][3600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.433 (4.059) Prec@1 52.34 (55.55) Prec@5 78.12 (78.38) + train[2018-10-12-06:25:18] Epoch: [026][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.150 (4.059) Prec@1 54.69 (55.54) Prec@5 82.81 (78.39) + train[2018-10-12-06:27:01] Epoch: [026][4000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.864 (4.060) Prec@1 57.03 (55.53) Prec@5 82.03 (78.37) + train[2018-10-12-06:28:44] Epoch: [026][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.309 (4.062) Prec@1 50.00 (55.48) Prec@5 74.22 (78.34) + train[2018-10-12-06:30:28] Epoch: [026][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.813 (4.063) Prec@1 60.94 (55.47) Prec@5 78.91 (78.33) + train[2018-10-12-06:32:11] Epoch: [026][4600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.117 (4.065) Prec@1 55.47 (55.43) Prec@5 75.78 (78.31) + train[2018-10-12-06:33:55] Epoch: [026][4800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.427 (4.066) Prec@1 48.44 (55.42) Prec@5 75.00 (78.30) + train[2018-10-12-06:35:39] Epoch: [026][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.176 (4.066) Prec@1 60.94 (55.40) Prec@5 77.34 (78.28) + train[2018-10-12-06:37:23] Epoch: [026][5200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.870 (4.066) Prec@1 62.50 (55.40) Prec@5 79.69 (78.29) + train[2018-10-12-06:39:07] Epoch: [026][5400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.998 (4.066) Prec@1 54.69 (55.39) Prec@5 73.44 (78.30) + train[2018-10-12-06:40:50] Epoch: [026][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.772 (4.067) Prec@1 59.38 (55.39) Prec@5 81.25 (78.29) + train[2018-10-12-06:42:35] Epoch: [026][5800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.151 (4.067) Prec@1 50.78 (55.39) Prec@5 79.69 (78.28) + train[2018-10-12-06:44:19] Epoch: [026][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.967 (4.068) Prec@1 55.47 (55.39) Prec@5 80.47 (78.26) + train[2018-10-12-06:46:02] Epoch: [026][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.263 (4.068) Prec@1 59.38 (55.40) Prec@5 76.56 (78.27) + train[2018-10-12-06:47:47] Epoch: [026][6400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.879 (4.068) Prec@1 60.16 (55.39) Prec@5 81.25 (78.27) + train[2018-10-12-06:49:31] Epoch: [026][6600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.949 (4.068) Prec@1 54.69 (55.38) Prec@5 79.69 (78.26) + train[2018-10-12-06:51:14] Epoch: [026][6800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.049 (4.068) Prec@1 54.69 (55.38) Prec@5 79.69 (78.25) + train[2018-10-12-06:52:59] Epoch: [026][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.961 (4.069) Prec@1 57.81 (55.38) Prec@5 80.47 (78.25) + train[2018-10-12-06:54:42] Epoch: [026][7200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.117 (4.070) Prec@1 50.00 (55.37) Prec@5 78.91 (78.24) + train[2018-10-12-06:56:26] Epoch: [026][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.434 (4.071) Prec@1 49.22 (55.35) Prec@5 75.00 (78.23) + train[2018-10-12-06:58:10] Epoch: [026][7600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.013 (4.071) Prec@1 57.81 (55.34) Prec@5 78.12 (78.21) + train[2018-10-12-06:59:54] Epoch: [026][7800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.923 (4.072) Prec@1 57.81 (55.34) Prec@5 75.78 (78.21) + train[2018-10-12-07:01:37] Epoch: [026][8000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.892 (4.073) Prec@1 50.00 (55.32) Prec@5 82.03 (78.19) + train[2018-10-12-07:03:21] Epoch: [026][8200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.155 (4.074) Prec@1 53.12 (55.31) Prec@5 77.34 (78.18) + train[2018-10-12-07:05:05] Epoch: [026][8400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.816 (4.074) Prec@1 58.59 (55.30) Prec@5 78.91 (78.17) + train[2018-10-12-07:06:49] Epoch: [026][8600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.283 (4.075) Prec@1 55.47 (55.29) Prec@5 74.22 (78.15) + train[2018-10-12-07:08:32] Epoch: [026][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.063 (4.075) Prec@1 57.03 (55.29) Prec@5 75.78 (78.14) + train[2018-10-12-07:10:16] Epoch: [026][9000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.854 (4.076) Prec@1 53.12 (55.28) Prec@5 80.47 (78.13) + train[2018-10-12-07:12:00] Epoch: [026][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.132 (4.076) Prec@1 59.38 (55.29) Prec@5 77.34 (78.13) + train[2018-10-12-07:13:43] Epoch: [026][9400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.139 (4.076) Prec@1 55.47 (55.28) Prec@5 75.78 (78.13) + train[2018-10-12-07:15:27] Epoch: [026][9600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.358 (4.076) Prec@1 50.00 (55.29) Prec@5 72.66 (78.13) + train[2018-10-12-07:17:10] Epoch: [026][9800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.109 (4.075) Prec@1 53.91 (55.29) Prec@5 78.91 (78.14) + train[2018-10-12-07:18:54] Epoch: [026][10000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.009 (4.076) Prec@1 54.69 (55.28) Prec@5 78.12 (78.13) + train[2018-10-12-07:18:58] Epoch: [026][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 5.025 (4.076) Prec@1 40.00 (55.28) Prec@5 73.33 (78.14) +[2018-10-12-07:18:58] **train** Prec@1 55.28 Prec@5 78.14 Error@1 44.72 Error@5 21.86 Loss:4.076 + test [2018-10-12-07:19:02] Epoch: [026][000/391] Time 4.23 (4.23) Data 4.09 (4.09) Loss 0.881 (0.881) Prec@1 83.59 (83.59) Prec@5 91.41 (91.41) + test [2018-10-12-07:19:30] Epoch: [026][200/391] Time 0.16 (0.16) Data 0.00 (0.02) Loss 1.910 (1.511) Prec@1 48.44 (64.79) Prec@5 80.47 (86.93) + test [2018-10-12-07:19:55] Epoch: [026][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 3.035 (1.730) Prec@1 31.25 (60.74) Prec@5 63.75 (83.62) +[2018-10-12-07:19:55] **test** Prec@1 60.74 Prec@5 83.62 Error@1 39.26 Error@5 16.38 Loss:1.730 +----> Best Accuracy : Acc@1=60.74, Acc@5=83.62, Error@1=39.26, Error@5=16.38 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-12-07:19:55] [Epoch=027/250] [Need: 325:09:51] LR=0.0439 ~ 0.0439, Batch=128 + train[2018-10-12-07:20:00] Epoch: [027][000/10010] Time 5.40 (5.40) Data 4.83 (4.83) Loss 4.138 (4.138) Prec@1 62.50 (62.50) Prec@5 78.91 (78.91) + train[2018-10-12-07:21:44] Epoch: [027][200/10010] Time 0.49 (0.54) Data 0.00 (0.02) Loss 3.882 (4.033) Prec@1 57.03 (55.82) Prec@5 80.47 (78.85) + train[2018-10-12-07:23:28] Epoch: [027][400/10010] Time 0.49 (0.53) Data 0.00 (0.01) Loss 3.809 (4.027) Prec@1 63.28 (55.99) Prec@5 78.12 (78.90) + train[2018-10-12-07:25:12] Epoch: [027][600/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 4.170 (4.018) Prec@1 51.56 (56.21) Prec@5 75.78 (79.01) + train[2018-10-12-07:26:55] Epoch: [027][800/10010] Time 0.54 (0.52) Data 0.00 (0.01) Loss 3.955 (4.013) Prec@1 57.03 (56.33) Prec@5 80.47 (79.11) + train[2018-10-12-07:28:38] Epoch: [027][1000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.353 (4.019) Prec@1 55.47 (56.20) Prec@5 75.00 (78.92) + train[2018-10-12-07:30:22] Epoch: [027][1200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.068 (4.024) Prec@1 55.47 (56.11) Prec@5 78.12 (78.86) + train[2018-10-12-07:32:05] Epoch: [027][1400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.465 (4.028) Prec@1 52.34 (56.04) Prec@5 74.22 (78.78) + train[2018-10-12-07:33:49] Epoch: [027][1600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.252 (4.030) Prec@1 53.12 (56.04) Prec@5 80.47 (78.76) + train[2018-10-12-07:35:33] Epoch: [027][1800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.143 (4.033) Prec@1 57.03 (56.00) Prec@5 77.34 (78.73) + train[2018-10-12-07:37:16] Epoch: [027][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.236 (4.034) Prec@1 49.22 (55.94) Prec@5 75.00 (78.71) + train[2018-10-12-07:38:59] Epoch: [027][2200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.101 (4.036) Prec@1 55.47 (55.90) Prec@5 77.34 (78.68) + train[2018-10-12-07:40:43] Epoch: [027][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.797 (4.035) Prec@1 60.16 (55.94) Prec@5 79.69 (78.70) + train[2018-10-12-07:42:27] Epoch: [027][2600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.022 (4.037) Prec@1 57.03 (55.94) Prec@5 80.47 (78.67) + train[2018-10-12-07:44:10] Epoch: [027][2800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.989 (4.038) Prec@1 53.91 (55.91) Prec@5 77.34 (78.63) + train[2018-10-12-07:45:53] Epoch: [027][3000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.720 (4.039) Prec@1 63.28 (55.92) Prec@5 82.03 (78.62) + train[2018-10-12-07:47:37] Epoch: [027][3200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.111 (4.039) Prec@1 54.69 (55.90) Prec@5 76.56 (78.63) + train[2018-10-12-07:49:21] Epoch: [027][3400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.259 (4.040) Prec@1 56.25 (55.89) Prec@5 75.78 (78.62) + train[2018-10-12-07:51:05] Epoch: [027][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.855 (4.041) Prec@1 58.59 (55.86) Prec@5 83.59 (78.61) + train[2018-10-12-07:52:48] Epoch: [027][3800/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.846 (4.041) Prec@1 57.81 (55.86) Prec@5 82.81 (78.60) + train[2018-10-12-07:54:32] Epoch: [027][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.144 (4.041) Prec@1 53.12 (55.84) Prec@5 82.81 (78.60) + train[2018-10-12-07:56:16] Epoch: [027][4200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.849 (4.043) Prec@1 59.38 (55.82) Prec@5 82.81 (78.57) + train[2018-10-12-07:58:00] Epoch: [027][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.221 (4.044) Prec@1 54.69 (55.79) Prec@5 73.44 (78.54) + train[2018-10-12-07:59:44] Epoch: [027][4600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.107 (4.045) Prec@1 57.81 (55.78) Prec@5 78.12 (78.52) + train[2018-10-12-08:01:29] Epoch: [027][4800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.143 (4.046) Prec@1 53.91 (55.78) Prec@5 78.12 (78.52) + train[2018-10-12-08:03:12] Epoch: [027][5000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.984 (4.046) Prec@1 58.59 (55.77) Prec@5 82.03 (78.50) + train[2018-10-12-08:04:56] Epoch: [027][5200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.358 (4.047) Prec@1 51.56 (55.75) Prec@5 74.22 (78.49) + train[2018-10-12-08:06:40] Epoch: [027][5400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.903 (4.048) Prec@1 52.34 (55.75) Prec@5 84.38 (78.48) + train[2018-10-12-08:08:24] Epoch: [027][5600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.071 (4.048) Prec@1 53.91 (55.75) Prec@5 81.25 (78.48) + train[2018-10-12-08:10:08] Epoch: [027][5800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.288 (4.049) Prec@1 55.47 (55.73) Prec@5 74.22 (78.46) + train[2018-10-12-08:11:52] Epoch: [027][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.863 (4.051) Prec@1 59.38 (55.70) Prec@5 78.91 (78.44) + train[2018-10-12-08:13:36] Epoch: [027][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.948 (4.051) Prec@1 50.78 (55.70) Prec@5 82.81 (78.44) + train[2018-10-12-08:15:19] Epoch: [027][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.850 (4.052) Prec@1 54.69 (55.68) Prec@5 85.16 (78.41) + train[2018-10-12-08:17:02] Epoch: [027][6600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.213 (4.053) Prec@1 52.34 (55.68) Prec@5 76.56 (78.41) + train[2018-10-12-08:18:46] Epoch: [027][6800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.259 (4.054) Prec@1 50.00 (55.67) Prec@5 76.56 (78.39) + train[2018-10-12-08:20:30] Epoch: [027][7000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.348 (4.054) Prec@1 52.34 (55.66) Prec@5 78.91 (78.39) + train[2018-10-12-08:22:14] Epoch: [027][7200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.901 (4.054) Prec@1 57.03 (55.66) Prec@5 81.25 (78.41) + train[2018-10-12-08:23:58] Epoch: [027][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.794 (4.054) Prec@1 55.47 (55.65) Prec@5 78.91 (78.41) + train[2018-10-12-08:25:42] Epoch: [027][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.148 (4.054) Prec@1 52.34 (55.64) Prec@5 74.22 (78.40) + train[2018-10-12-08:27:26] Epoch: [027][7800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.977 (4.055) Prec@1 52.34 (55.63) Prec@5 85.16 (78.38) + train[2018-10-12-08:29:09] Epoch: [027][8000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.015 (4.056) Prec@1 60.94 (55.61) Prec@5 78.91 (78.38) + train[2018-10-12-08:30:53] Epoch: [027][8200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.826 (4.056) Prec@1 60.94 (55.60) Prec@5 81.25 (78.37) + train[2018-10-12-08:32:37] Epoch: [027][8400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.632 (4.056) Prec@1 49.22 (55.59) Prec@5 71.09 (78.37) + train[2018-10-12-08:34:20] Epoch: [027][8600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.149 (4.055) Prec@1 57.03 (55.60) Prec@5 79.69 (78.38) + train[2018-10-12-08:36:04] Epoch: [027][8800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.593 (4.056) Prec@1 50.78 (55.58) Prec@5 77.34 (78.37) + train[2018-10-12-08:37:48] Epoch: [027][9000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.813 (4.057) Prec@1 57.81 (55.58) Prec@5 81.25 (78.37) + train[2018-10-12-08:39:32] Epoch: [027][9200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.423 (4.057) Prec@1 50.78 (55.58) Prec@5 71.88 (78.37) + train[2018-10-12-08:41:16] Epoch: [027][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.853 (4.057) Prec@1 59.38 (55.57) Prec@5 81.25 (78.36) + train[2018-10-12-08:43:00] Epoch: [027][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.098 (4.058) Prec@1 50.78 (55.55) Prec@5 76.56 (78.36) + train[2018-10-12-08:44:44] Epoch: [027][9800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.745 (4.059) Prec@1 57.03 (55.54) Prec@5 83.59 (78.35) + train[2018-10-12-08:46:27] Epoch: [027][10000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.785 (4.059) Prec@1 56.25 (55.53) Prec@5 78.91 (78.34) + train[2018-10-12-08:46:31] Epoch: [027][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.660 (4.059) Prec@1 40.00 (55.53) Prec@5 73.33 (78.34) +[2018-10-12-08:46:31] **train** Prec@1 55.53 Prec@5 78.34 Error@1 44.47 Error@5 21.66 Loss:4.059 + test [2018-10-12-08:46:35] Epoch: [027][000/391] Time 3.77 (3.77) Data 3.64 (3.64) Loss 1.014 (1.014) Prec@1 78.91 (78.91) Prec@5 91.41 (91.41) + test [2018-10-12-08:47:04] Epoch: [027][200/391] Time 0.17 (0.16) Data 0.00 (0.03) Loss 1.957 (1.491) Prec@1 53.91 (65.41) Prec@5 82.03 (87.66) + test [2018-10-12-08:47:29] Epoch: [027][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.909 (1.704) Prec@1 22.50 (61.34) Prec@5 71.25 (84.07) +[2018-10-12-08:47:29] **test** Prec@1 61.34 Prec@5 84.07 Error@1 38.66 Error@5 15.93 Loss:1.704 +----> Best Accuracy : Acc@1=61.34, Acc@5=84.07, Error@1=38.66, Error@5=15.93 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-12-08:47:29] [Epoch=028/250] [Need: 324:01:18] LR=0.0426 ~ 0.0426, Batch=128 + train[2018-10-12-08:47:34] Epoch: [028][000/10010] Time 5.14 (5.14) Data 4.58 (4.58) Loss 4.067 (4.067) Prec@1 59.38 (59.38) Prec@5 75.00 (75.00) + train[2018-10-12-08:49:18] Epoch: [028][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 4.182 (3.983) Prec@1 47.66 (56.51) Prec@5 75.78 (79.34) + train[2018-10-12-08:51:02] Epoch: [028][400/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 4.082 (3.991) Prec@1 53.12 (56.49) Prec@5 81.25 (79.24) + train[2018-10-12-08:52:45] Epoch: [028][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.745 (3.990) Prec@1 60.94 (56.67) Prec@5 86.72 (79.23) + train[2018-10-12-08:54:29] Epoch: [028][800/10010] Time 0.52 (0.52) Data 0.00 (0.01) Loss 4.075 (3.990) Prec@1 59.38 (56.74) Prec@5 77.34 (79.27) + train[2018-10-12-08:56:12] Epoch: [028][1000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.073 (3.998) Prec@1 54.69 (56.51) Prec@5 79.69 (79.16) + train[2018-10-12-08:57:56] Epoch: [028][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.926 (4.005) Prec@1 56.25 (56.41) Prec@5 78.12 (79.12) + train[2018-10-12-08:59:39] Epoch: [028][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.277 (4.005) Prec@1 55.47 (56.39) Prec@5 75.00 (79.13) + train[2018-10-12-09:01:23] Epoch: [028][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.247 (4.005) Prec@1 53.91 (56.40) Prec@5 71.88 (79.10) + train[2018-10-12-09:03:07] Epoch: [028][1800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.052 (4.008) Prec@1 53.12 (56.36) Prec@5 78.12 (79.07) + train[2018-10-12-09:04:50] Epoch: [028][2000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.756 (4.011) Prec@1 60.94 (56.34) Prec@5 83.59 (79.03) + train[2018-10-12-09:06:34] Epoch: [028][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.876 (4.012) Prec@1 62.50 (56.28) Prec@5 81.25 (79.01) + train[2018-10-12-09:08:18] Epoch: [028][2400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.721 (4.014) Prec@1 58.59 (56.22) Prec@5 82.81 (78.99) + train[2018-10-12-09:10:01] Epoch: [028][2600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.170 (4.016) Prec@1 50.78 (56.20) Prec@5 77.34 (78.97) + train[2018-10-12-09:11:44] Epoch: [028][2800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.914 (4.016) Prec@1 56.25 (56.21) Prec@5 79.69 (78.97) + train[2018-10-12-09:13:28] Epoch: [028][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.884 (4.017) Prec@1 60.16 (56.21) Prec@5 78.91 (78.97) + train[2018-10-12-09:15:12] Epoch: [028][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.280 (4.018) Prec@1 48.44 (56.16) Prec@5 76.56 (78.94) + train[2018-10-12-09:16:56] Epoch: [028][3400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.188 (4.020) Prec@1 51.56 (56.14) Prec@5 80.47 (78.92) + train[2018-10-12-09:18:40] Epoch: [028][3600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.926 (4.022) Prec@1 55.47 (56.13) Prec@5 80.47 (78.91) + train[2018-10-12-09:20:24] Epoch: [028][3800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.002 (4.022) Prec@1 59.38 (56.12) Prec@5 78.91 (78.91) + train[2018-10-12-09:22:08] Epoch: [028][4000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.132 (4.022) Prec@1 58.59 (56.13) Prec@5 78.91 (78.89) + train[2018-10-12-09:23:52] Epoch: [028][4200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.846 (4.023) Prec@1 54.69 (56.11) Prec@5 78.91 (78.87) + train[2018-10-12-09:25:36] Epoch: [028][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.064 (4.024) Prec@1 57.81 (56.10) Prec@5 79.69 (78.85) + train[2018-10-12-09:27:20] Epoch: [028][4600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.297 (4.025) Prec@1 50.78 (56.09) Prec@5 78.12 (78.85) + train[2018-10-12-09:29:04] Epoch: [028][4800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.196 (4.027) Prec@1 55.47 (56.06) Prec@5 75.00 (78.81) + train[2018-10-12-09:30:48] Epoch: [028][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.299 (4.029) Prec@1 52.34 (56.05) Prec@5 76.56 (78.78) + train[2018-10-12-09:32:32] Epoch: [028][5200/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.869 (4.029) Prec@1 60.16 (56.03) Prec@5 84.38 (78.78) + train[2018-10-12-09:34:15] Epoch: [028][5400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.222 (4.028) Prec@1 53.12 (56.05) Prec@5 76.56 (78.79) + train[2018-10-12-09:35:59] Epoch: [028][5600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.725 (4.029) Prec@1 60.16 (56.05) Prec@5 82.03 (78.78) + train[2018-10-12-09:37:42] Epoch: [028][5800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.135 (4.029) Prec@1 57.03 (56.05) Prec@5 76.56 (78.78) + train[2018-10-12-09:39:26] Epoch: [028][6000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.338 (4.030) Prec@1 50.00 (56.03) Prec@5 71.09 (78.76) + train[2018-10-12-09:41:10] Epoch: [028][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.915 (4.031) Prec@1 59.38 (56.00) Prec@5 80.47 (78.74) + train[2018-10-12-09:42:54] Epoch: [028][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.725 (4.032) Prec@1 60.16 (55.98) Prec@5 82.81 (78.73) + train[2018-10-12-09:44:37] Epoch: [028][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.827 (4.033) Prec@1 59.38 (55.98) Prec@5 79.69 (78.72) + train[2018-10-12-09:46:21] Epoch: [028][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.514 (4.033) Prec@1 47.66 (55.96) Prec@5 72.66 (78.71) + train[2018-10-12-09:48:05] Epoch: [028][7000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.268 (4.033) Prec@1 45.31 (55.96) Prec@5 73.44 (78.70) + train[2018-10-12-09:49:48] Epoch: [028][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.246 (4.034) Prec@1 54.69 (55.95) Prec@5 74.22 (78.69) + train[2018-10-12-09:51:32] Epoch: [028][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.800 (4.034) Prec@1 59.38 (55.94) Prec@5 82.03 (78.69) + train[2018-10-12-09:53:15] Epoch: [028][7600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.935 (4.035) Prec@1 60.94 (55.93) Prec@5 76.56 (78.68) + train[2018-10-12-09:54:59] Epoch: [028][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.599 (4.035) Prec@1 62.50 (55.91) Prec@5 85.16 (78.67) + train[2018-10-12-09:56:43] Epoch: [028][8000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.705 (4.036) Prec@1 62.50 (55.91) Prec@5 82.03 (78.66) + train[2018-10-12-09:58:26] Epoch: [028][8200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.833 (4.036) Prec@1 61.72 (55.90) Prec@5 82.03 (78.65) + train[2018-10-12-10:00:09] Epoch: [028][8400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.142 (4.037) Prec@1 58.59 (55.88) Prec@5 75.78 (78.64) + train[2018-10-12-10:01:53] Epoch: [028][8600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.986 (4.037) Prec@1 59.38 (55.88) Prec@5 80.47 (78.65) + train[2018-10-12-10:03:37] Epoch: [028][8800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.198 (4.038) Prec@1 52.34 (55.87) Prec@5 77.34 (78.64) + train[2018-10-12-10:05:21] Epoch: [028][9000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.756 (4.038) Prec@1 64.84 (55.86) Prec@5 80.47 (78.62) + train[2018-10-12-10:07:04] Epoch: [028][9200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.084 (4.038) Prec@1 53.12 (55.86) Prec@5 79.69 (78.63) + train[2018-10-12-10:08:48] Epoch: [028][9400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.422 (4.039) Prec@1 48.44 (55.85) Prec@5 75.00 (78.62) + train[2018-10-12-10:10:32] Epoch: [028][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.038 (4.039) Prec@1 59.38 (55.85) Prec@5 75.78 (78.62) + train[2018-10-12-10:12:15] Epoch: [028][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.302 (4.039) Prec@1 55.47 (55.84) Prec@5 73.44 (78.61) + train[2018-10-12-10:13:59] Epoch: [028][10000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.169 (4.040) Prec@1 50.00 (55.84) Prec@5 75.78 (78.60) + train[2018-10-12-10:14:03] Epoch: [028][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.022 (4.040) Prec@1 73.33 (55.84) Prec@5 86.67 (78.60) +[2018-10-12-10:14:03] **train** Prec@1 55.84 Prec@5 78.60 Error@1 44.16 Error@5 21.40 Loss:4.040 + test [2018-10-12-10:14:08] Epoch: [028][000/391] Time 4.54 (4.54) Data 4.39 (4.39) Loss 0.821 (0.821) Prec@1 83.59 (83.59) Prec@5 94.53 (94.53) + test [2018-10-12-10:14:36] Epoch: [028][200/391] Time 0.14 (0.16) Data 0.00 (0.03) Loss 2.438 (1.489) Prec@1 44.53 (65.02) Prec@5 68.75 (87.50) + test [2018-10-12-10:15:02] Epoch: [028][390/391] Time 0.08 (0.15) Data 0.00 (0.02) Loss 2.430 (1.703) Prec@1 40.00 (61.17) Prec@5 76.25 (83.94) +[2018-10-12-10:15:02] **test** Prec@1 61.17 Prec@5 83.94 Error@1 38.83 Error@5 16.06 Loss:1.703 +----> Best Accuracy : Acc@1=61.34, Acc@5=84.07, Error@1=38.66, Error@5=15.93 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-12-10:15:02] [Epoch=029/250] [Need: 322:27:06] LR=0.0413 ~ 0.0413, Batch=128 + train[2018-10-12-10:15:07] Epoch: [029][000/10010] Time 4.94 (4.94) Data 4.35 (4.35) Loss 3.967 (3.967) Prec@1 59.38 (59.38) Prec@5 81.25 (81.25) + train[2018-10-12-10:16:51] Epoch: [029][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 4.160 (3.961) Prec@1 49.22 (57.30) Prec@5 74.22 (79.56) + train[2018-10-12-10:18:35] Epoch: [029][400/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.909 (3.967) Prec@1 54.69 (57.11) Prec@5 75.78 (79.57) + train[2018-10-12-10:20:19] Epoch: [029][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 4.015 (3.977) Prec@1 52.34 (56.87) Prec@5 75.00 (79.41) + train[2018-10-12-10:22:03] Epoch: [029][800/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 4.001 (3.979) Prec@1 60.94 (56.86) Prec@5 79.69 (79.49) + train[2018-10-12-10:23:47] Epoch: [029][1000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.731 (3.982) Prec@1 64.06 (56.84) Prec@5 82.03 (79.42) + train[2018-10-12-10:25:31] Epoch: [029][1200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.047 (3.989) Prec@1 55.47 (56.67) Prec@5 78.12 (79.32) + train[2018-10-12-10:27:15] Epoch: [029][1400/10010] Time 0.60 (0.52) Data 0.00 (0.00) Loss 4.226 (3.990) Prec@1 56.25 (56.66) Prec@5 76.56 (79.31) + train[2018-10-12-10:28:59] Epoch: [029][1600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.341 (3.991) Prec@1 51.56 (56.66) Prec@5 77.34 (79.30) + train[2018-10-12-10:30:43] Epoch: [029][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.777 (3.994) Prec@1 58.59 (56.60) Prec@5 82.03 (79.26) + train[2018-10-12-10:32:27] Epoch: [029][2000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.617 (3.995) Prec@1 63.28 (56.56) Prec@5 82.81 (79.26) + train[2018-10-12-10:34:10] Epoch: [029][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.450 (3.998) Prec@1 50.78 (56.50) Prec@5 69.53 (79.17) + train[2018-10-12-10:35:53] Epoch: [029][2400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.844 (4.000) Prec@1 63.28 (56.51) Prec@5 82.81 (79.13) + train[2018-10-12-10:37:37] Epoch: [029][2600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.892 (4.002) Prec@1 57.03 (56.46) Prec@5 78.91 (79.12) + train[2018-10-12-10:39:20] Epoch: [029][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.798 (4.004) Prec@1 67.19 (56.46) Prec@5 82.03 (79.09) + train[2018-10-12-10:41:04] Epoch: [029][3000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.307 (4.007) Prec@1 50.00 (56.41) Prec@5 75.00 (79.05) + train[2018-10-12-10:42:48] Epoch: [029][3200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.731 (4.007) Prec@1 57.03 (56.41) Prec@5 86.72 (79.06) + train[2018-10-12-10:44:32] Epoch: [029][3400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.224 (4.007) Prec@1 52.34 (56.41) Prec@5 75.78 (79.05) + train[2018-10-12-10:46:16] Epoch: [029][3600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.786 (4.008) Prec@1 55.47 (56.41) Prec@5 81.25 (79.04) + train[2018-10-12-10:47:59] Epoch: [029][3800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.146 (4.007) Prec@1 57.03 (56.42) Prec@5 78.12 (79.03) + train[2018-10-12-10:49:42] Epoch: [029][4000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.265 (4.007) Prec@1 50.78 (56.42) Prec@5 72.66 (79.03) + train[2018-10-12-10:51:25] Epoch: [029][4200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.699 (4.009) Prec@1 61.72 (56.39) Prec@5 85.16 (79.01) + train[2018-10-12-10:53:09] Epoch: [029][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.085 (4.010) Prec@1 50.78 (56.37) Prec@5 82.81 (78.99) + train[2018-10-12-10:54:53] Epoch: [029][4600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.877 (4.009) Prec@1 61.72 (56.36) Prec@5 80.47 (79.00) + train[2018-10-12-10:56:37] Epoch: [029][4800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.126 (4.010) Prec@1 56.25 (56.35) Prec@5 78.12 (78.98) + train[2018-10-12-10:58:20] Epoch: [029][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.188 (4.009) Prec@1 48.44 (56.36) Prec@5 74.22 (78.99) + train[2018-10-12-11:00:03] Epoch: [029][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.251 (4.011) Prec@1 49.22 (56.33) Prec@5 78.91 (78.97) + train[2018-10-12-11:01:47] Epoch: [029][5400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.096 (4.011) Prec@1 60.16 (56.34) Prec@5 77.34 (78.97) + train[2018-10-12-11:03:31] Epoch: [029][5600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.062 (4.012) Prec@1 59.38 (56.33) Prec@5 78.12 (78.95) + train[2018-10-12-11:05:15] Epoch: [029][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.323 (4.012) Prec@1 53.12 (56.33) Prec@5 75.78 (78.94) + train[2018-10-12-11:06:59] Epoch: [029][6000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.104 (4.012) Prec@1 54.69 (56.33) Prec@5 78.12 (78.93) + train[2018-10-12-11:08:43] Epoch: [029][6200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.195 (4.013) Prec@1 50.78 (56.31) Prec@5 73.44 (78.92) + train[2018-10-12-11:10:27] Epoch: [029][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.442 (4.013) Prec@1 50.00 (56.30) Prec@5 71.09 (78.91) + train[2018-10-12-11:12:10] Epoch: [029][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.839 (4.013) Prec@1 58.59 (56.30) Prec@5 78.12 (78.91) + train[2018-10-12-11:13:53] Epoch: [029][6800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.301 (4.014) Prec@1 55.47 (56.29) Prec@5 73.44 (78.89) + train[2018-10-12-11:15:37] Epoch: [029][7000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.795 (4.015) Prec@1 55.47 (56.28) Prec@5 81.25 (78.88) + train[2018-10-12-11:17:21] Epoch: [029][7200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.071 (4.015) Prec@1 50.78 (56.27) Prec@5 78.91 (78.87) + train[2018-10-12-11:19:05] Epoch: [029][7400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.918 (4.016) Prec@1 58.59 (56.25) Prec@5 78.91 (78.86) + train[2018-10-12-11:20:49] Epoch: [029][7600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.187 (4.017) Prec@1 54.69 (56.24) Prec@5 74.22 (78.85) + train[2018-10-12-11:22:33] Epoch: [029][7800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.891 (4.017) Prec@1 57.81 (56.22) Prec@5 80.47 (78.85) + train[2018-10-12-11:24:16] Epoch: [029][8000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.773 (4.018) Prec@1 59.38 (56.22) Prec@5 80.47 (78.84) + train[2018-10-12-11:26:00] Epoch: [029][8200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.352 (4.019) Prec@1 45.31 (56.21) Prec@5 76.56 (78.82) + train[2018-10-12-11:27:43] Epoch: [029][8400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.990 (4.019) Prec@1 57.03 (56.20) Prec@5 82.81 (78.82) + train[2018-10-12-11:29:27] Epoch: [029][8600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.328 (4.019) Prec@1 55.47 (56.21) Prec@5 75.00 (78.83) + train[2018-10-12-11:31:11] Epoch: [029][8800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.964 (4.018) Prec@1 57.81 (56.20) Prec@5 76.56 (78.83) + train[2018-10-12-11:32:54] Epoch: [029][9000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.618 (4.018) Prec@1 64.84 (56.21) Prec@5 83.59 (78.84) + train[2018-10-12-11:34:38] Epoch: [029][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.133 (4.018) Prec@1 52.34 (56.20) Prec@5 76.56 (78.84) + train[2018-10-12-11:36:21] Epoch: [029][9400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.828 (4.019) Prec@1 57.81 (56.18) Prec@5 78.91 (78.83) + train[2018-10-12-11:38:04] Epoch: [029][9600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.267 (4.019) Prec@1 50.00 (56.18) Prec@5 78.91 (78.84) + train[2018-10-12-11:39:48] Epoch: [029][9800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.002 (4.020) Prec@1 63.28 (56.17) Prec@5 78.91 (78.82) + train[2018-10-12-11:41:31] Epoch: [029][10000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.916 (4.020) Prec@1 56.25 (56.17) Prec@5 78.91 (78.82) + train[2018-10-12-11:41:35] Epoch: [029][10009/10010] Time 0.14 (0.52) Data 0.00 (0.00) Loss 4.465 (4.020) Prec@1 53.33 (56.16) Prec@5 73.33 (78.82) +[2018-10-12-11:41:35] **train** Prec@1 56.16 Prec@5 78.82 Error@1 43.84 Error@5 21.18 Loss:4.020 + test [2018-10-12-11:41:39] Epoch: [029][000/391] Time 4.09 (4.09) Data 3.95 (3.95) Loss 0.953 (0.953) Prec@1 79.69 (79.69) Prec@5 92.19 (92.19) + test [2018-10-12-11:42:06] Epoch: [029][200/391] Time 0.15 (0.16) Data 0.00 (0.02) Loss 1.964 (1.491) Prec@1 51.56 (65.19) Prec@5 78.12 (87.40) + test [2018-10-12-11:42:31] Epoch: [029][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 3.002 (1.694) Prec@1 22.50 (61.49) Prec@5 67.50 (84.12) +[2018-10-12-11:42:31] **test** Prec@1 61.49 Prec@5 84.12 Error@1 38.51 Error@5 15.88 Loss:1.694 +----> Best Accuracy : Acc@1=61.49, Acc@5=84.12, Error@1=38.51, Error@5=15.88 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-12-11:42:31] [Epoch=030/250] [Need: 320:48:00] LR=0.0401 ~ 0.0401, Batch=128 + train[2018-10-12-11:42:36] Epoch: [030][000/10010] Time 4.62 (4.62) Data 4.05 (4.05) Loss 3.919 (3.919) Prec@1 60.16 (60.16) Prec@5 78.12 (78.12) + train[2018-10-12-11:44:20] Epoch: [030][200/10010] Time 0.54 (0.54) Data 0.00 (0.02) Loss 3.930 (3.969) Prec@1 57.81 (56.85) Prec@5 75.78 (79.37) + train[2018-10-12-11:46:03] Epoch: [030][400/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.771 (3.962) Prec@1 65.62 (57.40) Prec@5 78.91 (79.55) + train[2018-10-12-11:47:47] Epoch: [030][600/10010] Time 0.53 (0.52) Data 0.00 (0.01) Loss 3.902 (3.967) Prec@1 57.03 (57.26) Prec@5 78.12 (79.50) + train[2018-10-12-11:49:30] Epoch: [030][800/10010] Time 0.50 (0.52) Data 0.00 (0.01) Loss 3.836 (3.970) Prec@1 60.16 (57.13) Prec@5 82.03 (79.49) + train[2018-10-12-11:51:14] Epoch: [030][1000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.016 (3.972) Prec@1 60.16 (57.04) Prec@5 79.69 (79.47) + train[2018-10-12-11:52:57] Epoch: [030][1200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.262 (3.975) Prec@1 54.69 (56.99) Prec@5 73.44 (79.44) + train[2018-10-12-11:54:41] Epoch: [030][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.695 (3.978) Prec@1 62.50 (56.98) Prec@5 82.03 (79.41) + train[2018-10-12-11:56:26] Epoch: [030][1600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.790 (3.979) Prec@1 53.91 (56.94) Prec@5 82.03 (79.39) + train[2018-10-12-11:58:09] Epoch: [030][1800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.241 (3.982) Prec@1 53.12 (56.85) Prec@5 74.22 (79.35) + train[2018-10-12-11:59:52] Epoch: [030][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.203 (3.982) Prec@1 53.12 (56.82) Prec@5 74.22 (79.34) + train[2018-10-12-12:01:37] Epoch: [030][2200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.989 (3.985) Prec@1 53.12 (56.76) Prec@5 82.03 (79.31) + train[2018-10-12-12:03:21] Epoch: [030][2400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.639 (3.985) Prec@1 61.72 (56.77) Prec@5 85.16 (79.30) + train[2018-10-12-12:05:04] Epoch: [030][2600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.921 (3.983) Prec@1 53.91 (56.78) Prec@5 82.03 (79.34) + train[2018-10-12-12:06:49] Epoch: [030][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.204 (3.983) Prec@1 49.22 (56.77) Prec@5 77.34 (79.34) + train[2018-10-12-12:08:32] Epoch: [030][3000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.159 (3.984) Prec@1 52.34 (56.76) Prec@5 76.56 (79.33) + train[2018-10-12-12:10:16] Epoch: [030][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.147 (3.985) Prec@1 57.03 (56.75) Prec@5 79.69 (79.34) + train[2018-10-12-12:12:00] Epoch: [030][3400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.090 (3.987) Prec@1 52.34 (56.71) Prec@5 75.00 (79.29) + train[2018-10-12-12:13:43] Epoch: [030][3600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.708 (3.988) Prec@1 59.38 (56.70) Prec@5 88.28 (79.27) + train[2018-10-12-12:15:28] Epoch: [030][3800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.562 (3.988) Prec@1 48.44 (56.69) Prec@5 68.75 (79.27) + train[2018-10-12-12:17:11] Epoch: [030][4000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.640 (3.987) Prec@1 64.84 (56.68) Prec@5 85.94 (79.28) + train[2018-10-12-12:18:55] Epoch: [030][4200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.191 (3.990) Prec@1 53.12 (56.64) Prec@5 73.44 (79.24) + train[2018-10-12-12:20:38] Epoch: [030][4400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.653 (3.990) Prec@1 62.50 (56.65) Prec@5 84.38 (79.23) + train[2018-10-12-12:22:22] Epoch: [030][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.223 (3.992) Prec@1 56.25 (56.62) Prec@5 75.78 (79.22) + train[2018-10-12-12:24:07] Epoch: [030][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.935 (3.992) Prec@1 53.91 (56.61) Prec@5 82.03 (79.21) + train[2018-10-12-12:25:50] Epoch: [030][5000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.045 (3.992) Prec@1 56.25 (56.61) Prec@5 82.03 (79.20) + train[2018-10-12-12:27:34] Epoch: [030][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.259 (3.992) Prec@1 48.44 (56.61) Prec@5 74.22 (79.21) + train[2018-10-12-12:29:17] Epoch: [030][5400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.191 (3.993) Prec@1 52.34 (56.62) Prec@5 80.47 (79.19) + train[2018-10-12-12:31:01] Epoch: [030][5600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.160 (3.993) Prec@1 49.22 (56.62) Prec@5 82.03 (79.19) + train[2018-10-12-12:32:45] Epoch: [030][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.931 (3.993) Prec@1 58.59 (56.62) Prec@5 80.47 (79.19) + train[2018-10-12-12:34:29] Epoch: [030][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.351 (3.994) Prec@1 53.91 (56.60) Prec@5 72.66 (79.17) + train[2018-10-12-12:36:13] Epoch: [030][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.829 (3.995) Prec@1 61.72 (56.60) Prec@5 80.47 (79.17) + train[2018-10-12-12:37:56] Epoch: [030][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.812 (3.995) Prec@1 55.47 (56.59) Prec@5 82.03 (79.16) + train[2018-10-12-12:39:40] Epoch: [030][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.889 (3.995) Prec@1 64.84 (56.58) Prec@5 80.47 (79.16) + train[2018-10-12-12:41:24] Epoch: [030][6800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.947 (3.996) Prec@1 55.47 (56.56) Prec@5 78.12 (79.15) + train[2018-10-12-12:43:07] Epoch: [030][7000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.223 (3.997) Prec@1 53.12 (56.55) Prec@5 76.56 (79.14) + train[2018-10-12-12:44:50] Epoch: [030][7200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.988 (3.997) Prec@1 53.91 (56.55) Prec@5 80.47 (79.14) + train[2018-10-12-12:46:34] Epoch: [030][7400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.039 (3.997) Prec@1 58.59 (56.54) Prec@5 79.69 (79.14) + train[2018-10-12-12:48:18] Epoch: [030][7600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.162 (3.998) Prec@1 53.12 (56.52) Prec@5 75.78 (79.13) + train[2018-10-12-12:50:02] Epoch: [030][7800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.879 (3.998) Prec@1 53.12 (56.52) Prec@5 77.34 (79.12) + train[2018-10-12-12:51:45] Epoch: [030][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.329 (3.999) Prec@1 50.00 (56.50) Prec@5 77.34 (79.10) + train[2018-10-12-12:53:29] Epoch: [030][8200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.902 (3.999) Prec@1 56.25 (56.50) Prec@5 79.69 (79.10) + train[2018-10-12-12:55:13] Epoch: [030][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.026 (4.000) Prec@1 52.34 (56.48) Prec@5 75.78 (79.09) + train[2018-10-12-12:56:56] Epoch: [030][8600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.213 (4.000) Prec@1 56.25 (56.47) Prec@5 77.34 (79.08) + train[2018-10-12-12:58:40] Epoch: [030][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.688 (4.000) Prec@1 61.72 (56.47) Prec@5 82.03 (79.09) + train[2018-10-12-13:00:24] Epoch: [030][9000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.929 (4.000) Prec@1 53.91 (56.46) Prec@5 79.69 (79.09) + train[2018-10-12-13:02:08] Epoch: [030][9200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.192 (4.000) Prec@1 50.78 (56.46) Prec@5 76.56 (79.09) + train[2018-10-12-13:03:51] Epoch: [030][9400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.995 (4.001) Prec@1 57.81 (56.45) Prec@5 81.25 (79.08) + train[2018-10-12-13:05:35] Epoch: [030][9600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.333 (4.001) Prec@1 49.22 (56.44) Prec@5 74.22 (79.08) + train[2018-10-12-13:07:18] Epoch: [030][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.199 (4.001) Prec@1 52.34 (56.44) Prec@5 78.12 (79.07) + train[2018-10-12-13:09:02] Epoch: [030][10000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.304 (4.002) Prec@1 53.91 (56.43) Prec@5 79.69 (79.06) + train[2018-10-12-13:09:06] Epoch: [030][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 5.131 (4.002) Prec@1 53.33 (56.42) Prec@5 60.00 (79.06) +[2018-10-12-13:09:06] **train** Prec@1 56.42 Prec@5 79.06 Error@1 43.58 Error@5 20.94 Loss:4.002 + test [2018-10-12-13:09:10] Epoch: [030][000/391] Time 3.70 (3.70) Data 3.56 (3.56) Loss 0.833 (0.833) Prec@1 80.47 (80.47) Prec@5 92.19 (92.19) + test [2018-10-12-13:09:38] Epoch: [030][200/391] Time 0.12 (0.16) Data 0.00 (0.03) Loss 2.466 (1.483) Prec@1 42.19 (65.57) Prec@5 71.09 (87.26) + test [2018-10-12-13:10:03] Epoch: [030][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.995 (1.695) Prec@1 31.25 (61.57) Prec@5 66.25 (84.02) +[2018-10-12-13:10:03] **test** Prec@1 61.57 Prec@5 84.02 Error@1 38.43 Error@5 15.98 Loss:1.695 +----> Best Accuracy : Acc@1=61.57, Acc@5=84.02, Error@1=38.43, Error@5=15.98 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-12-13:10:03] [Epoch=031/250] [Need: 319:28:18] LR=0.0389 ~ 0.0389, Batch=128 + train[2018-10-12-13:10:09] Epoch: [031][000/10010] Time 5.86 (5.86) Data 5.30 (5.30) Loss 3.633 (3.633) Prec@1 57.81 (57.81) Prec@5 85.94 (85.94) + train[2018-10-12-13:11:52] Epoch: [031][200/10010] Time 0.54 (0.54) Data 0.00 (0.03) Loss 4.173 (3.950) Prec@1 52.34 (57.31) Prec@5 76.56 (79.67) + train[2018-10-12-13:13:36] Epoch: [031][400/10010] Time 0.56 (0.53) Data 0.00 (0.01) Loss 3.895 (3.946) Prec@1 57.03 (57.50) Prec@5 76.56 (79.77) + train[2018-10-12-13:15:19] Epoch: [031][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 4.145 (3.945) Prec@1 57.03 (57.48) Prec@5 77.34 (79.79) + train[2018-10-12-13:17:03] Epoch: [031][800/10010] Time 0.51 (0.52) Data 0.00 (0.01) Loss 3.637 (3.938) Prec@1 61.72 (57.48) Prec@5 83.59 (79.94) + train[2018-10-12-13:18:47] Epoch: [031][1000/10010] Time 0.50 (0.52) Data 0.00 (0.01) Loss 4.424 (3.942) Prec@1 50.78 (57.39) Prec@5 70.31 (79.90) + train[2018-10-12-13:20:30] Epoch: [031][1200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.150 (3.948) Prec@1 51.56 (57.33) Prec@5 78.91 (79.80) + train[2018-10-12-13:22:14] Epoch: [031][1400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.130 (3.947) Prec@1 52.34 (57.37) Prec@5 80.47 (79.79) + train[2018-10-12-13:23:57] Epoch: [031][1600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.967 (3.948) Prec@1 59.38 (57.33) Prec@5 77.34 (79.78) + train[2018-10-12-13:25:41] Epoch: [031][1800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.155 (3.952) Prec@1 57.81 (57.27) Prec@5 74.22 (79.72) + train[2018-10-12-13:27:25] Epoch: [031][2000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.766 (3.952) Prec@1 60.94 (57.29) Prec@5 84.38 (79.69) + train[2018-10-12-13:29:09] Epoch: [031][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.737 (3.953) Prec@1 58.59 (57.31) Prec@5 80.47 (79.69) + train[2018-10-12-13:30:52] Epoch: [031][2400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.002 (3.954) Prec@1 57.81 (57.27) Prec@5 82.81 (79.68) + train[2018-10-12-13:32:36] Epoch: [031][2600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.071 (3.955) Prec@1 52.34 (57.24) Prec@5 76.56 (79.66) + train[2018-10-12-13:34:20] Epoch: [031][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.035 (3.957) Prec@1 53.12 (57.20) Prec@5 80.47 (79.63) + train[2018-10-12-13:36:03] Epoch: [031][3000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.761 (3.959) Prec@1 57.81 (57.17) Prec@5 81.25 (79.61) + train[2018-10-12-13:37:48] Epoch: [031][3200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.909 (3.961) Prec@1 59.38 (57.15) Prec@5 82.81 (79.59) + train[2018-10-12-13:39:31] Epoch: [031][3400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.179 (3.961) Prec@1 45.31 (57.14) Prec@5 77.34 (79.57) + train[2018-10-12-13:41:15] Epoch: [031][3600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.602 (3.961) Prec@1 62.50 (57.15) Prec@5 83.59 (79.59) + train[2018-10-12-13:42:59] Epoch: [031][3800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.824 (3.962) Prec@1 59.38 (57.13) Prec@5 84.38 (79.59) + train[2018-10-12-13:44:43] Epoch: [031][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.923 (3.963) Prec@1 53.91 (57.11) Prec@5 79.69 (79.58) + train[2018-10-12-13:46:27] Epoch: [031][4200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.895 (3.963) Prec@1 56.25 (57.10) Prec@5 76.56 (79.56) + train[2018-10-12-13:48:11] Epoch: [031][4400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.398 (3.966) Prec@1 50.78 (57.05) Prec@5 75.78 (79.55) + train[2018-10-12-13:49:54] Epoch: [031][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.769 (3.967) Prec@1 61.72 (57.05) Prec@5 82.03 (79.53) + train[2018-10-12-13:51:38] Epoch: [031][4800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.763 (3.967) Prec@1 57.03 (57.06) Prec@5 83.59 (79.53) + train[2018-10-12-13:53:22] Epoch: [031][5000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.724 (3.968) Prec@1 55.47 (57.03) Prec@5 83.59 (79.52) + train[2018-10-12-13:55:06] Epoch: [031][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.233 (3.969) Prec@1 53.91 (57.02) Prec@5 73.44 (79.51) + train[2018-10-12-13:56:49] Epoch: [031][5400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.891 (3.969) Prec@1 60.94 (57.01) Prec@5 78.91 (79.51) + train[2018-10-12-13:58:33] Epoch: [031][5600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.299 (3.970) Prec@1 55.47 (57.01) Prec@5 78.12 (79.50) + train[2018-10-12-14:00:16] Epoch: [031][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.486 (3.970) Prec@1 47.66 (57.00) Prec@5 71.88 (79.48) + train[2018-10-12-14:02:01] Epoch: [031][6000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.113 (3.970) Prec@1 54.69 (56.99) Prec@5 76.56 (79.49) + train[2018-10-12-14:03:44] Epoch: [031][6200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.033 (3.971) Prec@1 57.03 (56.98) Prec@5 78.12 (79.48) + train[2018-10-12-14:05:27] Epoch: [031][6400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.027 (3.971) Prec@1 58.59 (56.98) Prec@5 77.34 (79.47) + train[2018-10-12-14:07:11] Epoch: [031][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.999 (3.972) Prec@1 57.03 (56.96) Prec@5 78.91 (79.46) + train[2018-10-12-14:08:55] Epoch: [031][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.101 (3.973) Prec@1 50.78 (56.94) Prec@5 78.12 (79.44) + train[2018-10-12-14:10:39] Epoch: [031][7000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.018 (3.974) Prec@1 55.47 (56.92) Prec@5 79.69 (79.42) + train[2018-10-12-14:12:22] Epoch: [031][7200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.779 (3.975) Prec@1 62.50 (56.92) Prec@5 82.81 (79.42) + train[2018-10-12-14:14:05] Epoch: [031][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.106 (3.975) Prec@1 57.81 (56.90) Prec@5 78.12 (79.42) + train[2018-10-12-14:15:49] Epoch: [031][7600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.831 (3.975) Prec@1 60.94 (56.90) Prec@5 83.59 (79.41) + train[2018-10-12-14:17:33] Epoch: [031][7800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.850 (3.976) Prec@1 59.38 (56.89) Prec@5 83.59 (79.40) + train[2018-10-12-14:19:17] Epoch: [031][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.918 (3.976) Prec@1 58.59 (56.88) Prec@5 79.69 (79.40) + train[2018-10-12-14:21:01] Epoch: [031][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.258 (3.977) Prec@1 55.47 (56.87) Prec@5 76.56 (79.39) + train[2018-10-12-14:22:44] Epoch: [031][8400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.192 (3.978) Prec@1 52.34 (56.86) Prec@5 79.69 (79.38) + train[2018-10-12-14:24:28] Epoch: [031][8600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.023 (3.978) Prec@1 49.22 (56.85) Prec@5 79.69 (79.37) + train[2018-10-12-14:26:11] Epoch: [031][8800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.441 (3.979) Prec@1 48.44 (56.84) Prec@5 73.44 (79.36) + train[2018-10-12-14:27:55] Epoch: [031][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.904 (3.979) Prec@1 60.94 (56.83) Prec@5 80.47 (79.35) + train[2018-10-12-14:29:39] Epoch: [031][9200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.878 (3.980) Prec@1 60.16 (56.81) Prec@5 78.91 (79.35) + train[2018-10-12-14:31:23] Epoch: [031][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.027 (3.981) Prec@1 55.47 (56.80) Prec@5 79.69 (79.33) + train[2018-10-12-14:33:07] Epoch: [031][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.058 (3.981) Prec@1 52.34 (56.79) Prec@5 77.34 (79.32) + train[2018-10-12-14:34:50] Epoch: [031][9800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.954 (3.982) Prec@1 55.47 (56.77) Prec@5 76.56 (79.31) + train[2018-10-12-14:36:34] Epoch: [031][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.196 (3.982) Prec@1 59.38 (56.76) Prec@5 71.09 (79.30) + train[2018-10-12-14:36:38] Epoch: [031][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 5.032 (3.982) Prec@1 53.33 (56.76) Prec@5 60.00 (79.30) +[2018-10-12-14:36:38] **train** Prec@1 56.76 Prec@5 79.30 Error@1 43.24 Error@5 20.70 Loss:3.982 + test [2018-10-12-14:36:42] Epoch: [031][000/391] Time 3.52 (3.52) Data 3.38 (3.38) Loss 0.867 (0.867) Prec@1 82.03 (82.03) Prec@5 96.88 (96.88) + test [2018-10-12-14:37:10] Epoch: [031][200/391] Time 0.12 (0.16) Data 0.00 (0.02) Loss 1.924 (1.437) Prec@1 53.12 (65.95) Prec@5 84.38 (87.97) + test [2018-10-12-14:37:35] Epoch: [031][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.867 (1.652) Prec@1 30.00 (62.28) Prec@5 70.00 (84.66) +[2018-10-12-14:37:35] **test** Prec@1 62.28 Prec@5 84.66 Error@1 37.72 Error@5 15.34 Loss:1.652 +----> Best Accuracy : Acc@1=62.28, Acc@5=84.66, Error@1=37.72, Error@5=15.34 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-12-14:37:35] [Epoch=032/250] [Need: 318:02:51] LR=0.0377 ~ 0.0377, Batch=128 + train[2018-10-12-14:37:39] Epoch: [032][000/10010] Time 4.41 (4.41) Data 3.76 (3.76) Loss 4.117 (4.117) Prec@1 52.34 (52.34) Prec@5 77.34 (77.34) + train[2018-10-12-14:39:24] Epoch: [032][200/10010] Time 0.52 (0.54) Data 0.00 (0.02) Loss 4.000 (3.926) Prec@1 59.38 (57.76) Prec@5 80.47 (80.03) + train[2018-10-12-14:41:08] Epoch: [032][400/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.970 (3.929) Prec@1 57.81 (57.77) Prec@5 76.56 (79.97) + train[2018-10-12-14:42:51] Epoch: [032][600/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.607 (3.924) Prec@1 57.81 (57.85) Prec@5 85.94 (80.07) + train[2018-10-12-14:44:35] Epoch: [032][800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.855 (3.931) Prec@1 53.91 (57.71) Prec@5 83.59 (80.00) + train[2018-10-12-14:46:19] Epoch: [032][1000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.039 (3.937) Prec@1 55.47 (57.60) Prec@5 76.56 (79.89) + train[2018-10-12-14:48:03] Epoch: [032][1200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.884 (3.937) Prec@1 57.81 (57.58) Prec@5 81.25 (79.86) + train[2018-10-12-14:49:47] Epoch: [032][1400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.064 (3.938) Prec@1 54.69 (57.54) Prec@5 77.34 (79.84) + train[2018-10-12-14:51:30] Epoch: [032][1600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.036 (3.943) Prec@1 57.81 (57.49) Prec@5 75.78 (79.78) + train[2018-10-12-14:53:14] Epoch: [032][1800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.773 (3.945) Prec@1 60.16 (57.47) Prec@5 82.03 (79.76) + train[2018-10-12-14:54:58] Epoch: [032][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.724 (3.945) Prec@1 60.94 (57.48) Prec@5 83.59 (79.77) + train[2018-10-12-14:56:41] Epoch: [032][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.630 (3.947) Prec@1 60.16 (57.44) Prec@5 83.59 (79.74) + train[2018-10-12-14:58:25] Epoch: [032][2400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.388 (3.946) Prec@1 46.88 (57.44) Prec@5 75.78 (79.75) + train[2018-10-12-15:00:09] Epoch: [032][2600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.964 (3.945) Prec@1 60.16 (57.43) Prec@5 78.12 (79.76) + train[2018-10-12-15:01:53] Epoch: [032][2800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.192 (3.945) Prec@1 52.34 (57.39) Prec@5 75.00 (79.78) + train[2018-10-12-15:03:37] Epoch: [032][3000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.976 (3.947) Prec@1 57.03 (57.39) Prec@5 77.34 (79.75) + train[2018-10-12-15:05:21] Epoch: [032][3200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.668 (3.947) Prec@1 62.50 (57.38) Prec@5 83.59 (79.73) + train[2018-10-12-15:07:05] Epoch: [032][3400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.819 (3.949) Prec@1 56.25 (57.34) Prec@5 81.25 (79.71) + train[2018-10-12-15:08:49] Epoch: [032][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.861 (3.951) Prec@1 63.28 (57.30) Prec@5 78.91 (79.68) + train[2018-10-12-15:10:33] Epoch: [032][3800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.744 (3.952) Prec@1 59.38 (57.27) Prec@5 80.47 (79.67) + train[2018-10-12-15:12:17] Epoch: [032][4000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.795 (3.952) Prec@1 58.59 (57.28) Prec@5 83.59 (79.68) + train[2018-10-12-15:14:01] Epoch: [032][4200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.134 (3.953) Prec@1 53.91 (57.26) Prec@5 81.25 (79.66) + train[2018-10-12-15:15:46] Epoch: [032][4400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.532 (3.953) Prec@1 63.28 (57.26) Prec@5 86.72 (79.65) + train[2018-10-12-15:17:29] Epoch: [032][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.144 (3.953) Prec@1 54.69 (57.26) Prec@5 78.91 (79.64) + train[2018-10-12-15:19:14] Epoch: [032][4800/10010] Time 0.59 (0.52) Data 0.00 (0.00) Loss 4.670 (3.955) Prec@1 48.44 (57.22) Prec@5 72.66 (79.62) + train[2018-10-12-15:20:58] Epoch: [032][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.738 (3.954) Prec@1 58.59 (57.24) Prec@5 81.25 (79.62) + train[2018-10-12-15:22:42] Epoch: [032][5200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.116 (3.954) Prec@1 53.12 (57.24) Prec@5 77.34 (79.63) + train[2018-10-12-15:24:25] Epoch: [032][5400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.825 (3.954) Prec@1 61.72 (57.24) Prec@5 81.25 (79.61) + train[2018-10-12-15:26:09] Epoch: [032][5600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.705 (3.955) Prec@1 62.50 (57.23) Prec@5 83.59 (79.60) + train[2018-10-12-15:27:53] Epoch: [032][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.829 (3.956) Prec@1 56.25 (57.21) Prec@5 80.47 (79.58) + train[2018-10-12-15:29:37] Epoch: [032][6000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.909 (3.956) Prec@1 59.38 (57.21) Prec@5 78.91 (79.58) + train[2018-10-12-15:31:21] Epoch: [032][6200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.609 (3.957) Prec@1 61.72 (57.18) Prec@5 83.59 (79.57) + train[2018-10-12-15:33:04] Epoch: [032][6400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.921 (3.958) Prec@1 57.03 (57.18) Prec@5 80.47 (79.57) + train[2018-10-12-15:34:48] Epoch: [032][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.146 (3.958) Prec@1 60.94 (57.16) Prec@5 74.22 (79.57) + train[2018-10-12-15:36:33] Epoch: [032][6800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.967 (3.959) Prec@1 57.03 (57.16) Prec@5 78.91 (79.56) + train[2018-10-12-15:38:17] Epoch: [032][7000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.942 (3.959) Prec@1 50.00 (57.15) Prec@5 82.03 (79.56) + train[2018-10-12-15:40:01] Epoch: [032][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.904 (3.960) Prec@1 57.03 (57.13) Prec@5 79.69 (79.55) + train[2018-10-12-15:41:45] Epoch: [032][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.748 (3.960) Prec@1 62.50 (57.13) Prec@5 80.47 (79.55) + train[2018-10-12-15:43:30] Epoch: [032][7600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.099 (3.961) Prec@1 55.47 (57.12) Prec@5 78.91 (79.54) + train[2018-10-12-15:45:13] Epoch: [032][7800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.931 (3.962) Prec@1 60.16 (57.10) Prec@5 76.56 (79.53) + train[2018-10-12-15:46:57] Epoch: [032][8000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.889 (3.962) Prec@1 56.25 (57.10) Prec@5 82.81 (79.52) + train[2018-10-12-15:48:41] Epoch: [032][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.145 (3.962) Prec@1 53.91 (57.08) Prec@5 76.56 (79.51) + train[2018-10-12-15:50:25] Epoch: [032][8400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.055 (3.963) Prec@1 55.47 (57.06) Prec@5 75.78 (79.49) + train[2018-10-12-15:52:09] Epoch: [032][8600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.129 (3.963) Prec@1 57.81 (57.06) Prec@5 78.12 (79.50) + train[2018-10-12-15:53:53] Epoch: [032][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.906 (3.963) Prec@1 59.38 (57.07) Prec@5 79.69 (79.50) + train[2018-10-12-15:55:37] Epoch: [032][9000/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 4.471 (3.964) Prec@1 52.34 (57.07) Prec@5 77.34 (79.49) + train[2018-10-12-15:57:21] Epoch: [032][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.235 (3.964) Prec@1 55.47 (57.07) Prec@5 76.56 (79.50) + train[2018-10-12-15:59:05] Epoch: [032][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.853 (3.964) Prec@1 58.59 (57.06) Prec@5 81.25 (79.49) + train[2018-10-12-16:00:49] Epoch: [032][9600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.934 (3.965) Prec@1 56.25 (57.05) Prec@5 81.25 (79.49) + train[2018-10-12-16:02:33] Epoch: [032][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.612 (3.965) Prec@1 64.84 (57.04) Prec@5 83.59 (79.49) + train[2018-10-12-16:04:16] Epoch: [032][10000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.150 (3.965) Prec@1 53.12 (57.03) Prec@5 75.78 (79.48) + train[2018-10-12-16:04:21] Epoch: [032][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.546 (3.965) Prec@1 40.00 (57.04) Prec@5 80.00 (79.48) +[2018-10-12-16:04:21] **train** Prec@1 57.04 Prec@5 79.48 Error@1 42.96 Error@5 20.52 Loss:3.965 + test [2018-10-12-16:04:25] Epoch: [032][000/391] Time 4.26 (4.26) Data 4.11 (4.11) Loss 0.846 (0.846) Prec@1 82.03 (82.03) Prec@5 92.19 (92.19) + test [2018-10-12-16:04:52] Epoch: [032][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.882 (1.460) Prec@1 59.38 (66.05) Prec@5 80.47 (87.84) + test [2018-10-12-16:05:17] Epoch: [032][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.592 (1.653) Prec@1 38.75 (62.43) Prec@5 76.25 (84.73) +[2018-10-12-16:05:17] **test** Prec@1 62.43 Prec@5 84.73 Error@1 37.57 Error@5 15.27 Loss:1.653 +----> Best Accuracy : Acc@1=62.43, Acc@5=84.73, Error@1=37.57, Error@5=15.27 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-12-16:05:17] [Epoch=033/250] [Need: 317:12:27] LR=0.0366 ~ 0.0366, Batch=128 + train[2018-10-12-16:05:23] Epoch: [033][000/10010] Time 5.08 (5.08) Data 4.46 (4.46) Loss 4.313 (4.313) Prec@1 50.78 (50.78) Prec@5 76.56 (76.56) + train[2018-10-12-16:07:06] Epoch: [033][200/10010] Time 0.51 (0.54) Data 0.00 (0.02) Loss 3.880 (3.938) Prec@1 57.81 (58.00) Prec@5 80.47 (79.64) + train[2018-10-12-16:08:50] Epoch: [033][400/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.930 (3.926) Prec@1 57.81 (57.88) Prec@5 77.34 (79.84) + train[2018-10-12-16:10:34] Epoch: [033][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 4.268 (3.931) Prec@1 54.69 (57.77) Prec@5 77.34 (79.86) + train[2018-10-12-16:12:17] Epoch: [033][800/10010] Time 0.56 (0.52) Data 0.00 (0.01) Loss 3.686 (3.924) Prec@1 59.38 (57.76) Prec@5 84.38 (80.00) + train[2018-10-12-16:14:01] Epoch: [033][1000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.925 (3.918) Prec@1 60.16 (57.84) Prec@5 77.34 (80.12) + train[2018-10-12-16:15:44] Epoch: [033][1200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.027 (3.916) Prec@1 58.59 (57.89) Prec@5 78.91 (80.11) + train[2018-10-12-16:17:28] Epoch: [033][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.814 (3.918) Prec@1 57.81 (57.86) Prec@5 80.47 (80.09) + train[2018-10-12-16:19:12] Epoch: [033][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.277 (3.916) Prec@1 51.56 (57.85) Prec@5 77.34 (80.13) + train[2018-10-12-16:20:55] Epoch: [033][1800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.737 (3.917) Prec@1 61.72 (57.83) Prec@5 78.91 (80.13) + train[2018-10-12-16:22:39] Epoch: [033][2000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.132 (3.918) Prec@1 56.25 (57.80) Prec@5 78.91 (80.13) + train[2018-10-12-16:24:23] Epoch: [033][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.644 (3.920) Prec@1 63.28 (57.74) Prec@5 84.38 (80.12) + train[2018-10-12-16:26:07] Epoch: [033][2400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.900 (3.924) Prec@1 53.91 (57.71) Prec@5 78.91 (80.05) + train[2018-10-12-16:27:51] Epoch: [033][2600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.842 (3.925) Prec@1 57.81 (57.69) Prec@5 82.03 (80.04) + train[2018-10-12-16:29:34] Epoch: [033][2800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.286 (3.926) Prec@1 54.69 (57.69) Prec@5 78.12 (80.03) + train[2018-10-12-16:31:18] Epoch: [033][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.047 (3.926) Prec@1 57.81 (57.70) Prec@5 80.47 (80.01) + train[2018-10-12-16:33:02] Epoch: [033][3200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.002 (3.927) Prec@1 58.59 (57.67) Prec@5 78.12 (79.99) + train[2018-10-12-16:34:45] Epoch: [033][3400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.055 (3.931) Prec@1 53.12 (57.63) Prec@5 82.03 (79.96) + train[2018-10-12-16:36:29] Epoch: [033][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.142 (3.932) Prec@1 57.03 (57.60) Prec@5 77.34 (79.94) + train[2018-10-12-16:38:13] Epoch: [033][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.641 (3.933) Prec@1 58.59 (57.57) Prec@5 85.16 (79.91) + train[2018-10-12-16:39:57] Epoch: [033][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.616 (3.932) Prec@1 62.50 (57.58) Prec@5 84.38 (79.93) + train[2018-10-12-16:41:41] Epoch: [033][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.758 (3.933) Prec@1 61.72 (57.55) Prec@5 80.47 (79.91) + train[2018-10-12-16:43:24] Epoch: [033][4400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.837 (3.935) Prec@1 57.81 (57.53) Prec@5 82.03 (79.90) + train[2018-10-12-16:45:08] Epoch: [033][4600/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.999 (3.935) Prec@1 56.25 (57.53) Prec@5 79.69 (79.88) + train[2018-10-12-16:46:51] Epoch: [033][4800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.626 (3.935) Prec@1 59.38 (57.52) Prec@5 85.94 (79.88) + train[2018-10-12-16:48:35] Epoch: [033][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.544 (3.936) Prec@1 64.06 (57.51) Prec@5 84.38 (79.87) + train[2018-10-12-16:50:18] Epoch: [033][5200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.949 (3.936) Prec@1 57.81 (57.51) Prec@5 79.69 (79.87) + train[2018-10-12-16:52:02] Epoch: [033][5400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.154 (3.936) Prec@1 51.56 (57.51) Prec@5 78.12 (79.86) + train[2018-10-12-16:53:46] Epoch: [033][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.127 (3.937) Prec@1 51.56 (57.50) Prec@5 78.91 (79.86) + train[2018-10-12-16:55:30] Epoch: [033][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.651 (3.938) Prec@1 63.28 (57.49) Prec@5 84.38 (79.85) + train[2018-10-12-16:57:14] Epoch: [033][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.728 (3.938) Prec@1 62.50 (57.48) Prec@5 82.81 (79.85) + train[2018-10-12-16:58:57] Epoch: [033][6200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.990 (3.938) Prec@1 57.81 (57.48) Prec@5 80.47 (79.85) + train[2018-10-12-17:00:41] Epoch: [033][6400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.234 (3.939) Prec@1 55.47 (57.47) Prec@5 76.56 (79.85) + train[2018-10-12-17:02:25] Epoch: [033][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.565 (3.940) Prec@1 62.50 (57.45) Prec@5 85.16 (79.84) + train[2018-10-12-17:04:09] Epoch: [033][6800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.056 (3.940) Prec@1 51.56 (57.46) Prec@5 74.22 (79.85) + train[2018-10-12-17:05:52] Epoch: [033][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.837 (3.940) Prec@1 59.38 (57.46) Prec@5 80.47 (79.84) + train[2018-10-12-17:07:37] Epoch: [033][7200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.889 (3.941) Prec@1 56.25 (57.45) Prec@5 79.69 (79.82) + train[2018-10-12-17:09:21] Epoch: [033][7400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.224 (3.942) Prec@1 46.88 (57.44) Prec@5 77.34 (79.81) + train[2018-10-12-17:11:05] Epoch: [033][7600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.983 (3.942) Prec@1 57.03 (57.43) Prec@5 78.91 (79.81) + train[2018-10-12-17:12:49] Epoch: [033][7800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.854 (3.942) Prec@1 51.56 (57.42) Prec@5 82.81 (79.80) + train[2018-10-12-17:14:33] Epoch: [033][8000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.098 (3.942) Prec@1 52.34 (57.42) Prec@5 77.34 (79.79) + train[2018-10-12-17:16:16] Epoch: [033][8200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.092 (3.942) Prec@1 60.16 (57.42) Prec@5 78.12 (79.80) + train[2018-10-12-17:18:00] Epoch: [033][8400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.791 (3.943) Prec@1 57.03 (57.41) Prec@5 81.25 (79.79) + train[2018-10-12-17:19:43] Epoch: [033][8600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.780 (3.943) Prec@1 56.25 (57.41) Prec@5 83.59 (79.79) + train[2018-10-12-17:21:27] Epoch: [033][8800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.156 (3.944) Prec@1 53.12 (57.39) Prec@5 80.47 (79.78) + train[2018-10-12-17:23:11] Epoch: [033][9000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.308 (3.944) Prec@1 46.09 (57.39) Prec@5 75.00 (79.77) + train[2018-10-12-17:24:55] Epoch: [033][9200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.739 (3.945) Prec@1 60.16 (57.39) Prec@5 83.59 (79.76) + train[2018-10-12-17:26:39] Epoch: [033][9400/10010] Time 0.59 (0.52) Data 0.00 (0.00) Loss 4.288 (3.945) Prec@1 53.12 (57.38) Prec@5 73.44 (79.76) + train[2018-10-12-17:28:22] Epoch: [033][9600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.059 (3.945) Prec@1 53.91 (57.38) Prec@5 80.47 (79.76) + train[2018-10-12-17:30:07] Epoch: [033][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.057 (3.946) Prec@1 53.12 (57.37) Prec@5 76.56 (79.76) + train[2018-10-12-17:31:50] Epoch: [033][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.065 (3.946) Prec@1 57.03 (57.35) Prec@5 80.47 (79.74) + train[2018-10-12-17:31:54] Epoch: [033][10009/10010] Time 0.21 (0.52) Data 0.00 (0.00) Loss 4.236 (3.946) Prec@1 60.00 (57.36) Prec@5 86.67 (79.74) +[2018-10-12-17:31:54] **train** Prec@1 57.36 Prec@5 79.74 Error@1 42.64 Error@5 20.26 Loss:3.946 + test [2018-10-12-17:31:58] Epoch: [033][000/391] Time 4.54 (4.54) Data 4.38 (4.38) Loss 0.818 (0.818) Prec@1 87.50 (87.50) Prec@5 95.31 (95.31) + test [2018-10-12-17:32:26] Epoch: [033][200/391] Time 0.13 (0.16) Data 0.00 (0.02) Loss 2.099 (1.442) Prec@1 50.00 (66.29) Prec@5 78.12 (88.30) + test [2018-10-12-17:32:50] Epoch: [033][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.985 (1.642) Prec@1 32.50 (62.46) Prec@5 70.00 (85.12) +[2018-10-12-17:32:50] **test** Prec@1 62.46 Prec@5 85.12 Error@1 37.54 Error@5 14.88 Loss:1.642 +----> Best Accuracy : Acc@1=62.46, Acc@5=85.12, Error@1=37.54, Error@5=14.88 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-12-17:32:51] [Epoch=034/250] [Need: 315:11:12] LR=0.0355 ~ 0.0355, Batch=128 + train[2018-10-12-17:32:56] Epoch: [034][000/10010] Time 5.22 (5.22) Data 4.66 (4.66) Loss 3.907 (3.907) Prec@1 55.47 (55.47) Prec@5 82.03 (82.03) + train[2018-10-12-17:34:40] Epoch: [034][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 4.018 (3.906) Prec@1 59.38 (57.70) Prec@5 79.69 (80.61) + train[2018-10-12-17:36:23] Epoch: [034][400/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.696 (3.902) Prec@1 64.06 (58.00) Prec@5 83.59 (80.50) + train[2018-10-12-17:38:07] Epoch: [034][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.702 (3.900) Prec@1 58.59 (58.19) Prec@5 80.47 (80.47) + train[2018-10-12-17:39:51] Epoch: [034][800/10010] Time 0.55 (0.52) Data 0.00 (0.01) Loss 4.058 (3.902) Prec@1 50.00 (58.16) Prec@5 75.78 (80.41) + train[2018-10-12-17:41:35] Epoch: [034][1000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.540 (3.901) Prec@1 62.50 (58.17) Prec@5 86.72 (80.35) + train[2018-10-12-17:43:18] Epoch: [034][1200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.798 (3.900) Prec@1 57.81 (58.14) Prec@5 78.12 (80.38) + train[2018-10-12-17:45:02] Epoch: [034][1400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 4.152 (3.903) Prec@1 57.81 (58.11) Prec@5 78.12 (80.33) + train[2018-10-12-17:46:46] Epoch: [034][1600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.750 (3.903) Prec@1 57.03 (58.09) Prec@5 85.94 (80.34) + train[2018-10-12-17:48:30] Epoch: [034][1800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.903 (3.906) Prec@1 53.91 (58.08) Prec@5 82.81 (80.33) + train[2018-10-12-17:50:14] Epoch: [034][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.486 (3.910) Prec@1 52.34 (58.06) Prec@5 73.44 (80.23) + train[2018-10-12-17:51:58] Epoch: [034][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.014 (3.911) Prec@1 56.25 (58.02) Prec@5 78.91 (80.21) + train[2018-10-12-17:53:42] Epoch: [034][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.323 (3.911) Prec@1 52.34 (58.04) Prec@5 76.56 (80.23) + train[2018-10-12-17:55:26] Epoch: [034][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.976 (3.911) Prec@1 58.59 (58.03) Prec@5 74.22 (80.21) + train[2018-10-12-17:57:10] Epoch: [034][2800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.617 (3.911) Prec@1 62.50 (58.02) Prec@5 78.91 (80.21) + train[2018-10-12-17:58:54] Epoch: [034][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.884 (3.911) Prec@1 54.69 (58.01) Prec@5 82.03 (80.20) + train[2018-10-12-18:00:39] Epoch: [034][3200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.690 (3.911) Prec@1 60.94 (57.99) Prec@5 85.94 (80.19) + train[2018-10-12-18:02:23] Epoch: [034][3400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.821 (3.914) Prec@1 54.69 (57.96) Prec@5 82.81 (80.16) + train[2018-10-12-18:04:07] Epoch: [034][3600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.162 (3.917) Prec@1 53.91 (57.91) Prec@5 76.56 (80.14) + train[2018-10-12-18:05:51] Epoch: [034][3800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.798 (3.918) Prec@1 57.03 (57.87) Prec@5 78.91 (80.12) + train[2018-10-12-18:07:35] Epoch: [034][4000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.907 (3.919) Prec@1 56.25 (57.86) Prec@5 82.81 (80.09) + train[2018-10-12-18:09:19] Epoch: [034][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.143 (3.919) Prec@1 56.25 (57.88) Prec@5 75.78 (80.10) + train[2018-10-12-18:11:03] Epoch: [034][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.921 (3.920) Prec@1 54.69 (57.84) Prec@5 81.25 (80.08) + train[2018-10-12-18:12:47] Epoch: [034][4600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.870 (3.920) Prec@1 51.56 (57.83) Prec@5 79.69 (80.09) + train[2018-10-12-18:14:31] Epoch: [034][4800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.947 (3.920) Prec@1 54.69 (57.81) Prec@5 82.03 (80.08) + train[2018-10-12-18:16:15] Epoch: [034][5000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.511 (3.921) Prec@1 62.50 (57.81) Prec@5 86.72 (80.07) + train[2018-10-12-18:17:59] Epoch: [034][5200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.025 (3.921) Prec@1 52.34 (57.80) Prec@5 81.25 (80.07) + train[2018-10-12-18:19:44] Epoch: [034][5400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.704 (3.922) Prec@1 60.94 (57.78) Prec@5 82.81 (80.07) + train[2018-10-12-18:21:27] Epoch: [034][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.289 (3.921) Prec@1 50.78 (57.79) Prec@5 75.78 (80.07) + train[2018-10-12-18:23:12] Epoch: [034][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.053 (3.922) Prec@1 60.16 (57.78) Prec@5 75.78 (80.05) + train[2018-10-12-18:24:55] Epoch: [034][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.945 (3.922) Prec@1 57.03 (57.78) Prec@5 76.56 (80.05) + train[2018-10-12-18:26:39] Epoch: [034][6200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.805 (3.924) Prec@1 59.38 (57.77) Prec@5 82.03 (80.03) + train[2018-10-12-18:28:22] Epoch: [034][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.129 (3.924) Prec@1 53.12 (57.75) Prec@5 74.22 (80.03) + train[2018-10-12-18:30:06] Epoch: [034][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.780 (3.925) Prec@1 55.47 (57.72) Prec@5 78.91 (80.01) + train[2018-10-12-18:31:50] Epoch: [034][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.015 (3.925) Prec@1 53.12 (57.71) Prec@5 80.47 (80.01) + train[2018-10-12-18:33:34] Epoch: [034][7000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.006 (3.926) Prec@1 54.69 (57.70) Prec@5 80.47 (80.00) + train[2018-10-12-18:35:18] Epoch: [034][7200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.895 (3.927) Prec@1 56.25 (57.67) Prec@5 79.69 (79.99) + train[2018-10-12-18:37:01] Epoch: [034][7400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.114 (3.927) Prec@1 55.47 (57.66) Prec@5 81.25 (79.98) + train[2018-10-12-18:38:45] Epoch: [034][7600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.245 (3.928) Prec@1 53.91 (57.66) Prec@5 71.88 (79.97) + train[2018-10-12-18:40:29] Epoch: [034][7800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.979 (3.928) Prec@1 60.16 (57.64) Prec@5 80.47 (79.96) + train[2018-10-12-18:42:13] Epoch: [034][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.029 (3.929) Prec@1 56.25 (57.63) Prec@5 75.00 (79.96) + train[2018-10-12-18:43:57] Epoch: [034][8200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.897 (3.929) Prec@1 57.03 (57.62) Prec@5 80.47 (79.96) + train[2018-10-12-18:45:41] Epoch: [034][8400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.978 (3.929) Prec@1 53.91 (57.63) Prec@5 79.69 (79.96) + train[2018-10-12-18:47:25] Epoch: [034][8600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.003 (3.929) Prec@1 55.47 (57.62) Prec@5 78.12 (79.95) + train[2018-10-12-18:49:09] Epoch: [034][8800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.800 (3.930) Prec@1 64.84 (57.62) Prec@5 83.59 (79.95) + train[2018-10-12-18:50:52] Epoch: [034][9000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.123 (3.930) Prec@1 54.69 (57.62) Prec@5 77.34 (79.95) + train[2018-10-12-18:52:36] Epoch: [034][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.958 (3.930) Prec@1 55.47 (57.61) Prec@5 78.12 (79.94) + train[2018-10-12-18:54:20] Epoch: [034][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.512 (3.931) Prec@1 64.84 (57.60) Prec@5 85.94 (79.93) + train[2018-10-12-18:56:04] Epoch: [034][9600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.094 (3.931) Prec@1 56.25 (57.60) Prec@5 77.34 (79.93) + train[2018-10-12-18:57:47] Epoch: [034][9800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.042 (3.931) Prec@1 50.00 (57.59) Prec@5 72.66 (79.92) + train[2018-10-12-18:59:32] Epoch: [034][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.751 (3.931) Prec@1 63.28 (57.59) Prec@5 82.81 (79.92) + train[2018-10-12-18:59:36] Epoch: [034][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 5.241 (3.931) Prec@1 33.33 (57.59) Prec@5 60.00 (79.92) +[2018-10-12-18:59:36] **train** Prec@1 57.59 Prec@5 79.92 Error@1 42.41 Error@5 20.08 Loss:3.931 + test [2018-10-12-18:59:40] Epoch: [034][000/391] Time 3.86 (3.86) Data 3.73 (3.73) Loss 1.046 (1.046) Prec@1 78.12 (78.12) Prec@5 91.41 (91.41) + test [2018-10-12-19:00:08] Epoch: [034][200/391] Time 0.14 (0.16) Data 0.00 (0.03) Loss 2.153 (1.413) Prec@1 50.78 (67.00) Prec@5 78.12 (88.60) + test [2018-10-12-19:00:33] Epoch: [034][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.696 (1.621) Prec@1 26.25 (62.90) Prec@5 70.00 (85.31) +[2018-10-12-19:00:33] **test** Prec@1 62.90 Prec@5 85.31 Error@1 37.10 Error@5 14.69 Loss:1.621 +----> Best Accuracy : Acc@1=62.90, Acc@5=85.31, Error@1=37.10, Error@5=14.69 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-12-19:00:33] [Epoch=035/250] [Need: 314:18:14] LR=0.0344 ~ 0.0344, Batch=128 + train[2018-10-12-19:00:39] Epoch: [035][000/10010] Time 5.51 (5.51) Data 4.95 (4.95) Loss 4.081 (4.081) Prec@1 52.34 (52.34) Prec@5 80.47 (80.47) + train[2018-10-12-19:02:23] Epoch: [035][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.675 (3.900) Prec@1 63.28 (58.03) Prec@5 84.38 (80.12) + train[2018-10-12-19:04:07] Epoch: [035][400/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 4.056 (3.875) Prec@1 57.03 (58.29) Prec@5 75.78 (80.61) + train[2018-10-12-19:05:51] Epoch: [035][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 4.085 (3.883) Prec@1 54.69 (58.19) Prec@5 78.12 (80.48) + train[2018-10-12-19:07:34] Epoch: [035][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.791 (3.888) Prec@1 59.38 (58.17) Prec@5 84.38 (80.46) + train[2018-10-12-19:09:18] Epoch: [035][1000/10010] Time 0.52 (0.52) Data 0.00 (0.01) Loss 3.638 (3.885) Prec@1 61.72 (58.21) Prec@5 82.81 (80.51) + train[2018-10-12-19:11:02] Epoch: [035][1200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.186 (3.886) Prec@1 55.47 (58.20) Prec@5 76.56 (80.52) + train[2018-10-12-19:12:45] Epoch: [035][1400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.859 (3.888) Prec@1 61.72 (58.15) Prec@5 78.12 (80.49) + train[2018-10-12-19:14:29] Epoch: [035][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.911 (3.887) Prec@1 63.28 (58.22) Prec@5 80.47 (80.50) + train[2018-10-12-19:16:13] Epoch: [035][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.496 (3.887) Prec@1 50.00 (58.23) Prec@5 70.31 (80.50) + train[2018-10-12-19:17:57] Epoch: [035][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.513 (3.889) Prec@1 66.41 (58.18) Prec@5 84.38 (80.47) + train[2018-10-12-19:19:41] Epoch: [035][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.239 (3.891) Prec@1 46.88 (58.19) Prec@5 77.34 (80.46) + train[2018-10-12-19:21:24] Epoch: [035][2400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.127 (3.890) Prec@1 56.25 (58.20) Prec@5 75.00 (80.47) + train[2018-10-12-19:23:08] Epoch: [035][2600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.583 (3.892) Prec@1 63.28 (58.18) Prec@5 84.38 (80.44) + train[2018-10-12-19:24:52] Epoch: [035][2800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.442 (3.893) Prec@1 67.19 (58.19) Prec@5 86.72 (80.43) + train[2018-10-12-19:26:35] Epoch: [035][3000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.719 (3.895) Prec@1 58.59 (58.13) Prec@5 82.81 (80.40) + train[2018-10-12-19:28:19] Epoch: [035][3200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.280 (3.895) Prec@1 56.25 (58.13) Prec@5 75.00 (80.40) + train[2018-10-12-19:30:03] Epoch: [035][3400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.825 (3.895) Prec@1 57.81 (58.14) Prec@5 82.81 (80.40) + train[2018-10-12-19:31:46] Epoch: [035][3600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.812 (3.896) Prec@1 57.81 (58.12) Prec@5 82.03 (80.40) + train[2018-10-12-19:33:30] Epoch: [035][3800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.138 (3.896) Prec@1 56.25 (58.16) Prec@5 75.78 (80.39) + train[2018-10-12-19:35:14] Epoch: [035][4000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.848 (3.896) Prec@1 59.38 (58.16) Prec@5 82.03 (80.37) + train[2018-10-12-19:36:58] Epoch: [035][4200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.615 (3.897) Prec@1 63.28 (58.13) Prec@5 83.59 (80.36) + train[2018-10-12-19:38:41] Epoch: [035][4400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.190 (3.897) Prec@1 56.25 (58.12) Prec@5 76.56 (80.35) + train[2018-10-12-19:40:26] Epoch: [035][4600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.089 (3.898) Prec@1 54.69 (58.11) Prec@5 80.47 (80.34) + train[2018-10-12-19:42:09] Epoch: [035][4800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.740 (3.899) Prec@1 64.84 (58.09) Prec@5 81.25 (80.32) + train[2018-10-12-19:43:53] Epoch: [035][5000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.537 (3.899) Prec@1 61.72 (58.09) Prec@5 84.38 (80.32) + train[2018-10-12-19:45:37] Epoch: [035][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.001 (3.900) Prec@1 50.78 (58.06) Prec@5 83.59 (80.31) + train[2018-10-12-19:47:21] Epoch: [035][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.189 (3.901) Prec@1 54.69 (58.06) Prec@5 75.78 (80.30) + train[2018-10-12-19:49:05] Epoch: [035][5600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.888 (3.902) Prec@1 58.59 (58.05) Prec@5 80.47 (80.28) + train[2018-10-12-19:50:49] Epoch: [035][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.747 (3.903) Prec@1 60.94 (58.06) Prec@5 78.91 (80.26) + train[2018-10-12-19:52:32] Epoch: [035][6000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.995 (3.903) Prec@1 57.81 (58.04) Prec@5 78.91 (80.25) + train[2018-10-12-19:54:16] Epoch: [035][6200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.445 (3.904) Prec@1 45.31 (58.03) Prec@5 70.31 (80.25) + train[2018-10-12-19:56:00] Epoch: [035][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.067 (3.905) Prec@1 54.69 (58.02) Prec@5 79.69 (80.24) + train[2018-10-12-19:57:44] Epoch: [035][6600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.084 (3.906) Prec@1 56.25 (57.99) Prec@5 78.12 (80.22) + train[2018-10-12-19:59:28] Epoch: [035][6800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.127 (3.906) Prec@1 59.38 (57.99) Prec@5 78.91 (80.21) + train[2018-10-12-20:01:12] Epoch: [035][7000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.926 (3.906) Prec@1 54.69 (57.99) Prec@5 79.69 (80.21) + train[2018-10-12-20:02:56] Epoch: [035][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.340 (3.906) Prec@1 67.97 (57.99) Prec@5 88.28 (80.21) + train[2018-10-12-20:04:40] Epoch: [035][7400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.514 (3.907) Prec@1 63.28 (57.97) Prec@5 85.94 (80.20) + train[2018-10-12-20:06:24] Epoch: [035][7600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.918 (3.907) Prec@1 57.03 (57.97) Prec@5 79.69 (80.20) + train[2018-10-12-20:08:08] Epoch: [035][7800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.859 (3.907) Prec@1 56.25 (57.96) Prec@5 79.69 (80.20) + train[2018-10-12-20:09:52] Epoch: [035][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.088 (3.908) Prec@1 57.03 (57.94) Prec@5 78.12 (80.19) + train[2018-10-12-20:11:36] Epoch: [035][8200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.730 (3.909) Prec@1 58.59 (57.92) Prec@5 82.81 (80.18) + train[2018-10-12-20:13:20] Epoch: [035][8400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.120 (3.909) Prec@1 50.78 (57.93) Prec@5 78.12 (80.18) + train[2018-10-12-20:15:05] Epoch: [035][8600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.913 (3.909) Prec@1 60.94 (57.91) Prec@5 77.34 (80.17) + train[2018-10-12-20:16:49] Epoch: [035][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.686 (3.910) Prec@1 60.94 (57.90) Prec@5 85.94 (80.16) + train[2018-10-12-20:18:32] Epoch: [035][9000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.942 (3.910) Prec@1 57.03 (57.89) Prec@5 78.91 (80.16) + train[2018-10-12-20:20:17] Epoch: [035][9200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.067 (3.911) Prec@1 56.25 (57.88) Prec@5 80.47 (80.15) + train[2018-10-12-20:22:00] Epoch: [035][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.106 (3.911) Prec@1 59.38 (57.88) Prec@5 74.22 (80.14) + train[2018-10-12-20:23:44] Epoch: [035][9600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.832 (3.912) Prec@1 61.72 (57.86) Prec@5 82.03 (80.12) + train[2018-10-12-20:25:28] Epoch: [035][9800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.861 (3.913) Prec@1 60.94 (57.85) Prec@5 82.03 (80.12) + train[2018-10-12-20:27:11] Epoch: [035][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.883 (3.913) Prec@1 50.78 (57.84) Prec@5 80.47 (80.10) + train[2018-10-12-20:27:16] Epoch: [035][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 3.721 (3.913) Prec@1 66.67 (57.84) Prec@5 86.67 (80.10) +[2018-10-12-20:27:16] **train** Prec@1 57.84 Prec@5 80.10 Error@1 42.16 Error@5 19.90 Loss:3.913 + test [2018-10-12-20:27:20] Epoch: [035][000/391] Time 4.38 (4.38) Data 4.24 (4.24) Loss 0.935 (0.935) Prec@1 77.34 (77.34) Prec@5 92.97 (92.97) + test [2018-10-12-20:27:47] Epoch: [035][200/391] Time 0.13 (0.16) Data 0.00 (0.02) Loss 1.943 (1.400) Prec@1 50.78 (67.34) Prec@5 80.47 (88.66) + test [2018-10-12-20:28:12] Epoch: [035][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 3.084 (1.608) Prec@1 21.25 (63.19) Prec@5 66.25 (85.34) +[2018-10-12-20:28:12] **test** Prec@1 63.19 Prec@5 85.34 Error@1 36.81 Error@5 14.66 Loss:1.608 +----> Best Accuracy : Acc@1=63.19, Acc@5=85.34, Error@1=36.81, Error@5=14.66 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-12-20:28:13] [Epoch=036/250] [Need: 312:37:40] LR=0.0334 ~ 0.0334, Batch=128 + train[2018-10-12-20:28:18] Epoch: [036][000/10010] Time 5.42 (5.42) Data 4.86 (4.86) Loss 3.975 (3.975) Prec@1 57.03 (57.03) Prec@5 78.91 (78.91) + train[2018-10-12-20:30:02] Epoch: [036][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.996 (3.847) Prec@1 57.03 (58.98) Prec@5 78.91 (81.10) + train[2018-10-12-20:31:46] Epoch: [036][400/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 4.067 (3.860) Prec@1 54.69 (58.87) Prec@5 77.34 (80.86) + train[2018-10-12-20:33:30] Epoch: [036][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.727 (3.870) Prec@1 58.59 (58.73) Prec@5 78.91 (80.74) + train[2018-10-12-20:35:14] Epoch: [036][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 4.093 (3.864) Prec@1 60.16 (58.76) Prec@5 78.91 (80.81) + train[2018-10-12-20:36:57] Epoch: [036][1000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.924 (3.860) Prec@1 60.16 (58.81) Prec@5 81.25 (80.89) + train[2018-10-12-20:38:41] Epoch: [036][1200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.194 (3.865) Prec@1 53.91 (58.70) Prec@5 79.69 (80.82) + train[2018-10-12-20:40:25] Epoch: [036][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.071 (3.870) Prec@1 52.34 (58.60) Prec@5 78.12 (80.71) + train[2018-10-12-20:42:09] Epoch: [036][1600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.814 (3.873) Prec@1 60.94 (58.55) Prec@5 76.56 (80.67) + train[2018-10-12-20:43:54] Epoch: [036][1800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.934 (3.871) Prec@1 50.00 (58.56) Prec@5 79.69 (80.70) + train[2018-10-12-20:45:38] Epoch: [036][2000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.003 (3.873) Prec@1 53.91 (58.52) Prec@5 78.91 (80.66) + train[2018-10-12-20:47:22] Epoch: [036][2200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.061 (3.877) Prec@1 54.69 (58.46) Prec@5 78.12 (80.62) + train[2018-10-12-20:49:05] Epoch: [036][2400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.584 (3.876) Prec@1 61.72 (58.44) Prec@5 84.38 (80.61) + train[2018-10-12-20:50:49] Epoch: [036][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.070 (3.877) Prec@1 60.94 (58.41) Prec@5 76.56 (80.60) + train[2018-10-12-20:52:32] Epoch: [036][2800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.942 (3.879) Prec@1 60.16 (58.37) Prec@5 80.47 (80.55) + train[2018-10-12-20:54:17] Epoch: [036][3000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.959 (3.880) Prec@1 53.91 (58.37) Prec@5 81.25 (80.55) + train[2018-10-12-20:56:01] Epoch: [036][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.077 (3.879) Prec@1 54.69 (58.39) Prec@5 78.12 (80.58) + train[2018-10-12-20:57:45] Epoch: [036][3400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.030 (3.880) Prec@1 57.03 (58.37) Prec@5 79.69 (80.56) + train[2018-10-12-20:59:29] Epoch: [036][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.779 (3.881) Prec@1 61.72 (58.36) Prec@5 83.59 (80.56) + train[2018-10-12-21:01:13] Epoch: [036][3800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.187 (3.882) Prec@1 54.69 (58.35) Prec@5 76.56 (80.53) + train[2018-10-12-21:02:56] Epoch: [036][4000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.064 (3.883) Prec@1 51.56 (58.34) Prec@5 78.91 (80.51) + train[2018-10-12-21:04:40] Epoch: [036][4200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.628 (3.884) Prec@1 60.16 (58.33) Prec@5 84.38 (80.50) + train[2018-10-12-21:06:23] Epoch: [036][4400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.154 (3.884) Prec@1 53.91 (58.31) Prec@5 78.91 (80.48) + train[2018-10-12-21:08:07] Epoch: [036][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.040 (3.884) Prec@1 61.72 (58.32) Prec@5 78.91 (80.49) + train[2018-10-12-21:09:52] Epoch: [036][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.888 (3.884) Prec@1 54.69 (58.32) Prec@5 80.47 (80.49) + train[2018-10-12-21:11:35] Epoch: [036][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.788 (3.884) Prec@1 59.38 (58.32) Prec@5 80.47 (80.48) + train[2018-10-12-21:13:19] Epoch: [036][5200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.760 (3.883) Prec@1 55.47 (58.33) Prec@5 82.03 (80.48) + train[2018-10-12-21:15:03] Epoch: [036][5400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.824 (3.883) Prec@1 57.81 (58.34) Prec@5 82.03 (80.49) + train[2018-10-12-21:16:47] Epoch: [036][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.109 (3.884) Prec@1 55.47 (58.31) Prec@5 75.78 (80.48) + train[2018-10-12-21:18:30] Epoch: [036][5800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.249 (3.883) Prec@1 50.78 (58.32) Prec@5 75.78 (80.49) + train[2018-10-12-21:20:14] Epoch: [036][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.868 (3.884) Prec@1 62.50 (58.30) Prec@5 79.69 (80.47) + train[2018-10-12-21:21:58] Epoch: [036][6200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.872 (3.886) Prec@1 59.38 (58.28) Prec@5 81.25 (80.45) + train[2018-10-12-21:23:41] Epoch: [036][6400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.705 (3.887) Prec@1 64.84 (58.26) Prec@5 82.81 (80.45) + train[2018-10-12-21:25:25] Epoch: [036][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.995 (3.888) Prec@1 50.00 (58.25) Prec@5 82.03 (80.43) + train[2018-10-12-21:27:08] Epoch: [036][6800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.805 (3.889) Prec@1 59.38 (58.24) Prec@5 80.47 (80.41) + train[2018-10-12-21:28:52] Epoch: [036][7000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.834 (3.890) Prec@1 59.38 (58.23) Prec@5 82.03 (80.39) + train[2018-10-12-21:30:36] Epoch: [036][7200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.118 (3.890) Prec@1 53.12 (58.22) Prec@5 80.47 (80.39) + train[2018-10-12-21:32:20] Epoch: [036][7400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.808 (3.891) Prec@1 58.59 (58.21) Prec@5 83.59 (80.38) + train[2018-10-12-21:34:04] Epoch: [036][7600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.580 (3.891) Prec@1 64.06 (58.20) Prec@5 85.16 (80.38) + train[2018-10-12-21:35:48] Epoch: [036][7800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.661 (3.891) Prec@1 59.38 (58.19) Prec@5 84.38 (80.38) + train[2018-10-12-21:37:32] Epoch: [036][8000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.825 (3.892) Prec@1 62.50 (58.18) Prec@5 80.47 (80.37) + train[2018-10-12-21:39:16] Epoch: [036][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.543 (3.893) Prec@1 67.97 (58.18) Prec@5 84.38 (80.36) + train[2018-10-12-21:41:00] Epoch: [036][8400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.950 (3.892) Prec@1 54.69 (58.18) Prec@5 82.03 (80.36) + train[2018-10-12-21:42:44] Epoch: [036][8600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.071 (3.893) Prec@1 58.59 (58.18) Prec@5 76.56 (80.37) + train[2018-10-12-21:44:27] Epoch: [036][8800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.450 (3.893) Prec@1 52.34 (58.17) Prec@5 75.00 (80.36) + train[2018-10-12-21:46:11] Epoch: [036][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.198 (3.894) Prec@1 57.03 (58.16) Prec@5 75.78 (80.35) + train[2018-10-12-21:47:56] Epoch: [036][9200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.006 (3.894) Prec@1 61.72 (58.15) Prec@5 73.44 (80.35) + train[2018-10-12-21:49:40] Epoch: [036][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.271 (3.894) Prec@1 57.03 (58.15) Prec@5 76.56 (80.34) + train[2018-10-12-21:51:24] Epoch: [036][9600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.770 (3.896) Prec@1 57.03 (58.14) Prec@5 82.81 (80.34) + train[2018-10-12-21:53:07] Epoch: [036][9800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.038 (3.896) Prec@1 60.16 (58.13) Prec@5 74.22 (80.33) + train[2018-10-12-21:54:51] Epoch: [036][10000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.945 (3.897) Prec@1 52.34 (58.12) Prec@5 81.25 (80.32) + train[2018-10-12-21:54:56] Epoch: [036][10009/10010] Time 0.18 (0.52) Data 0.00 (0.00) Loss 4.127 (3.897) Prec@1 60.00 (58.12) Prec@5 80.00 (80.32) +[2018-10-12-21:54:56] **train** Prec@1 58.12 Prec@5 80.32 Error@1 41.88 Error@5 19.68 Loss:3.897 + test [2018-10-12-21:55:00] Epoch: [036][000/391] Time 4.06 (4.06) Data 3.92 (3.92) Loss 1.050 (1.050) Prec@1 78.91 (78.91) Prec@5 91.41 (91.41) + test [2018-10-12-21:55:27] Epoch: [036][200/391] Time 0.14 (0.16) Data 0.00 (0.02) Loss 1.894 (1.391) Prec@1 57.03 (67.50) Prec@5 81.25 (88.94) + test [2018-10-12-21:55:52] Epoch: [036][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.779 (1.596) Prec@1 35.00 (63.59) Prec@5 70.00 (85.70) +[2018-10-12-21:55:52] **test** Prec@1 63.59 Prec@5 85.70 Error@1 36.41 Error@5 14.30 Loss:1.596 +----> Best Accuracy : Acc@1=63.59, Acc@5=85.70, Error@1=36.41, Error@5=14.30 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-12-21:55:53] [Epoch=037/250] [Need: 311:12:55] LR=0.0324 ~ 0.0324, Batch=128 + train[2018-10-12-21:55:58] Epoch: [037][000/10010] Time 5.01 (5.01) Data 4.44 (4.44) Loss 3.854 (3.854) Prec@1 61.72 (61.72) Prec@5 77.34 (77.34) + train[2018-10-12-21:57:42] Epoch: [037][200/10010] Time 0.49 (0.54) Data 0.00 (0.02) Loss 3.849 (3.843) Prec@1 59.38 (58.83) Prec@5 79.69 (80.98) + train[2018-10-12-21:59:25] Epoch: [037][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 4.154 (3.843) Prec@1 52.34 (59.06) Prec@5 77.34 (81.12) + train[2018-10-12-22:01:09] Epoch: [037][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.498 (3.832) Prec@1 64.84 (59.16) Prec@5 85.94 (81.28) + train[2018-10-12-22:02:53] Epoch: [037][800/10010] Time 0.54 (0.52) Data 0.00 (0.01) Loss 3.887 (3.835) Prec@1 60.16 (59.04) Prec@5 81.25 (81.18) + train[2018-10-12-22:04:36] Epoch: [037][1000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.946 (3.838) Prec@1 60.16 (59.04) Prec@5 78.91 (81.14) + train[2018-10-12-22:06:20] Epoch: [037][1200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.240 (3.837) Prec@1 52.34 (59.13) Prec@5 76.56 (81.16) + train[2018-10-12-22:08:03] Epoch: [037][1400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.994 (3.844) Prec@1 57.03 (59.05) Prec@5 81.25 (81.03) + train[2018-10-12-22:09:47] Epoch: [037][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.062 (3.845) Prec@1 52.34 (59.06) Prec@5 77.34 (81.01) + train[2018-10-12-22:11:31] Epoch: [037][1800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.202 (3.846) Prec@1 73.44 (59.01) Prec@5 87.50 (81.01) + train[2018-10-12-22:13:15] Epoch: [037][2000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.572 (3.847) Prec@1 60.94 (59.00) Prec@5 85.94 (81.01) + train[2018-10-12-22:14:59] Epoch: [037][2200/10010] Time 0.59 (0.52) Data 0.00 (0.00) Loss 4.217 (3.850) Prec@1 50.78 (58.94) Prec@5 72.66 (80.95) + train[2018-10-12-22:16:43] Epoch: [037][2400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.610 (3.852) Prec@1 66.41 (58.92) Prec@5 85.94 (80.93) + train[2018-10-12-22:18:27] Epoch: [037][2600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.657 (3.851) Prec@1 63.28 (58.93) Prec@5 81.25 (80.92) + train[2018-10-12-22:20:10] Epoch: [037][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.678 (3.852) Prec@1 64.84 (58.91) Prec@5 82.03 (80.91) + train[2018-10-12-22:21:54] Epoch: [037][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.092 (3.854) Prec@1 52.34 (58.87) Prec@5 77.34 (80.89) + train[2018-10-12-22:23:37] Epoch: [037][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.991 (3.854) Prec@1 53.12 (58.88) Prec@5 78.12 (80.88) + train[2018-10-12-22:25:22] Epoch: [037][3400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.982 (3.854) Prec@1 51.56 (58.88) Prec@5 78.91 (80.89) + train[2018-10-12-22:27:05] Epoch: [037][3600/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.687 (3.855) Prec@1 60.94 (58.86) Prec@5 83.59 (80.88) + train[2018-10-12-22:28:49] Epoch: [037][3800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.661 (3.857) Prec@1 58.59 (58.83) Prec@5 82.03 (80.86) + train[2018-10-12-22:30:32] Epoch: [037][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.760 (3.858) Prec@1 58.59 (58.80) Prec@5 84.38 (80.84) + train[2018-10-12-22:32:16] Epoch: [037][4200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.506 (3.860) Prec@1 63.28 (58.78) Prec@5 85.94 (80.81) + train[2018-10-12-22:34:00] Epoch: [037][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.830 (3.861) Prec@1 60.94 (58.76) Prec@5 79.69 (80.79) + train[2018-10-12-22:35:43] Epoch: [037][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.902 (3.861) Prec@1 60.16 (58.74) Prec@5 78.12 (80.79) + train[2018-10-12-22:37:27] Epoch: [037][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.088 (3.863) Prec@1 50.78 (58.71) Prec@5 81.25 (80.77) + train[2018-10-12-22:39:11] Epoch: [037][5000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.919 (3.863) Prec@1 57.03 (58.72) Prec@5 80.47 (80.75) + train[2018-10-12-22:40:55] Epoch: [037][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.366 (3.863) Prec@1 48.44 (58.72) Prec@5 70.31 (80.75) + train[2018-10-12-22:42:38] Epoch: [037][5400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.401 (3.863) Prec@1 67.97 (58.71) Prec@5 85.94 (80.74) + train[2018-10-12-22:44:22] Epoch: [037][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.428 (3.865) Prec@1 48.44 (58.68) Prec@5 72.66 (80.72) + train[2018-10-12-22:46:05] Epoch: [037][5800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.964 (3.866) Prec@1 53.12 (58.67) Prec@5 79.69 (80.71) + train[2018-10-12-22:47:50] Epoch: [037][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.194 (3.867) Prec@1 55.47 (58.65) Prec@5 74.22 (80.70) + train[2018-10-12-22:49:34] Epoch: [037][6200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.026 (3.867) Prec@1 59.38 (58.64) Prec@5 78.12 (80.69) + train[2018-10-12-22:51:18] Epoch: [037][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.760 (3.868) Prec@1 60.16 (58.62) Prec@5 83.59 (80.68) + train[2018-10-12-22:53:02] Epoch: [037][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.056 (3.868) Prec@1 51.56 (58.63) Prec@5 76.56 (80.68) + train[2018-10-12-22:54:47] Epoch: [037][6800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.978 (3.869) Prec@1 58.59 (58.60) Prec@5 78.91 (80.67) + train[2018-10-12-22:56:30] Epoch: [037][7000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.829 (3.870) Prec@1 61.72 (58.59) Prec@5 82.03 (80.66) + train[2018-10-12-22:58:13] Epoch: [037][7200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.774 (3.870) Prec@1 62.50 (58.59) Prec@5 81.25 (80.66) + train[2018-10-12-22:59:57] Epoch: [037][7400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.939 (3.871) Prec@1 54.69 (58.57) Prec@5 79.69 (80.64) + train[2018-10-12-23:01:41] Epoch: [037][7600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.838 (3.872) Prec@1 59.38 (58.56) Prec@5 78.12 (80.63) + train[2018-10-12-23:03:25] Epoch: [037][7800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.893 (3.872) Prec@1 60.94 (58.55) Prec@5 83.59 (80.63) + train[2018-10-12-23:05:09] Epoch: [037][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.649 (3.873) Prec@1 45.31 (58.53) Prec@5 66.41 (80.61) + train[2018-10-12-23:06:53] Epoch: [037][8200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.869 (3.874) Prec@1 57.81 (58.51) Prec@5 82.03 (80.60) + train[2018-10-12-23:08:36] Epoch: [037][8400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.219 (3.875) Prec@1 48.44 (58.50) Prec@5 76.56 (80.58) + train[2018-10-12-23:10:20] Epoch: [037][8600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.705 (3.876) Prec@1 64.84 (58.49) Prec@5 84.38 (80.57) + train[2018-10-12-23:12:04] Epoch: [037][8800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.862 (3.877) Prec@1 57.81 (58.47) Prec@5 78.12 (80.55) + train[2018-10-12-23:13:48] Epoch: [037][9000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.054 (3.877) Prec@1 54.69 (58.46) Prec@5 78.12 (80.55) + train[2018-10-12-23:15:32] Epoch: [037][9200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.005 (3.878) Prec@1 53.91 (58.44) Prec@5 77.34 (80.54) + train[2018-10-12-23:17:16] Epoch: [037][9400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.123 (3.878) Prec@1 53.12 (58.44) Prec@5 78.91 (80.53) + train[2018-10-12-23:18:59] Epoch: [037][9600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.904 (3.879) Prec@1 60.16 (58.43) Prec@5 83.59 (80.53) + train[2018-10-12-23:20:42] Epoch: [037][9800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.005 (3.879) Prec@1 56.25 (58.42) Prec@5 81.25 (80.53) + train[2018-10-12-23:22:26] Epoch: [037][10000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.829 (3.880) Prec@1 62.50 (58.40) Prec@5 80.47 (80.51) + train[2018-10-12-23:22:31] Epoch: [037][10009/10010] Time 0.21 (0.52) Data 0.00 (0.00) Loss 3.155 (3.880) Prec@1 66.67 (58.41) Prec@5 93.33 (80.51) +[2018-10-12-23:22:31] **train** Prec@1 58.41 Prec@5 80.51 Error@1 41.59 Error@5 19.49 Loss:3.880 + test [2018-10-12-23:22:34] Epoch: [037][000/391] Time 3.40 (3.40) Data 3.25 (3.25) Loss 0.867 (0.867) Prec@1 83.59 (83.59) Prec@5 92.19 (92.19) + test [2018-10-12-23:23:02] Epoch: [037][200/391] Time 0.16 (0.16) Data 0.00 (0.03) Loss 1.696 (1.399) Prec@1 60.94 (67.59) Prec@5 82.81 (88.72) + test [2018-10-12-23:23:27] Epoch: [037][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.411 (1.597) Prec@1 33.75 (63.67) Prec@5 78.75 (85.54) +[2018-10-12-23:23:28] **test** Prec@1 63.67 Prec@5 85.54 Error@1 36.33 Error@5 14.46 Loss:1.597 +----> Best Accuracy : Acc@1=63.67, Acc@5=85.54, Error@1=36.33, Error@5=14.46 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-12-23:23:28] [Epoch=038/250] [Need: 309:28:17] LR=0.0314 ~ 0.0314, Batch=128 + train[2018-10-12-23:23:33] Epoch: [038][000/10010] Time 5.14 (5.14) Data 4.50 (4.50) Loss 3.756 (3.756) Prec@1 60.94 (60.94) Prec@5 85.16 (85.16) + train[2018-10-12-23:25:16] Epoch: [038][200/10010] Time 0.53 (0.54) Data 0.00 (0.02) Loss 3.856 (3.843) Prec@1 59.38 (58.83) Prec@5 82.81 (81.01) + train[2018-10-12-23:27:01] Epoch: [038][400/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 4.164 (3.833) Prec@1 56.25 (59.15) Prec@5 75.78 (81.05) + train[2018-10-12-23:28:44] Epoch: [038][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.892 (3.827) Prec@1 59.38 (59.22) Prec@5 82.03 (81.18) + train[2018-10-12-23:30:29] Epoch: [038][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.672 (3.830) Prec@1 60.16 (59.21) Prec@5 82.81 (81.14) + train[2018-10-12-23:32:12] Epoch: [038][1000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.910 (3.834) Prec@1 56.25 (59.13) Prec@5 82.81 (81.09) + train[2018-10-12-23:33:56] Epoch: [038][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.901 (3.831) Prec@1 54.69 (59.21) Prec@5 81.25 (81.14) + train[2018-10-12-23:35:40] Epoch: [038][1400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.691 (3.836) Prec@1 64.06 (59.15) Prec@5 82.81 (81.08) + train[2018-10-12-23:37:23] Epoch: [038][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.805 (3.839) Prec@1 57.81 (59.07) Prec@5 78.91 (81.04) + train[2018-10-12-23:39:07] Epoch: [038][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.495 (3.840) Prec@1 62.50 (59.10) Prec@5 82.81 (81.02) + train[2018-10-12-23:40:51] Epoch: [038][2000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.722 (3.841) Prec@1 65.62 (59.05) Prec@5 78.91 (81.01) + train[2018-10-12-23:42:35] Epoch: [038][2200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.628 (3.840) Prec@1 61.72 (59.06) Prec@5 83.59 (81.02) + train[2018-10-12-23:44:19] Epoch: [038][2400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.124 (3.840) Prec@1 54.69 (59.03) Prec@5 75.00 (81.04) + train[2018-10-12-23:46:02] Epoch: [038][2600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.903 (3.841) Prec@1 57.81 (59.03) Prec@5 79.69 (81.04) + train[2018-10-12-23:47:46] Epoch: [038][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.174 (3.841) Prec@1 54.69 (59.03) Prec@5 76.56 (81.02) + train[2018-10-12-23:49:30] Epoch: [038][3000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.625 (3.840) Prec@1 60.16 (59.04) Prec@5 83.59 (81.02) + train[2018-10-12-23:51:13] Epoch: [038][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.749 (3.840) Prec@1 59.38 (59.03) Prec@5 82.81 (81.03) + train[2018-10-12-23:52:57] Epoch: [038][3400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.603 (3.841) Prec@1 64.06 (59.03) Prec@5 85.16 (81.03) + train[2018-10-12-23:54:41] Epoch: [038][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.968 (3.842) Prec@1 60.16 (59.02) Prec@5 81.25 (81.03) + train[2018-10-12-23:56:25] Epoch: [038][3800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.495 (3.843) Prec@1 62.50 (59.01) Prec@5 84.38 (81.00) + train[2018-10-12-23:58:10] Epoch: [038][4000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.235 (3.845) Prec@1 52.34 (58.99) Prec@5 74.22 (80.98) + train[2018-10-12-23:59:54] Epoch: [038][4200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.900 (3.846) Prec@1 64.84 (58.97) Prec@5 82.81 (80.96) + train[2018-10-13-00:01:37] Epoch: [038][4400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.942 (3.847) Prec@1 57.81 (58.93) Prec@5 79.69 (80.94) + train[2018-10-13-00:03:21] Epoch: [038][4600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.597 (3.848) Prec@1 63.28 (58.91) Prec@5 85.16 (80.93) + train[2018-10-13-00:05:05] Epoch: [038][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.890 (3.847) Prec@1 53.91 (58.92) Prec@5 82.03 (80.93) + train[2018-10-13-00:06:49] Epoch: [038][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.707 (3.850) Prec@1 60.16 (58.89) Prec@5 82.03 (80.90) + train[2018-10-13-00:08:33] Epoch: [038][5200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.643 (3.852) Prec@1 64.06 (58.87) Prec@5 82.03 (80.86) + train[2018-10-13-00:10:17] Epoch: [038][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.834 (3.853) Prec@1 60.94 (58.87) Prec@5 79.69 (80.85) + train[2018-10-13-00:12:00] Epoch: [038][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.969 (3.853) Prec@1 55.47 (58.86) Prec@5 84.38 (80.84) + train[2018-10-13-00:13:43] Epoch: [038][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.043 (3.854) Prec@1 60.16 (58.85) Prec@5 76.56 (80.83) + train[2018-10-13-00:15:27] Epoch: [038][6000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.859 (3.855) Prec@1 58.59 (58.84) Prec@5 80.47 (80.82) + train[2018-10-13-00:17:11] Epoch: [038][6200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.655 (3.856) Prec@1 64.06 (58.81) Prec@5 85.16 (80.80) + train[2018-10-13-00:18:54] Epoch: [038][6400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.846 (3.857) Prec@1 54.69 (58.79) Prec@5 83.59 (80.80) + train[2018-10-13-00:20:38] Epoch: [038][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.927 (3.857) Prec@1 57.03 (58.79) Prec@5 82.03 (80.80) + train[2018-10-13-00:22:22] Epoch: [038][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.603 (3.858) Prec@1 60.94 (58.78) Prec@5 82.03 (80.78) + train[2018-10-13-00:24:05] Epoch: [038][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.176 (3.858) Prec@1 57.81 (58.78) Prec@5 76.56 (80.78) + train[2018-10-13-00:25:50] Epoch: [038][7200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.574 (3.859) Prec@1 65.62 (58.78) Prec@5 85.94 (80.78) + train[2018-10-13-00:27:34] Epoch: [038][7400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.788 (3.859) Prec@1 53.91 (58.78) Prec@5 82.81 (80.77) + train[2018-10-13-00:29:18] Epoch: [038][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.613 (3.859) Prec@1 60.16 (58.77) Prec@5 85.94 (80.77) + train[2018-10-13-00:31:02] Epoch: [038][7800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.462 (3.860) Prec@1 66.41 (58.77) Prec@5 82.81 (80.76) + train[2018-10-13-00:32:47] Epoch: [038][8000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.033 (3.860) Prec@1 53.91 (58.75) Prec@5 77.34 (80.76) + train[2018-10-13-00:34:30] Epoch: [038][8200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.895 (3.860) Prec@1 52.34 (58.75) Prec@5 79.69 (80.75) + train[2018-10-13-00:36:14] Epoch: [038][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.714 (3.861) Prec@1 63.28 (58.75) Prec@5 82.81 (80.74) + train[2018-10-13-00:37:58] Epoch: [038][8600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.263 (3.861) Prec@1 49.22 (58.75) Prec@5 74.22 (80.74) + train[2018-10-13-00:39:42] Epoch: [038][8800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.525 (3.861) Prec@1 63.28 (58.75) Prec@5 83.59 (80.75) + train[2018-10-13-00:41:26] Epoch: [038][9000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.854 (3.861) Prec@1 54.69 (58.74) Prec@5 82.81 (80.74) + train[2018-10-13-00:43:09] Epoch: [038][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.224 (3.862) Prec@1 50.78 (58.73) Prec@5 76.56 (80.74) + train[2018-10-13-00:44:53] Epoch: [038][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.950 (3.862) Prec@1 59.38 (58.72) Prec@5 80.47 (80.73) + train[2018-10-13-00:46:37] Epoch: [038][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.731 (3.863) Prec@1 60.16 (58.71) Prec@5 82.03 (80.72) + train[2018-10-13-00:48:21] Epoch: [038][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.795 (3.863) Prec@1 56.25 (58.69) Prec@5 82.81 (80.71) + train[2018-10-13-00:50:04] Epoch: [038][10000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.934 (3.864) Prec@1 55.47 (58.68) Prec@5 76.56 (80.71) + train[2018-10-13-00:50:09] Epoch: [038][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.709 (3.864) Prec@1 33.33 (58.68) Prec@5 73.33 (80.71) +[2018-10-13-00:50:09] **train** Prec@1 58.68 Prec@5 80.71 Error@1 41.32 Error@5 19.29 Loss:3.864 + test [2018-10-13-00:50:13] Epoch: [038][000/391] Time 4.51 (4.51) Data 4.38 (4.38) Loss 0.946 (0.946) Prec@1 79.69 (79.69) Prec@5 91.41 (91.41) + test [2018-10-13-00:50:40] Epoch: [038][200/391] Time 0.16 (0.16) Data 0.02 (0.02) Loss 1.837 (1.386) Prec@1 53.12 (67.56) Prec@5 84.38 (88.78) + test [2018-10-13-00:51:05] Epoch: [038][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.715 (1.590) Prec@1 35.00 (63.57) Prec@5 75.00 (85.66) +[2018-10-13-00:51:05] **test** Prec@1 63.57 Prec@5 85.66 Error@1 36.43 Error@5 14.34 Loss:1.590 +----> Best Accuracy : Acc@1=63.67, Acc@5=85.54, Error@1=36.33, Error@5=14.46 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-13-00:51:05] [Epoch=039/250] [Need: 308:08:30] LR=0.0305 ~ 0.0305, Batch=128 + train[2018-10-13-00:51:10] Epoch: [039][000/10010] Time 5.06 (5.06) Data 4.47 (4.47) Loss 3.559 (3.559) Prec@1 65.62 (65.62) Prec@5 83.59 (83.59) + train[2018-10-13-00:52:54] Epoch: [039][200/10010] Time 0.55 (0.54) Data 0.00 (0.02) Loss 3.854 (3.803) Prec@1 56.25 (59.85) Prec@5 77.34 (81.39) + train[2018-10-13-00:54:38] Epoch: [039][400/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.875 (3.814) Prec@1 56.25 (59.57) Prec@5 78.12 (81.20) + train[2018-10-13-00:56:21] Epoch: [039][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.469 (3.822) Prec@1 66.41 (59.45) Prec@5 86.72 (81.08) + train[2018-10-13-00:58:06] Epoch: [039][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.905 (3.819) Prec@1 55.47 (59.49) Prec@5 78.91 (81.10) + train[2018-10-13-00:59:51] Epoch: [039][1000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.722 (3.821) Prec@1 66.41 (59.45) Prec@5 82.03 (81.14) + train[2018-10-13-01:01:34] Epoch: [039][1200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.842 (3.820) Prec@1 58.59 (59.51) Prec@5 82.03 (81.20) + train[2018-10-13-01:03:18] Epoch: [039][1400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.856 (3.822) Prec@1 60.94 (59.47) Prec@5 77.34 (81.20) + train[2018-10-13-01:05:02] Epoch: [039][1600/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.636 (3.824) Prec@1 62.50 (59.47) Prec@5 80.47 (81.21) + train[2018-10-13-01:06:45] Epoch: [039][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.087 (3.825) Prec@1 53.12 (59.40) Prec@5 81.25 (81.16) + train[2018-10-13-01:08:29] Epoch: [039][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.220 (3.827) Prec@1 53.91 (59.34) Prec@5 78.91 (81.10) + train[2018-10-13-01:10:12] Epoch: [039][2200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.062 (3.829) Prec@1 53.91 (59.33) Prec@5 78.91 (81.10) + train[2018-10-13-01:11:56] Epoch: [039][2400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.063 (3.831) Prec@1 59.38 (59.29) Prec@5 79.69 (81.07) + train[2018-10-13-01:13:40] Epoch: [039][2600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.959 (3.830) Prec@1 60.16 (59.29) Prec@5 78.91 (81.09) + train[2018-10-13-01:15:24] Epoch: [039][2800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.494 (3.830) Prec@1 63.28 (59.27) Prec@5 82.81 (81.10) + train[2018-10-13-01:17:07] Epoch: [039][3000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.347 (3.831) Prec@1 53.12 (59.23) Prec@5 75.00 (81.09) + train[2018-10-13-01:18:50] Epoch: [039][3200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.438 (3.833) Prec@1 67.19 (59.22) Prec@5 86.72 (81.07) + train[2018-10-13-01:20:34] Epoch: [039][3400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.182 (3.834) Prec@1 54.69 (59.19) Prec@5 75.78 (81.06) + train[2018-10-13-01:22:17] Epoch: [039][3600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.247 (3.834) Prec@1 55.47 (59.19) Prec@5 74.22 (81.06) + train[2018-10-13-01:24:00] Epoch: [039][3800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.865 (3.835) Prec@1 59.38 (59.17) Prec@5 81.25 (81.04) + train[2018-10-13-01:25:44] Epoch: [039][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.818 (3.836) Prec@1 60.94 (59.18) Prec@5 80.47 (81.02) + train[2018-10-13-01:27:28] Epoch: [039][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.610 (3.837) Prec@1 64.84 (59.16) Prec@5 81.25 (81.01) + train[2018-10-13-01:29:12] Epoch: [039][4400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.525 (3.838) Prec@1 64.84 (59.15) Prec@5 82.03 (80.99) + train[2018-10-13-01:30:56] Epoch: [039][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.734 (3.837) Prec@1 58.59 (59.15) Prec@5 82.03 (81.01) + train[2018-10-13-01:32:40] Epoch: [039][4800/10010] Time 0.59 (0.52) Data 0.00 (0.00) Loss 4.149 (3.838) Prec@1 60.16 (59.13) Prec@5 75.78 (80.99) + train[2018-10-13-01:34:24] Epoch: [039][5000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.755 (3.839) Prec@1 60.16 (59.11) Prec@5 80.47 (80.99) + train[2018-10-13-01:36:09] Epoch: [039][5200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.741 (3.840) Prec@1 56.25 (59.09) Prec@5 85.94 (80.99) + train[2018-10-13-01:37:52] Epoch: [039][5400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.823 (3.840) Prec@1 58.59 (59.08) Prec@5 83.59 (80.98) + train[2018-10-13-01:39:36] Epoch: [039][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.427 (3.841) Prec@1 66.41 (59.06) Prec@5 86.72 (80.96) + train[2018-10-13-01:41:19] Epoch: [039][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.879 (3.841) Prec@1 58.59 (59.05) Prec@5 80.47 (80.96) + train[2018-10-13-01:43:03] Epoch: [039][6000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.894 (3.842) Prec@1 58.59 (59.04) Prec@5 83.59 (80.95) + train[2018-10-13-01:44:47] Epoch: [039][6200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.849 (3.842) Prec@1 58.59 (59.03) Prec@5 78.12 (80.95) + train[2018-10-13-01:46:31] Epoch: [039][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.006 (3.843) Prec@1 57.03 (59.01) Prec@5 76.56 (80.95) + train[2018-10-13-01:48:15] Epoch: [039][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.820 (3.844) Prec@1 61.72 (59.00) Prec@5 82.81 (80.94) + train[2018-10-13-01:49:58] Epoch: [039][6800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.113 (3.844) Prec@1 53.91 (59.00) Prec@5 79.69 (80.94) + train[2018-10-13-01:51:42] Epoch: [039][7000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.882 (3.844) Prec@1 54.69 (58.99) Prec@5 82.03 (80.94) + train[2018-10-13-01:53:26] Epoch: [039][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.460 (3.844) Prec@1 64.84 (58.98) Prec@5 87.50 (80.95) + train[2018-10-13-01:55:09] Epoch: [039][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.782 (3.844) Prec@1 58.59 (58.97) Prec@5 81.25 (80.94) + train[2018-10-13-01:56:54] Epoch: [039][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.008 (3.845) Prec@1 57.81 (58.96) Prec@5 82.81 (80.93) + train[2018-10-13-01:58:38] Epoch: [039][7800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.953 (3.845) Prec@1 58.59 (58.96) Prec@5 80.47 (80.93) + train[2018-10-13-02:00:21] Epoch: [039][8000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.037 (3.846) Prec@1 58.59 (58.94) Prec@5 78.91 (80.91) + train[2018-10-13-02:02:05] Epoch: [039][8200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.818 (3.846) Prec@1 57.03 (58.94) Prec@5 84.38 (80.91) + train[2018-10-13-02:03:49] Epoch: [039][8400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.815 (3.848) Prec@1 55.47 (58.91) Prec@5 82.03 (80.89) + train[2018-10-13-02:05:33] Epoch: [039][8600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.399 (3.848) Prec@1 48.44 (58.90) Prec@5 71.88 (80.88) + train[2018-10-13-02:07:16] Epoch: [039][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.582 (3.848) Prec@1 57.81 (58.90) Prec@5 83.59 (80.88) + train[2018-10-13-02:09:00] Epoch: [039][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.638 (3.849) Prec@1 65.62 (58.89) Prec@5 83.59 (80.87) + train[2018-10-13-02:10:43] Epoch: [039][9200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.720 (3.850) Prec@1 60.94 (58.88) Prec@5 82.81 (80.86) + train[2018-10-13-02:12:27] Epoch: [039][9400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.432 (3.850) Prec@1 66.41 (58.88) Prec@5 84.38 (80.86) + train[2018-10-13-02:14:11] Epoch: [039][9600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.949 (3.850) Prec@1 59.38 (58.87) Prec@5 76.56 (80.85) + train[2018-10-13-02:15:55] Epoch: [039][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.422 (3.850) Prec@1 64.06 (58.87) Prec@5 88.28 (80.85) + train[2018-10-13-02:17:38] Epoch: [039][10000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.914 (3.851) Prec@1 53.12 (58.86) Prec@5 80.47 (80.83) + train[2018-10-13-02:17:43] Epoch: [039][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.044 (3.851) Prec@1 66.67 (58.86) Prec@5 80.00 (80.84) +[2018-10-13-02:17:43] **train** Prec@1 58.86 Prec@5 80.84 Error@1 41.14 Error@5 19.16 Loss:3.851 + test [2018-10-13-02:17:47] Epoch: [039][000/391] Time 3.93 (3.93) Data 3.79 (3.79) Loss 0.980 (0.980) Prec@1 79.69 (79.69) Prec@5 92.97 (92.97) + test [2018-10-13-02:18:14] Epoch: [039][200/391] Time 0.13 (0.16) Data 0.00 (0.02) Loss 1.949 (1.375) Prec@1 50.00 (67.82) Prec@5 79.69 (88.90) + test [2018-10-13-02:18:39] Epoch: [039][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.901 (1.579) Prec@1 33.75 (64.03) Prec@5 63.75 (85.83) +[2018-10-13-02:18:39] **test** Prec@1 64.03 Prec@5 85.83 Error@1 35.97 Error@5 14.17 Loss:1.579 +----> Best Accuracy : Acc@1=64.03, Acc@5=85.83, Error@1=35.97, Error@5=14.17 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-13-02:18:40] [Epoch=040/250] [Need: 306:30:33] LR=0.0296 ~ 0.0296, Batch=128 + train[2018-10-13-02:18:45] Epoch: [040][000/10010] Time 5.62 (5.62) Data 4.96 (4.96) Loss 4.081 (4.081) Prec@1 58.59 (58.59) Prec@5 78.12 (78.12) + train[2018-10-13-02:20:29] Epoch: [040][200/10010] Time 0.52 (0.55) Data 0.00 (0.02) Loss 3.820 (3.795) Prec@1 57.03 (60.23) Prec@5 79.69 (81.50) + train[2018-10-13-02:22:14] Epoch: [040][400/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.726 (3.793) Prec@1 58.59 (60.06) Prec@5 83.59 (81.58) + train[2018-10-13-02:23:58] Epoch: [040][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 4.133 (3.794) Prec@1 57.03 (59.98) Prec@5 76.56 (81.58) + train[2018-10-13-02:25:41] Epoch: [040][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.954 (3.796) Prec@1 60.16 (59.97) Prec@5 80.47 (81.55) + train[2018-10-13-02:27:25] Epoch: [040][1000/10010] Time 0.53 (0.52) Data 0.00 (0.01) Loss 4.149 (3.800) Prec@1 53.12 (59.86) Prec@5 75.00 (81.53) + train[2018-10-13-02:29:09] Epoch: [040][1200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.682 (3.802) Prec@1 65.62 (59.79) Prec@5 87.50 (81.54) + train[2018-10-13-02:30:52] Epoch: [040][1400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.873 (3.804) Prec@1 63.28 (59.75) Prec@5 83.59 (81.53) + train[2018-10-13-02:32:37] Epoch: [040][1600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.546 (3.806) Prec@1 64.84 (59.74) Prec@5 86.72 (81.47) + train[2018-10-13-02:34:21] Epoch: [040][1800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.709 (3.807) Prec@1 57.81 (59.74) Prec@5 82.81 (81.47) + train[2018-10-13-02:36:05] Epoch: [040][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.128 (3.808) Prec@1 58.59 (59.74) Prec@5 78.91 (81.45) + train[2018-10-13-02:37:49] Epoch: [040][2200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.838 (3.809) Prec@1 62.50 (59.71) Prec@5 81.25 (81.46) + train[2018-10-13-02:39:32] Epoch: [040][2400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.782 (3.811) Prec@1 59.38 (59.66) Prec@5 83.59 (81.43) + train[2018-10-13-02:41:16] Epoch: [040][2600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.550 (3.812) Prec@1 57.81 (59.64) Prec@5 84.38 (81.42) + train[2018-10-13-02:43:00] Epoch: [040][2800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.041 (3.812) Prec@1 60.16 (59.63) Prec@5 78.12 (81.42) + train[2018-10-13-02:44:44] Epoch: [040][3000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.895 (3.813) Prec@1 53.12 (59.60) Prec@5 84.38 (81.41) + train[2018-10-13-02:46:29] Epoch: [040][3200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.336 (3.814) Prec@1 64.06 (59.58) Prec@5 85.94 (81.39) + train[2018-10-13-02:48:13] Epoch: [040][3400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.702 (3.816) Prec@1 59.38 (59.54) Prec@5 85.16 (81.36) + train[2018-10-13-02:49:57] Epoch: [040][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.721 (3.815) Prec@1 60.16 (59.54) Prec@5 83.59 (81.35) + train[2018-10-13-02:51:41] Epoch: [040][3800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.828 (3.816) Prec@1 61.72 (59.52) Prec@5 83.59 (81.34) + train[2018-10-13-02:53:25] Epoch: [040][4000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.710 (3.817) Prec@1 65.62 (59.51) Prec@5 81.25 (81.33) + train[2018-10-13-02:55:09] Epoch: [040][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.960 (3.816) Prec@1 53.12 (59.51) Prec@5 80.47 (81.34) + train[2018-10-13-02:56:52] Epoch: [040][4400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.203 (3.817) Prec@1 53.91 (59.48) Prec@5 76.56 (81.33) + train[2018-10-13-02:58:36] Epoch: [040][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.752 (3.818) Prec@1 60.94 (59.45) Prec@5 82.03 (81.30) + train[2018-10-13-03:00:20] Epoch: [040][4800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.889 (3.820) Prec@1 60.16 (59.43) Prec@5 85.16 (81.28) + train[2018-10-13-03:02:05] Epoch: [040][5000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.211 (3.820) Prec@1 50.78 (59.41) Prec@5 74.22 (81.27) + train[2018-10-13-03:03:48] Epoch: [040][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.747 (3.821) Prec@1 58.59 (59.40) Prec@5 79.69 (81.26) + train[2018-10-13-03:05:32] Epoch: [040][5400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.480 (3.822) Prec@1 64.06 (59.39) Prec@5 84.38 (81.26) + train[2018-10-13-03:07:17] Epoch: [040][5600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.835 (3.823) Prec@1 54.69 (59.37) Prec@5 77.34 (81.25) + train[2018-10-13-03:09:00] Epoch: [040][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.853 (3.823) Prec@1 57.03 (59.36) Prec@5 84.38 (81.24) + train[2018-10-13-03:10:44] Epoch: [040][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.765 (3.824) Prec@1 62.50 (59.34) Prec@5 82.81 (81.24) + train[2018-10-13-03:12:28] Epoch: [040][6200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.547 (3.826) Prec@1 65.62 (59.31) Prec@5 82.81 (81.22) + train[2018-10-13-03:14:13] Epoch: [040][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.830 (3.826) Prec@1 57.03 (59.30) Prec@5 77.34 (81.21) + train[2018-10-13-03:15:57] Epoch: [040][6600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.972 (3.827) Prec@1 58.59 (59.29) Prec@5 78.91 (81.19) + train[2018-10-13-03:17:41] Epoch: [040][6800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.773 (3.828) Prec@1 59.38 (59.28) Prec@5 82.03 (81.19) + train[2018-10-13-03:19:25] Epoch: [040][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.877 (3.827) Prec@1 60.94 (59.28) Prec@5 82.81 (81.19) + train[2018-10-13-03:21:09] Epoch: [040][7200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.642 (3.827) Prec@1 47.66 (59.28) Prec@5 68.75 (81.19) + train[2018-10-13-03:22:53] Epoch: [040][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.711 (3.828) Prec@1 59.38 (59.27) Prec@5 86.72 (81.17) + train[2018-10-13-03:24:37] Epoch: [040][7600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.766 (3.829) Prec@1 61.72 (59.27) Prec@5 82.81 (81.16) + train[2018-10-13-03:26:21] Epoch: [040][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.796 (3.829) Prec@1 62.50 (59.26) Prec@5 78.91 (81.17) + train[2018-10-13-03:28:04] Epoch: [040][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.739 (3.830) Prec@1 60.94 (59.24) Prec@5 82.03 (81.15) + train[2018-10-13-03:29:48] Epoch: [040][8200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.974 (3.830) Prec@1 59.38 (59.24) Prec@5 78.91 (81.14) + train[2018-10-13-03:31:32] Epoch: [040][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.074 (3.830) Prec@1 53.91 (59.23) Prec@5 75.00 (81.13) + train[2018-10-13-03:33:16] Epoch: [040][8600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.637 (3.831) Prec@1 63.28 (59.21) Prec@5 83.59 (81.12) + train[2018-10-13-03:34:59] Epoch: [040][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.852 (3.832) Prec@1 55.47 (59.19) Prec@5 82.81 (81.11) + train[2018-10-13-03:36:43] Epoch: [040][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.845 (3.832) Prec@1 66.41 (59.18) Prec@5 79.69 (81.10) + train[2018-10-13-03:38:26] Epoch: [040][9200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.853 (3.833) Prec@1 55.47 (59.17) Prec@5 80.47 (81.09) + train[2018-10-13-03:40:11] Epoch: [040][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.748 (3.834) Prec@1 55.47 (59.16) Prec@5 79.69 (81.07) + train[2018-10-13-03:41:54] Epoch: [040][9600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.914 (3.834) Prec@1 53.91 (59.15) Prec@5 75.00 (81.07) + train[2018-10-13-03:43:39] Epoch: [040][9800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.971 (3.834) Prec@1 63.28 (59.15) Prec@5 80.47 (81.07) + train[2018-10-13-03:45:23] Epoch: [040][10000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.805 (3.834) Prec@1 58.59 (59.15) Prec@5 75.78 (81.07) + train[2018-10-13-03:45:27] Epoch: [040][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 4.830 (3.834) Prec@1 40.00 (59.15) Prec@5 73.33 (81.07) +[2018-10-13-03:45:27] **train** Prec@1 59.15 Prec@5 81.07 Error@1 40.85 Error@5 18.93 Loss:3.834 + test [2018-10-13-03:45:31] Epoch: [040][000/391] Time 3.76 (3.76) Data 3.62 (3.62) Loss 0.946 (0.946) Prec@1 78.91 (78.91) Prec@5 92.19 (92.19) + test [2018-10-13-03:45:59] Epoch: [040][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.936 (1.395) Prec@1 48.44 (67.44) Prec@5 82.03 (88.95) + test [2018-10-13-03:46:24] Epoch: [040][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.927 (1.576) Prec@1 25.00 (63.85) Prec@5 67.50 (85.95) +[2018-10-13-03:46:24] **test** Prec@1 63.85 Prec@5 85.95 Error@1 36.15 Error@5 14.05 Loss:1.576 +----> Best Accuracy : Acc@1=64.03, Acc@5=85.83, Error@1=35.97, Error@5=14.17 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-13-03:46:24] [Epoch=041/250] [Need: 305:38:57] LR=0.0287 ~ 0.0287, Batch=128 + train[2018-10-13-03:46:30] Epoch: [041][000/10010] Time 5.43 (5.43) Data 4.81 (4.81) Loss 4.090 (4.090) Prec@1 57.03 (57.03) Prec@5 79.69 (79.69) + train[2018-10-13-03:48:14] Epoch: [041][200/10010] Time 0.52 (0.54) Data 0.00 (0.02) Loss 3.333 (3.794) Prec@1 67.97 (60.12) Prec@5 85.94 (81.62) + train[2018-10-13-03:49:58] Epoch: [041][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.870 (3.783) Prec@1 56.25 (60.10) Prec@5 78.12 (81.64) + train[2018-10-13-03:51:41] Epoch: [041][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.975 (3.786) Prec@1 57.81 (60.00) Prec@5 78.12 (81.61) + train[2018-10-13-03:53:25] Epoch: [041][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.438 (3.782) Prec@1 67.19 (60.01) Prec@5 86.72 (81.70) + train[2018-10-13-03:55:09] Epoch: [041][1000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.856 (3.786) Prec@1 62.50 (60.05) Prec@5 80.47 (81.65) + train[2018-10-13-03:56:54] Epoch: [041][1200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.150 (3.787) Prec@1 57.81 (60.02) Prec@5 78.12 (81.60) + train[2018-10-13-03:58:38] Epoch: [041][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.529 (3.789) Prec@1 56.25 (59.96) Prec@5 85.94 (81.60) + train[2018-10-13-04:00:22] Epoch: [041][1600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.930 (3.791) Prec@1 58.59 (59.90) Prec@5 82.81 (81.59) + train[2018-10-13-04:02:06] Epoch: [041][1800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.902 (3.790) Prec@1 62.50 (59.94) Prec@5 77.34 (81.60) + train[2018-10-13-04:03:49] Epoch: [041][2000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.727 (3.795) Prec@1 63.28 (59.85) Prec@5 81.25 (81.54) + train[2018-10-13-04:05:33] Epoch: [041][2200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.885 (3.794) Prec@1 57.81 (59.91) Prec@5 78.91 (81.55) + train[2018-10-13-04:07:17] Epoch: [041][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.739 (3.793) Prec@1 62.50 (59.92) Prec@5 82.03 (81.59) + train[2018-10-13-04:09:01] Epoch: [041][2600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.267 (3.794) Prec@1 51.56 (59.89) Prec@5 74.22 (81.58) + train[2018-10-13-04:10:45] Epoch: [041][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.890 (3.793) Prec@1 53.91 (59.91) Prec@5 81.25 (81.61) + train[2018-10-13-04:12:29] Epoch: [041][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.079 (3.795) Prec@1 57.03 (59.87) Prec@5 78.91 (81.58) + train[2018-10-13-04:14:13] Epoch: [041][3200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.784 (3.796) Prec@1 61.72 (59.85) Prec@5 81.25 (81.56) + train[2018-10-13-04:15:57] Epoch: [041][3400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.760 (3.797) Prec@1 62.50 (59.83) Prec@5 80.47 (81.55) + train[2018-10-13-04:17:42] Epoch: [041][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.028 (3.797) Prec@1 56.25 (59.82) Prec@5 77.34 (81.54) + train[2018-10-13-04:19:26] Epoch: [041][3800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.880 (3.799) Prec@1 60.94 (59.79) Prec@5 78.12 (81.50) + train[2018-10-13-04:21:11] Epoch: [041][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.904 (3.800) Prec@1 56.25 (59.78) Prec@5 78.91 (81.48) + train[2018-10-13-04:22:55] Epoch: [041][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.815 (3.802) Prec@1 62.50 (59.76) Prec@5 81.25 (81.45) + train[2018-10-13-04:24:39] Epoch: [041][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.001 (3.802) Prec@1 58.59 (59.76) Prec@5 77.34 (81.45) + train[2018-10-13-04:26:23] Epoch: [041][4600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.236 (3.802) Prec@1 53.91 (59.75) Prec@5 75.00 (81.45) + train[2018-10-13-04:28:07] Epoch: [041][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.938 (3.803) Prec@1 57.81 (59.73) Prec@5 78.12 (81.45) + train[2018-10-13-04:29:51] Epoch: [041][5000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.896 (3.804) Prec@1 57.03 (59.72) Prec@5 80.47 (81.44) + train[2018-10-13-04:31:35] Epoch: [041][5200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.699 (3.805) Prec@1 58.59 (59.69) Prec@5 82.03 (81.41) + train[2018-10-13-04:33:18] Epoch: [041][5400/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.895 (3.808) Prec@1 58.59 (59.66) Prec@5 82.03 (81.38) + train[2018-10-13-04:35:02] Epoch: [041][5600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.765 (3.809) Prec@1 57.03 (59.62) Prec@5 82.03 (81.35) + train[2018-10-13-04:36:46] Epoch: [041][5800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.202 (3.809) Prec@1 57.03 (59.64) Prec@5 71.88 (81.36) + train[2018-10-13-04:38:31] Epoch: [041][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.797 (3.809) Prec@1 57.03 (59.63) Prec@5 80.47 (81.36) + train[2018-10-13-04:40:15] Epoch: [041][6200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.602 (3.809) Prec@1 60.94 (59.61) Prec@5 87.50 (81.35) + train[2018-10-13-04:41:59] Epoch: [041][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.660 (3.810) Prec@1 59.38 (59.60) Prec@5 85.94 (81.34) + train[2018-10-13-04:43:43] Epoch: [041][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.858 (3.811) Prec@1 57.03 (59.59) Prec@5 80.47 (81.33) + train[2018-10-13-04:45:27] Epoch: [041][6800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.057 (3.811) Prec@1 52.34 (59.58) Prec@5 77.34 (81.33) + train[2018-10-13-04:47:11] Epoch: [041][7000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.939 (3.812) Prec@1 51.56 (59.57) Prec@5 80.47 (81.32) + train[2018-10-13-04:48:55] Epoch: [041][7200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.777 (3.813) Prec@1 57.03 (59.57) Prec@5 82.03 (81.31) + train[2018-10-13-04:50:39] Epoch: [041][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.625 (3.814) Prec@1 61.72 (59.55) Prec@5 82.81 (81.29) + train[2018-10-13-04:52:24] Epoch: [041][7600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.759 (3.814) Prec@1 64.06 (59.54) Prec@5 82.03 (81.29) + train[2018-10-13-04:54:08] Epoch: [041][7800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.831 (3.814) Prec@1 55.47 (59.54) Prec@5 83.59 (81.28) + train[2018-10-13-04:55:51] Epoch: [041][8000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.762 (3.815) Prec@1 58.59 (59.53) Prec@5 83.59 (81.28) + train[2018-10-13-04:57:36] Epoch: [041][8200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.878 (3.815) Prec@1 63.28 (59.52) Prec@5 82.03 (81.27) + train[2018-10-13-04:59:20] Epoch: [041][8400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.613 (3.816) Prec@1 59.38 (59.50) Prec@5 82.03 (81.25) + train[2018-10-13-05:01:04] Epoch: [041][8600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.971 (3.817) Prec@1 60.16 (59.49) Prec@5 76.56 (81.25) + train[2018-10-13-05:02:47] Epoch: [041][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.756 (3.817) Prec@1 64.84 (59.48) Prec@5 83.59 (81.24) + train[2018-10-13-05:04:31] Epoch: [041][9000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.626 (3.818) Prec@1 67.97 (59.47) Prec@5 84.38 (81.22) + train[2018-10-13-05:06:15] Epoch: [041][9200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.924 (3.819) Prec@1 54.69 (59.45) Prec@5 80.47 (81.20) + train[2018-10-13-05:07:59] Epoch: [041][9400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.274 (3.820) Prec@1 64.06 (59.43) Prec@5 85.94 (81.20) + train[2018-10-13-05:09:44] Epoch: [041][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.468 (3.821) Prec@1 64.84 (59.42) Prec@5 83.59 (81.18) + train[2018-10-13-05:11:28] Epoch: [041][9800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.810 (3.821) Prec@1 59.38 (59.41) Prec@5 82.03 (81.18) + train[2018-10-13-05:13:11] Epoch: [041][10000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.786 (3.822) Prec@1 61.72 (59.40) Prec@5 78.91 (81.17) + train[2018-10-13-05:13:15] Epoch: [041][10009/10010] Time 0.14 (0.52) Data 0.00 (0.00) Loss 4.739 (3.822) Prec@1 53.33 (59.40) Prec@5 66.67 (81.17) +[2018-10-13-05:13:15] **train** Prec@1 59.40 Prec@5 81.17 Error@1 40.60 Error@5 18.83 Loss:3.822 + test [2018-10-13-05:13:20] Epoch: [041][000/391] Time 4.04 (4.04) Data 3.90 (3.90) Loss 0.927 (0.927) Prec@1 82.03 (82.03) Prec@5 93.75 (93.75) + test [2018-10-13-05:13:47] Epoch: [041][200/391] Time 0.14 (0.16) Data 0.00 (0.02) Loss 1.715 (1.360) Prec@1 58.59 (68.31) Prec@5 86.72 (89.25) + test [2018-10-13-05:14:12] Epoch: [041][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.923 (1.564) Prec@1 32.50 (64.33) Prec@5 66.25 (86.07) +[2018-10-13-05:14:12] **test** Prec@1 64.33 Prec@5 86.07 Error@1 35.67 Error@5 13.93 Loss:1.564 +----> Best Accuracy : Acc@1=64.33, Acc@5=86.07, Error@1=35.67, Error@5=13.93 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-13-05:14:12] [Epoch=042/250] [Need: 304:22:53] LR=0.0278 ~ 0.0278, Batch=128 + train[2018-10-13-05:14:18] Epoch: [042][000/10010] Time 5.64 (5.64) Data 5.09 (5.09) Loss 3.750 (3.750) Prec@1 64.06 (64.06) Prec@5 82.03 (82.03) + train[2018-10-13-05:16:02] Epoch: [042][200/10010] Time 0.51 (0.54) Data 0.00 (0.03) Loss 3.811 (3.753) Prec@1 56.25 (60.76) Prec@5 81.25 (82.37) + train[2018-10-13-05:17:46] Epoch: [042][400/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.941 (3.750) Prec@1 54.69 (60.68) Prec@5 82.03 (82.28) + train[2018-10-13-05:19:30] Epoch: [042][600/10010] Time 0.56 (0.53) Data 0.00 (0.01) Loss 3.526 (3.750) Prec@1 64.06 (60.69) Prec@5 86.72 (82.23) + train[2018-10-13-05:21:14] Epoch: [042][800/10010] Time 0.49 (0.53) Data 0.00 (0.01) Loss 4.031 (3.762) Prec@1 53.91 (60.46) Prec@5 78.91 (82.05) + train[2018-10-13-05:22:57] Epoch: [042][1000/10010] Time 0.51 (0.52) Data 0.00 (0.01) Loss 3.749 (3.764) Prec@1 62.50 (60.41) Prec@5 85.16 (82.03) + train[2018-10-13-05:24:41] Epoch: [042][1200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.660 (3.766) Prec@1 57.81 (60.33) Prec@5 87.50 (81.99) + train[2018-10-13-05:26:25] Epoch: [042][1400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.002 (3.767) Prec@1 61.72 (60.36) Prec@5 80.47 (81.99) + train[2018-10-13-05:28:08] Epoch: [042][1600/10010] Time 0.59 (0.52) Data 0.00 (0.00) Loss 3.903 (3.770) Prec@1 57.81 (60.25) Prec@5 80.47 (81.95) + train[2018-10-13-05:29:53] Epoch: [042][1800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.685 (3.774) Prec@1 60.94 (60.18) Prec@5 82.81 (81.89) + train[2018-10-13-05:31:36] Epoch: [042][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.123 (3.776) Prec@1 55.47 (60.14) Prec@5 75.78 (81.87) + train[2018-10-13-05:33:21] Epoch: [042][2200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.694 (3.776) Prec@1 61.72 (60.13) Prec@5 83.59 (81.88) + train[2018-10-13-05:35:05] Epoch: [042][2400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.415 (3.777) Prec@1 64.84 (60.10) Prec@5 89.06 (81.84) + train[2018-10-13-05:36:48] Epoch: [042][2600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.928 (3.777) Prec@1 56.25 (60.10) Prec@5 81.25 (81.82) + train[2018-10-13-05:38:33] Epoch: [042][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.725 (3.781) Prec@1 64.06 (60.04) Prec@5 81.25 (81.77) + train[2018-10-13-05:40:17] Epoch: [042][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.987 (3.782) Prec@1 60.94 (60.03) Prec@5 77.34 (81.76) + train[2018-10-13-05:42:00] Epoch: [042][3200/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.697 (3.782) Prec@1 60.16 (60.04) Prec@5 83.59 (81.75) + train[2018-10-13-05:43:44] Epoch: [042][3400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.019 (3.783) Prec@1 56.25 (60.05) Prec@5 75.78 (81.75) + train[2018-10-13-05:45:28] Epoch: [042][3600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.870 (3.784) Prec@1 53.91 (60.03) Prec@5 83.59 (81.72) + train[2018-10-13-05:47:12] Epoch: [042][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.207 (3.785) Prec@1 50.78 (60.03) Prec@5 76.56 (81.70) + train[2018-10-13-05:48:56] Epoch: [042][4000/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.993 (3.787) Prec@1 53.91 (59.99) Prec@5 78.91 (81.65) + train[2018-10-13-05:50:40] Epoch: [042][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.984 (3.788) Prec@1 53.91 (59.97) Prec@5 78.91 (81.64) + train[2018-10-13-05:52:24] Epoch: [042][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.675 (3.788) Prec@1 63.28 (59.97) Prec@5 83.59 (81.63) + train[2018-10-13-05:54:08] Epoch: [042][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.709 (3.789) Prec@1 64.06 (59.96) Prec@5 84.38 (81.61) + train[2018-10-13-05:55:51] Epoch: [042][4800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.993 (3.790) Prec@1 59.38 (59.95) Prec@5 81.25 (81.61) + train[2018-10-13-05:57:35] Epoch: [042][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.654 (3.789) Prec@1 60.16 (59.95) Prec@5 83.59 (81.61) + train[2018-10-13-05:59:19] Epoch: [042][5200/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.586 (3.791) Prec@1 62.50 (59.94) Prec@5 83.59 (81.60) + train[2018-10-13-06:01:03] Epoch: [042][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.876 (3.792) Prec@1 60.16 (59.91) Prec@5 82.81 (81.57) + train[2018-10-13-06:02:46] Epoch: [042][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.585 (3.794) Prec@1 64.06 (59.87) Prec@5 84.38 (81.55) + train[2018-10-13-06:04:30] Epoch: [042][5800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.769 (3.795) Prec@1 60.94 (59.86) Prec@5 78.91 (81.54) + train[2018-10-13-06:06:15] Epoch: [042][6000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.893 (3.795) Prec@1 58.59 (59.85) Prec@5 75.78 (81.54) + train[2018-10-13-06:07:58] Epoch: [042][6200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.453 (3.796) Prec@1 67.19 (59.84) Prec@5 88.28 (81.53) + train[2018-10-13-06:09:43] Epoch: [042][6400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.587 (3.797) Prec@1 65.62 (59.83) Prec@5 85.94 (81.53) + train[2018-10-13-06:11:26] Epoch: [042][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.402 (3.796) Prec@1 53.91 (59.83) Prec@5 71.09 (81.52) + train[2018-10-13-06:13:10] Epoch: [042][6800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.654 (3.797) Prec@1 58.59 (59.82) Prec@5 84.38 (81.52) + train[2018-10-13-06:14:54] Epoch: [042][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.785 (3.797) Prec@1 62.50 (59.83) Prec@5 80.47 (81.52) + train[2018-10-13-06:16:38] Epoch: [042][7200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.799 (3.797) Prec@1 60.94 (59.83) Prec@5 82.03 (81.51) + train[2018-10-13-06:18:22] Epoch: [042][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.039 (3.798) Prec@1 57.81 (59.81) Prec@5 75.78 (81.50) + train[2018-10-13-06:20:06] Epoch: [042][7600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.140 (3.799) Prec@1 57.81 (59.79) Prec@5 78.91 (81.49) + train[2018-10-13-06:21:50] Epoch: [042][7800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.521 (3.800) Prec@1 64.06 (59.76) Prec@5 83.59 (81.48) + train[2018-10-13-06:23:34] Epoch: [042][8000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.961 (3.801) Prec@1 57.81 (59.75) Prec@5 77.34 (81.48) + train[2018-10-13-06:25:18] Epoch: [042][8200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.067 (3.802) Prec@1 57.81 (59.74) Prec@5 73.44 (81.47) + train[2018-10-13-06:27:02] Epoch: [042][8400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.801 (3.802) Prec@1 56.25 (59.73) Prec@5 81.25 (81.46) + train[2018-10-13-06:28:46] Epoch: [042][8600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.465 (3.802) Prec@1 66.41 (59.72) Prec@5 89.84 (81.45) + train[2018-10-13-06:30:30] Epoch: [042][8800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.191 (3.803) Prec@1 53.91 (59.72) Prec@5 71.88 (81.45) + train[2018-10-13-06:32:14] Epoch: [042][9000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.114 (3.804) Prec@1 46.88 (59.70) Prec@5 79.69 (81.43) + train[2018-10-13-06:33:58] Epoch: [042][9200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.742 (3.804) Prec@1 63.28 (59.69) Prec@5 82.03 (81.43) + train[2018-10-13-06:35:41] Epoch: [042][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.898 (3.805) Prec@1 56.25 (59.67) Prec@5 80.47 (81.41) + train[2018-10-13-06:37:25] Epoch: [042][9600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.846 (3.805) Prec@1 60.16 (59.67) Prec@5 82.03 (81.41) + train[2018-10-13-06:39:08] Epoch: [042][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.933 (3.805) Prec@1 57.03 (59.67) Prec@5 79.69 (81.41) + train[2018-10-13-06:40:51] Epoch: [042][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.016 (3.805) Prec@1 57.03 (59.65) Prec@5 83.59 (81.40) + train[2018-10-13-06:40:56] Epoch: [042][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.888 (3.805) Prec@1 53.33 (59.65) Prec@5 80.00 (81.40) +[2018-10-13-06:40:56] **train** Prec@1 59.65 Prec@5 81.40 Error@1 40.35 Error@5 18.60 Loss:3.805 + test [2018-10-13-06:41:00] Epoch: [042][000/391] Time 4.20 (4.20) Data 4.05 (4.05) Loss 0.853 (0.853) Prec@1 83.59 (83.59) Prec@5 93.75 (93.75) + test [2018-10-13-06:41:27] Epoch: [042][200/391] Time 0.12 (0.16) Data 0.00 (0.03) Loss 1.895 (1.318) Prec@1 58.59 (68.68) Prec@5 78.12 (89.55) + test [2018-10-13-06:41:52] Epoch: [042][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.523 (1.521) Prec@1 40.00 (64.76) Prec@5 71.25 (86.37) +[2018-10-13-06:41:52] **test** Prec@1 64.76 Prec@5 86.37 Error@1 35.24 Error@5 13.63 Loss:1.521 +----> Best Accuracy : Acc@1=64.76, Acc@5=86.37, Error@1=35.24, Error@5=13.63 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-13-06:41:52] [Epoch=043/250] [Need: 302:26:23] LR=0.0270 ~ 0.0270, Batch=128 + train[2018-10-13-06:41:58] Epoch: [043][000/10010] Time 5.77 (5.77) Data 5.21 (5.21) Loss 3.820 (3.820) Prec@1 60.16 (60.16) Prec@5 77.34 (77.34) + train[2018-10-13-06:43:42] Epoch: [043][200/10010] Time 0.51 (0.54) Data 0.00 (0.03) Loss 4.262 (3.741) Prec@1 51.56 (60.37) Prec@5 77.34 (82.29) + train[2018-10-13-06:45:25] Epoch: [043][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.825 (3.748) Prec@1 57.81 (60.34) Prec@5 81.25 (82.09) + train[2018-10-13-06:47:09] Epoch: [043][600/10010] Time 0.56 (0.53) Data 0.00 (0.01) Loss 3.530 (3.757) Prec@1 63.28 (60.32) Prec@5 81.25 (82.04) + train[2018-10-13-06:48:53] Epoch: [043][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.359 (3.753) Prec@1 64.84 (60.42) Prec@5 88.28 (82.09) + train[2018-10-13-06:50:37] Epoch: [043][1000/10010] Time 0.53 (0.52) Data 0.00 (0.01) Loss 4.013 (3.749) Prec@1 53.91 (60.50) Prec@5 80.47 (82.16) + train[2018-10-13-06:52:20] Epoch: [043][1200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.137 (3.755) Prec@1 57.03 (60.38) Prec@5 79.69 (82.16) + train[2018-10-13-06:54:04] Epoch: [043][1400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.030 (3.760) Prec@1 53.12 (60.29) Prec@5 77.34 (82.03) + train[2018-10-13-06:55:47] Epoch: [043][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.774 (3.763) Prec@1 66.41 (60.27) Prec@5 80.47 (81.97) + train[2018-10-13-06:57:31] Epoch: [043][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.221 (3.766) Prec@1 70.31 (60.20) Prec@5 88.28 (81.94) + train[2018-10-13-06:59:15] Epoch: [043][2000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.707 (3.767) Prec@1 64.06 (60.23) Prec@5 78.12 (81.91) + train[2018-10-13-07:00:58] Epoch: [043][2200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.681 (3.768) Prec@1 60.94 (60.21) Prec@5 84.38 (81.91) + train[2018-10-13-07:02:42] Epoch: [043][2400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.713 (3.769) Prec@1 59.38 (60.21) Prec@5 82.03 (81.88) + train[2018-10-13-07:04:26] Epoch: [043][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.030 (3.772) Prec@1 60.94 (60.18) Prec@5 78.12 (81.85) + train[2018-10-13-07:06:10] Epoch: [043][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.768 (3.774) Prec@1 57.03 (60.16) Prec@5 78.12 (81.82) + train[2018-10-13-07:07:54] Epoch: [043][3000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.558 (3.774) Prec@1 64.06 (60.16) Prec@5 86.72 (81.81) + train[2018-10-13-07:09:38] Epoch: [043][3200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.137 (3.776) Prec@1 57.81 (60.10) Prec@5 78.91 (81.78) + train[2018-10-13-07:11:21] Epoch: [043][3400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.781 (3.777) Prec@1 57.81 (60.07) Prec@5 82.81 (81.77) + train[2018-10-13-07:13:05] Epoch: [043][3600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.328 (3.777) Prec@1 68.75 (60.06) Prec@5 85.16 (81.77) + train[2018-10-13-07:14:49] Epoch: [043][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.727 (3.778) Prec@1 62.50 (60.03) Prec@5 80.47 (81.76) + train[2018-10-13-07:16:32] Epoch: [043][4000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.897 (3.778) Prec@1 53.91 (60.04) Prec@5 82.81 (81.77) + train[2018-10-13-07:18:16] Epoch: [043][4200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.888 (3.778) Prec@1 62.50 (60.06) Prec@5 78.91 (81.76) + train[2018-10-13-07:20:00] Epoch: [043][4400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.654 (3.780) Prec@1 65.62 (60.02) Prec@5 84.38 (81.74) + train[2018-10-13-07:21:43] Epoch: [043][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.309 (3.780) Prec@1 67.97 (60.02) Prec@5 87.50 (81.74) + train[2018-10-13-07:23:27] Epoch: [043][4800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.228 (3.780) Prec@1 51.56 (60.01) Prec@5 77.34 (81.74) + train[2018-10-13-07:25:10] Epoch: [043][5000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.842 (3.781) Prec@1 58.59 (60.01) Prec@5 81.25 (81.73) + train[2018-10-13-07:26:54] Epoch: [043][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.612 (3.783) Prec@1 65.62 (59.98) Prec@5 82.81 (81.71) + train[2018-10-13-07:28:38] Epoch: [043][5400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.391 (3.782) Prec@1 70.31 (59.98) Prec@5 84.38 (81.70) + train[2018-10-13-07:30:22] Epoch: [043][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.821 (3.782) Prec@1 61.72 (59.98) Prec@5 78.91 (81.70) + train[2018-10-13-07:32:06] Epoch: [043][5800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.982 (3.784) Prec@1 53.91 (59.96) Prec@5 76.56 (81.68) + train[2018-10-13-07:33:49] Epoch: [043][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.827 (3.784) Prec@1 60.94 (59.96) Prec@5 78.91 (81.67) + train[2018-10-13-07:35:33] Epoch: [043][6200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.568 (3.785) Prec@1 62.50 (59.96) Prec@5 83.59 (81.67) + train[2018-10-13-07:37:18] Epoch: [043][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.835 (3.786) Prec@1 57.81 (59.94) Prec@5 82.03 (81.65) + train[2018-10-13-07:39:01] Epoch: [043][6600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.794 (3.786) Prec@1 60.94 (59.92) Prec@5 83.59 (81.65) + train[2018-10-13-07:40:45] Epoch: [043][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.815 (3.787) Prec@1 60.94 (59.90) Prec@5 80.47 (81.64) + train[2018-10-13-07:42:29] Epoch: [043][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.567 (3.787) Prec@1 64.06 (59.90) Prec@5 82.81 (81.63) + train[2018-10-13-07:44:13] Epoch: [043][7200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.643 (3.787) Prec@1 60.94 (59.91) Prec@5 82.81 (81.63) + train[2018-10-13-07:45:57] Epoch: [043][7400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.909 (3.788) Prec@1 62.50 (59.90) Prec@5 77.34 (81.61) + train[2018-10-13-07:47:41] Epoch: [043][7600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.632 (3.788) Prec@1 64.06 (59.90) Prec@5 85.94 (81.61) + train[2018-10-13-07:49:25] Epoch: [043][7800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.584 (3.788) Prec@1 58.59 (59.89) Prec@5 85.94 (81.61) + train[2018-10-13-07:51:08] Epoch: [043][8000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.583 (3.789) Prec@1 60.16 (59.89) Prec@5 83.59 (81.61) + train[2018-10-13-07:52:53] Epoch: [043][8200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.584 (3.789) Prec@1 63.28 (59.87) Prec@5 83.59 (81.60) + train[2018-10-13-07:54:36] Epoch: [043][8400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.790 (3.790) Prec@1 59.38 (59.86) Prec@5 82.03 (81.60) + train[2018-10-13-07:56:21] Epoch: [043][8600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.033 (3.790) Prec@1 51.56 (59.86) Prec@5 80.47 (81.59) + train[2018-10-13-07:58:05] Epoch: [043][8800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.706 (3.791) Prec@1 59.38 (59.85) Prec@5 82.81 (81.58) + train[2018-10-13-07:59:49] Epoch: [043][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.838 (3.791) Prec@1 57.81 (59.83) Prec@5 78.91 (81.58) + train[2018-10-13-08:01:33] Epoch: [043][9200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.636 (3.792) Prec@1 67.19 (59.82) Prec@5 84.38 (81.57) + train[2018-10-13-08:03:17] Epoch: [043][9400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.784 (3.793) Prec@1 58.59 (59.82) Prec@5 81.25 (81.56) + train[2018-10-13-08:05:01] Epoch: [043][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.629 (3.793) Prec@1 60.94 (59.81) Prec@5 85.16 (81.55) + train[2018-10-13-08:06:45] Epoch: [043][9800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.887 (3.794) Prec@1 62.50 (59.80) Prec@5 77.34 (81.54) + train[2018-10-13-08:08:28] Epoch: [043][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.945 (3.793) Prec@1 56.25 (59.80) Prec@5 78.12 (81.55) + train[2018-10-13-08:08:32] Epoch: [043][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.300 (3.793) Prec@1 60.00 (59.80) Prec@5 86.67 (81.55) +[2018-10-13-08:08:32] **train** Prec@1 59.80 Prec@5 81.55 Error@1 40.20 Error@5 18.45 Loss:3.793 + test [2018-10-13-08:08:37] Epoch: [043][000/391] Time 4.15 (4.15) Data 4.02 (4.02) Loss 1.031 (1.031) Prec@1 78.12 (78.12) Prec@5 91.41 (91.41) + test [2018-10-13-08:09:04] Epoch: [043][200/391] Time 0.13 (0.16) Data 0.00 (0.02) Loss 2.178 (1.391) Prec@1 42.19 (67.41) Prec@5 77.34 (88.63) + test [2018-10-13-08:09:29] Epoch: [043][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.702 (1.573) Prec@1 36.25 (64.07) Prec@5 75.00 (85.92) +[2018-10-13-08:09:29] **test** Prec@1 64.07 Prec@5 85.92 Error@1 35.93 Error@5 14.08 Loss:1.573 +----> Best Accuracy : Acc@1=64.76, Acc@5=86.37, Error@1=35.24, Error@5=13.63 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-13-08:09:29] [Epoch=044/250] [Need: 300:48:46] LR=0.0262 ~ 0.0262, Batch=128 + train[2018-10-13-08:09:34] Epoch: [044][000/10010] Time 4.69 (4.69) Data 4.07 (4.07) Loss 3.543 (3.543) Prec@1 60.16 (60.16) Prec@5 86.72 (86.72) + train[2018-10-13-08:11:18] Epoch: [044][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 3.565 (3.721) Prec@1 66.41 (60.86) Prec@5 85.16 (82.47) + train[2018-10-13-08:13:02] Epoch: [044][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.739 (3.738) Prec@1 58.59 (60.64) Prec@5 82.03 (82.22) + train[2018-10-13-08:14:46] Epoch: [044][600/10010] Time 0.49 (0.53) Data 0.00 (0.01) Loss 3.944 (3.751) Prec@1 57.03 (60.49) Prec@5 75.78 (82.06) + train[2018-10-13-08:16:31] Epoch: [044][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 4.203 (3.751) Prec@1 53.12 (60.54) Prec@5 74.22 (82.05) + train[2018-10-13-08:18:14] Epoch: [044][1000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.670 (3.754) Prec@1 63.28 (60.47) Prec@5 83.59 (81.99) + train[2018-10-13-08:19:59] Epoch: [044][1200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.628 (3.752) Prec@1 60.94 (60.45) Prec@5 86.72 (82.03) + train[2018-10-13-08:21:42] Epoch: [044][1400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.687 (3.752) Prec@1 63.28 (60.47) Prec@5 82.81 (82.01) + train[2018-10-13-08:23:26] Epoch: [044][1600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.501 (3.751) Prec@1 67.97 (60.49) Prec@5 83.59 (82.05) + train[2018-10-13-08:25:10] Epoch: [044][1800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.672 (3.753) Prec@1 61.72 (60.48) Prec@5 85.16 (82.05) + train[2018-10-13-08:26:54] Epoch: [044][2000/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 4.201 (3.753) Prec@1 53.91 (60.50) Prec@5 75.78 (82.05) + train[2018-10-13-08:28:37] Epoch: [044][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.090 (3.756) Prec@1 53.12 (60.44) Prec@5 73.44 (82.00) + train[2018-10-13-08:30:22] Epoch: [044][2400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.599 (3.758) Prec@1 62.50 (60.39) Prec@5 82.81 (81.96) + train[2018-10-13-08:32:05] Epoch: [044][2600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.283 (3.760) Prec@1 70.31 (60.40) Prec@5 89.06 (81.94) + train[2018-10-13-08:33:49] Epoch: [044][2800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.574 (3.761) Prec@1 60.94 (60.37) Prec@5 85.16 (81.94) + train[2018-10-13-08:35:33] Epoch: [044][3000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.149 (3.761) Prec@1 55.47 (60.35) Prec@5 75.00 (81.91) + train[2018-10-13-08:37:18] Epoch: [044][3200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.643 (3.762) Prec@1 67.19 (60.34) Prec@5 85.16 (81.91) + train[2018-10-13-08:39:01] Epoch: [044][3400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.051 (3.763) Prec@1 52.34 (60.33) Prec@5 78.91 (81.91) + train[2018-10-13-08:40:45] Epoch: [044][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.862 (3.763) Prec@1 60.16 (60.31) Prec@5 80.47 (81.89) + train[2018-10-13-08:42:29] Epoch: [044][3800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.624 (3.763) Prec@1 57.03 (60.32) Prec@5 82.81 (81.90) + train[2018-10-13-08:44:13] Epoch: [044][4000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.082 (3.764) Prec@1 57.81 (60.30) Prec@5 75.00 (81.89) + train[2018-10-13-08:45:57] Epoch: [044][4200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.224 (3.765) Prec@1 59.38 (60.27) Prec@5 72.66 (81.87) + train[2018-10-13-08:47:40] Epoch: [044][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.955 (3.766) Prec@1 53.12 (60.25) Prec@5 82.81 (81.85) + train[2018-10-13-08:49:24] Epoch: [044][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.678 (3.766) Prec@1 61.72 (60.25) Prec@5 81.25 (81.85) + train[2018-10-13-08:51:08] Epoch: [044][4800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.852 (3.767) Prec@1 59.38 (60.23) Prec@5 83.59 (81.84) + train[2018-10-13-08:52:52] Epoch: [044][5000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.573 (3.767) Prec@1 65.62 (60.24) Prec@5 82.81 (81.84) + train[2018-10-13-08:54:36] Epoch: [044][5200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.020 (3.768) Prec@1 60.16 (60.22) Prec@5 76.56 (81.83) + train[2018-10-13-08:56:19] Epoch: [044][5400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.669 (3.769) Prec@1 61.72 (60.20) Prec@5 85.16 (81.82) + train[2018-10-13-08:58:03] Epoch: [044][5600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.794 (3.770) Prec@1 56.25 (60.20) Prec@5 80.47 (81.81) + train[2018-10-13-08:59:47] Epoch: [044][5800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.577 (3.770) Prec@1 65.62 (60.18) Prec@5 85.94 (81.80) + train[2018-10-13-09:01:31] Epoch: [044][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.587 (3.771) Prec@1 59.38 (60.18) Prec@5 85.16 (81.79) + train[2018-10-13-09:03:15] Epoch: [044][6200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.863 (3.771) Prec@1 58.59 (60.18) Prec@5 81.25 (81.78) + train[2018-10-13-09:04:59] Epoch: [044][6400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.469 (3.770) Prec@1 60.16 (60.18) Prec@5 85.94 (81.78) + train[2018-10-13-09:06:43] Epoch: [044][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.951 (3.771) Prec@1 58.59 (60.17) Prec@5 75.78 (81.78) + train[2018-10-13-09:08:27] Epoch: [044][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.946 (3.771) Prec@1 60.94 (60.17) Prec@5 81.25 (81.78) + train[2018-10-13-09:10:10] Epoch: [044][7000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.636 (3.772) Prec@1 60.16 (60.16) Prec@5 85.16 (81.77) + train[2018-10-13-09:11:54] Epoch: [044][7200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.624 (3.772) Prec@1 61.72 (60.15) Prec@5 80.47 (81.77) + train[2018-10-13-09:13:38] Epoch: [044][7400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.740 (3.773) Prec@1 62.50 (60.14) Prec@5 82.03 (81.76) + train[2018-10-13-09:15:22] Epoch: [044][7600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.575 (3.773) Prec@1 60.16 (60.12) Prec@5 87.50 (81.75) + train[2018-10-13-09:17:06] Epoch: [044][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.475 (3.774) Prec@1 68.75 (60.12) Prec@5 87.50 (81.75) + train[2018-10-13-09:18:50] Epoch: [044][8000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.551 (3.775) Prec@1 63.28 (60.10) Prec@5 82.03 (81.73) + train[2018-10-13-09:20:34] Epoch: [044][8200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.671 (3.776) Prec@1 64.84 (60.09) Prec@5 82.81 (81.73) + train[2018-10-13-09:22:18] Epoch: [044][8400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.077 (3.776) Prec@1 57.03 (60.08) Prec@5 75.78 (81.72) + train[2018-10-13-09:24:02] Epoch: [044][8600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.706 (3.776) Prec@1 64.06 (60.07) Prec@5 85.16 (81.72) + train[2018-10-13-09:25:46] Epoch: [044][8800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.241 (3.776) Prec@1 53.91 (60.07) Prec@5 75.78 (81.71) + train[2018-10-13-09:27:29] Epoch: [044][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.837 (3.777) Prec@1 60.16 (60.05) Prec@5 78.12 (81.70) + train[2018-10-13-09:29:13] Epoch: [044][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.722 (3.778) Prec@1 57.03 (60.05) Prec@5 82.03 (81.70) + train[2018-10-13-09:30:56] Epoch: [044][9400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.042 (3.778) Prec@1 55.47 (60.04) Prec@5 77.34 (81.69) + train[2018-10-13-09:32:41] Epoch: [044][9600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.852 (3.779) Prec@1 57.03 (60.03) Prec@5 84.38 (81.68) + train[2018-10-13-09:34:25] Epoch: [044][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.966 (3.779) Prec@1 57.03 (60.02) Prec@5 77.34 (81.68) + train[2018-10-13-09:36:09] Epoch: [044][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.645 (3.780) Prec@1 63.28 (60.02) Prec@5 84.38 (81.68) + train[2018-10-13-09:36:13] Epoch: [044][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.688 (3.780) Prec@1 40.00 (60.02) Prec@5 86.67 (81.68) +[2018-10-13-09:36:13] **train** Prec@1 60.02 Prec@5 81.68 Error@1 39.98 Error@5 18.32 Loss:3.780 + test [2018-10-13-09:36:17] Epoch: [044][000/391] Time 3.96 (3.96) Data 3.82 (3.82) Loss 0.852 (0.852) Prec@1 85.16 (85.16) Prec@5 94.53 (94.53) + test [2018-10-13-09:36:45] Epoch: [044][200/391] Time 0.12 (0.16) Data 0.00 (0.02) Loss 1.742 (1.337) Prec@1 57.03 (68.86) Prec@5 82.03 (89.36) + test [2018-10-13-09:37:10] Epoch: [044][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.718 (1.525) Prec@1 30.00 (65.05) Prec@5 75.00 (86.38) +[2018-10-13-09:37:10] **test** Prec@1 65.05 Prec@5 86.38 Error@1 34.95 Error@5 13.62 Loss:1.525 +----> Best Accuracy : Acc@1=65.05, Acc@5=86.38, Error@1=34.95, Error@5=13.62 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-13-09:37:10] [Epoch=045/250] [Need: 299:33:46] LR=0.0254 ~ 0.0254, Batch=128 + train[2018-10-13-09:37:14] Epoch: [045][000/10010] Time 4.54 (4.54) Data 3.93 (3.93) Loss 3.947 (3.947) Prec@1 59.38 (59.38) Prec@5 82.03 (82.03) + train[2018-10-13-09:38:58] Epoch: [045][200/10010] Time 0.55 (0.54) Data 0.00 (0.02) Loss 3.380 (3.724) Prec@1 66.41 (60.67) Prec@5 88.28 (82.37) + train[2018-10-13-09:40:41] Epoch: [045][400/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.662 (3.723) Prec@1 64.84 (60.82) Prec@5 82.81 (82.34) + train[2018-10-13-09:42:25] Epoch: [045][600/10010] Time 0.50 (0.52) Data 0.00 (0.01) Loss 4.203 (3.724) Prec@1 53.12 (60.85) Prec@5 74.22 (82.36) + train[2018-10-13-09:44:09] Epoch: [045][800/10010] Time 0.50 (0.52) Data 0.00 (0.01) Loss 3.882 (3.722) Prec@1 61.72 (60.87) Prec@5 78.91 (82.41) + train[2018-10-13-09:45:52] Epoch: [045][1000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.850 (3.722) Prec@1 57.03 (60.91) Prec@5 80.47 (82.45) + train[2018-10-13-09:47:36] Epoch: [045][1200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.806 (3.730) Prec@1 54.69 (60.83) Prec@5 81.25 (82.31) + train[2018-10-13-09:49:19] Epoch: [045][1400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.748 (3.725) Prec@1 59.38 (60.92) Prec@5 82.03 (82.37) + train[2018-10-13-09:51:03] Epoch: [045][1600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.627 (3.727) Prec@1 64.06 (60.89) Prec@5 83.59 (82.33) + train[2018-10-13-09:52:46] Epoch: [045][1800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.327 (3.729) Prec@1 63.28 (60.88) Prec@5 89.84 (82.33) + train[2018-10-13-09:54:30] Epoch: [045][2000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.717 (3.732) Prec@1 66.41 (60.83) Prec@5 81.25 (82.27) + train[2018-10-13-09:56:14] Epoch: [045][2200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.409 (3.736) Prec@1 68.75 (60.76) Prec@5 86.72 (82.22) + train[2018-10-13-09:57:58] Epoch: [045][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.339 (3.736) Prec@1 70.31 (60.76) Prec@5 87.50 (82.23) + train[2018-10-13-09:59:41] Epoch: [045][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.906 (3.739) Prec@1 62.50 (60.74) Prec@5 78.12 (82.20) + train[2018-10-13-10:01:25] Epoch: [045][2800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.622 (3.741) Prec@1 64.06 (60.72) Prec@5 84.38 (82.17) + train[2018-10-13-10:03:09] Epoch: [045][3000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.730 (3.742) Prec@1 58.59 (60.68) Prec@5 83.59 (82.15) + train[2018-10-13-10:04:54] Epoch: [045][3200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.857 (3.744) Prec@1 60.16 (60.67) Prec@5 78.91 (82.13) + train[2018-10-13-10:06:38] Epoch: [045][3400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.719 (3.744) Prec@1 67.19 (60.66) Prec@5 80.47 (82.13) + train[2018-10-13-10:08:22] Epoch: [045][3600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.940 (3.744) Prec@1 60.94 (60.67) Prec@5 80.47 (82.14) + train[2018-10-13-10:10:07] Epoch: [045][3800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.719 (3.745) Prec@1 58.59 (60.64) Prec@5 82.81 (82.13) + train[2018-10-13-10:11:51] Epoch: [045][4000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.797 (3.747) Prec@1 64.06 (60.60) Prec@5 81.25 (82.10) + train[2018-10-13-10:13:36] Epoch: [045][4200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.527 (3.748) Prec@1 63.28 (60.58) Prec@5 81.25 (82.10) + train[2018-10-13-10:15:20] Epoch: [045][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.031 (3.748) Prec@1 56.25 (60.57) Prec@5 78.91 (82.09) + train[2018-10-13-10:17:04] Epoch: [045][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.711 (3.749) Prec@1 59.38 (60.56) Prec@5 84.38 (82.07) + train[2018-10-13-10:18:48] Epoch: [045][4800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.600 (3.749) Prec@1 59.38 (60.55) Prec@5 83.59 (82.07) + train[2018-10-13-10:20:32] Epoch: [045][5000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.038 (3.750) Prec@1 53.91 (60.54) Prec@5 75.00 (82.07) + train[2018-10-13-10:22:17] Epoch: [045][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.461 (3.750) Prec@1 62.50 (60.54) Prec@5 89.06 (82.06) + train[2018-10-13-10:24:00] Epoch: [045][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.556 (3.751) Prec@1 62.50 (60.53) Prec@5 84.38 (82.06) + train[2018-10-13-10:25:44] Epoch: [045][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.353 (3.751) Prec@1 67.19 (60.53) Prec@5 86.72 (82.06) + train[2018-10-13-10:27:28] Epoch: [045][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.974 (3.751) Prec@1 58.59 (60.51) Prec@5 82.03 (82.06) + train[2018-10-13-10:29:12] Epoch: [045][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.900 (3.753) Prec@1 54.69 (60.49) Prec@5 81.25 (82.05) + train[2018-10-13-10:30:56] Epoch: [045][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.381 (3.754) Prec@1 67.97 (60.47) Prec@5 87.50 (82.04) + train[2018-10-13-10:32:40] Epoch: [045][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.620 (3.754) Prec@1 64.06 (60.46) Prec@5 79.69 (82.04) + train[2018-10-13-10:34:25] Epoch: [045][6600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.694 (3.755) Prec@1 58.59 (60.45) Prec@5 79.69 (82.02) + train[2018-10-13-10:36:09] Epoch: [045][6800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.841 (3.755) Prec@1 57.81 (60.45) Prec@5 80.47 (82.02) + train[2018-10-13-10:37:53] Epoch: [045][7000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.879 (3.756) Prec@1 57.81 (60.44) Prec@5 78.91 (82.00) + train[2018-10-13-10:39:38] Epoch: [045][7200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.699 (3.757) Prec@1 60.16 (60.43) Prec@5 82.03 (82.00) + train[2018-10-13-10:41:21] Epoch: [045][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.882 (3.757) Prec@1 60.94 (60.42) Prec@5 78.12 (81.99) + train[2018-10-13-10:43:05] Epoch: [045][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.888 (3.758) Prec@1 59.38 (60.42) Prec@5 76.56 (81.98) + train[2018-10-13-10:44:49] Epoch: [045][7800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.895 (3.758) Prec@1 58.59 (60.40) Prec@5 82.03 (81.98) + train[2018-10-13-10:46:33] Epoch: [045][8000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.989 (3.758) Prec@1 54.69 (60.40) Prec@5 80.47 (81.97) + train[2018-10-13-10:48:17] Epoch: [045][8200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.491 (3.759) Prec@1 68.75 (60.40) Prec@5 85.16 (81.96) + train[2018-10-13-10:50:01] Epoch: [045][8400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.906 (3.759) Prec@1 53.91 (60.39) Prec@5 80.47 (81.97) + train[2018-10-13-10:51:45] Epoch: [045][8600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.766 (3.759) Prec@1 57.81 (60.38) Prec@5 82.03 (81.96) + train[2018-10-13-10:53:30] Epoch: [045][8800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.001 (3.759) Prec@1 53.91 (60.38) Prec@5 80.47 (81.97) + train[2018-10-13-10:55:14] Epoch: [045][9000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.264 (3.760) Prec@1 69.53 (60.37) Prec@5 89.84 (81.96) + train[2018-10-13-10:56:57] Epoch: [045][9200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.617 (3.760) Prec@1 60.94 (60.36) Prec@5 78.12 (81.97) + train[2018-10-13-10:58:41] Epoch: [045][9400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.774 (3.760) Prec@1 63.28 (60.36) Prec@5 80.47 (81.96) + train[2018-10-13-11:00:26] Epoch: [045][9600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.946 (3.760) Prec@1 55.47 (60.35) Prec@5 80.47 (81.96) + train[2018-10-13-11:02:10] Epoch: [045][9800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.191 (3.761) Prec@1 53.91 (60.34) Prec@5 75.00 (81.95) + train[2018-10-13-11:03:54] Epoch: [045][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.772 (3.762) Prec@1 63.28 (60.33) Prec@5 82.03 (81.94) + train[2018-10-13-11:03:59] Epoch: [045][10009/10010] Time 0.21 (0.52) Data 0.00 (0.00) Loss 3.446 (3.762) Prec@1 80.00 (60.33) Prec@5 86.67 (81.94) +[2018-10-13-11:03:59] **train** Prec@1 60.33 Prec@5 81.94 Error@1 39.67 Error@5 18.06 Loss:3.762 + test [2018-10-13-11:04:03] Epoch: [045][000/391] Time 4.67 (4.67) Data 4.53 (4.53) Loss 0.970 (0.970) Prec@1 78.91 (78.91) Prec@5 92.19 (92.19) + test [2018-10-13-11:04:31] Epoch: [045][200/391] Time 0.13 (0.16) Data 0.00 (0.02) Loss 1.523 (1.315) Prec@1 62.50 (69.20) Prec@5 86.72 (89.92) + test [2018-10-13-11:04:56] Epoch: [045][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.755 (1.526) Prec@1 37.50 (65.01) Prec@5 70.00 (86.68) +[2018-10-13-11:04:56] **test** Prec@1 65.01 Prec@5 86.68 Error@1 34.99 Error@5 13.32 Loss:1.526 +----> Best Accuracy : Acc@1=65.05, Acc@5=86.38, Error@1=34.95, Error@5=13.62 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-13-11:04:56] [Epoch=046/250] [Need: 298:24:35] LR=0.0246 ~ 0.0246, Batch=128 + train[2018-10-13-11:05:01] Epoch: [046][000/10010] Time 5.59 (5.59) Data 5.05 (5.05) Loss 4.047 (4.047) Prec@1 53.91 (53.91) Prec@5 79.69 (79.69) + train[2018-10-13-11:06:45] Epoch: [046][200/10010] Time 0.54 (0.54) Data 0.00 (0.03) Loss 4.325 (3.711) Prec@1 49.22 (61.36) Prec@5 71.88 (82.42) + train[2018-10-13-11:08:29] Epoch: [046][400/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.724 (3.703) Prec@1 60.16 (61.56) Prec@5 81.25 (82.62) + train[2018-10-13-11:10:13] Epoch: [046][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.898 (3.718) Prec@1 57.03 (61.22) Prec@5 79.69 (82.41) + train[2018-10-13-11:11:57] Epoch: [046][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.853 (3.709) Prec@1 65.62 (61.35) Prec@5 80.47 (82.53) + train[2018-10-13-11:13:41] Epoch: [046][1000/10010] Time 0.51 (0.52) Data 0.00 (0.01) Loss 4.151 (3.712) Prec@1 53.12 (61.23) Prec@5 77.34 (82.54) + train[2018-10-13-11:15:25] Epoch: [046][1200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.840 (3.710) Prec@1 61.72 (61.20) Prec@5 82.03 (82.58) + train[2018-10-13-11:17:09] Epoch: [046][1400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.880 (3.712) Prec@1 58.59 (61.17) Prec@5 80.47 (82.55) + train[2018-10-13-11:18:53] Epoch: [046][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.961 (3.715) Prec@1 55.47 (61.11) Prec@5 82.03 (82.52) + train[2018-10-13-11:20:36] Epoch: [046][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.825 (3.717) Prec@1 58.59 (61.04) Prec@5 78.91 (82.50) + train[2018-10-13-11:22:20] Epoch: [046][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.843 (3.716) Prec@1 58.59 (61.10) Prec@5 81.25 (82.51) + train[2018-10-13-11:24:04] Epoch: [046][2200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.351 (3.715) Prec@1 66.41 (61.11) Prec@5 86.72 (82.53) + train[2018-10-13-11:25:48] Epoch: [046][2400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.710 (3.718) Prec@1 60.94 (61.09) Prec@5 84.38 (82.50) + train[2018-10-13-11:27:32] Epoch: [046][2600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.129 (3.721) Prec@1 52.34 (61.04) Prec@5 78.12 (82.48) + train[2018-10-13-11:29:15] Epoch: [046][2800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.521 (3.721) Prec@1 64.06 (61.04) Prec@5 82.81 (82.47) + train[2018-10-13-11:30:59] Epoch: [046][3000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.156 (3.724) Prec@1 57.03 (60.98) Prec@5 75.78 (82.42) + train[2018-10-13-11:32:43] Epoch: [046][3200/10010] Time 0.59 (0.52) Data 0.00 (0.00) Loss 3.582 (3.726) Prec@1 62.50 (60.96) Prec@5 83.59 (82.40) + train[2018-10-13-11:34:27] Epoch: [046][3400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.793 (3.727) Prec@1 60.94 (60.94) Prec@5 80.47 (82.38) + train[2018-10-13-11:36:10] Epoch: [046][3600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.437 (3.728) Prec@1 52.34 (60.89) Prec@5 71.88 (82.35) + train[2018-10-13-11:37:53] Epoch: [046][3800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.774 (3.729) Prec@1 57.81 (60.88) Prec@5 85.16 (82.35) + train[2018-10-13-11:39:37] Epoch: [046][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.298 (3.730) Prec@1 65.62 (60.85) Prec@5 87.50 (82.33) + train[2018-10-13-11:41:20] Epoch: [046][4200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.971 (3.731) Prec@1 57.81 (60.83) Prec@5 81.25 (82.31) + train[2018-10-13-11:43:04] Epoch: [046][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.855 (3.733) Prec@1 58.59 (60.82) Prec@5 78.12 (82.29) + train[2018-10-13-11:44:48] Epoch: [046][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.602 (3.734) Prec@1 64.06 (60.79) Prec@5 85.16 (82.27) + train[2018-10-13-11:46:32] Epoch: [046][4800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.614 (3.735) Prec@1 60.94 (60.77) Prec@5 85.16 (82.25) + train[2018-10-13-11:48:16] Epoch: [046][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.644 (3.736) Prec@1 60.94 (60.77) Prec@5 82.03 (82.24) + train[2018-10-13-11:50:00] Epoch: [046][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.471 (3.738) Prec@1 67.19 (60.74) Prec@5 85.16 (82.22) + train[2018-10-13-11:51:43] Epoch: [046][5400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.595 (3.738) Prec@1 59.38 (60.74) Prec@5 83.59 (82.21) + train[2018-10-13-11:53:27] Epoch: [046][5600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.940 (3.738) Prec@1 53.12 (60.75) Prec@5 79.69 (82.22) + train[2018-10-13-11:55:11] Epoch: [046][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.010 (3.739) Prec@1 57.81 (60.74) Prec@5 78.91 (82.21) + train[2018-10-13-11:56:55] Epoch: [046][6000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.556 (3.739) Prec@1 64.84 (60.73) Prec@5 85.16 (82.19) + train[2018-10-13-11:58:39] Epoch: [046][6200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.836 (3.740) Prec@1 60.16 (60.70) Prec@5 79.69 (82.18) + train[2018-10-13-12:00:23] Epoch: [046][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.674 (3.740) Prec@1 60.94 (60.69) Prec@5 82.81 (82.18) + train[2018-10-13-12:02:07] Epoch: [046][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.820 (3.742) Prec@1 64.84 (60.67) Prec@5 82.81 (82.17) + train[2018-10-13-12:03:51] Epoch: [046][6800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.724 (3.742) Prec@1 60.16 (60.67) Prec@5 82.81 (82.17) + train[2018-10-13-12:05:34] Epoch: [046][7000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.823 (3.743) Prec@1 57.81 (60.65) Prec@5 81.25 (82.15) + train[2018-10-13-12:07:18] Epoch: [046][7200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.098 (3.744) Prec@1 57.03 (60.65) Prec@5 76.56 (82.14) + train[2018-10-13-12:09:02] Epoch: [046][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.602 (3.745) Prec@1 69.53 (60.63) Prec@5 83.59 (82.12) + train[2018-10-13-12:10:46] Epoch: [046][7600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.627 (3.745) Prec@1 60.94 (60.62) Prec@5 80.47 (82.11) + train[2018-10-13-12:12:29] Epoch: [046][7800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.918 (3.746) Prec@1 59.38 (60.59) Prec@5 78.12 (82.10) + train[2018-10-13-12:14:13] Epoch: [046][8000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.928 (3.746) Prec@1 57.03 (60.58) Prec@5 78.91 (82.10) + train[2018-10-13-12:15:56] Epoch: [046][8200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 4.233 (3.747) Prec@1 53.91 (60.58) Prec@5 74.22 (82.08) + train[2018-10-13-12:17:41] Epoch: [046][8400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.704 (3.748) Prec@1 64.84 (60.57) Prec@5 85.16 (82.07) + train[2018-10-13-12:19:25] Epoch: [046][8600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.950 (3.748) Prec@1 56.25 (60.56) Prec@5 77.34 (82.06) + train[2018-10-13-12:21:08] Epoch: [046][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.679 (3.748) Prec@1 62.50 (60.57) Prec@5 85.16 (82.06) + train[2018-10-13-12:22:52] Epoch: [046][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.465 (3.749) Prec@1 64.84 (60.55) Prec@5 88.28 (82.05) + train[2018-10-13-12:24:36] Epoch: [046][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.205 (3.750) Prec@1 57.03 (60.54) Prec@5 75.78 (82.04) + train[2018-10-13-12:26:20] Epoch: [046][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.897 (3.750) Prec@1 60.16 (60.53) Prec@5 78.91 (82.03) + train[2018-10-13-12:28:04] Epoch: [046][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.928 (3.751) Prec@1 56.25 (60.53) Prec@5 81.25 (82.02) + train[2018-10-13-12:29:48] Epoch: [046][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.754 (3.752) Prec@1 59.38 (60.51) Prec@5 83.59 (82.00) + train[2018-10-13-12:31:31] Epoch: [046][10000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.772 (3.753) Prec@1 52.34 (60.50) Prec@5 84.38 (82.00) + train[2018-10-13-12:31:36] Epoch: [046][10009/10010] Time 0.21 (0.52) Data 0.00 (0.00) Loss 4.769 (3.753) Prec@1 46.67 (60.50) Prec@5 66.67 (82.00) +[2018-10-13-12:31:36] **train** Prec@1 60.50 Prec@5 82.00 Error@1 39.50 Error@5 18.00 Loss:3.753 + test [2018-10-13-12:31:40] Epoch: [046][000/391] Time 4.27 (4.27) Data 4.13 (4.13) Loss 0.827 (0.827) Prec@1 84.38 (84.38) Prec@5 94.53 (94.53) + test [2018-10-13-12:32:07] Epoch: [046][200/391] Time 0.12 (0.16) Data 0.00 (0.02) Loss 1.583 (1.333) Prec@1 65.62 (68.82) Prec@5 84.38 (89.62) + test [2018-10-13-12:32:32] Epoch: [046][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.551 (1.529) Prec@1 36.25 (65.07) Prec@5 78.75 (86.68) +[2018-10-13-12:32:32] **test** Prec@1 65.07 Prec@5 86.68 Error@1 34.93 Error@5 13.32 Loss:1.529 +----> Best Accuracy : Acc@1=65.07, Acc@5=86.68, Error@1=34.93, Error@5=13.32 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-13-12:32:32] [Epoch=047/250] [Need: 296:23:24] LR=0.0239 ~ 0.0239, Batch=128 + train[2018-10-13-12:32:38] Epoch: [047][000/10010] Time 5.75 (5.75) Data 5.19 (5.19) Loss 3.699 (3.699) Prec@1 63.28 (63.28) Prec@5 82.81 (82.81) + train[2018-10-13-12:34:22] Epoch: [047][200/10010] Time 0.49 (0.55) Data 0.00 (0.03) Loss 3.583 (3.704) Prec@1 59.38 (61.42) Prec@5 83.59 (82.80) + train[2018-10-13-12:36:06] Epoch: [047][400/10010] Time 0.57 (0.53) Data 0.00 (0.01) Loss 3.484 (3.691) Prec@1 62.50 (61.66) Prec@5 87.50 (82.91) + train[2018-10-13-12:37:50] Epoch: [047][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.486 (3.689) Prec@1 68.75 (61.52) Prec@5 85.94 (82.97) + train[2018-10-13-12:39:33] Epoch: [047][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.648 (3.700) Prec@1 64.06 (61.39) Prec@5 80.47 (82.77) + train[2018-10-13-12:41:16] Epoch: [047][1000/10010] Time 0.50 (0.52) Data 0.00 (0.01) Loss 3.615 (3.700) Prec@1 62.50 (61.36) Prec@5 79.69 (82.72) + train[2018-10-13-12:43:00] Epoch: [047][1200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.705 (3.704) Prec@1 57.03 (61.29) Prec@5 85.16 (82.67) + train[2018-10-13-12:44:44] Epoch: [047][1400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.702 (3.708) Prec@1 63.28 (61.24) Prec@5 83.59 (82.58) + train[2018-10-13-12:46:28] Epoch: [047][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.794 (3.713) Prec@1 57.81 (61.21) Prec@5 77.34 (82.52) + train[2018-10-13-12:48:12] Epoch: [047][1800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.617 (3.714) Prec@1 59.38 (61.18) Prec@5 84.38 (82.51) + train[2018-10-13-12:49:55] Epoch: [047][2000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.706 (3.715) Prec@1 62.50 (61.16) Prec@5 82.03 (82.49) + train[2018-10-13-12:51:39] Epoch: [047][2200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.945 (3.717) Prec@1 59.38 (61.11) Prec@5 75.78 (82.46) + train[2018-10-13-12:53:23] Epoch: [047][2400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.855 (3.719) Prec@1 56.25 (61.11) Prec@5 82.81 (82.42) + train[2018-10-13-12:55:06] Epoch: [047][2600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.699 (3.718) Prec@1 59.38 (61.10) Prec@5 85.16 (82.42) + train[2018-10-13-12:56:50] Epoch: [047][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.944 (3.719) Prec@1 57.03 (61.11) Prec@5 79.69 (82.41) + train[2018-10-13-12:58:33] Epoch: [047][3000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.387 (3.718) Prec@1 71.88 (61.10) Prec@5 84.38 (82.43) + train[2018-10-13-13:00:17] Epoch: [047][3200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.457 (3.718) Prec@1 64.84 (61.10) Prec@5 87.50 (82.43) + train[2018-10-13-13:02:01] Epoch: [047][3400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.868 (3.718) Prec@1 58.59 (61.11) Prec@5 76.56 (82.41) + train[2018-10-13-13:03:45] Epoch: [047][3600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.405 (3.720) Prec@1 65.62 (61.06) Prec@5 87.50 (82.39) + train[2018-10-13-13:05:29] Epoch: [047][3800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.109 (3.720) Prec@1 52.34 (61.07) Prec@5 74.22 (82.38) + train[2018-10-13-13:07:12] Epoch: [047][4000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.910 (3.721) Prec@1 58.59 (61.03) Prec@5 77.34 (82.35) + train[2018-10-13-13:08:56] Epoch: [047][4200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.889 (3.723) Prec@1 60.16 (61.00) Prec@5 78.12 (82.33) + train[2018-10-13-13:10:39] Epoch: [047][4400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.770 (3.723) Prec@1 62.50 (61.00) Prec@5 85.94 (82.34) + train[2018-10-13-13:12:23] Epoch: [047][4600/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.631 (3.724) Prec@1 60.94 (60.96) Prec@5 79.69 (82.33) + train[2018-10-13-13:14:07] Epoch: [047][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.541 (3.725) Prec@1 62.50 (60.94) Prec@5 83.59 (82.31) + train[2018-10-13-13:15:51] Epoch: [047][5000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.451 (3.726) Prec@1 67.97 (60.92) Prec@5 85.94 (82.29) + train[2018-10-13-13:17:35] Epoch: [047][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.987 (3.727) Prec@1 62.50 (60.90) Prec@5 77.34 (82.28) + train[2018-10-13-13:19:19] Epoch: [047][5400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.300 (3.728) Prec@1 67.19 (60.89) Prec@5 86.72 (82.28) + train[2018-10-13-13:21:02] Epoch: [047][5600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.495 (3.728) Prec@1 66.41 (60.90) Prec@5 85.16 (82.28) + train[2018-10-13-13:22:46] Epoch: [047][5800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.749 (3.729) Prec@1 64.06 (60.89) Prec@5 83.59 (82.27) + train[2018-10-13-13:24:30] Epoch: [047][6000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.337 (3.730) Prec@1 68.75 (60.86) Prec@5 85.16 (82.26) + train[2018-10-13-13:26:13] Epoch: [047][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.048 (3.730) Prec@1 55.47 (60.87) Prec@5 77.34 (82.25) + train[2018-10-13-13:27:56] Epoch: [047][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.730 (3.730) Prec@1 60.94 (60.86) Prec@5 85.16 (82.25) + train[2018-10-13-13:29:40] Epoch: [047][6600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.577 (3.731) Prec@1 64.84 (60.85) Prec@5 85.16 (82.24) + train[2018-10-13-13:31:23] Epoch: [047][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.424 (3.731) Prec@1 60.94 (60.84) Prec@5 85.16 (82.24) + train[2018-10-13-13:33:07] Epoch: [047][7000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.707 (3.732) Prec@1 61.72 (60.82) Prec@5 81.25 (82.23) + train[2018-10-13-13:34:50] Epoch: [047][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.404 (3.732) Prec@1 66.41 (60.82) Prec@5 85.94 (82.24) + train[2018-10-13-13:36:34] Epoch: [047][7400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.433 (3.732) Prec@1 64.06 (60.80) Prec@5 85.94 (82.23) + train[2018-10-13-13:38:17] Epoch: [047][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.673 (3.733) Prec@1 65.62 (60.80) Prec@5 82.03 (82.23) + train[2018-10-13-13:40:01] Epoch: [047][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.757 (3.732) Prec@1 57.81 (60.81) Prec@5 81.25 (82.23) + train[2018-10-13-13:41:44] Epoch: [047][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.625 (3.733) Prec@1 60.16 (60.80) Prec@5 84.38 (82.22) + train[2018-10-13-13:43:29] Epoch: [047][8200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.849 (3.734) Prec@1 60.94 (60.79) Prec@5 82.81 (82.21) + train[2018-10-13-13:45:12] Epoch: [047][8400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.579 (3.734) Prec@1 66.41 (60.79) Prec@5 84.38 (82.21) + train[2018-10-13-13:46:56] Epoch: [047][8600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.674 (3.734) Prec@1 60.16 (60.78) Prec@5 82.81 (82.21) + train[2018-10-13-13:48:40] Epoch: [047][8800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.151 (3.734) Prec@1 53.12 (60.77) Prec@5 75.78 (82.21) + train[2018-10-13-13:50:23] Epoch: [047][9000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.765 (3.735) Prec@1 60.94 (60.77) Prec@5 82.81 (82.20) + train[2018-10-13-13:52:07] Epoch: [047][9200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.888 (3.735) Prec@1 59.38 (60.76) Prec@5 82.03 (82.20) + train[2018-10-13-13:53:51] Epoch: [047][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.972 (3.736) Prec@1 57.81 (60.74) Prec@5 79.69 (82.19) + train[2018-10-13-13:55:34] Epoch: [047][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.959 (3.737) Prec@1 59.38 (60.73) Prec@5 82.81 (82.18) + train[2018-10-13-13:57:18] Epoch: [047][9800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.803 (3.737) Prec@1 58.59 (60.72) Prec@5 82.03 (82.18) + train[2018-10-13-13:59:02] Epoch: [047][10000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.647 (3.738) Prec@1 65.62 (60.72) Prec@5 82.03 (82.18) + train[2018-10-13-13:59:06] Epoch: [047][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 3.932 (3.738) Prec@1 53.33 (60.72) Prec@5 86.67 (82.18) +[2018-10-13-13:59:06] **train** Prec@1 60.72 Prec@5 82.18 Error@1 39.28 Error@5 17.82 Loss:3.738 + test [2018-10-13-13:59:10] Epoch: [047][000/391] Time 3.56 (3.56) Data 3.43 (3.43) Loss 0.769 (0.769) Prec@1 81.25 (81.25) Prec@5 94.53 (94.53) + test [2018-10-13-13:59:38] Epoch: [047][200/391] Time 0.12 (0.16) Data 0.00 (0.03) Loss 1.608 (1.320) Prec@1 58.59 (69.02) Prec@5 85.94 (89.75) + test [2018-10-13-14:00:03] Epoch: [047][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.702 (1.508) Prec@1 32.50 (65.52) Prec@5 72.50 (86.81) +[2018-10-13-14:00:03] **test** Prec@1 65.52 Prec@5 86.81 Error@1 34.48 Error@5 13.19 Loss:1.508 +----> Best Accuracy : Acc@1=65.52, Acc@5=86.81, Error@1=34.48, Error@5=13.19 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-13-14:00:03] [Epoch=048/250] [Need: 294:37:50] LR=0.0232 ~ 0.0232, Batch=128 + train[2018-10-13-14:00:07] Epoch: [048][000/10010] Time 4.31 (4.31) Data 3.70 (3.70) Loss 3.754 (3.754) Prec@1 62.50 (62.50) Prec@5 82.03 (82.03) + train[2018-10-13-14:01:51] Epoch: [048][200/10010] Time 0.53 (0.54) Data 0.00 (0.02) Loss 3.745 (3.677) Prec@1 60.16 (62.19) Prec@5 79.69 (82.91) + train[2018-10-13-14:03:35] Epoch: [048][400/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.871 (3.673) Prec@1 57.81 (62.00) Prec@5 82.03 (82.96) + train[2018-10-13-14:05:20] Epoch: [048][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.592 (3.674) Prec@1 62.50 (61.90) Prec@5 84.38 (82.98) + train[2018-10-13-14:07:03] Epoch: [048][800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.530 (3.679) Prec@1 59.38 (61.79) Prec@5 82.03 (82.93) + train[2018-10-13-14:08:47] Epoch: [048][1000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.579 (3.677) Prec@1 67.19 (61.84) Prec@5 83.59 (82.93) + train[2018-10-13-14:10:30] Epoch: [048][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.598 (3.687) Prec@1 64.06 (61.63) Prec@5 82.03 (82.78) + train[2018-10-13-14:12:15] Epoch: [048][1400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.218 (3.689) Prec@1 49.22 (61.58) Prec@5 77.34 (82.73) + train[2018-10-13-14:13:58] Epoch: [048][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.829 (3.694) Prec@1 55.47 (61.50) Prec@5 79.69 (82.69) + train[2018-10-13-14:15:42] Epoch: [048][1800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.593 (3.696) Prec@1 59.38 (61.44) Prec@5 83.59 (82.68) + train[2018-10-13-14:17:25] Epoch: [048][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.881 (3.695) Prec@1 58.59 (61.44) Prec@5 78.12 (82.68) + train[2018-10-13-14:19:10] Epoch: [048][2200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.764 (3.694) Prec@1 62.50 (61.44) Prec@5 81.25 (82.71) + train[2018-10-13-14:20:54] Epoch: [048][2400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.774 (3.696) Prec@1 59.38 (61.39) Prec@5 82.03 (82.67) + train[2018-10-13-14:22:37] Epoch: [048][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.629 (3.696) Prec@1 63.28 (61.39) Prec@5 83.59 (82.67) + train[2018-10-13-14:24:21] Epoch: [048][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.530 (3.698) Prec@1 67.97 (61.34) Prec@5 85.94 (82.65) + train[2018-10-13-14:26:04] Epoch: [048][3000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.827 (3.701) Prec@1 57.81 (61.30) Prec@5 79.69 (82.62) + train[2018-10-13-14:27:48] Epoch: [048][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.777 (3.702) Prec@1 60.94 (61.30) Prec@5 82.03 (82.61) + train[2018-10-13-14:29:32] Epoch: [048][3400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.678 (3.703) Prec@1 60.94 (61.27) Prec@5 85.16 (82.59) + train[2018-10-13-14:31:16] Epoch: [048][3600/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.726 (3.705) Prec@1 64.06 (61.26) Prec@5 81.25 (82.59) + train[2018-10-13-14:33:00] Epoch: [048][3800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.811 (3.706) Prec@1 58.59 (61.25) Prec@5 80.47 (82.57) + train[2018-10-13-14:34:43] Epoch: [048][4000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.839 (3.707) Prec@1 58.59 (61.23) Prec@5 86.72 (82.55) + train[2018-10-13-14:36:27] Epoch: [048][4200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.639 (3.709) Prec@1 63.28 (61.19) Prec@5 85.16 (82.53) + train[2018-10-13-14:38:11] Epoch: [048][4400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.548 (3.709) Prec@1 62.50 (61.19) Prec@5 82.03 (82.52) + train[2018-10-13-14:39:55] Epoch: [048][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.663 (3.710) Prec@1 60.94 (61.17) Prec@5 82.03 (82.51) + train[2018-10-13-14:41:39] Epoch: [048][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.360 (3.712) Prec@1 65.62 (61.13) Prec@5 91.41 (82.50) + train[2018-10-13-14:43:23] Epoch: [048][5000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.495 (3.713) Prec@1 60.94 (61.12) Prec@5 85.16 (82.49) + train[2018-10-13-14:45:07] Epoch: [048][5200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.867 (3.715) Prec@1 59.38 (61.10) Prec@5 77.34 (82.45) + train[2018-10-13-14:46:52] Epoch: [048][5400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.450 (3.715) Prec@1 68.75 (61.08) Prec@5 82.81 (82.45) + train[2018-10-13-14:48:36] Epoch: [048][5600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.852 (3.716) Prec@1 61.72 (61.08) Prec@5 79.69 (82.44) + train[2018-10-13-14:50:20] Epoch: [048][5800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.570 (3.716) Prec@1 67.19 (61.09) Prec@5 82.81 (82.45) + train[2018-10-13-14:52:03] Epoch: [048][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.845 (3.716) Prec@1 57.81 (61.09) Prec@5 82.03 (82.44) + train[2018-10-13-14:53:47] Epoch: [048][6200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.880 (3.716) Prec@1 59.38 (61.08) Prec@5 80.47 (82.44) + train[2018-10-13-14:55:31] Epoch: [048][6400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.140 (3.716) Prec@1 57.81 (61.07) Prec@5 78.12 (82.44) + train[2018-10-13-14:57:14] Epoch: [048][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.462 (3.716) Prec@1 64.06 (61.07) Prec@5 85.94 (82.44) + train[2018-10-13-14:58:58] Epoch: [048][6800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.962 (3.717) Prec@1 58.59 (61.05) Prec@5 77.34 (82.43) + train[2018-10-13-15:00:42] Epoch: [048][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.829 (3.719) Prec@1 57.03 (61.03) Prec@5 80.47 (82.41) + train[2018-10-13-15:02:26] Epoch: [048][7200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.323 (3.719) Prec@1 61.72 (61.02) Prec@5 87.50 (82.40) + train[2018-10-13-15:04:10] Epoch: [048][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.617 (3.720) Prec@1 62.50 (61.01) Prec@5 81.25 (82.39) + train[2018-10-13-15:05:53] Epoch: [048][7600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.699 (3.720) Prec@1 63.28 (61.00) Prec@5 84.38 (82.39) + train[2018-10-13-15:07:37] Epoch: [048][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.773 (3.720) Prec@1 59.38 (61.01) Prec@5 80.47 (82.39) + train[2018-10-13-15:09:21] Epoch: [048][8000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.859 (3.720) Prec@1 57.03 (61.00) Prec@5 82.81 (82.38) + train[2018-10-13-15:11:05] Epoch: [048][8200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.926 (3.721) Prec@1 57.81 (60.99) Prec@5 80.47 (82.37) + train[2018-10-13-15:12:50] Epoch: [048][8400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.802 (3.720) Prec@1 53.91 (61.00) Prec@5 79.69 (82.37) + train[2018-10-13-15:14:33] Epoch: [048][8600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.770 (3.721) Prec@1 62.50 (60.99) Prec@5 78.91 (82.37) + train[2018-10-13-15:16:17] Epoch: [048][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.814 (3.722) Prec@1 61.72 (60.98) Prec@5 80.47 (82.36) + train[2018-10-13-15:18:01] Epoch: [048][9000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.960 (3.722) Prec@1 59.38 (60.99) Prec@5 76.56 (82.36) + train[2018-10-13-15:19:44] Epoch: [048][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.687 (3.722) Prec@1 60.94 (60.99) Prec@5 82.03 (82.36) + train[2018-10-13-15:21:28] Epoch: [048][9400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.806 (3.722) Prec@1 61.72 (60.99) Prec@5 82.03 (82.35) + train[2018-10-13-15:23:12] Epoch: [048][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.991 (3.722) Prec@1 56.25 (60.99) Prec@5 78.12 (82.35) + train[2018-10-13-15:24:56] Epoch: [048][9800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.811 (3.723) Prec@1 59.38 (60.97) Prec@5 81.25 (82.33) + train[2018-10-13-15:26:40] Epoch: [048][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.686 (3.723) Prec@1 66.41 (60.97) Prec@5 84.38 (82.33) + train[2018-10-13-15:26:44] Epoch: [048][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.284 (3.723) Prec@1 40.00 (60.97) Prec@5 66.67 (82.33) +[2018-10-13-15:26:44] **train** Prec@1 60.97 Prec@5 82.33 Error@1 39.03 Error@5 17.67 Loss:3.723 + test [2018-10-13-15:26:48] Epoch: [048][000/391] Time 3.85 (3.85) Data 3.72 (3.72) Loss 1.130 (1.130) Prec@1 76.56 (76.56) Prec@5 89.84 (89.84) + test [2018-10-13-15:27:16] Epoch: [048][200/391] Time 0.13 (0.16) Data 0.00 (0.02) Loss 1.469 (1.331) Prec@1 67.19 (69.31) Prec@5 89.06 (89.63) + test [2018-10-13-15:27:41] Epoch: [048][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.836 (1.523) Prec@1 30.00 (65.54) Prec@5 71.25 (86.62) +[2018-10-13-15:27:41] **test** Prec@1 65.54 Prec@5 86.62 Error@1 34.46 Error@5 13.38 Loss:1.523 +----> Best Accuracy : Acc@1=65.54, Acc@5=86.62, Error@1=34.46, Error@5=13.38 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-13-15:27:42] [Epoch=049/250] [Need: 293:36:44] LR=0.0225 ~ 0.0225, Batch=128 + train[2018-10-13-15:27:46] Epoch: [049][000/10010] Time 4.72 (4.72) Data 4.06 (4.06) Loss 3.721 (3.721) Prec@1 57.03 (57.03) Prec@5 81.25 (81.25) + train[2018-10-13-15:29:30] Epoch: [049][200/10010] Time 0.53 (0.54) Data 0.00 (0.02) Loss 3.530 (3.664) Prec@1 66.41 (62.26) Prec@5 84.38 (82.89) + train[2018-10-13-15:31:14] Epoch: [049][400/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.933 (3.661) Prec@1 57.03 (62.27) Prec@5 80.47 (83.08) + train[2018-10-13-15:32:58] Epoch: [049][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 4.148 (3.674) Prec@1 58.59 (62.04) Prec@5 78.12 (82.91) + train[2018-10-13-15:34:41] Epoch: [049][800/10010] Time 0.53 (0.52) Data 0.00 (0.01) Loss 3.672 (3.676) Prec@1 59.38 (61.92) Prec@5 87.50 (82.90) + train[2018-10-13-15:36:25] Epoch: [049][1000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.761 (3.676) Prec@1 61.72 (61.86) Prec@5 82.81 (82.96) + train[2018-10-13-15:38:09] Epoch: [049][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.637 (3.680) Prec@1 59.38 (61.76) Prec@5 81.25 (82.90) + train[2018-10-13-15:39:52] Epoch: [049][1400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.841 (3.681) Prec@1 56.25 (61.73) Prec@5 81.25 (82.90) + train[2018-10-13-15:41:36] Epoch: [049][1600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.737 (3.682) Prec@1 59.38 (61.72) Prec@5 86.72 (82.90) + train[2018-10-13-15:43:20] Epoch: [049][1800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.936 (3.683) Prec@1 59.38 (61.67) Prec@5 81.25 (82.87) + train[2018-10-13-15:45:04] Epoch: [049][2000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.707 (3.685) Prec@1 57.03 (61.66) Prec@5 80.47 (82.84) + train[2018-10-13-15:46:48] Epoch: [049][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.439 (3.685) Prec@1 63.28 (61.65) Prec@5 82.81 (82.84) + train[2018-10-13-15:48:32] Epoch: [049][2400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.626 (3.685) Prec@1 64.84 (61.63) Prec@5 82.81 (82.85) + train[2018-10-13-15:50:15] Epoch: [049][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.606 (3.687) Prec@1 60.16 (61.60) Prec@5 83.59 (82.82) + train[2018-10-13-15:51:59] Epoch: [049][2800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.019 (3.690) Prec@1 63.28 (61.57) Prec@5 73.44 (82.79) + train[2018-10-13-15:53:43] Epoch: [049][3000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.319 (3.691) Prec@1 67.97 (61.54) Prec@5 89.84 (82.77) + train[2018-10-13-15:55:27] Epoch: [049][3200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.860 (3.692) Prec@1 61.72 (61.52) Prec@5 79.69 (82.74) + train[2018-10-13-15:57:11] Epoch: [049][3400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.564 (3.693) Prec@1 64.06 (61.51) Prec@5 83.59 (82.73) + train[2018-10-13-15:58:55] Epoch: [049][3600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.742 (3.694) Prec@1 63.28 (61.49) Prec@5 82.03 (82.73) + train[2018-10-13-16:00:40] Epoch: [049][3800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.017 (3.695) Prec@1 55.47 (61.46) Prec@5 81.25 (82.71) + train[2018-10-13-16:02:24] Epoch: [049][4000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.314 (3.695) Prec@1 64.84 (61.45) Prec@5 90.62 (82.70) + train[2018-10-13-16:04:08] Epoch: [049][4200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.028 (3.697) Prec@1 50.00 (61.41) Prec@5 80.47 (82.68) + train[2018-10-13-16:05:52] Epoch: [049][4400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.875 (3.698) Prec@1 57.03 (61.41) Prec@5 79.69 (82.67) + train[2018-10-13-16:07:36] Epoch: [049][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.774 (3.699) Prec@1 57.81 (61.39) Prec@5 82.81 (82.66) + train[2018-10-13-16:09:20] Epoch: [049][4800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.986 (3.700) Prec@1 53.12 (61.37) Prec@5 80.47 (82.64) + train[2018-10-13-16:11:05] Epoch: [049][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.594 (3.700) Prec@1 64.84 (61.36) Prec@5 85.16 (82.64) + train[2018-10-13-16:12:48] Epoch: [049][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.856 (3.701) Prec@1 60.16 (61.36) Prec@5 78.12 (82.62) + train[2018-10-13-16:14:32] Epoch: [049][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.754 (3.701) Prec@1 59.38 (61.34) Prec@5 85.16 (82.62) + train[2018-10-13-16:16:17] Epoch: [049][5600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.718 (3.701) Prec@1 57.81 (61.35) Prec@5 85.16 (82.61) + train[2018-10-13-16:18:01] Epoch: [049][5800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.798 (3.701) Prec@1 59.38 (61.35) Prec@5 77.34 (82.61) + train[2018-10-13-16:19:45] Epoch: [049][6000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.819 (3.702) Prec@1 57.03 (61.34) Prec@5 79.69 (82.61) + train[2018-10-13-16:21:29] Epoch: [049][6200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.957 (3.703) Prec@1 55.47 (61.31) Prec@5 77.34 (82.59) + train[2018-10-13-16:23:13] Epoch: [049][6400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.765 (3.703) Prec@1 58.59 (61.29) Prec@5 78.12 (82.58) + train[2018-10-13-16:24:57] Epoch: [049][6600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.917 (3.704) Prec@1 56.25 (61.29) Prec@5 76.56 (82.57) + train[2018-10-13-16:26:40] Epoch: [049][6800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.775 (3.705) Prec@1 57.81 (61.28) Prec@5 82.03 (82.56) + train[2018-10-13-16:28:24] Epoch: [049][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.499 (3.705) Prec@1 62.50 (61.28) Prec@5 84.38 (82.56) + train[2018-10-13-16:30:08] Epoch: [049][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.475 (3.705) Prec@1 66.41 (61.28) Prec@5 85.94 (82.55) + train[2018-10-13-16:31:52] Epoch: [049][7400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.858 (3.705) Prec@1 61.72 (61.28) Prec@5 76.56 (82.54) + train[2018-10-13-16:33:36] Epoch: [049][7600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.617 (3.707) Prec@1 63.28 (61.26) Prec@5 81.25 (82.53) + train[2018-10-13-16:35:20] Epoch: [049][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.943 (3.707) Prec@1 53.91 (61.24) Prec@5 80.47 (82.52) + train[2018-10-13-16:37:04] Epoch: [049][8000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.670 (3.708) Prec@1 65.62 (61.24) Prec@5 84.38 (82.51) + train[2018-10-13-16:38:47] Epoch: [049][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.858 (3.709) Prec@1 57.03 (61.22) Prec@5 80.47 (82.49) + train[2018-10-13-16:40:31] Epoch: [049][8400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.270 (3.709) Prec@1 53.91 (61.22) Prec@5 74.22 (82.48) + train[2018-10-13-16:42:15] Epoch: [049][8600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.626 (3.710) Prec@1 62.50 (61.21) Prec@5 85.16 (82.48) + train[2018-10-13-16:43:59] Epoch: [049][8800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.591 (3.710) Prec@1 64.06 (61.21) Prec@5 84.38 (82.48) + train[2018-10-13-16:45:43] Epoch: [049][9000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.697 (3.710) Prec@1 61.72 (61.21) Prec@5 81.25 (82.47) + train[2018-10-13-16:47:27] Epoch: [049][9200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.557 (3.711) Prec@1 64.06 (61.20) Prec@5 82.03 (82.47) + train[2018-10-13-16:49:12] Epoch: [049][9400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.828 (3.712) Prec@1 60.94 (61.18) Prec@5 80.47 (82.46) + train[2018-10-13-16:50:55] Epoch: [049][9600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.942 (3.712) Prec@1 56.25 (61.17) Prec@5 78.12 (82.46) + train[2018-10-13-16:52:40] Epoch: [049][9800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.493 (3.712) Prec@1 65.62 (61.16) Prec@5 84.38 (82.45) + train[2018-10-13-16:54:23] Epoch: [049][10000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.651 (3.713) Prec@1 59.38 (61.15) Prec@5 87.50 (82.44) + train[2018-10-13-16:54:27] Epoch: [049][10009/10010] Time 0.21 (0.52) Data 0.00 (0.00) Loss 4.469 (3.713) Prec@1 46.67 (61.14) Prec@5 66.67 (82.44) +[2018-10-13-16:54:28] **train** Prec@1 61.14 Prec@5 82.44 Error@1 38.86 Error@5 17.56 Loss:3.713 + test [2018-10-13-16:54:31] Epoch: [049][000/391] Time 3.55 (3.55) Data 3.41 (3.41) Loss 0.864 (0.864) Prec@1 82.03 (82.03) Prec@5 92.97 (92.97) + test [2018-10-13-16:54:59] Epoch: [049][200/391] Time 0.14 (0.16) Data 0.00 (0.03) Loss 1.780 (1.294) Prec@1 53.91 (69.35) Prec@5 85.16 (90.17) + test [2018-10-13-16:55:24] Epoch: [049][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.751 (1.503) Prec@1 33.75 (65.40) Prec@5 73.75 (86.92) +[2018-10-13-16:55:24] **test** Prec@1 65.40 Prec@5 86.92 Error@1 34.60 Error@5 13.08 Loss:1.503 +----> Best Accuracy : Acc@1=65.54, Acc@5=86.62, Error@1=34.46, Error@5=13.38 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-13-16:55:24] [Epoch=050/250] [Need: 292:21:30] LR=0.0218 ~ 0.0218, Batch=128 + train[2018-10-13-16:55:28] Epoch: [050][000/10010] Time 4.38 (4.38) Data 3.80 (3.80) Loss 3.698 (3.698) Prec@1 64.06 (64.06) Prec@5 80.47 (80.47) + train[2018-10-13-16:57:13] Epoch: [050][200/10010] Time 0.51 (0.54) Data 0.00 (0.02) Loss 3.823 (3.685) Prec@1 60.94 (61.99) Prec@5 82.81 (82.77) + train[2018-10-13-16:58:57] Epoch: [050][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.536 (3.655) Prec@1 67.19 (62.37) Prec@5 85.94 (83.12) + train[2018-10-13-17:00:40] Epoch: [050][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.500 (3.655) Prec@1 66.41 (62.27) Prec@5 84.38 (83.18) + train[2018-10-13-17:02:24] Epoch: [050][800/10010] Time 0.54 (0.52) Data 0.00 (0.01) Loss 3.751 (3.668) Prec@1 60.94 (61.98) Prec@5 80.47 (83.05) + train[2018-10-13-17:04:07] Epoch: [050][1000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.860 (3.669) Prec@1 60.94 (61.93) Prec@5 80.47 (82.98) + train[2018-10-13-17:05:51] Epoch: [050][1200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.131 (3.670) Prec@1 49.22 (61.93) Prec@5 75.00 (82.95) + train[2018-10-13-17:07:35] Epoch: [050][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.494 (3.668) Prec@1 63.28 (61.94) Prec@5 85.94 (82.99) + train[2018-10-13-17:09:19] Epoch: [050][1600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.892 (3.669) Prec@1 58.59 (61.91) Prec@5 79.69 (83.00) + train[2018-10-13-17:11:03] Epoch: [050][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.701 (3.669) Prec@1 64.06 (61.86) Prec@5 79.69 (82.98) + train[2018-10-13-17:12:46] Epoch: [050][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.497 (3.669) Prec@1 63.28 (61.86) Prec@5 88.28 (82.98) + train[2018-10-13-17:14:29] Epoch: [050][2200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.698 (3.669) Prec@1 62.50 (61.88) Prec@5 82.81 (82.99) + train[2018-10-13-17:16:13] Epoch: [050][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.674 (3.669) Prec@1 65.62 (61.88) Prec@5 83.59 (83.00) + train[2018-10-13-17:17:57] Epoch: [050][2600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.813 (3.672) Prec@1 57.81 (61.83) Prec@5 79.69 (82.96) + train[2018-10-13-17:19:41] Epoch: [050][2800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.891 (3.671) Prec@1 58.59 (61.83) Prec@5 80.47 (82.96) + train[2018-10-13-17:21:25] Epoch: [050][3000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.774 (3.672) Prec@1 60.16 (61.81) Prec@5 82.03 (82.95) + train[2018-10-13-17:23:08] Epoch: [050][3200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.403 (3.675) Prec@1 67.97 (61.79) Prec@5 83.59 (82.93) + train[2018-10-13-17:24:52] Epoch: [050][3400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.892 (3.675) Prec@1 62.50 (61.79) Prec@5 82.03 (82.93) + train[2018-10-13-17:26:35] Epoch: [050][3600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.789 (3.676) Prec@1 60.94 (61.78) Prec@5 83.59 (82.92) + train[2018-10-13-17:28:19] Epoch: [050][3800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.512 (3.678) Prec@1 65.62 (61.75) Prec@5 84.38 (82.88) + train[2018-10-13-17:30:03] Epoch: [050][4000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.808 (3.680) Prec@1 56.25 (61.71) Prec@5 82.03 (82.85) + train[2018-10-13-17:31:47] Epoch: [050][4200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.791 (3.682) Prec@1 53.91 (61.66) Prec@5 83.59 (82.84) + train[2018-10-13-17:33:31] Epoch: [050][4400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.547 (3.683) Prec@1 62.50 (61.66) Prec@5 88.28 (82.83) + train[2018-10-13-17:35:14] Epoch: [050][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.796 (3.684) Prec@1 57.03 (61.64) Prec@5 80.47 (82.80) + train[2018-10-13-17:36:59] Epoch: [050][4800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.930 (3.685) Prec@1 61.72 (61.61) Prec@5 84.38 (82.81) + train[2018-10-13-17:38:43] Epoch: [050][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.848 (3.685) Prec@1 60.94 (61.61) Prec@5 81.25 (82.81) + train[2018-10-13-17:40:27] Epoch: [050][5200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.729 (3.686) Prec@1 62.50 (61.59) Prec@5 83.59 (82.80) + train[2018-10-13-17:42:11] Epoch: [050][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.405 (3.685) Prec@1 64.84 (61.60) Prec@5 88.28 (82.81) + train[2018-10-13-17:43:55] Epoch: [050][5600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.806 (3.686) Prec@1 55.47 (61.59) Prec@5 82.03 (82.80) + train[2018-10-13-17:45:39] Epoch: [050][5800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.637 (3.687) Prec@1 66.41 (61.57) Prec@5 82.81 (82.79) + train[2018-10-13-17:47:23] Epoch: [050][6000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.503 (3.687) Prec@1 70.31 (61.56) Prec@5 84.38 (82.78) + train[2018-10-13-17:49:06] Epoch: [050][6200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.736 (3.687) Prec@1 56.25 (61.56) Prec@5 81.25 (82.78) + train[2018-10-13-17:50:51] Epoch: [050][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.529 (3.687) Prec@1 66.41 (61.55) Prec@5 85.16 (82.78) + train[2018-10-13-17:52:34] Epoch: [050][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.819 (3.688) Prec@1 58.59 (61.54) Prec@5 81.25 (82.77) + train[2018-10-13-17:54:17] Epoch: [050][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.391 (3.688) Prec@1 67.19 (61.54) Prec@5 86.72 (82.77) + train[2018-10-13-17:56:01] Epoch: [050][7000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.680 (3.689) Prec@1 63.28 (61.53) Prec@5 82.03 (82.77) + train[2018-10-13-17:57:46] Epoch: [050][7200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.362 (3.689) Prec@1 66.41 (61.52) Prec@5 85.94 (82.76) + train[2018-10-13-17:59:29] Epoch: [050][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.844 (3.689) Prec@1 57.03 (61.53) Prec@5 81.25 (82.75) + train[2018-10-13-18:01:13] Epoch: [050][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.683 (3.691) Prec@1 60.16 (61.51) Prec@5 82.81 (82.73) + train[2018-10-13-18:02:57] Epoch: [050][7800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.750 (3.692) Prec@1 61.72 (61.48) Prec@5 78.91 (82.72) + train[2018-10-13-18:04:41] Epoch: [050][8000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.671 (3.692) Prec@1 61.72 (61.48) Prec@5 82.81 (82.72) + train[2018-10-13-18:06:25] Epoch: [050][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.747 (3.693) Prec@1 57.03 (61.47) Prec@5 84.38 (82.71) + train[2018-10-13-18:08:09] Epoch: [050][8400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.842 (3.693) Prec@1 60.94 (61.46) Prec@5 78.91 (82.70) + train[2018-10-13-18:09:53] Epoch: [050][8600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.434 (3.693) Prec@1 66.41 (61.46) Prec@5 89.84 (82.70) + train[2018-10-13-18:11:36] Epoch: [050][8800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.522 (3.693) Prec@1 67.97 (61.45) Prec@5 86.72 (82.70) + train[2018-10-13-18:13:20] Epoch: [050][9000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.702 (3.694) Prec@1 58.59 (61.44) Prec@5 85.16 (82.70) + train[2018-10-13-18:15:04] Epoch: [050][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.021 (3.695) Prec@1 57.81 (61.43) Prec@5 80.47 (82.68) + train[2018-10-13-18:16:48] Epoch: [050][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.545 (3.695) Prec@1 67.97 (61.42) Prec@5 84.38 (82.68) + train[2018-10-13-18:18:31] Epoch: [050][9600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.657 (3.695) Prec@1 59.38 (61.43) Prec@5 84.38 (82.68) + train[2018-10-13-18:20:15] Epoch: [050][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.603 (3.696) Prec@1 64.84 (61.42) Prec@5 83.59 (82.67) + train[2018-10-13-18:21:59] Epoch: [050][10000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.818 (3.696) Prec@1 55.47 (61.41) Prec@5 78.12 (82.66) + train[2018-10-13-18:22:04] Epoch: [050][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 5.632 (3.696) Prec@1 33.33 (61.41) Prec@5 53.33 (82.66) +[2018-10-13-18:22:04] **train** Prec@1 61.41 Prec@5 82.66 Error@1 38.59 Error@5 17.34 Loss:3.696 + test [2018-10-13-18:22:08] Epoch: [050][000/391] Time 4.15 (4.15) Data 4.01 (4.01) Loss 0.868 (0.868) Prec@1 79.69 (79.69) Prec@5 95.31 (95.31) + test [2018-10-13-18:22:35] Epoch: [050][200/391] Time 0.12 (0.16) Data 0.00 (0.03) Loss 1.352 (1.299) Prec@1 68.75 (69.71) Prec@5 91.41 (90.28) + test [2018-10-13-18:23:00] Epoch: [050][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.810 (1.487) Prec@1 32.50 (66.06) Prec@5 73.75 (87.21) +[2018-10-13-18:23:01] **test** Prec@1 66.06 Prec@5 87.21 Error@1 33.94 Error@5 12.79 Loss:1.487 +----> Best Accuracy : Acc@1=66.06, Acc@5=87.21, Error@1=33.94, Error@5=12.79 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-13-18:23:01] [Epoch=051/250] [Need: 290:34:25] LR=0.0212 ~ 0.0212, Batch=128 + train[2018-10-13-18:23:06] Epoch: [051][000/10010] Time 5.54 (5.54) Data 4.99 (4.99) Loss 3.863 (3.863) Prec@1 60.16 (60.16) Prec@5 80.47 (80.47) + train[2018-10-13-18:24:50] Epoch: [051][200/10010] Time 0.51 (0.54) Data 0.00 (0.02) Loss 3.413 (3.647) Prec@1 64.84 (62.40) Prec@5 85.94 (83.31) + train[2018-10-13-18:26:34] Epoch: [051][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.694 (3.651) Prec@1 64.06 (62.40) Prec@5 84.38 (83.23) + train[2018-10-13-18:28:17] Epoch: [051][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.396 (3.653) Prec@1 64.84 (62.24) Prec@5 85.16 (83.24) + train[2018-10-13-18:30:00] Epoch: [051][800/10010] Time 0.50 (0.52) Data 0.00 (0.01) Loss 3.581 (3.659) Prec@1 61.72 (62.14) Prec@5 82.81 (83.13) + train[2018-10-13-18:31:44] Epoch: [051][1000/10010] Time 0.52 (0.52) Data 0.00 (0.01) Loss 3.725 (3.660) Prec@1 63.28 (62.09) Prec@5 81.25 (83.16) + train[2018-10-13-18:33:28] Epoch: [051][1200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.591 (3.660) Prec@1 66.41 (62.12) Prec@5 84.38 (83.13) + train[2018-10-13-18:35:12] Epoch: [051][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.454 (3.658) Prec@1 61.72 (62.13) Prec@5 85.94 (83.13) + train[2018-10-13-18:36:56] Epoch: [051][1600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.394 (3.658) Prec@1 68.75 (62.13) Prec@5 85.16 (83.16) + train[2018-10-13-18:38:40] Epoch: [051][1800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.424 (3.660) Prec@1 64.84 (62.08) Prec@5 85.94 (83.14) + train[2018-10-13-18:40:24] Epoch: [051][2000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.504 (3.659) Prec@1 63.28 (62.05) Prec@5 82.81 (83.15) + train[2018-10-13-18:42:08] Epoch: [051][2200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.524 (3.659) Prec@1 62.50 (62.04) Prec@5 85.16 (83.14) + train[2018-10-13-18:43:53] Epoch: [051][2400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.913 (3.659) Prec@1 57.81 (62.07) Prec@5 81.25 (83.14) + train[2018-10-13-18:45:36] Epoch: [051][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.758 (3.660) Prec@1 60.94 (62.07) Prec@5 83.59 (83.11) + train[2018-10-13-18:47:20] Epoch: [051][2800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.511 (3.661) Prec@1 64.84 (62.05) Prec@5 84.38 (83.10) + train[2018-10-13-18:49:04] Epoch: [051][3000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.318 (3.661) Prec@1 47.66 (62.04) Prec@5 72.66 (83.09) + train[2018-10-13-18:50:48] Epoch: [051][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.225 (3.663) Prec@1 65.62 (62.00) Prec@5 88.28 (83.05) + train[2018-10-13-18:52:32] Epoch: [051][3400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.206 (3.664) Prec@1 57.03 (61.98) Prec@5 77.34 (83.04) + train[2018-10-13-18:54:16] Epoch: [051][3600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.928 (3.665) Prec@1 61.72 (61.94) Prec@5 83.59 (83.03) + train[2018-10-13-18:56:00] Epoch: [051][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.064 (3.665) Prec@1 71.88 (61.95) Prec@5 92.19 (83.03) + train[2018-10-13-18:57:44] Epoch: [051][4000/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 4.286 (3.666) Prec@1 55.47 (61.93) Prec@5 74.22 (83.02) + train[2018-10-13-18:59:28] Epoch: [051][4200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.340 (3.668) Prec@1 70.31 (61.89) Prec@5 87.50 (82.99) + train[2018-10-13-19:01:13] Epoch: [051][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.040 (3.669) Prec@1 56.25 (61.89) Prec@5 81.25 (82.99) + train[2018-10-13-19:02:57] Epoch: [051][4600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.492 (3.669) Prec@1 63.28 (61.89) Prec@5 83.59 (83.00) + train[2018-10-13-19:04:41] Epoch: [051][4800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.000 (3.670) Prec@1 52.34 (61.85) Prec@5 78.12 (82.99) + train[2018-10-13-19:06:25] Epoch: [051][5000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.475 (3.671) Prec@1 63.28 (61.83) Prec@5 85.94 (82.97) + train[2018-10-13-19:08:09] Epoch: [051][5200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.760 (3.672) Prec@1 60.94 (61.82) Prec@5 81.25 (82.96) + train[2018-10-13-19:09:53] Epoch: [051][5400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.423 (3.672) Prec@1 65.62 (61.82) Prec@5 85.16 (82.96) + train[2018-10-13-19:11:38] Epoch: [051][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.895 (3.672) Prec@1 60.16 (61.81) Prec@5 82.03 (82.96) + train[2018-10-13-19:13:22] Epoch: [051][5800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.856 (3.673) Prec@1 60.94 (61.81) Prec@5 78.12 (82.95) + train[2018-10-13-19:15:06] Epoch: [051][6000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.701 (3.674) Prec@1 63.28 (61.81) Prec@5 81.25 (82.94) + train[2018-10-13-19:16:51] Epoch: [051][6200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.805 (3.674) Prec@1 57.03 (61.80) Prec@5 84.38 (82.94) + train[2018-10-13-19:18:35] Epoch: [051][6400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.761 (3.675) Prec@1 62.50 (61.80) Prec@5 81.25 (82.93) + train[2018-10-13-19:20:19] Epoch: [051][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.645 (3.675) Prec@1 62.50 (61.79) Prec@5 82.81 (82.92) + train[2018-10-13-19:22:03] Epoch: [051][6800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.574 (3.675) Prec@1 59.38 (61.79) Prec@5 85.94 (82.92) + train[2018-10-13-19:23:47] Epoch: [051][7000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.529 (3.676) Prec@1 66.41 (61.77) Prec@5 84.38 (82.91) + train[2018-10-13-19:25:31] Epoch: [051][7200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.799 (3.678) Prec@1 57.81 (61.74) Prec@5 81.25 (82.89) + train[2018-10-13-19:27:15] Epoch: [051][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.618 (3.678) Prec@1 65.62 (61.73) Prec@5 84.38 (82.88) + train[2018-10-13-19:29:00] Epoch: [051][7600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 4.181 (3.678) Prec@1 53.12 (61.71) Prec@5 77.34 (82.88) + train[2018-10-13-19:30:43] Epoch: [051][7800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.737 (3.678) Prec@1 62.50 (61.71) Prec@5 80.47 (82.88) + train[2018-10-13-19:32:27] Epoch: [051][8000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.766 (3.679) Prec@1 58.59 (61.70) Prec@5 85.16 (82.88) + train[2018-10-13-19:34:11] Epoch: [051][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.536 (3.680) Prec@1 67.97 (61.69) Prec@5 81.25 (82.86) + train[2018-10-13-19:35:55] Epoch: [051][8400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.796 (3.680) Prec@1 60.94 (61.69) Prec@5 82.81 (82.86) + train[2018-10-13-19:37:39] Epoch: [051][8600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.538 (3.680) Prec@1 63.28 (61.69) Prec@5 83.59 (82.86) + train[2018-10-13-19:39:23] Epoch: [051][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.068 (3.681) Prec@1 55.47 (61.67) Prec@5 76.56 (82.85) + train[2018-10-13-19:41:08] Epoch: [051][9000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.862 (3.681) Prec@1 60.16 (61.67) Prec@5 80.47 (82.84) + train[2018-10-13-19:42:52] Epoch: [051][9200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.270 (3.683) Prec@1 53.91 (61.65) Prec@5 74.22 (82.82) + train[2018-10-13-19:44:35] Epoch: [051][9400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.487 (3.683) Prec@1 64.06 (61.64) Prec@5 82.03 (82.81) + train[2018-10-13-19:46:20] Epoch: [051][9600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.679 (3.684) Prec@1 64.06 (61.63) Prec@5 80.47 (82.80) + train[2018-10-13-19:48:03] Epoch: [051][9800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.908 (3.685) Prec@1 55.47 (61.62) Prec@5 82.03 (82.79) + train[2018-10-13-19:49:47] Epoch: [051][10000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.673 (3.686) Prec@1 59.38 (61.60) Prec@5 82.03 (82.78) + train[2018-10-13-19:49:52] Epoch: [051][10009/10010] Time 0.21 (0.52) Data 0.00 (0.00) Loss 5.470 (3.686) Prec@1 33.33 (61.60) Prec@5 53.33 (82.78) +[2018-10-13-19:49:52] **train** Prec@1 61.60 Prec@5 82.78 Error@1 38.40 Error@5 17.22 Loss:3.686 + test [2018-10-13-19:49:56] Epoch: [051][000/391] Time 3.93 (3.93) Data 3.79 (3.79) Loss 0.797 (0.797) Prec@1 84.38 (84.38) Prec@5 93.75 (93.75) + test [2018-10-13-19:50:24] Epoch: [051][200/391] Time 0.12 (0.16) Data 0.00 (0.03) Loss 1.771 (1.311) Prec@1 57.81 (69.43) Prec@5 86.72 (89.96) + test [2018-10-13-19:50:50] Epoch: [051][390/391] Time 0.08 (0.15) Data 0.00 (0.02) Loss 2.851 (1.505) Prec@1 33.75 (65.56) Prec@5 76.25 (87.09) +[2018-10-13-19:50:50] **test** Prec@1 65.56 Prec@5 87.09 Error@1 34.44 Error@5 12.91 Loss:1.505 +----> Best Accuracy : Acc@1=66.06, Acc@5=87.21, Error@1=33.94, Error@5=12.79 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-13-19:50:50] [Epoch=052/250] [Need: 289:49:56] LR=0.0205 ~ 0.0205, Batch=128 + train[2018-10-13-19:50:55] Epoch: [052][000/10010] Time 4.91 (4.91) Data 4.30 (4.30) Loss 3.668 (3.668) Prec@1 63.28 (63.28) Prec@5 85.16 (85.16) + train[2018-10-13-19:52:40] Epoch: [052][200/10010] Time 0.55 (0.55) Data 0.00 (0.02) Loss 3.762 (3.643) Prec@1 57.81 (62.49) Prec@5 85.16 (83.31) + train[2018-10-13-19:54:25] Epoch: [052][400/10010] Time 0.56 (0.53) Data 0.00 (0.01) Loss 3.650 (3.654) Prec@1 60.94 (62.28) Prec@5 84.38 (83.13) + train[2018-10-13-19:56:08] Epoch: [052][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.302 (3.642) Prec@1 63.28 (62.39) Prec@5 88.28 (83.26) + train[2018-10-13-19:57:52] Epoch: [052][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.959 (3.644) Prec@1 55.47 (62.36) Prec@5 81.25 (83.25) + train[2018-10-13-19:59:36] Epoch: [052][1000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.481 (3.644) Prec@1 67.19 (62.38) Prec@5 85.94 (83.30) + train[2018-10-13-20:01:20] Epoch: [052][1200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.992 (3.647) Prec@1 53.12 (62.30) Prec@5 78.12 (83.28) + train[2018-10-13-20:03:03] Epoch: [052][1400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.125 (3.648) Prec@1 53.12 (62.24) Prec@5 77.34 (83.26) + train[2018-10-13-20:04:48] Epoch: [052][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.467 (3.649) Prec@1 69.53 (62.23) Prec@5 87.50 (83.23) + train[2018-10-13-20:06:31] Epoch: [052][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.311 (3.646) Prec@1 71.09 (62.31) Prec@5 85.94 (83.27) + train[2018-10-13-20:08:15] Epoch: [052][2000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.619 (3.649) Prec@1 65.62 (62.28) Prec@5 84.38 (83.24) + train[2018-10-13-20:09:58] Epoch: [052][2200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.404 (3.651) Prec@1 64.06 (62.24) Prec@5 88.28 (83.23) + train[2018-10-13-20:11:41] Epoch: [052][2400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.808 (3.651) Prec@1 58.59 (62.24) Prec@5 85.94 (83.20) + train[2018-10-13-20:13:25] Epoch: [052][2600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.357 (3.653) Prec@1 65.62 (62.21) Prec@5 87.50 (83.18) + train[2018-10-13-20:15:09] Epoch: [052][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.783 (3.653) Prec@1 63.28 (62.17) Prec@5 84.38 (83.16) + train[2018-10-13-20:16:53] Epoch: [052][3000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.895 (3.654) Prec@1 54.69 (62.18) Prec@5 77.34 (83.15) + train[2018-10-13-20:18:37] Epoch: [052][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.807 (3.655) Prec@1 55.47 (62.17) Prec@5 85.16 (83.15) + train[2018-10-13-20:20:20] Epoch: [052][3400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.894 (3.657) Prec@1 53.91 (62.13) Prec@5 80.47 (83.13) + train[2018-10-13-20:22:05] Epoch: [052][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.817 (3.659) Prec@1 58.59 (62.11) Prec@5 82.03 (83.10) + train[2018-10-13-20:23:48] Epoch: [052][3800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.669 (3.659) Prec@1 60.16 (62.10) Prec@5 84.38 (83.10) + train[2018-10-13-20:25:32] Epoch: [052][4000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.949 (3.660) Prec@1 53.91 (62.07) Prec@5 76.56 (83.09) + train[2018-10-13-20:27:16] Epoch: [052][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.738 (3.659) Prec@1 64.06 (62.08) Prec@5 82.03 (83.10) + train[2018-10-13-20:28:59] Epoch: [052][4400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 4.071 (3.659) Prec@1 53.91 (62.07) Prec@5 76.56 (83.11) + train[2018-10-13-20:30:43] Epoch: [052][4600/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.977 (3.659) Prec@1 57.81 (62.07) Prec@5 78.12 (83.11) + train[2018-10-13-20:32:27] Epoch: [052][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.493 (3.659) Prec@1 63.28 (62.07) Prec@5 85.16 (83.13) + train[2018-10-13-20:34:11] Epoch: [052][5000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.478 (3.659) Prec@1 64.06 (62.06) Prec@5 87.50 (83.13) + train[2018-10-13-20:35:54] Epoch: [052][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.508 (3.660) Prec@1 64.06 (62.04) Prec@5 85.16 (83.12) + train[2018-10-13-20:37:38] Epoch: [052][5400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.905 (3.661) Prec@1 61.72 (62.01) Prec@5 77.34 (83.11) + train[2018-10-13-20:39:22] Epoch: [052][5600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.442 (3.662) Prec@1 58.59 (62.00) Prec@5 87.50 (83.10) + train[2018-10-13-20:41:06] Epoch: [052][5800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.444 (3.663) Prec@1 62.50 (61.98) Prec@5 87.50 (83.10) + train[2018-10-13-20:42:50] Epoch: [052][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.795 (3.663) Prec@1 62.50 (61.98) Prec@5 82.03 (83.08) + train[2018-10-13-20:44:33] Epoch: [052][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.451 (3.664) Prec@1 63.28 (61.96) Prec@5 85.16 (83.06) + train[2018-10-13-20:46:17] Epoch: [052][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.720 (3.664) Prec@1 55.47 (61.96) Prec@5 86.72 (83.06) + train[2018-10-13-20:48:01] Epoch: [052][6600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.516 (3.665) Prec@1 60.94 (61.95) Prec@5 85.94 (83.05) + train[2018-10-13-20:49:45] Epoch: [052][6800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.718 (3.666) Prec@1 57.03 (61.93) Prec@5 85.16 (83.03) + train[2018-10-13-20:51:30] Epoch: [052][7000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.321 (3.666) Prec@1 64.06 (61.91) Prec@5 87.50 (83.03) + train[2018-10-13-20:53:13] Epoch: [052][7200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.601 (3.666) Prec@1 64.84 (61.91) Prec@5 82.81 (83.02) + train[2018-10-13-20:54:57] Epoch: [052][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.462 (3.667) Prec@1 69.53 (61.91) Prec@5 84.38 (83.02) + train[2018-10-13-20:56:41] Epoch: [052][7600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.813 (3.667) Prec@1 55.47 (61.90) Prec@5 84.38 (83.01) + train[2018-10-13-20:58:25] Epoch: [052][7800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.693 (3.668) Prec@1 58.59 (61.89) Prec@5 85.16 (83.01) + train[2018-10-13-21:00:09] Epoch: [052][8000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.561 (3.668) Prec@1 61.72 (61.89) Prec@5 84.38 (83.01) + train[2018-10-13-21:01:52] Epoch: [052][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.728 (3.668) Prec@1 65.62 (61.88) Prec@5 80.47 (83.00) + train[2018-10-13-21:03:36] Epoch: [052][8400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.606 (3.669) Prec@1 67.19 (61.87) Prec@5 82.81 (82.99) + train[2018-10-13-21:05:20] Epoch: [052][8600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.522 (3.670) Prec@1 68.75 (61.85) Prec@5 86.72 (82.97) + train[2018-10-13-21:07:04] Epoch: [052][8800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.412 (3.671) Prec@1 70.31 (61.84) Prec@5 82.81 (82.96) + train[2018-10-13-21:08:47] Epoch: [052][9000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.486 (3.671) Prec@1 65.62 (61.83) Prec@5 84.38 (82.95) + train[2018-10-13-21:10:31] Epoch: [052][9200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.809 (3.672) Prec@1 60.94 (61.82) Prec@5 81.25 (82.95) + train[2018-10-13-21:12:15] Epoch: [052][9400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.583 (3.672) Prec@1 57.03 (61.82) Prec@5 80.47 (82.94) + train[2018-10-13-21:13:58] Epoch: [052][9600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.207 (3.673) Prec@1 67.19 (61.80) Prec@5 87.50 (82.93) + train[2018-10-13-21:15:41] Epoch: [052][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.697 (3.673) Prec@1 58.59 (61.80) Prec@5 82.81 (82.93) + train[2018-10-13-21:17:24] Epoch: [052][10000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.435 (3.673) Prec@1 68.75 (61.79) Prec@5 87.50 (82.93) + train[2018-10-13-21:17:28] Epoch: [052][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 5.498 (3.673) Prec@1 33.33 (61.78) Prec@5 53.33 (82.93) +[2018-10-13-21:17:28] **train** Prec@1 61.78 Prec@5 82.93 Error@1 38.22 Error@5 17.07 Loss:3.673 + test [2018-10-13-21:17:32] Epoch: [052][000/391] Time 4.19 (4.19) Data 4.05 (4.05) Loss 0.981 (0.981) Prec@1 78.12 (78.12) Prec@5 89.84 (89.84) + test [2018-10-13-21:18:00] Epoch: [052][200/391] Time 0.16 (0.16) Data 0.01 (0.02) Loss 1.554 (1.272) Prec@1 56.25 (70.16) Prec@5 89.06 (90.30) + test [2018-10-13-21:18:26] Epoch: [052][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.701 (1.469) Prec@1 33.75 (66.25) Prec@5 73.75 (87.36) +[2018-10-13-21:18:26] **test** Prec@1 66.25 Prec@5 87.36 Error@1 33.75 Error@5 12.64 Loss:1.469 +----> Best Accuracy : Acc@1=66.25, Acc@5=87.36, Error@1=33.75, Error@5=12.64 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-13-21:18:26] [Epoch=053/250] [Need: 287:35:17] LR=0.0199 ~ 0.0199, Batch=128 + train[2018-10-13-21:18:31] Epoch: [053][000/10010] Time 4.89 (4.89) Data 4.25 (4.25) Loss 3.757 (3.757) Prec@1 62.50 (62.50) Prec@5 86.72 (86.72) + train[2018-10-13-21:20:15] Epoch: [053][200/10010] Time 0.49 (0.54) Data 0.00 (0.02) Loss 3.488 (3.642) Prec@1 62.50 (62.29) Prec@5 85.94 (83.55) + train[2018-10-13-21:21:59] Epoch: [053][400/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.840 (3.640) Prec@1 57.03 (62.47) Prec@5 84.38 (83.53) + train[2018-10-13-21:23:42] Epoch: [053][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.476 (3.640) Prec@1 63.28 (62.44) Prec@5 83.59 (83.48) + train[2018-10-13-21:25:26] Epoch: [053][800/10010] Time 0.50 (0.52) Data 0.00 (0.01) Loss 3.518 (3.638) Prec@1 63.28 (62.43) Prec@5 84.38 (83.43) + train[2018-10-13-21:27:09] Epoch: [053][1000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.510 (3.640) Prec@1 64.84 (62.40) Prec@5 83.59 (83.40) + train[2018-10-13-21:28:53] Epoch: [053][1200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.330 (3.640) Prec@1 65.62 (62.35) Prec@5 89.06 (83.40) + train[2018-10-13-21:30:36] Epoch: [053][1400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.452 (3.642) Prec@1 64.06 (62.33) Prec@5 87.50 (83.39) + train[2018-10-13-21:32:20] Epoch: [053][1600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.310 (3.642) Prec@1 68.75 (62.32) Prec@5 85.94 (83.37) + train[2018-10-13-21:34:05] Epoch: [053][1800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.469 (3.639) Prec@1 61.72 (62.39) Prec@5 88.28 (83.39) + train[2018-10-13-21:35:48] Epoch: [053][2000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.947 (3.639) Prec@1 60.94 (62.38) Prec@5 78.12 (83.40) + train[2018-10-13-21:37:32] Epoch: [053][2200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.845 (3.639) Prec@1 60.94 (62.40) Prec@5 81.25 (83.38) + train[2018-10-13-21:39:16] Epoch: [053][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.689 (3.639) Prec@1 57.81 (62.41) Prec@5 82.81 (83.40) + train[2018-10-13-21:40:59] Epoch: [053][2600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.509 (3.639) Prec@1 67.97 (62.41) Prec@5 84.38 (83.37) + train[2018-10-13-21:42:43] Epoch: [053][2800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.564 (3.640) Prec@1 63.28 (62.41) Prec@5 82.81 (83.33) + train[2018-10-13-21:44:28] Epoch: [053][3000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.618 (3.641) Prec@1 62.50 (62.38) Prec@5 82.81 (83.34) + train[2018-10-13-21:46:11] Epoch: [053][3200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.616 (3.642) Prec@1 67.19 (62.35) Prec@5 82.81 (83.31) + train[2018-10-13-21:47:55] Epoch: [053][3400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.694 (3.642) Prec@1 61.72 (62.35) Prec@5 82.81 (83.31) + train[2018-10-13-21:49:39] Epoch: [053][3600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.668 (3.642) Prec@1 66.41 (62.34) Prec@5 81.25 (83.32) + train[2018-10-13-21:51:23] Epoch: [053][3800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.719 (3.643) Prec@1 61.72 (62.32) Prec@5 80.47 (83.31) + train[2018-10-13-21:53:07] Epoch: [053][4000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.622 (3.645) Prec@1 61.72 (62.30) Prec@5 84.38 (83.29) + train[2018-10-13-21:54:51] Epoch: [053][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.543 (3.646) Prec@1 62.50 (62.29) Prec@5 84.38 (83.28) + train[2018-10-13-21:56:34] Epoch: [053][4400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.849 (3.648) Prec@1 60.16 (62.26) Prec@5 79.69 (83.24) + train[2018-10-13-21:58:18] Epoch: [053][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.121 (3.648) Prec@1 56.25 (62.23) Prec@5 75.78 (83.24) + train[2018-10-13-22:00:02] Epoch: [053][4800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.945 (3.650) Prec@1 60.94 (62.21) Prec@5 78.91 (83.22) + train[2018-10-13-22:01:46] Epoch: [053][5000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.754 (3.650) Prec@1 61.72 (62.21) Prec@5 79.69 (83.22) + train[2018-10-13-22:03:29] Epoch: [053][5200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.734 (3.651) Prec@1 54.69 (62.18) Prec@5 84.38 (83.21) + train[2018-10-13-22:05:13] Epoch: [053][5400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.656 (3.650) Prec@1 58.59 (62.19) Prec@5 84.38 (83.21) + train[2018-10-13-22:06:56] Epoch: [053][5600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.853 (3.651) Prec@1 59.38 (62.18) Prec@5 84.38 (83.20) + train[2018-10-13-22:08:40] Epoch: [053][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.621 (3.651) Prec@1 62.50 (62.17) Prec@5 82.81 (83.19) + train[2018-10-13-22:10:24] Epoch: [053][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.682 (3.652) Prec@1 61.72 (62.16) Prec@5 80.47 (83.18) + train[2018-10-13-22:12:07] Epoch: [053][6200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.426 (3.652) Prec@1 67.19 (62.16) Prec@5 85.94 (83.18) + train[2018-10-13-22:13:51] Epoch: [053][6400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.942 (3.653) Prec@1 57.03 (62.13) Prec@5 82.81 (83.17) + train[2018-10-13-22:15:35] Epoch: [053][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.701 (3.653) Prec@1 59.38 (62.13) Prec@5 80.47 (83.18) + train[2018-10-13-22:17:19] Epoch: [053][6800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.686 (3.652) Prec@1 60.94 (62.14) Prec@5 82.03 (83.18) + train[2018-10-13-22:19:03] Epoch: [053][7000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.610 (3.653) Prec@1 57.03 (62.14) Prec@5 82.81 (83.17) + train[2018-10-13-22:20:47] Epoch: [053][7200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.705 (3.654) Prec@1 60.16 (62.11) Prec@5 84.38 (83.17) + train[2018-10-13-22:22:30] Epoch: [053][7400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.579 (3.656) Prec@1 61.72 (62.09) Prec@5 82.81 (83.15) + train[2018-10-13-22:24:14] Epoch: [053][7600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.893 (3.657) Prec@1 57.03 (62.07) Prec@5 78.91 (83.14) + train[2018-10-13-22:25:58] Epoch: [053][7800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.298 (3.657) Prec@1 70.31 (62.07) Prec@5 89.06 (83.13) + train[2018-10-13-22:27:42] Epoch: [053][8000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.716 (3.657) Prec@1 64.84 (62.06) Prec@5 86.72 (83.13) + train[2018-10-13-22:29:26] Epoch: [053][8200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.770 (3.658) Prec@1 62.50 (62.05) Prec@5 82.03 (83.12) + train[2018-10-13-22:31:09] Epoch: [053][8400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.506 (3.660) Prec@1 68.75 (62.03) Prec@5 84.38 (83.10) + train[2018-10-13-22:32:54] Epoch: [053][8600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.658 (3.659) Prec@1 64.84 (62.03) Prec@5 82.03 (83.10) + train[2018-10-13-22:34:37] Epoch: [053][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.563 (3.659) Prec@1 68.75 (62.03) Prec@5 84.38 (83.11) + train[2018-10-13-22:36:21] Epoch: [053][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.709 (3.660) Prec@1 58.59 (62.02) Prec@5 82.03 (83.11) + train[2018-10-13-22:38:05] Epoch: [053][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.284 (3.660) Prec@1 67.97 (62.01) Prec@5 85.94 (83.11) + train[2018-10-13-22:39:49] Epoch: [053][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.552 (3.660) Prec@1 64.06 (62.02) Prec@5 84.38 (83.11) + train[2018-10-13-22:41:33] Epoch: [053][9600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.587 (3.660) Prec@1 64.06 (62.01) Prec@5 82.81 (83.10) + train[2018-10-13-22:43:16] Epoch: [053][9800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.742 (3.661) Prec@1 57.81 (62.00) Prec@5 84.38 (83.09) + train[2018-10-13-22:45:00] Epoch: [053][10000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.798 (3.661) Prec@1 57.81 (61.99) Prec@5 78.12 (83.08) + train[2018-10-13-22:45:04] Epoch: [053][10009/10010] Time 0.23 (0.52) Data 0.00 (0.00) Loss 3.367 (3.661) Prec@1 66.67 (61.99) Prec@5 86.67 (83.08) +[2018-10-13-22:45:05] **train** Prec@1 61.99 Prec@5 83.08 Error@1 38.01 Error@5 16.92 Loss:3.661 + test [2018-10-13-22:45:08] Epoch: [053][000/391] Time 3.80 (3.80) Data 3.65 (3.65) Loss 0.971 (0.971) Prec@1 77.34 (77.34) Prec@5 93.75 (93.75) + test [2018-10-13-22:45:36] Epoch: [053][200/391] Time 0.12 (0.16) Data 0.00 (0.02) Loss 1.436 (1.260) Prec@1 64.84 (70.19) Prec@5 89.84 (90.40) + test [2018-10-13-22:46:01] Epoch: [053][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.632 (1.448) Prec@1 37.50 (66.61) Prec@5 73.75 (87.54) +[2018-10-13-22:46:01] **test** Prec@1 66.61 Prec@5 87.54 Error@1 33.39 Error@5 12.46 Loss:1.448 +----> Best Accuracy : Acc@1=66.61, Acc@5=87.54, Error@1=33.39, Error@5=12.46 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-13-22:46:01] [Epoch=054/250] [Need: 286:08:21] LR=0.0193 ~ 0.0193, Batch=128 + train[2018-10-13-22:46:06] Epoch: [054][000/10010] Time 4.95 (4.95) Data 4.36 (4.36) Loss 3.326 (3.326) Prec@1 70.31 (70.31) Prec@5 86.72 (86.72) + train[2018-10-13-22:47:52] Epoch: [054][200/10010] Time 0.53 (0.55) Data 0.00 (0.02) Loss 3.651 (3.589) Prec@1 60.94 (63.20) Prec@5 83.59 (83.94) + train[2018-10-13-22:49:37] Epoch: [054][400/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 3.846 (3.595) Prec@1 63.28 (63.08) Prec@5 82.03 (83.99) + train[2018-10-13-22:51:21] Epoch: [054][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 4.276 (3.605) Prec@1 48.44 (63.03) Prec@5 75.00 (83.85) + train[2018-10-13-22:53:06] Epoch: [054][800/10010] Time 0.56 (0.53) Data 0.00 (0.01) Loss 3.709 (3.613) Prec@1 62.50 (62.90) Prec@5 81.25 (83.72) + train[2018-10-13-22:54:51] Epoch: [054][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.779 (3.611) Prec@1 60.16 (62.92) Prec@5 84.38 (83.73) + train[2018-10-13-22:56:36] Epoch: [054][1200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.445 (3.615) Prec@1 66.41 (62.81) Prec@5 86.72 (83.67) + train[2018-10-13-22:58:21] Epoch: [054][1400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.342 (3.616) Prec@1 64.84 (62.77) Prec@5 87.50 (83.64) + train[2018-10-13-23:00:06] Epoch: [054][1600/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.939 (3.619) Prec@1 57.03 (62.70) Prec@5 80.47 (83.61) + train[2018-10-13-23:01:51] Epoch: [054][1800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.847 (3.622) Prec@1 64.84 (62.65) Prec@5 82.81 (83.58) + train[2018-10-13-23:03:35] Epoch: [054][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.733 (3.623) Prec@1 63.28 (62.64) Prec@5 85.16 (83.57) + train[2018-10-13-23:05:20] Epoch: [054][2200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.481 (3.623) Prec@1 65.62 (62.63) Prec@5 87.50 (83.59) + train[2018-10-13-23:07:05] Epoch: [054][2400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.621 (3.626) Prec@1 67.19 (62.60) Prec@5 84.38 (83.58) + train[2018-10-13-23:08:52] Epoch: [054][2600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.319 (3.625) Prec@1 65.62 (62.59) Prec@5 89.84 (83.59) + train[2018-10-13-23:10:37] Epoch: [054][2800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.461 (3.626) Prec@1 71.09 (62.59) Prec@5 85.94 (83.58) + train[2018-10-13-23:12:23] Epoch: [054][3000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.753 (3.627) Prec@1 61.72 (62.57) Prec@5 82.81 (83.56) + train[2018-10-13-23:14:09] Epoch: [054][3200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.582 (3.627) Prec@1 64.84 (62.56) Prec@5 80.47 (83.55) + train[2018-10-13-23:15:54] Epoch: [054][3400/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.660 (3.627) Prec@1 64.06 (62.56) Prec@5 83.59 (83.54) + train[2018-10-13-23:17:40] Epoch: [054][3600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.699 (3.628) Prec@1 60.94 (62.54) Prec@5 83.59 (83.53) + train[2018-10-13-23:19:25] Epoch: [054][3800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.531 (3.630) Prec@1 64.84 (62.52) Prec@5 87.50 (83.50) + train[2018-10-13-23:21:09] Epoch: [054][4000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.302 (3.629) Prec@1 66.41 (62.53) Prec@5 86.72 (83.49) + train[2018-10-13-23:22:55] Epoch: [054][4200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.507 (3.630) Prec@1 67.19 (62.52) Prec@5 84.38 (83.48) + train[2018-10-13-23:24:40] Epoch: [054][4400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.936 (3.630) Prec@1 56.25 (62.52) Prec@5 78.91 (83.46) + train[2018-10-13-23:26:25] Epoch: [054][4600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.696 (3.630) Prec@1 60.16 (62.53) Prec@5 84.38 (83.47) + train[2018-10-13-23:28:09] Epoch: [054][4800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.782 (3.632) Prec@1 69.53 (62.51) Prec@5 82.03 (83.45) + train[2018-10-13-23:29:54] Epoch: [054][5000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.880 (3.632) Prec@1 62.50 (62.50) Prec@5 80.47 (83.45) + train[2018-10-13-23:31:39] Epoch: [054][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.922 (3.634) Prec@1 57.81 (62.47) Prec@5 83.59 (83.43) + train[2018-10-13-23:33:23] Epoch: [054][5400/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.670 (3.634) Prec@1 61.72 (62.46) Prec@5 81.25 (83.44) + train[2018-10-13-23:35:08] Epoch: [054][5600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.615 (3.635) Prec@1 60.16 (62.46) Prec@5 84.38 (83.43) + train[2018-10-13-23:36:52] Epoch: [054][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.622 (3.635) Prec@1 61.72 (62.44) Prec@5 83.59 (83.41) + train[2018-10-13-23:38:37] Epoch: [054][6000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.669 (3.637) Prec@1 60.16 (62.41) Prec@5 82.03 (83.39) + train[2018-10-13-23:40:21] Epoch: [054][6200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.509 (3.638) Prec@1 60.94 (62.40) Prec@5 85.94 (83.38) + train[2018-10-13-23:42:05] Epoch: [054][6400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.614 (3.639) Prec@1 61.72 (62.39) Prec@5 85.94 (83.37) + train[2018-10-13-23:43:51] Epoch: [054][6600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.578 (3.640) Prec@1 67.19 (62.37) Prec@5 82.03 (83.34) + train[2018-10-13-23:45:35] Epoch: [054][6800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.589 (3.640) Prec@1 61.72 (62.36) Prec@5 85.94 (83.34) + train[2018-10-13-23:47:20] Epoch: [054][7000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.552 (3.642) Prec@1 65.62 (62.32) Prec@5 85.16 (83.30) + train[2018-10-13-23:49:05] Epoch: [054][7200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 4.027 (3.643) Prec@1 57.81 (62.32) Prec@5 75.00 (83.29) + train[2018-10-13-23:50:49] Epoch: [054][7400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.954 (3.643) Prec@1 55.47 (62.31) Prec@5 78.12 (83.28) + train[2018-10-13-23:52:34] Epoch: [054][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.467 (3.644) Prec@1 64.06 (62.30) Prec@5 84.38 (83.28) + train[2018-10-13-23:54:19] Epoch: [054][7800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.453 (3.644) Prec@1 65.62 (62.30) Prec@5 84.38 (83.27) + train[2018-10-13-23:56:05] Epoch: [054][8000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.552 (3.644) Prec@1 63.28 (62.29) Prec@5 85.16 (83.26) + train[2018-10-13-23:57:52] Epoch: [054][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.496 (3.644) Prec@1 63.28 (62.28) Prec@5 86.72 (83.26) + train[2018-10-13-23:59:37] Epoch: [054][8400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 4.054 (3.645) Prec@1 55.47 (62.27) Prec@5 79.69 (83.27) + train[2018-10-14-00:01:24] Epoch: [054][8600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.604 (3.646) Prec@1 60.94 (62.25) Prec@5 84.38 (83.25) + train[2018-10-14-00:03:11] Epoch: [054][8800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.353 (3.647) Prec@1 71.88 (62.25) Prec@5 88.28 (83.24) + train[2018-10-14-00:04:58] Epoch: [054][9000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.798 (3.647) Prec@1 59.38 (62.24) Prec@5 79.69 (83.24) + train[2018-10-14-00:06:43] Epoch: [054][9200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.695 (3.648) Prec@1 60.16 (62.23) Prec@5 80.47 (83.23) + train[2018-10-14-00:08:29] Epoch: [054][9400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.628 (3.649) Prec@1 63.28 (62.22) Prec@5 85.94 (83.22) + train[2018-10-14-00:10:13] Epoch: [054][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.585 (3.649) Prec@1 63.28 (62.20) Prec@5 85.16 (83.21) + train[2018-10-14-00:11:59] Epoch: [054][9800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.626 (3.650) Prec@1 59.38 (62.18) Prec@5 85.16 (83.20) + train[2018-10-14-00:13:43] Epoch: [054][10000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.623 (3.651) Prec@1 64.84 (62.16) Prec@5 86.72 (83.19) + train[2018-10-14-00:13:48] Epoch: [054][10009/10010] Time 0.22 (0.53) Data 0.00 (0.00) Loss 4.225 (3.651) Prec@1 53.33 (62.16) Prec@5 80.00 (83.19) +[2018-10-14-00:13:48] **train** Prec@1 62.16 Prec@5 83.19 Error@1 37.84 Error@5 16.81 Loss:3.651 + test [2018-10-14-00:13:52] Epoch: [054][000/391] Time 4.08 (4.08) Data 3.94 (3.94) Loss 0.783 (0.783) Prec@1 85.16 (85.16) Prec@5 94.53 (94.53) + test [2018-10-14-00:14:19] Epoch: [054][200/391] Time 0.13 (0.16) Data 0.00 (0.02) Loss 1.840 (1.281) Prec@1 55.47 (70.05) Prec@5 83.59 (90.52) + test [2018-10-14-00:14:45] Epoch: [054][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.564 (1.461) Prec@1 36.25 (66.55) Prec@5 73.75 (87.75) +[2018-10-14-00:14:45] **test** Prec@1 66.55 Prec@5 87.75 Error@1 33.45 Error@5 12.25 Loss:1.461 +----> Best Accuracy : Acc@1=66.61, Acc@5=87.54, Error@1=33.39, Error@5=12.46 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-14-00:14:45] [Epoch=055/250] [Need: 288:20:51] LR=0.0187 ~ 0.0187, Batch=128 + train[2018-10-14-00:14:49] Epoch: [055][000/10010] Time 4.06 (4.06) Data 3.51 (3.51) Loss 3.759 (3.759) Prec@1 59.38 (59.38) Prec@5 80.47 (80.47) + train[2018-10-14-00:16:33] Epoch: [055][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 3.938 (3.610) Prec@1 58.59 (63.25) Prec@5 78.12 (83.71) + train[2018-10-14-00:18:18] Epoch: [055][400/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 4.074 (3.611) Prec@1 59.38 (63.08) Prec@5 78.91 (83.73) + train[2018-10-14-00:20:02] Epoch: [055][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.736 (3.605) Prec@1 58.59 (63.15) Prec@5 82.81 (83.78) + train[2018-10-14-00:21:48] Epoch: [055][800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.622 (3.608) Prec@1 63.28 (63.07) Prec@5 83.59 (83.72) + train[2018-10-14-00:23:32] Epoch: [055][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.613 (3.609) Prec@1 65.62 (63.03) Prec@5 80.47 (83.72) + train[2018-10-14-00:25:18] Epoch: [055][1200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.413 (3.606) Prec@1 65.62 (62.96) Prec@5 87.50 (83.78) + train[2018-10-14-00:27:03] Epoch: [055][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.412 (3.610) Prec@1 64.84 (62.89) Prec@5 87.50 (83.75) + train[2018-10-14-00:28:48] Epoch: [055][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.619 (3.612) Prec@1 60.16 (62.80) Prec@5 81.25 (83.69) + train[2018-10-14-00:30:33] Epoch: [055][1800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.794 (3.616) Prec@1 61.72 (62.76) Prec@5 81.25 (83.63) + train[2018-10-14-00:32:17] Epoch: [055][2000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.563 (3.615) Prec@1 62.50 (62.80) Prec@5 84.38 (83.63) + train[2018-10-14-00:34:02] Epoch: [055][2200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.514 (3.615) Prec@1 60.16 (62.82) Prec@5 86.72 (83.63) + train[2018-10-14-00:35:50] Epoch: [055][2400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.610 (3.615) Prec@1 64.84 (62.78) Prec@5 85.94 (83.63) + train[2018-10-14-00:37:36] Epoch: [055][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.361 (3.617) Prec@1 68.75 (62.75) Prec@5 87.50 (83.60) + train[2018-10-14-00:39:23] Epoch: [055][2800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.552 (3.617) Prec@1 64.84 (62.76) Prec@5 85.16 (83.59) + train[2018-10-14-00:41:10] Epoch: [055][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.730 (3.619) Prec@1 61.72 (62.75) Prec@5 81.25 (83.56) + train[2018-10-14-00:42:55] Epoch: [055][3200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.722 (3.619) Prec@1 57.03 (62.74) Prec@5 78.12 (83.57) + train[2018-10-14-00:44:40] Epoch: [055][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.946 (3.619) Prec@1 61.72 (62.73) Prec@5 79.69 (83.58) + train[2018-10-14-00:46:27] Epoch: [055][3600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.577 (3.619) Prec@1 60.94 (62.73) Prec@5 85.16 (83.59) + train[2018-10-14-00:48:14] Epoch: [055][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.834 (3.619) Prec@1 60.94 (62.70) Prec@5 85.16 (83.58) + train[2018-10-14-00:50:01] Epoch: [055][4000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.701 (3.620) Prec@1 62.50 (62.69) Prec@5 83.59 (83.57) + train[2018-10-14-00:51:48] Epoch: [055][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.420 (3.621) Prec@1 60.94 (62.67) Prec@5 89.84 (83.55) + train[2018-10-14-00:53:35] Epoch: [055][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.316 (3.623) Prec@1 64.84 (62.64) Prec@5 88.28 (83.54) + train[2018-10-14-00:55:23] Epoch: [055][4600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.755 (3.624) Prec@1 56.25 (62.63) Prec@5 82.03 (83.53) + train[2018-10-14-00:57:10] Epoch: [055][4800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.463 (3.624) Prec@1 66.41 (62.63) Prec@5 84.38 (83.52) + train[2018-10-14-00:58:55] Epoch: [055][5000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 4.011 (3.625) Prec@1 53.91 (62.61) Prec@5 80.47 (83.50) + train[2018-10-14-01:00:39] Epoch: [055][5200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.412 (3.626) Prec@1 62.50 (62.60) Prec@5 89.84 (83.48) + train[2018-10-14-01:02:24] Epoch: [055][5400/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.484 (3.627) Prec@1 65.62 (62.60) Prec@5 84.38 (83.48) + train[2018-10-14-01:04:09] Epoch: [055][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.554 (3.627) Prec@1 64.84 (62.59) Prec@5 83.59 (83.48) + train[2018-10-14-01:05:54] Epoch: [055][5800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.603 (3.628) Prec@1 59.38 (62.57) Prec@5 82.03 (83.46) + train[2018-10-14-01:07:39] Epoch: [055][6000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.814 (3.629) Prec@1 59.38 (62.57) Prec@5 82.03 (83.45) + train[2018-10-14-01:09:24] Epoch: [055][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.573 (3.629) Prec@1 62.50 (62.57) Prec@5 82.81 (83.45) + train[2018-10-14-01:11:09] Epoch: [055][6400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.607 (3.629) Prec@1 60.16 (62.56) Prec@5 83.59 (83.44) + train[2018-10-14-01:12:56] Epoch: [055][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.493 (3.630) Prec@1 63.28 (62.54) Prec@5 85.16 (83.43) + train[2018-10-14-01:14:40] Epoch: [055][6800/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.250 (3.630) Prec@1 71.88 (62.54) Prec@5 89.06 (83.43) + train[2018-10-14-01:16:24] Epoch: [055][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.479 (3.631) Prec@1 63.28 (62.53) Prec@5 84.38 (83.42) + train[2018-10-14-01:18:08] Epoch: [055][7200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.505 (3.631) Prec@1 62.50 (62.53) Prec@5 84.38 (83.42) + train[2018-10-14-01:19:52] Epoch: [055][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.618 (3.631) Prec@1 63.28 (62.53) Prec@5 83.59 (83.43) + train[2018-10-14-01:21:37] Epoch: [055][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.400 (3.632) Prec@1 68.75 (62.53) Prec@5 84.38 (83.42) + train[2018-10-14-01:23:23] Epoch: [055][7800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.611 (3.632) Prec@1 61.72 (62.52) Prec@5 83.59 (83.42) + train[2018-10-14-01:25:09] Epoch: [055][8000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.703 (3.633) Prec@1 64.84 (62.51) Prec@5 85.16 (83.41) + train[2018-10-14-01:26:55] Epoch: [055][8200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.876 (3.634) Prec@1 59.38 (62.49) Prec@5 83.59 (83.39) + train[2018-10-14-01:28:42] Epoch: [055][8400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.806 (3.634) Prec@1 56.25 (62.48) Prec@5 81.25 (83.39) + train[2018-10-14-01:30:29] Epoch: [055][8600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.552 (3.635) Prec@1 63.28 (62.46) Prec@5 85.16 (83.38) + train[2018-10-14-01:32:16] Epoch: [055][8800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.721 (3.636) Prec@1 57.81 (62.45) Prec@5 80.47 (83.37) + train[2018-10-14-01:34:02] Epoch: [055][9000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.538 (3.636) Prec@1 67.19 (62.45) Prec@5 85.16 (83.36) + train[2018-10-14-01:35:49] Epoch: [055][9200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.485 (3.636) Prec@1 64.06 (62.44) Prec@5 84.38 (83.36) + train[2018-10-14-01:37:35] Epoch: [055][9400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.488 (3.637) Prec@1 61.72 (62.43) Prec@5 84.38 (83.36) + train[2018-10-14-01:39:22] Epoch: [055][9600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.259 (3.638) Prec@1 70.31 (62.42) Prec@5 87.50 (83.35) + train[2018-10-14-01:41:08] Epoch: [055][9800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.934 (3.638) Prec@1 56.25 (62.41) Prec@5 78.91 (83.34) + train[2018-10-14-01:42:56] Epoch: [055][10000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.490 (3.639) Prec@1 61.72 (62.40) Prec@5 88.28 (83.33) + train[2018-10-14-01:43:00] Epoch: [055][10009/10010] Time 0.21 (0.53) Data 0.00 (0.00) Loss 3.211 (3.639) Prec@1 66.67 (62.40) Prec@5 93.33 (83.33) +[2018-10-14-01:43:00] **train** Prec@1 62.40 Prec@5 83.33 Error@1 37.60 Error@5 16.67 Loss:3.639 + test [2018-10-14-01:43:05] Epoch: [055][000/391] Time 4.24 (4.24) Data 4.09 (4.09) Loss 0.882 (0.882) Prec@1 79.69 (79.69) Prec@5 94.53 (94.53) + test [2018-10-14-01:43:32] Epoch: [055][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.537 (1.263) Prec@1 64.06 (70.48) Prec@5 89.06 (90.32) + test [2018-10-14-01:43:57] Epoch: [055][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.608 (1.456) Prec@1 33.75 (66.60) Prec@5 75.00 (87.50) +[2018-10-14-01:43:57] **test** Prec@1 66.60 Prec@5 87.50 Error@1 33.40 Error@5 12.50 Loss:1.456 +----> Best Accuracy : Acc@1=66.61, Acc@5=87.54, Error@1=33.39, Error@5=12.46 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-14-01:43:58] [Epoch=056/250] [Need: 288:27:19] LR=0.0182 ~ 0.0182, Batch=128 + train[2018-10-14-01:44:04] Epoch: [056][000/10010] Time 6.08 (6.08) Data 5.52 (5.52) Loss 3.468 (3.468) Prec@1 60.94 (60.94) Prec@5 86.72 (86.72) + train[2018-10-14-01:45:47] Epoch: [056][200/10010] Time 0.52 (0.54) Data 0.00 (0.03) Loss 3.652 (3.606) Prec@1 60.94 (62.99) Prec@5 82.81 (83.66) + train[2018-10-14-01:47:31] Epoch: [056][400/10010] Time 0.49 (0.53) Data 0.00 (0.01) Loss 3.445 (3.609) Prec@1 66.41 (63.06) Prec@5 83.59 (83.66) + train[2018-10-14-01:49:16] Epoch: [056][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.787 (3.602) Prec@1 62.50 (63.20) Prec@5 81.25 (83.73) + train[2018-10-14-01:51:01] Epoch: [056][800/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.175 (3.597) Prec@1 71.09 (63.25) Prec@5 91.41 (83.81) + train[2018-10-14-01:52:46] Epoch: [056][1000/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.902 (3.594) Prec@1 61.72 (63.27) Prec@5 77.34 (83.85) + train[2018-10-14-01:54:31] Epoch: [056][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.743 (3.593) Prec@1 57.81 (63.28) Prec@5 82.81 (83.87) + train[2018-10-14-01:56:16] Epoch: [056][1400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.628 (3.594) Prec@1 61.72 (63.22) Prec@5 83.59 (83.85) + train[2018-10-14-01:58:01] Epoch: [056][1600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.707 (3.598) Prec@1 64.06 (63.15) Prec@5 80.47 (83.82) + train[2018-10-14-01:59:46] Epoch: [056][1800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.953 (3.601) Prec@1 62.50 (63.10) Prec@5 78.91 (83.77) + train[2018-10-14-02:01:30] Epoch: [056][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.791 (3.602) Prec@1 63.28 (63.10) Prec@5 82.03 (83.77) + train[2018-10-14-02:03:15] Epoch: [056][2200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.433 (3.601) Prec@1 66.41 (63.11) Prec@5 84.38 (83.79) + train[2018-10-14-02:05:00] Epoch: [056][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.726 (3.605) Prec@1 64.06 (63.05) Prec@5 83.59 (83.74) + train[2018-10-14-02:06:45] Epoch: [056][2600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.326 (3.608) Prec@1 66.41 (62.98) Prec@5 90.62 (83.74) + train[2018-10-14-02:08:31] Epoch: [056][2800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.903 (3.609) Prec@1 57.81 (62.95) Prec@5 82.03 (83.74) + train[2018-10-14-02:10:17] Epoch: [056][3000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 4.034 (3.609) Prec@1 60.94 (62.96) Prec@5 77.34 (83.74) + train[2018-10-14-02:12:03] Epoch: [056][3200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 4.113 (3.609) Prec@1 52.34 (62.96) Prec@5 78.12 (83.72) + train[2018-10-14-02:13:50] Epoch: [056][3400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.590 (3.611) Prec@1 64.06 (62.93) Prec@5 84.38 (83.70) + train[2018-10-14-02:15:36] Epoch: [056][3600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.886 (3.612) Prec@1 57.81 (62.92) Prec@5 85.94 (83.68) + train[2018-10-14-02:17:23] Epoch: [056][3800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.620 (3.612) Prec@1 64.84 (62.91) Prec@5 82.03 (83.67) + train[2018-10-14-02:19:09] Epoch: [056][4000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.502 (3.613) Prec@1 67.19 (62.90) Prec@5 85.16 (83.67) + train[2018-10-14-02:20:56] Epoch: [056][4200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.685 (3.614) Prec@1 60.16 (62.87) Prec@5 84.38 (83.66) + train[2018-10-14-02:22:43] Epoch: [056][4400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.897 (3.613) Prec@1 57.81 (62.87) Prec@5 78.12 (83.67) + train[2018-10-14-02:24:31] Epoch: [056][4600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.440 (3.614) Prec@1 67.97 (62.85) Prec@5 85.94 (83.65) + train[2018-10-14-02:26:18] Epoch: [056][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 4.085 (3.615) Prec@1 51.56 (62.84) Prec@5 76.56 (83.66) + train[2018-10-14-02:28:05] Epoch: [056][5000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.574 (3.615) Prec@1 65.62 (62.83) Prec@5 83.59 (83.64) + train[2018-10-14-02:29:52] Epoch: [056][5200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.566 (3.617) Prec@1 65.62 (62.79) Prec@5 87.50 (83.62) + train[2018-10-14-02:31:40] Epoch: [056][5400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.505 (3.618) Prec@1 64.84 (62.78) Prec@5 88.28 (83.62) + train[2018-10-14-02:33:27] Epoch: [056][5600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.885 (3.618) Prec@1 56.25 (62.77) Prec@5 83.59 (83.61) + train[2018-10-14-02:35:14] Epoch: [056][5800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.416 (3.619) Prec@1 69.53 (62.77) Prec@5 88.28 (83.61) + train[2018-10-14-02:37:01] Epoch: [056][6000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.459 (3.619) Prec@1 67.97 (62.78) Prec@5 87.50 (83.60) + train[2018-10-14-02:38:48] Epoch: [056][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.743 (3.619) Prec@1 63.28 (62.77) Prec@5 83.59 (83.60) + train[2018-10-14-02:40:35] Epoch: [056][6400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.609 (3.619) Prec@1 58.59 (62.77) Prec@5 85.16 (83.60) + train[2018-10-14-02:42:22] Epoch: [056][6600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.736 (3.619) Prec@1 65.62 (62.76) Prec@5 78.12 (83.59) + train[2018-10-14-02:44:08] Epoch: [056][6800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.787 (3.620) Prec@1 59.38 (62.75) Prec@5 81.25 (83.57) + train[2018-10-14-02:45:55] Epoch: [056][7000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.489 (3.621) Prec@1 61.72 (62.73) Prec@5 88.28 (83.56) + train[2018-10-14-02:47:41] Epoch: [056][7200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.378 (3.622) Prec@1 71.88 (62.70) Prec@5 88.28 (83.55) + train[2018-10-14-02:49:27] Epoch: [056][7400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.741 (3.623) Prec@1 62.50 (62.69) Prec@5 78.91 (83.54) + train[2018-10-14-02:51:14] Epoch: [056][7600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.481 (3.623) Prec@1 64.06 (62.67) Prec@5 88.28 (83.53) + train[2018-10-14-02:53:02] Epoch: [056][7800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.657 (3.624) Prec@1 59.38 (62.66) Prec@5 79.69 (83.52) + train[2018-10-14-02:54:50] Epoch: [056][8000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.727 (3.624) Prec@1 60.16 (62.66) Prec@5 82.03 (83.51) + train[2018-10-14-02:56:37] Epoch: [056][8200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.687 (3.625) Prec@1 60.16 (62.65) Prec@5 85.94 (83.50) + train[2018-10-14-02:58:25] Epoch: [056][8400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.526 (3.625) Prec@1 65.62 (62.66) Prec@5 84.38 (83.50) + train[2018-10-14-03:00:11] Epoch: [056][8600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.755 (3.625) Prec@1 60.94 (62.64) Prec@5 79.69 (83.49) + train[2018-10-14-03:01:58] Epoch: [056][8800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.670 (3.625) Prec@1 62.50 (62.63) Prec@5 81.25 (83.50) + train[2018-10-14-03:03:46] Epoch: [056][9000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.593 (3.626) Prec@1 61.72 (62.63) Prec@5 86.72 (83.49) + train[2018-10-14-03:05:33] Epoch: [056][9200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.508 (3.627) Prec@1 67.97 (62.61) Prec@5 80.47 (83.48) + train[2018-10-14-03:07:20] Epoch: [056][9400/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.505 (3.627) Prec@1 64.06 (62.61) Prec@5 87.50 (83.48) + train[2018-10-14-03:09:07] Epoch: [056][9600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.675 (3.627) Prec@1 61.72 (62.60) Prec@5 82.81 (83.48) + train[2018-10-14-03:10:55] Epoch: [056][9800/10010] Time 0.65 (0.53) Data 0.00 (0.00) Loss 3.749 (3.628) Prec@1 62.50 (62.59) Prec@5 80.47 (83.47) + train[2018-10-14-03:12:41] Epoch: [056][10000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.803 (3.628) Prec@1 56.25 (62.58) Prec@5 78.91 (83.46) + train[2018-10-14-03:12:45] Epoch: [056][10009/10010] Time 0.14 (0.53) Data 0.00 (0.00) Loss 3.874 (3.628) Prec@1 60.00 (62.58) Prec@5 80.00 (83.46) +[2018-10-14-03:12:45] **train** Prec@1 62.58 Prec@5 83.46 Error@1 37.42 Error@5 16.54 Loss:3.628 + test [2018-10-14-03:12:50] Epoch: [056][000/391] Time 4.54 (4.54) Data 4.38 (4.38) Loss 0.710 (0.710) Prec@1 86.72 (86.72) Prec@5 96.88 (96.88) + test [2018-10-14-03:13:19] Epoch: [056][200/391] Time 0.14 (0.17) Data 0.00 (0.04) Loss 1.551 (1.237) Prec@1 64.06 (70.95) Prec@5 89.06 (90.73) + test [2018-10-14-03:13:45] Epoch: [056][390/391] Time 0.08 (0.15) Data 0.00 (0.02) Loss 2.729 (1.433) Prec@1 32.50 (66.93) Prec@5 71.25 (87.76) +[2018-10-14-03:13:45] **test** Prec@1 66.93 Prec@5 87.76 Error@1 33.07 Error@5 12.24 Loss:1.433 +----> Best Accuracy : Acc@1=66.93, Acc@5=87.76, Error@1=33.07, Error@5=12.24 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-14-03:13:45] [Epoch=057/250] [Need: 288:50:22] LR=0.0176 ~ 0.0176, Batch=128 + train[2018-10-14-03:13:50] Epoch: [057][000/10010] Time 4.65 (4.65) Data 3.95 (3.95) Loss 3.443 (3.443) Prec@1 65.62 (65.62) Prec@5 85.16 (85.16) + train[2018-10-14-03:15:35] Epoch: [057][200/10010] Time 0.51 (0.55) Data 0.00 (0.02) Loss 3.804 (3.590) Prec@1 57.81 (63.24) Prec@5 82.03 (83.71) + train[2018-10-14-03:17:21] Epoch: [057][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 3.412 (3.592) Prec@1 60.16 (63.16) Prec@5 82.03 (83.90) + train[2018-10-14-03:19:04] Epoch: [057][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.789 (3.583) Prec@1 60.94 (63.23) Prec@5 81.25 (84.07) + train[2018-10-14-03:20:47] Epoch: [057][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.682 (3.583) Prec@1 63.28 (63.27) Prec@5 82.03 (84.02) + train[2018-10-14-03:22:31] Epoch: [057][1000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.411 (3.584) Prec@1 66.41 (63.31) Prec@5 85.16 (83.93) + train[2018-10-14-03:24:14] Epoch: [057][1200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.703 (3.585) Prec@1 64.84 (63.29) Prec@5 82.03 (83.92) + train[2018-10-14-03:25:57] Epoch: [057][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.758 (3.588) Prec@1 56.25 (63.25) Prec@5 82.81 (83.89) + train[2018-10-14-03:27:41] Epoch: [057][1600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.617 (3.589) Prec@1 61.72 (63.20) Prec@5 82.81 (83.90) + train[2018-10-14-03:29:25] Epoch: [057][1800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.463 (3.590) Prec@1 66.41 (63.15) Prec@5 88.28 (83.89) + train[2018-10-14-03:31:09] Epoch: [057][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.441 (3.592) Prec@1 67.97 (63.13) Prec@5 85.16 (83.87) + train[2018-10-14-03:32:53] Epoch: [057][2200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.387 (3.592) Prec@1 66.41 (63.13) Prec@5 87.50 (83.87) + train[2018-10-14-03:34:36] Epoch: [057][2400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.426 (3.594) Prec@1 63.28 (63.11) Prec@5 89.06 (83.86) + train[2018-10-14-03:36:21] Epoch: [057][2600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.632 (3.596) Prec@1 62.50 (63.07) Prec@5 81.25 (83.85) + train[2018-10-14-03:38:05] Epoch: [057][2800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.441 (3.593) Prec@1 63.28 (63.10) Prec@5 85.16 (83.88) + train[2018-10-14-03:39:49] Epoch: [057][3000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.217 (3.592) Prec@1 68.75 (63.10) Prec@5 89.06 (83.88) + train[2018-10-14-03:41:33] Epoch: [057][3200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.584 (3.593) Prec@1 62.50 (63.09) Prec@5 80.47 (83.86) + train[2018-10-14-03:43:17] Epoch: [057][3400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.334 (3.595) Prec@1 64.06 (63.07) Prec@5 86.72 (83.82) + train[2018-10-14-03:45:02] Epoch: [057][3600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.456 (3.595) Prec@1 67.19 (63.07) Prec@5 84.38 (83.81) + train[2018-10-14-03:46:47] Epoch: [057][3800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.492 (3.597) Prec@1 67.19 (63.05) Prec@5 84.38 (83.79) + train[2018-10-14-03:48:30] Epoch: [057][4000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.858 (3.598) Prec@1 57.81 (63.03) Prec@5 82.03 (83.78) + train[2018-10-14-03:50:14] Epoch: [057][4200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.554 (3.598) Prec@1 64.06 (63.02) Prec@5 82.03 (83.77) + train[2018-10-14-03:51:58] Epoch: [057][4400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.736 (3.598) Prec@1 61.72 (63.02) Prec@5 84.38 (83.78) + train[2018-10-14-03:53:42] Epoch: [057][4600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.602 (3.598) Prec@1 56.25 (63.01) Prec@5 85.16 (83.78) + train[2018-10-14-03:55:27] Epoch: [057][4800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.636 (3.599) Prec@1 61.72 (62.99) Prec@5 82.81 (83.77) + train[2018-10-14-03:57:11] Epoch: [057][5000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.740 (3.601) Prec@1 60.94 (62.98) Prec@5 82.03 (83.76) + train[2018-10-14-03:58:55] Epoch: [057][5200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.612 (3.600) Prec@1 64.84 (62.99) Prec@5 85.16 (83.76) + train[2018-10-14-04:00:39] Epoch: [057][5400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.798 (3.601) Prec@1 62.50 (62.98) Prec@5 81.25 (83.74) + train[2018-10-14-04:02:24] Epoch: [057][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.781 (3.603) Prec@1 58.59 (62.94) Prec@5 81.25 (83.73) + train[2018-10-14-04:04:08] Epoch: [057][5800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.474 (3.604) Prec@1 63.28 (62.92) Prec@5 87.50 (83.71) + train[2018-10-14-04:05:51] Epoch: [057][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.498 (3.604) Prec@1 63.28 (62.93) Prec@5 85.94 (83.71) + train[2018-10-14-04:07:36] Epoch: [057][6200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.976 (3.605) Prec@1 59.38 (62.91) Prec@5 79.69 (83.69) + train[2018-10-14-04:09:21] Epoch: [057][6400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.571 (3.605) Prec@1 61.72 (62.91) Prec@5 84.38 (83.69) + train[2018-10-14-04:11:05] Epoch: [057][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.640 (3.606) Prec@1 60.94 (62.90) Prec@5 83.59 (83.69) + train[2018-10-14-04:12:49] Epoch: [057][6800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.814 (3.606) Prec@1 61.72 (62.90) Prec@5 79.69 (83.69) + train[2018-10-14-04:14:33] Epoch: [057][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.689 (3.606) Prec@1 59.38 (62.90) Prec@5 86.72 (83.68) + train[2018-10-14-04:16:18] Epoch: [057][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.215 (3.607) Prec@1 67.97 (62.89) Prec@5 88.28 (83.68) + train[2018-10-14-04:18:01] Epoch: [057][7400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.546 (3.608) Prec@1 64.06 (62.88) Prec@5 84.38 (83.67) + train[2018-10-14-04:19:45] Epoch: [057][7600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.726 (3.608) Prec@1 58.59 (62.87) Prec@5 84.38 (83.66) + train[2018-10-14-04:21:30] Epoch: [057][7800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.682 (3.609) Prec@1 64.06 (62.86) Prec@5 83.59 (83.64) + train[2018-10-14-04:23:14] Epoch: [057][8000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.585 (3.610) Prec@1 67.97 (62.85) Prec@5 78.91 (83.64) + train[2018-10-14-04:24:58] Epoch: [057][8200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.071 (3.611) Prec@1 58.59 (62.84) Prec@5 76.56 (83.63) + train[2018-10-14-04:26:42] Epoch: [057][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.480 (3.611) Prec@1 58.59 (62.83) Prec@5 84.38 (83.63) + train[2018-10-14-04:28:25] Epoch: [057][8600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.489 (3.612) Prec@1 62.50 (62.83) Prec@5 84.38 (83.61) + train[2018-10-14-04:30:09] Epoch: [057][8800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.765 (3.613) Prec@1 61.72 (62.81) Prec@5 79.69 (83.60) + train[2018-10-14-04:31:53] Epoch: [057][9000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.654 (3.613) Prec@1 60.16 (62.80) Prec@5 85.16 (83.60) + train[2018-10-14-04:33:37] Epoch: [057][9200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.820 (3.614) Prec@1 63.28 (62.80) Prec@5 81.25 (83.59) + train[2018-10-14-04:35:22] Epoch: [057][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.772 (3.614) Prec@1 57.03 (62.80) Prec@5 83.59 (83.59) + train[2018-10-14-04:37:05] Epoch: [057][9600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.497 (3.614) Prec@1 60.94 (62.80) Prec@5 82.81 (83.59) + train[2018-10-14-04:38:50] Epoch: [057][9800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.887 (3.614) Prec@1 59.38 (62.79) Prec@5 75.78 (83.58) + train[2018-10-14-04:40:33] Epoch: [057][10000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.639 (3.615) Prec@1 62.50 (62.78) Prec@5 83.59 (83.58) + train[2018-10-14-04:40:38] Epoch: [057][10009/10010] Time 0.21 (0.52) Data 0.00 (0.00) Loss 5.156 (3.615) Prec@1 46.67 (62.78) Prec@5 73.33 (83.58) +[2018-10-14-04:40:38] **train** Prec@1 62.78 Prec@5 83.58 Error@1 37.22 Error@5 16.42 Loss:3.615 + test [2018-10-14-04:40:42] Epoch: [057][000/391] Time 4.40 (4.40) Data 4.27 (4.27) Loss 0.749 (0.749) Prec@1 82.81 (82.81) Prec@5 96.88 (96.88) + test [2018-10-14-04:41:09] Epoch: [057][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.605 (1.236) Prec@1 62.50 (71.23) Prec@5 85.16 (90.83) + test [2018-10-14-04:41:33] Epoch: [057][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.498 (1.422) Prec@1 42.50 (67.46) Prec@5 80.00 (87.94) +[2018-10-14-04:41:33] **test** Prec@1 67.46 Prec@5 87.94 Error@1 32.54 Error@5 12.06 Loss:1.422 +----> Best Accuracy : Acc@1=67.46, Acc@5=87.94, Error@1=32.54, Error@5=12.06 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-14-04:41:33] [Epoch=058/250] [Need: 280:57:47] LR=0.0171 ~ 0.0171, Batch=128 + train[2018-10-14-04:41:38] Epoch: [058][000/10010] Time 4.45 (4.45) Data 3.86 (3.86) Loss 3.384 (3.384) Prec@1 65.62 (65.62) Prec@5 85.94 (85.94) + train[2018-10-14-04:43:22] Epoch: [058][200/10010] Time 0.52 (0.54) Data 0.00 (0.02) Loss 2.994 (3.553) Prec@1 75.00 (64.07) Prec@5 90.62 (84.66) + train[2018-10-14-04:45:07] Epoch: [058][400/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.478 (3.561) Prec@1 64.06 (63.82) Prec@5 85.94 (84.40) + train[2018-10-14-04:46:51] Epoch: [058][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.650 (3.563) Prec@1 63.28 (63.75) Prec@5 82.03 (84.31) + train[2018-10-14-04:48:35] Epoch: [058][800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.674 (3.572) Prec@1 64.06 (63.59) Prec@5 81.25 (84.13) + train[2018-10-14-04:50:19] Epoch: [058][1000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.781 (3.571) Prec@1 60.16 (63.63) Prec@5 78.91 (84.16) + train[2018-10-14-04:52:02] Epoch: [058][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.389 (3.573) Prec@1 64.84 (63.60) Prec@5 87.50 (84.19) + train[2018-10-14-04:53:46] Epoch: [058][1400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.513 (3.572) Prec@1 70.31 (63.58) Prec@5 82.81 (84.18) + train[2018-10-14-04:55:31] Epoch: [058][1600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.781 (3.572) Prec@1 59.38 (63.52) Prec@5 80.47 (84.17) + train[2018-10-14-04:57:15] Epoch: [058][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.427 (3.571) Prec@1 67.19 (63.51) Prec@5 86.72 (84.17) + train[2018-10-14-04:58:59] Epoch: [058][2000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.194 (3.575) Prec@1 69.53 (63.46) Prec@5 87.50 (84.12) + train[2018-10-14-05:00:43] Epoch: [058][2200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.567 (3.577) Prec@1 58.59 (63.43) Prec@5 82.81 (84.09) + train[2018-10-14-05:02:27] Epoch: [058][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.584 (3.580) Prec@1 61.72 (63.42) Prec@5 85.16 (84.07) + train[2018-10-14-05:04:12] Epoch: [058][2600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.488 (3.580) Prec@1 68.75 (63.42) Prec@5 86.72 (84.07) + train[2018-10-14-05:05:56] Epoch: [058][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.660 (3.580) Prec@1 65.62 (63.42) Prec@5 80.47 (84.05) + train[2018-10-14-05:07:40] Epoch: [058][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.748 (3.581) Prec@1 64.84 (63.40) Prec@5 82.81 (84.02) + train[2018-10-14-05:09:24] Epoch: [058][3200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.594 (3.582) Prec@1 64.06 (63.40) Prec@5 85.16 (84.02) + train[2018-10-14-05:11:08] Epoch: [058][3400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.560 (3.583) Prec@1 62.50 (63.39) Prec@5 87.50 (84.01) + train[2018-10-14-05:12:52] Epoch: [058][3600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.580 (3.584) Prec@1 65.62 (63.36) Prec@5 82.03 (84.00) + train[2018-10-14-05:14:36] Epoch: [058][3800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.640 (3.586) Prec@1 64.84 (63.32) Prec@5 85.94 (83.98) + train[2018-10-14-05:16:20] Epoch: [058][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.637 (3.587) Prec@1 60.94 (63.30) Prec@5 83.59 (83.96) + train[2018-10-14-05:18:05] Epoch: [058][4200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.414 (3.587) Prec@1 64.84 (63.30) Prec@5 86.72 (83.97) + train[2018-10-14-05:19:49] Epoch: [058][4400/10010] Time 0.63 (0.52) Data 0.00 (0.00) Loss 3.539 (3.586) Prec@1 62.50 (63.30) Prec@5 85.94 (83.98) + train[2018-10-14-05:21:34] Epoch: [058][4600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.329 (3.587) Prec@1 64.84 (63.28) Prec@5 85.94 (83.97) + train[2018-10-14-05:23:18] Epoch: [058][4800/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 4.291 (3.589) Prec@1 50.78 (63.24) Prec@5 71.88 (83.93) + train[2018-10-14-05:25:02] Epoch: [058][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.654 (3.590) Prec@1 61.72 (63.23) Prec@5 83.59 (83.92) + train[2018-10-14-05:26:47] Epoch: [058][5200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.344 (3.590) Prec@1 66.41 (63.22) Prec@5 88.28 (83.92) + train[2018-10-14-05:28:31] Epoch: [058][5400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.287 (3.591) Prec@1 70.31 (63.21) Prec@5 86.72 (83.91) + train[2018-10-14-05:30:16] Epoch: [058][5600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.793 (3.592) Prec@1 59.38 (63.19) Prec@5 79.69 (83.89) + train[2018-10-14-05:32:00] Epoch: [058][5800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.825 (3.593) Prec@1 59.38 (63.17) Prec@5 82.81 (83.88) + train[2018-10-14-05:33:44] Epoch: [058][6000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.781 (3.594) Prec@1 60.16 (63.15) Prec@5 78.91 (83.86) + train[2018-10-14-05:35:28] Epoch: [058][6200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.410 (3.594) Prec@1 68.75 (63.14) Prec@5 84.38 (83.85) + train[2018-10-14-05:37:12] Epoch: [058][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.877 (3.595) Prec@1 60.94 (63.13) Prec@5 82.81 (83.84) + train[2018-10-14-05:38:56] Epoch: [058][6600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.728 (3.595) Prec@1 60.94 (63.12) Prec@5 80.47 (83.84) + train[2018-10-14-05:40:40] Epoch: [058][6800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.732 (3.596) Prec@1 59.38 (63.09) Prec@5 80.47 (83.83) + train[2018-10-14-05:42:24] Epoch: [058][7000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.310 (3.597) Prec@1 64.84 (63.08) Prec@5 89.84 (83.82) + train[2018-10-14-05:44:08] Epoch: [058][7200/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 4.206 (3.596) Prec@1 51.56 (63.10) Prec@5 76.56 (83.83) + train[2018-10-14-05:45:52] Epoch: [058][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.340 (3.597) Prec@1 71.09 (63.08) Prec@5 87.50 (83.82) + train[2018-10-14-05:47:36] Epoch: [058][7600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.745 (3.598) Prec@1 57.81 (63.07) Prec@5 83.59 (83.80) + train[2018-10-14-05:49:21] Epoch: [058][7800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.985 (3.598) Prec@1 56.25 (63.06) Prec@5 78.12 (83.80) + train[2018-10-14-05:51:06] Epoch: [058][8000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.431 (3.599) Prec@1 60.94 (63.06) Prec@5 83.59 (83.79) + train[2018-10-14-05:52:50] Epoch: [058][8200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.691 (3.598) Prec@1 64.06 (63.06) Prec@5 83.59 (83.79) + train[2018-10-14-05:54:34] Epoch: [058][8400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.549 (3.599) Prec@1 65.62 (63.05) Prec@5 85.16 (83.79) + train[2018-10-14-05:56:18] Epoch: [058][8600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.846 (3.599) Prec@1 59.38 (63.05) Prec@5 77.34 (83.78) + train[2018-10-14-05:58:03] Epoch: [058][8800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.313 (3.600) Prec@1 67.97 (63.03) Prec@5 84.38 (83.78) + train[2018-10-14-05:59:47] Epoch: [058][9000/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.799 (3.600) Prec@1 63.28 (63.03) Prec@5 80.47 (83.78) + train[2018-10-14-06:01:32] Epoch: [058][9200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.661 (3.600) Prec@1 64.84 (63.03) Prec@5 82.81 (83.78) + train[2018-10-14-06:03:15] Epoch: [058][9400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.634 (3.600) Prec@1 57.03 (63.02) Prec@5 85.94 (83.77) + train[2018-10-14-06:05:00] Epoch: [058][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.913 (3.601) Prec@1 62.50 (63.01) Prec@5 79.69 (83.76) + train[2018-10-14-06:06:43] Epoch: [058][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.792 (3.601) Prec@1 60.16 (63.00) Prec@5 82.81 (83.76) + train[2018-10-14-06:08:28] Epoch: [058][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.201 (3.601) Prec@1 75.00 (62.99) Prec@5 87.50 (83.76) + train[2018-10-14-06:08:33] Epoch: [058][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.640 (3.601) Prec@1 53.33 (62.99) Prec@5 66.67 (83.76) +[2018-10-14-06:08:33] **train** Prec@1 62.99 Prec@5 83.76 Error@1 37.01 Error@5 16.24 Loss:3.601 + test [2018-10-14-06:08:37] Epoch: [058][000/391] Time 4.04 (4.04) Data 3.90 (3.90) Loss 0.751 (0.751) Prec@1 84.38 (84.38) Prec@5 96.09 (96.09) + test [2018-10-14-06:09:03] Epoch: [058][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.493 (1.239) Prec@1 58.59 (70.91) Prec@5 87.50 (90.59) + test [2018-10-14-06:09:28] Epoch: [058][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 3.028 (1.431) Prec@1 28.75 (67.07) Prec@5 70.00 (87.78) +[2018-10-14-06:09:28] **test** Prec@1 67.07 Prec@5 87.78 Error@1 32.93 Error@5 12.22 Loss:1.431 +----> Best Accuracy : Acc@1=67.46, Acc@5=87.94, Error@1=32.54, Error@5=12.06 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-14-06:09:28] [Epoch=059/250] [Need: 279:52:45] LR=0.0166 ~ 0.0166, Batch=128 + train[2018-10-14-06:09:34] Epoch: [059][000/10010] Time 5.32 (5.32) Data 4.73 (4.73) Loss 3.934 (3.934) Prec@1 60.94 (60.94) Prec@5 79.69 (79.69) + train[2018-10-14-06:11:18] Epoch: [059][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.797 (3.555) Prec@1 58.59 (63.74) Prec@5 83.59 (84.45) + train[2018-10-14-06:13:03] Epoch: [059][400/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.386 (3.555) Prec@1 68.75 (63.78) Prec@5 88.28 (84.44) + train[2018-10-14-06:14:46] Epoch: [059][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.706 (3.555) Prec@1 57.81 (63.87) Prec@5 84.38 (84.32) + train[2018-10-14-06:16:31] Epoch: [059][800/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.822 (3.554) Prec@1 57.03 (63.91) Prec@5 85.16 (84.32) + train[2018-10-14-06:18:16] Epoch: [059][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.444 (3.560) Prec@1 65.62 (63.78) Prec@5 92.97 (84.25) + train[2018-10-14-06:19:59] Epoch: [059][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.766 (3.561) Prec@1 53.91 (63.74) Prec@5 84.38 (84.26) + train[2018-10-14-06:21:43] Epoch: [059][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.307 (3.564) Prec@1 64.84 (63.64) Prec@5 88.28 (84.23) + train[2018-10-14-06:23:26] Epoch: [059][1600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.788 (3.563) Prec@1 57.81 (63.70) Prec@5 82.81 (84.23) + train[2018-10-14-06:25:10] Epoch: [059][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.379 (3.565) Prec@1 67.97 (63.66) Prec@5 88.28 (84.20) + train[2018-10-14-06:26:54] Epoch: [059][2000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.455 (3.565) Prec@1 66.41 (63.73) Prec@5 86.72 (84.20) + train[2018-10-14-06:28:37] Epoch: [059][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.592 (3.565) Prec@1 57.03 (63.72) Prec@5 84.38 (84.19) + train[2018-10-14-06:30:21] Epoch: [059][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.694 (3.565) Prec@1 64.84 (63.69) Prec@5 80.47 (84.20) + train[2018-10-14-06:32:05] Epoch: [059][2600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.705 (3.566) Prec@1 65.62 (63.68) Prec@5 84.38 (84.20) + train[2018-10-14-06:33:50] Epoch: [059][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 4.158 (3.566) Prec@1 55.47 (63.67) Prec@5 75.78 (84.18) + train[2018-10-14-06:35:33] Epoch: [059][3000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.579 (3.567) Prec@1 61.72 (63.66) Prec@5 84.38 (84.18) + train[2018-10-14-06:37:18] Epoch: [059][3200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.780 (3.568) Prec@1 60.94 (63.64) Prec@5 86.72 (84.17) + train[2018-10-14-06:39:02] Epoch: [059][3400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.538 (3.568) Prec@1 66.41 (63.64) Prec@5 85.16 (84.16) + train[2018-10-14-06:40:46] Epoch: [059][3600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.624 (3.571) Prec@1 60.94 (63.62) Prec@5 84.38 (84.13) + train[2018-10-14-06:42:30] Epoch: [059][3800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.761 (3.571) Prec@1 58.59 (63.61) Prec@5 86.72 (84.14) + train[2018-10-14-06:44:15] Epoch: [059][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.432 (3.572) Prec@1 64.06 (63.57) Prec@5 86.72 (84.12) + train[2018-10-14-06:45:58] Epoch: [059][4200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.502 (3.571) Prec@1 70.31 (63.58) Prec@5 83.59 (84.12) + train[2018-10-14-06:47:43] Epoch: [059][4400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.490 (3.571) Prec@1 67.19 (63.57) Prec@5 83.59 (84.12) + train[2018-10-14-06:49:27] Epoch: [059][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.347 (3.573) Prec@1 67.97 (63.55) Prec@5 84.38 (84.10) + train[2018-10-14-06:51:11] Epoch: [059][4800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.707 (3.573) Prec@1 64.06 (63.55) Prec@5 82.03 (84.09) + train[2018-10-14-06:52:55] Epoch: [059][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.497 (3.574) Prec@1 59.38 (63.54) Prec@5 86.72 (84.09) + train[2018-10-14-06:54:39] Epoch: [059][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.755 (3.576) Prec@1 59.38 (63.50) Prec@5 86.72 (84.06) + train[2018-10-14-06:56:24] Epoch: [059][5400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.635 (3.577) Prec@1 59.38 (63.46) Prec@5 82.81 (84.04) + train[2018-10-14-06:58:08] Epoch: [059][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.733 (3.578) Prec@1 61.72 (63.44) Prec@5 83.59 (84.04) + train[2018-10-14-06:59:53] Epoch: [059][5800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.500 (3.579) Prec@1 60.16 (63.43) Prec@5 85.94 (84.02) + train[2018-10-14-07:01:36] Epoch: [059][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.327 (3.580) Prec@1 67.97 (63.42) Prec@5 89.06 (84.01) + train[2018-10-14-07:03:20] Epoch: [059][6200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.576 (3.580) Prec@1 63.28 (63.41) Prec@5 83.59 (84.01) + train[2018-10-14-07:05:04] Epoch: [059][6400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.805 (3.581) Prec@1 57.03 (63.40) Prec@5 82.03 (83.99) + train[2018-10-14-07:06:48] Epoch: [059][6600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.628 (3.581) Prec@1 64.06 (63.39) Prec@5 82.81 (83.98) + train[2018-10-14-07:08:33] Epoch: [059][6800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.781 (3.582) Prec@1 56.25 (63.38) Prec@5 81.25 (83.96) + train[2018-10-14-07:10:18] Epoch: [059][7000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.715 (3.583) Prec@1 66.41 (63.37) Prec@5 82.03 (83.96) + train[2018-10-14-07:12:01] Epoch: [059][7200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.659 (3.583) Prec@1 57.03 (63.36) Prec@5 82.03 (83.96) + train[2018-10-14-07:13:46] Epoch: [059][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.411 (3.584) Prec@1 63.28 (63.34) Prec@5 86.72 (83.95) + train[2018-10-14-07:15:30] Epoch: [059][7600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.592 (3.585) Prec@1 66.41 (63.32) Prec@5 85.16 (83.93) + train[2018-10-14-07:17:15] Epoch: [059][7800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 4.055 (3.586) Prec@1 51.56 (63.30) Prec@5 78.91 (83.93) + train[2018-10-14-07:19:00] Epoch: [059][8000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.769 (3.587) Prec@1 60.16 (63.28) Prec@5 82.81 (83.91) + train[2018-10-14-07:20:44] Epoch: [059][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.341 (3.587) Prec@1 64.84 (63.28) Prec@5 85.94 (83.91) + train[2018-10-14-07:22:28] Epoch: [059][8400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.745 (3.587) Prec@1 59.38 (63.26) Prec@5 82.03 (83.90) + train[2018-10-14-07:24:14] Epoch: [059][8600/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.235 (3.588) Prec@1 71.09 (63.24) Prec@5 89.84 (83.89) + train[2018-10-14-07:26:00] Epoch: [059][8800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.283 (3.589) Prec@1 65.62 (63.23) Prec@5 89.06 (83.88) + train[2018-10-14-07:27:45] Epoch: [059][9000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.241 (3.589) Prec@1 69.53 (63.23) Prec@5 85.94 (83.88) + train[2018-10-14-07:29:31] Epoch: [059][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.436 (3.590) Prec@1 64.84 (63.20) Prec@5 87.50 (83.86) + train[2018-10-14-07:31:16] Epoch: [059][9400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.341 (3.591) Prec@1 65.62 (63.20) Prec@5 85.16 (83.86) + train[2018-10-14-07:33:01] Epoch: [059][9600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.683 (3.591) Prec@1 58.59 (63.19) Prec@5 82.81 (83.85) + train[2018-10-14-07:34:47] Epoch: [059][9800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.403 (3.591) Prec@1 71.09 (63.18) Prec@5 85.16 (83.86) + train[2018-10-14-07:36:32] Epoch: [059][10000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.287 (3.592) Prec@1 69.53 (63.17) Prec@5 88.28 (83.85) + train[2018-10-14-07:36:36] Epoch: [059][10009/10010] Time 0.21 (0.52) Data 0.00 (0.00) Loss 4.773 (3.592) Prec@1 40.00 (63.17) Prec@5 66.67 (83.85) +[2018-10-14-07:36:36] **train** Prec@1 63.17 Prec@5 83.85 Error@1 36.83 Error@5 16.15 Loss:3.592 + test [2018-10-14-07:36:41] Epoch: [059][000/391] Time 4.25 (4.25) Data 4.11 (4.11) Loss 0.838 (0.838) Prec@1 82.03 (82.03) Prec@5 92.97 (92.97) + test [2018-10-14-07:37:07] Epoch: [059][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.654 (1.246) Prec@1 54.69 (70.92) Prec@5 87.50 (90.74) + test [2018-10-14-07:37:32] Epoch: [059][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.563 (1.427) Prec@1 37.50 (67.18) Prec@5 77.50 (87.95) +[2018-10-14-07:37:32] **test** Prec@1 67.18 Prec@5 87.95 Error@1 32.82 Error@5 12.05 Loss:1.427 +----> Best Accuracy : Acc@1=67.46, Acc@5=87.94, Error@1=32.54, Error@5=12.06 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-14-07:37:32] [Epoch=060/250] [Need: 278:51:01] LR=0.0161 ~ 0.0161, Batch=128 + train[2018-10-14-07:37:37] Epoch: [060][000/10010] Time 4.82 (4.82) Data 4.17 (4.17) Loss 4.048 (4.048) Prec@1 53.91 (53.91) Prec@5 76.56 (76.56) + train[2018-10-14-07:39:21] Epoch: [060][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 3.788 (3.516) Prec@1 59.38 (64.53) Prec@5 82.81 (85.15) + train[2018-10-14-07:41:05] Epoch: [060][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.265 (3.527) Prec@1 75.00 (64.30) Prec@5 88.28 (84.94) + train[2018-10-14-07:42:50] Epoch: [060][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.185 (3.534) Prec@1 71.88 (64.27) Prec@5 88.28 (84.73) + train[2018-10-14-07:44:34] Epoch: [060][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.360 (3.532) Prec@1 65.62 (64.28) Prec@5 86.72 (84.72) + train[2018-10-14-07:46:17] Epoch: [060][1000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.474 (3.540) Prec@1 66.41 (64.06) Prec@5 85.94 (84.65) + train[2018-10-14-07:48:01] Epoch: [060][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.931 (3.542) Prec@1 58.59 (64.08) Prec@5 78.12 (84.58) + train[2018-10-14-07:49:45] Epoch: [060][1400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.296 (3.543) Prec@1 68.75 (64.02) Prec@5 87.50 (84.58) + train[2018-10-14-07:51:29] Epoch: [060][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.486 (3.542) Prec@1 61.72 (64.06) Prec@5 85.16 (84.57) + train[2018-10-14-07:53:13] Epoch: [060][1800/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.332 (3.546) Prec@1 63.28 (63.99) Prec@5 87.50 (84.51) + train[2018-10-14-07:54:58] Epoch: [060][2000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.350 (3.548) Prec@1 67.19 (63.97) Prec@5 88.28 (84.45) + train[2018-10-14-07:56:42] Epoch: [060][2200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.430 (3.550) Prec@1 61.72 (63.94) Prec@5 86.72 (84.42) + train[2018-10-14-07:58:25] Epoch: [060][2400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.657 (3.552) Prec@1 57.81 (63.91) Prec@5 85.16 (84.39) + train[2018-10-14-08:00:09] Epoch: [060][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.449 (3.553) Prec@1 65.62 (63.90) Prec@5 86.72 (84.39) + train[2018-10-14-08:01:54] Epoch: [060][2800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.774 (3.554) Prec@1 60.16 (63.87) Prec@5 81.25 (84.36) + train[2018-10-14-08:03:40] Epoch: [060][3000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.462 (3.556) Prec@1 65.62 (63.84) Prec@5 86.72 (84.33) + train[2018-10-14-08:05:26] Epoch: [060][3200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.629 (3.557) Prec@1 61.72 (63.81) Prec@5 83.59 (84.32) + train[2018-10-14-08:07:11] Epoch: [060][3400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.549 (3.559) Prec@1 62.50 (63.77) Prec@5 85.16 (84.31) + train[2018-10-14-08:08:58] Epoch: [060][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.612 (3.561) Prec@1 59.38 (63.71) Prec@5 83.59 (84.28) + train[2018-10-14-08:10:43] Epoch: [060][3800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.218 (3.562) Prec@1 69.53 (63.70) Prec@5 88.28 (84.27) + train[2018-10-14-08:12:30] Epoch: [060][4000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.402 (3.563) Prec@1 67.19 (63.70) Prec@5 85.16 (84.25) + train[2018-10-14-08:14:16] Epoch: [060][4200/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.611 (3.564) Prec@1 60.16 (63.69) Prec@5 82.81 (84.25) + train[2018-10-14-08:16:03] Epoch: [060][4400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.743 (3.565) Prec@1 67.97 (63.69) Prec@5 83.59 (84.22) + train[2018-10-14-08:17:50] Epoch: [060][4600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.814 (3.566) Prec@1 53.91 (63.66) Prec@5 82.81 (84.21) + train[2018-10-14-08:19:36] Epoch: [060][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.594 (3.567) Prec@1 65.62 (63.63) Prec@5 84.38 (84.19) + train[2018-10-14-08:21:21] Epoch: [060][5000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.378 (3.567) Prec@1 69.53 (63.63) Prec@5 85.16 (84.19) + train[2018-10-14-08:23:07] Epoch: [060][5200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.463 (3.566) Prec@1 62.50 (63.64) Prec@5 89.06 (84.19) + train[2018-10-14-08:24:52] Epoch: [060][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.453 (3.567) Prec@1 64.84 (63.63) Prec@5 84.38 (84.19) + train[2018-10-14-08:26:37] Epoch: [060][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.677 (3.569) Prec@1 54.69 (63.60) Prec@5 83.59 (84.17) + train[2018-10-14-08:28:21] Epoch: [060][5800/10010] Time 0.61 (0.53) Data 0.00 (0.00) Loss 3.645 (3.569) Prec@1 57.81 (63.58) Prec@5 84.38 (84.16) + train[2018-10-14-08:30:05] Epoch: [060][6000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.591 (3.570) Prec@1 58.59 (63.56) Prec@5 84.38 (84.14) + train[2018-10-14-08:31:51] Epoch: [060][6200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.487 (3.570) Prec@1 64.84 (63.58) Prec@5 83.59 (84.15) + train[2018-10-14-08:33:35] Epoch: [060][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.389 (3.570) Prec@1 67.19 (63.57) Prec@5 83.59 (84.15) + train[2018-10-14-08:35:19] Epoch: [060][6600/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.473 (3.570) Prec@1 64.06 (63.55) Prec@5 85.16 (84.14) + train[2018-10-14-08:37:03] Epoch: [060][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.534 (3.571) Prec@1 67.97 (63.55) Prec@5 83.59 (84.13) + train[2018-10-14-08:38:47] Epoch: [060][7000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.505 (3.571) Prec@1 64.06 (63.53) Prec@5 86.72 (84.12) + train[2018-10-14-08:40:33] Epoch: [060][7200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.664 (3.572) Prec@1 60.16 (63.52) Prec@5 85.16 (84.11) + train[2018-10-14-08:42:18] Epoch: [060][7400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.778 (3.573) Prec@1 60.16 (63.51) Prec@5 82.81 (84.10) + train[2018-10-14-08:44:03] Epoch: [060][7600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.755 (3.573) Prec@1 60.94 (63.50) Prec@5 79.69 (84.09) + train[2018-10-14-08:45:47] Epoch: [060][7800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.424 (3.574) Prec@1 67.97 (63.49) Prec@5 87.50 (84.08) + train[2018-10-14-08:47:31] Epoch: [060][8000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.630 (3.575) Prec@1 60.94 (63.47) Prec@5 80.47 (84.07) + train[2018-10-14-08:49:15] Epoch: [060][8200/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.468 (3.575) Prec@1 65.62 (63.47) Prec@5 86.72 (84.07) + train[2018-10-14-08:51:01] Epoch: [060][8400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.646 (3.575) Prec@1 65.62 (63.46) Prec@5 83.59 (84.06) + train[2018-10-14-08:52:47] Epoch: [060][8600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.867 (3.576) Prec@1 53.91 (63.46) Prec@5 78.91 (84.05) + train[2018-10-14-08:54:33] Epoch: [060][8800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.364 (3.576) Prec@1 67.19 (63.45) Prec@5 84.38 (84.04) + train[2018-10-14-08:56:19] Epoch: [060][9000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.432 (3.577) Prec@1 67.19 (63.43) Prec@5 87.50 (84.03) + train[2018-10-14-08:58:02] Epoch: [060][9200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.605 (3.577) Prec@1 65.62 (63.42) Prec@5 85.16 (84.02) + train[2018-10-14-08:59:48] Epoch: [060][9400/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.572 (3.578) Prec@1 65.62 (63.42) Prec@5 82.81 (84.02) + train[2018-10-14-09:01:34] Epoch: [060][9600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.108 (3.578) Prec@1 65.62 (63.41) Prec@5 89.84 (84.02) + train[2018-10-14-09:03:21] Epoch: [060][9800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.559 (3.578) Prec@1 65.62 (63.40) Prec@5 86.72 (84.02) + train[2018-10-14-09:05:07] Epoch: [060][10000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.463 (3.579) Prec@1 61.72 (63.39) Prec@5 90.62 (84.01) + train[2018-10-14-09:05:11] Epoch: [060][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 4.233 (3.579) Prec@1 60.00 (63.39) Prec@5 73.33 (84.01) +[2018-10-14-09:05:11] **train** Prec@1 63.39 Prec@5 84.01 Error@1 36.61 Error@5 15.99 Loss:3.579 + test [2018-10-14-09:05:15] Epoch: [060][000/391] Time 4.28 (4.28) Data 4.15 (4.15) Loss 0.782 (0.782) Prec@1 81.25 (81.25) Prec@5 95.31 (95.31) + test [2018-10-14-09:05:41] Epoch: [060][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.477 (1.239) Prec@1 59.38 (70.91) Prec@5 90.62 (90.64) + test [2018-10-14-09:06:05] Epoch: [060][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.441 (1.416) Prec@1 38.75 (67.35) Prec@5 76.25 (87.90) +[2018-10-14-09:06:05] **test** Prec@1 67.35 Prec@5 87.90 Error@1 32.65 Error@5 12.10 Loss:1.416 +----> Best Accuracy : Acc@1=67.46, Acc@5=87.94, Error@1=32.54, Error@5=12.06 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-14-09:06:06] [Epoch=061/250] [Need: 278:57:50] LR=0.0156 ~ 0.0156, Batch=128 + train[2018-10-14-09:06:11] Epoch: [061][000/10010] Time 5.27 (5.27) Data 4.67 (4.67) Loss 3.270 (3.270) Prec@1 68.75 (68.75) Prec@5 88.28 (88.28) + train[2018-10-14-09:07:55] Epoch: [061][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 3.407 (3.519) Prec@1 61.72 (64.47) Prec@5 87.50 (84.79) + train[2018-10-14-09:09:40] Epoch: [061][400/10010] Time 0.49 (0.53) Data 0.00 (0.01) Loss 3.634 (3.529) Prec@1 54.69 (64.28) Prec@5 83.59 (84.52) + train[2018-10-14-09:11:23] Epoch: [061][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.790 (3.532) Prec@1 57.81 (64.34) Prec@5 82.81 (84.50) + train[2018-10-14-09:13:07] Epoch: [061][800/10010] Time 0.56 (0.53) Data 0.00 (0.01) Loss 3.440 (3.535) Prec@1 64.06 (64.32) Prec@5 85.94 (84.49) + train[2018-10-14-09:14:51] Epoch: [061][1000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.171 (3.538) Prec@1 67.97 (64.27) Prec@5 87.50 (84.46) + train[2018-10-14-09:16:37] Epoch: [061][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.649 (3.538) Prec@1 60.94 (64.30) Prec@5 78.12 (84.40) + train[2018-10-14-09:18:21] Epoch: [061][1400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.819 (3.537) Prec@1 56.25 (64.28) Prec@5 83.59 (84.48) + train[2018-10-14-09:20:05] Epoch: [061][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.673 (3.536) Prec@1 59.38 (64.31) Prec@5 85.16 (84.54) + train[2018-10-14-09:21:49] Epoch: [061][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.371 (3.539) Prec@1 63.28 (64.21) Prec@5 86.72 (84.49) + train[2018-10-14-09:23:33] Epoch: [061][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.597 (3.539) Prec@1 61.72 (64.20) Prec@5 79.69 (84.48) + train[2018-10-14-09:25:17] Epoch: [061][2200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.471 (3.539) Prec@1 62.50 (64.20) Prec@5 82.81 (84.50) + train[2018-10-14-09:27:01] Epoch: [061][2400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.651 (3.540) Prec@1 58.59 (64.16) Prec@5 83.59 (84.48) + train[2018-10-14-09:28:46] Epoch: [061][2600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.738 (3.542) Prec@1 64.84 (64.10) Prec@5 80.47 (84.47) + train[2018-10-14-09:30:30] Epoch: [061][2800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.648 (3.543) Prec@1 57.81 (64.11) Prec@5 81.25 (84.46) + train[2018-10-14-09:32:14] Epoch: [061][3000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.683 (3.544) Prec@1 62.50 (64.06) Prec@5 82.03 (84.44) + train[2018-10-14-09:33:59] Epoch: [061][3200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.197 (3.545) Prec@1 70.31 (64.06) Prec@5 86.72 (84.44) + train[2018-10-14-09:35:44] Epoch: [061][3400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.693 (3.546) Prec@1 60.94 (64.02) Prec@5 82.81 (84.43) + train[2018-10-14-09:37:28] Epoch: [061][3600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.668 (3.546) Prec@1 60.16 (64.04) Prec@5 83.59 (84.43) + train[2018-10-14-09:39:12] Epoch: [061][3800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.885 (3.548) Prec@1 58.59 (64.00) Prec@5 77.34 (84.41) + train[2018-10-14-09:40:57] Epoch: [061][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.626 (3.549) Prec@1 63.28 (63.97) Prec@5 83.59 (84.39) + train[2018-10-14-09:42:41] Epoch: [061][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.391 (3.549) Prec@1 62.50 (63.99) Prec@5 85.16 (84.39) + train[2018-10-14-09:44:24] Epoch: [061][4400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.770 (3.551) Prec@1 61.72 (63.96) Prec@5 81.25 (84.38) + train[2018-10-14-09:46:09] Epoch: [061][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.506 (3.552) Prec@1 64.06 (63.95) Prec@5 80.47 (84.37) + train[2018-10-14-09:47:54] Epoch: [061][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.678 (3.552) Prec@1 63.28 (63.94) Prec@5 83.59 (84.37) + train[2018-10-14-09:49:38] Epoch: [061][5000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.668 (3.552) Prec@1 60.16 (63.93) Prec@5 83.59 (84.36) + train[2018-10-14-09:51:22] Epoch: [061][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.929 (3.553) Prec@1 59.38 (63.91) Prec@5 78.12 (84.35) + train[2018-10-14-09:53:07] Epoch: [061][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.467 (3.554) Prec@1 66.41 (63.89) Prec@5 85.94 (84.34) + train[2018-10-14-09:54:52] Epoch: [061][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.571 (3.555) Prec@1 62.50 (63.87) Prec@5 85.16 (84.33) + train[2018-10-14-09:56:35] Epoch: [061][5800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.328 (3.555) Prec@1 74.22 (63.87) Prec@5 85.16 (84.32) + train[2018-10-14-09:58:19] Epoch: [061][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.197 (3.556) Prec@1 70.31 (63.85) Prec@5 89.84 (84.31) + train[2018-10-14-10:00:03] Epoch: [061][6200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.577 (3.556) Prec@1 61.72 (63.84) Prec@5 85.16 (84.30) + train[2018-10-14-10:01:47] Epoch: [061][6400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.633 (3.557) Prec@1 65.62 (63.83) Prec@5 82.81 (84.29) + train[2018-10-14-10:03:31] Epoch: [061][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.084 (3.558) Prec@1 69.53 (63.81) Prec@5 90.62 (84.27) + train[2018-10-14-10:05:15] Epoch: [061][6800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.592 (3.558) Prec@1 63.28 (63.81) Prec@5 82.81 (84.27) + train[2018-10-14-10:06:59] Epoch: [061][7000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.225 (3.559) Prec@1 72.66 (63.79) Prec@5 89.84 (84.27) + train[2018-10-14-10:08:44] Epoch: [061][7200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.669 (3.559) Prec@1 58.59 (63.79) Prec@5 82.81 (84.27) + train[2018-10-14-10:10:28] Epoch: [061][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.552 (3.560) Prec@1 64.84 (63.77) Prec@5 82.03 (84.26) + train[2018-10-14-10:12:13] Epoch: [061][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.838 (3.561) Prec@1 60.94 (63.75) Prec@5 78.91 (84.24) + train[2018-10-14-10:13:57] Epoch: [061][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.572 (3.562) Prec@1 62.50 (63.73) Prec@5 82.81 (84.24) + train[2018-10-14-10:15:41] Epoch: [061][8000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.380 (3.563) Prec@1 64.84 (63.72) Prec@5 85.16 (84.22) + train[2018-10-14-10:17:25] Epoch: [061][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.315 (3.564) Prec@1 70.31 (63.70) Prec@5 85.94 (84.22) + train[2018-10-14-10:19:09] Epoch: [061][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.533 (3.564) Prec@1 63.28 (63.69) Prec@5 81.25 (84.22) + train[2018-10-14-10:20:52] Epoch: [061][8600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.501 (3.565) Prec@1 62.50 (63.67) Prec@5 84.38 (84.21) + train[2018-10-14-10:22:36] Epoch: [061][8800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.468 (3.565) Prec@1 62.50 (63.67) Prec@5 84.38 (84.21) + train[2018-10-14-10:24:20] Epoch: [061][9000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.172 (3.566) Prec@1 70.31 (63.66) Prec@5 85.94 (84.20) + train[2018-10-14-10:26:04] Epoch: [061][9200/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.821 (3.567) Prec@1 54.69 (63.64) Prec@5 81.25 (84.19) + train[2018-10-14-10:27:51] Epoch: [061][9400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.891 (3.567) Prec@1 57.81 (63.62) Prec@5 77.34 (84.18) + train[2018-10-14-10:29:37] Epoch: [061][9600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.749 (3.567) Prec@1 62.50 (63.62) Prec@5 83.59 (84.18) + train[2018-10-14-10:31:24] Epoch: [061][9800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.952 (3.568) Prec@1 58.59 (63.61) Prec@5 80.47 (84.17) + train[2018-10-14-10:33:10] Epoch: [061][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.296 (3.568) Prec@1 71.88 (63.59) Prec@5 85.16 (84.16) + train[2018-10-14-10:33:14] Epoch: [061][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 4.583 (3.568) Prec@1 46.67 (63.59) Prec@5 73.33 (84.15) +[2018-10-14-10:33:14] **train** Prec@1 63.59 Prec@5 84.15 Error@1 36.41 Error@5 15.85 Loss:3.568 + test [2018-10-14-10:33:18] Epoch: [061][000/391] Time 3.61 (3.61) Data 3.47 (3.47) Loss 0.862 (0.862) Prec@1 84.38 (84.38) Prec@5 94.53 (94.53) + test [2018-10-14-10:33:45] Epoch: [061][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.574 (1.220) Prec@1 54.69 (71.61) Prec@5 90.62 (90.96) + test [2018-10-14-10:34:09] Epoch: [061][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.494 (1.410) Prec@1 42.50 (67.67) Prec@5 75.00 (88.12) +[2018-10-14-10:34:10] **test** Prec@1 67.67 Prec@5 88.12 Error@1 32.33 Error@5 11.88 Loss:1.410 +----> Best Accuracy : Acc@1=67.67, Acc@5=88.12, Error@1=32.33, Error@5=11.88 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-14-10:34:10] [Epoch=062/250] [Need: 275:56:56] LR=0.0151 ~ 0.0151, Batch=128 + train[2018-10-14-10:34:14] Epoch: [062][000/10010] Time 4.54 (4.54) Data 3.94 (3.94) Loss 3.440 (3.440) Prec@1 64.06 (64.06) Prec@5 86.72 (86.72) + train[2018-10-14-10:35:59] Epoch: [062][200/10010] Time 0.51 (0.54) Data 0.00 (0.02) Loss 3.800 (3.519) Prec@1 60.16 (64.57) Prec@5 83.59 (84.81) + train[2018-10-14-10:37:43] Epoch: [062][400/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.769 (3.519) Prec@1 63.28 (64.64) Prec@5 81.25 (84.78) + train[2018-10-14-10:39:27] Epoch: [062][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.574 (3.519) Prec@1 66.41 (64.54) Prec@5 84.38 (84.78) + train[2018-10-14-10:41:11] Epoch: [062][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.595 (3.528) Prec@1 63.28 (64.43) Prec@5 81.25 (84.65) + train[2018-10-14-10:42:55] Epoch: [062][1000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.509 (3.532) Prec@1 67.97 (64.36) Prec@5 84.38 (84.61) + train[2018-10-14-10:44:39] Epoch: [062][1200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.248 (3.534) Prec@1 67.19 (64.32) Prec@5 89.84 (84.58) + train[2018-10-14-10:46:22] Epoch: [062][1400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.799 (3.535) Prec@1 60.16 (64.29) Prec@5 83.59 (84.54) + train[2018-10-14-10:48:06] Epoch: [062][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.450 (3.535) Prec@1 67.19 (64.30) Prec@5 83.59 (84.53) + train[2018-10-14-10:49:49] Epoch: [062][1800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.725 (3.540) Prec@1 58.59 (64.21) Prec@5 82.81 (84.47) + train[2018-10-14-10:51:33] Epoch: [062][2000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.475 (3.541) Prec@1 62.50 (64.17) Prec@5 86.72 (84.48) + train[2018-10-14-10:53:17] Epoch: [062][2200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.549 (3.542) Prec@1 57.81 (64.15) Prec@5 85.16 (84.48) + train[2018-10-14-10:55:02] Epoch: [062][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.210 (3.542) Prec@1 68.75 (64.17) Prec@5 88.28 (84.47) + train[2018-10-14-10:56:46] Epoch: [062][2600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.480 (3.543) Prec@1 60.16 (64.13) Prec@5 85.16 (84.47) + train[2018-10-14-10:58:30] Epoch: [062][2800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.318 (3.543) Prec@1 60.94 (64.13) Prec@5 89.84 (84.49) + train[2018-10-14-11:00:14] Epoch: [062][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.466 (3.543) Prec@1 64.06 (64.12) Prec@5 83.59 (84.49) + train[2018-10-14-11:01:58] Epoch: [062][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.685 (3.544) Prec@1 61.72 (64.11) Prec@5 83.59 (84.48) + train[2018-10-14-11:03:42] Epoch: [062][3400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.476 (3.545) Prec@1 69.53 (64.08) Prec@5 83.59 (84.47) + train[2018-10-14-11:05:26] Epoch: [062][3600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.595 (3.545) Prec@1 65.62 (64.06) Prec@5 80.47 (84.47) + train[2018-10-14-11:07:10] Epoch: [062][3800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.482 (3.546) Prec@1 61.72 (64.05) Prec@5 84.38 (84.46) + train[2018-10-14-11:08:54] Epoch: [062][4000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.990 (3.545) Prec@1 57.81 (64.06) Prec@5 77.34 (84.46) + train[2018-10-14-11:10:38] Epoch: [062][4200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.579 (3.545) Prec@1 64.84 (64.05) Prec@5 82.81 (84.45) + train[2018-10-14-11:12:23] Epoch: [062][4400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.625 (3.544) Prec@1 64.06 (64.07) Prec@5 79.69 (84.47) + train[2018-10-14-11:14:07] Epoch: [062][4600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.875 (3.545) Prec@1 58.59 (64.04) Prec@5 77.34 (84.45) + train[2018-10-14-11:15:52] Epoch: [062][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.633 (3.546) Prec@1 65.62 (64.04) Prec@5 82.81 (84.44) + train[2018-10-14-11:17:36] Epoch: [062][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.534 (3.545) Prec@1 66.41 (64.06) Prec@5 82.81 (84.44) + train[2018-10-14-11:19:21] Epoch: [062][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.258 (3.546) Prec@1 70.31 (64.03) Prec@5 88.28 (84.42) + train[2018-10-14-11:21:05] Epoch: [062][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.697 (3.547) Prec@1 62.50 (64.00) Prec@5 78.12 (84.41) + train[2018-10-14-11:22:49] Epoch: [062][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.792 (3.547) Prec@1 60.16 (64.00) Prec@5 81.25 (84.41) + train[2018-10-14-11:24:33] Epoch: [062][5800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.578 (3.548) Prec@1 61.72 (63.99) Prec@5 82.81 (84.39) + train[2018-10-14-11:26:17] Epoch: [062][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.652 (3.549) Prec@1 63.28 (63.97) Prec@5 81.25 (84.36) + train[2018-10-14-11:28:01] Epoch: [062][6200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.395 (3.549) Prec@1 64.06 (63.95) Prec@5 85.16 (84.36) + train[2018-10-14-11:29:45] Epoch: [062][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.831 (3.550) Prec@1 55.47 (63.94) Prec@5 82.81 (84.36) + train[2018-10-14-11:31:30] Epoch: [062][6600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.498 (3.551) Prec@1 62.50 (63.91) Prec@5 85.94 (84.35) + train[2018-10-14-11:33:14] Epoch: [062][6800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.553 (3.550) Prec@1 64.06 (63.91) Prec@5 83.59 (84.35) + train[2018-10-14-11:34:59] Epoch: [062][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.804 (3.551) Prec@1 55.47 (63.89) Prec@5 83.59 (84.34) + train[2018-10-14-11:36:43] Epoch: [062][7200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.855 (3.552) Prec@1 61.72 (63.87) Prec@5 80.47 (84.33) + train[2018-10-14-11:38:27] Epoch: [062][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.756 (3.552) Prec@1 61.72 (63.87) Prec@5 80.47 (84.33) + train[2018-10-14-11:40:11] Epoch: [062][7600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.318 (3.554) Prec@1 65.62 (63.85) Prec@5 89.84 (84.32) + train[2018-10-14-11:41:58] Epoch: [062][7800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.314 (3.554) Prec@1 71.09 (63.84) Prec@5 85.94 (84.31) + train[2018-10-14-11:43:42] Epoch: [062][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.355 (3.555) Prec@1 66.41 (63.83) Prec@5 83.59 (84.30) + train[2018-10-14-11:45:28] Epoch: [062][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.311 (3.555) Prec@1 70.31 (63.83) Prec@5 87.50 (84.30) + train[2018-10-14-11:47:13] Epoch: [062][8400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.483 (3.554) Prec@1 66.41 (63.84) Prec@5 82.03 (84.31) + train[2018-10-14-11:48:58] Epoch: [062][8600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.591 (3.555) Prec@1 64.06 (63.83) Prec@5 83.59 (84.30) + train[2018-10-14-11:50:44] Epoch: [062][8800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.594 (3.555) Prec@1 59.38 (63.82) Prec@5 83.59 (84.29) + train[2018-10-14-11:52:31] Epoch: [062][9000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.470 (3.555) Prec@1 67.97 (63.80) Prec@5 85.94 (84.29) + train[2018-10-14-11:54:18] Epoch: [062][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.756 (3.556) Prec@1 64.84 (63.79) Prec@5 79.69 (84.28) + train[2018-10-14-11:56:04] Epoch: [062][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.757 (3.556) Prec@1 61.72 (63.79) Prec@5 80.47 (84.27) + train[2018-10-14-11:57:49] Epoch: [062][9600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.557 (3.556) Prec@1 64.06 (63.78) Prec@5 83.59 (84.27) + train[2018-10-14-11:59:35] Epoch: [062][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.559 (3.557) Prec@1 65.62 (63.77) Prec@5 84.38 (84.26) + train[2018-10-14-12:01:20] Epoch: [062][10000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.802 (3.557) Prec@1 58.59 (63.77) Prec@5 78.91 (84.26) + train[2018-10-14-12:01:24] Epoch: [062][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 3.681 (3.557) Prec@1 46.67 (63.77) Prec@5 86.67 (84.26) +[2018-10-14-12:01:24] **train** Prec@1 63.77 Prec@5 84.26 Error@1 36.23 Error@5 15.74 Loss:3.557 + test [2018-10-14-12:01:28] Epoch: [062][000/391] Time 3.90 (3.90) Data 3.77 (3.77) Loss 0.656 (0.656) Prec@1 85.94 (85.94) Prec@5 96.88 (96.88) + test [2018-10-14-12:01:55] Epoch: [062][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.581 (1.221) Prec@1 57.81 (71.25) Prec@5 85.94 (91.01) + test [2018-10-14-12:02:20] Epoch: [062][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.556 (1.403) Prec@1 38.75 (67.60) Prec@5 72.50 (88.21) +[2018-10-14-12:02:20] **test** Prec@1 67.60 Prec@5 88.21 Error@1 32.40 Error@5 11.79 Loss:1.403 +----> Best Accuracy : Acc@1=67.67, Acc@5=88.12, Error@1=32.33, Error@5=11.88 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-14-12:02:20] [Epoch=063/250] [Need: 274:47:57] LR=0.0147 ~ 0.0147, Batch=128 + train[2018-10-14-12:02:24] Epoch: [063][000/10010] Time 4.22 (4.22) Data 3.65 (3.65) Loss 3.606 (3.606) Prec@1 61.72 (61.72) Prec@5 82.03 (82.03) + train[2018-10-14-12:04:10] Epoch: [063][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.338 (3.507) Prec@1 69.53 (64.81) Prec@5 90.62 (84.83) + train[2018-10-14-12:05:55] Epoch: [063][400/10010] Time 0.53 (0.54) Data 0.00 (0.01) Loss 3.545 (3.500) Prec@1 61.72 (64.94) Prec@5 86.72 (84.88) + train[2018-10-14-12:07:39] Epoch: [063][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.693 (3.504) Prec@1 57.81 (64.74) Prec@5 82.03 (84.83) + train[2018-10-14-12:09:22] Epoch: [063][800/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.716 (3.511) Prec@1 64.84 (64.62) Prec@5 80.47 (84.70) + train[2018-10-14-12:11:07] Epoch: [063][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.755 (3.515) Prec@1 59.38 (64.57) Prec@5 80.47 (84.67) + train[2018-10-14-12:12:52] Epoch: [063][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.549 (3.517) Prec@1 64.84 (64.50) Prec@5 86.72 (84.68) + train[2018-10-14-12:14:35] Epoch: [063][1400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.649 (3.518) Prec@1 60.94 (64.50) Prec@5 82.81 (84.70) + train[2018-10-14-12:16:20] Epoch: [063][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.236 (3.518) Prec@1 73.44 (64.51) Prec@5 89.84 (84.72) + train[2018-10-14-12:18:04] Epoch: [063][1800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.525 (3.519) Prec@1 64.84 (64.49) Prec@5 82.81 (84.70) + train[2018-10-14-12:19:48] Epoch: [063][2000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.892 (3.522) Prec@1 58.59 (64.42) Prec@5 77.34 (84.67) + train[2018-10-14-12:21:32] Epoch: [063][2200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.662 (3.525) Prec@1 60.16 (64.37) Prec@5 82.81 (84.62) + train[2018-10-14-12:23:16] Epoch: [063][2400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.613 (3.527) Prec@1 59.38 (64.35) Prec@5 84.38 (84.60) + train[2018-10-14-12:25:00] Epoch: [063][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.764 (3.529) Prec@1 63.28 (64.31) Prec@5 80.47 (84.58) + train[2018-10-14-12:26:45] Epoch: [063][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.755 (3.530) Prec@1 64.06 (64.29) Prec@5 78.91 (84.56) + train[2018-10-14-12:28:29] Epoch: [063][3000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.316 (3.530) Prec@1 70.31 (64.25) Prec@5 89.84 (84.57) + train[2018-10-14-12:30:13] Epoch: [063][3200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.179 (3.531) Prec@1 69.53 (64.25) Prec@5 89.84 (84.56) + train[2018-10-14-12:31:58] Epoch: [063][3400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.822 (3.533) Prec@1 62.50 (64.25) Prec@5 82.03 (84.53) + train[2018-10-14-12:33:43] Epoch: [063][3600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.464 (3.533) Prec@1 65.62 (64.24) Prec@5 85.16 (84.52) + train[2018-10-14-12:35:27] Epoch: [063][3800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.639 (3.534) Prec@1 64.06 (64.23) Prec@5 83.59 (84.51) + train[2018-10-14-12:37:10] Epoch: [063][4000/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.671 (3.534) Prec@1 63.28 (64.21) Prec@5 82.03 (84.51) + train[2018-10-14-12:38:54] Epoch: [063][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.217 (3.535) Prec@1 68.75 (64.21) Prec@5 91.41 (84.50) + train[2018-10-14-12:40:39] Epoch: [063][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.164 (3.534) Prec@1 69.53 (64.22) Prec@5 89.06 (84.51) + train[2018-10-14-12:42:22] Epoch: [063][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.652 (3.535) Prec@1 67.19 (64.21) Prec@5 86.72 (84.50) + train[2018-10-14-12:44:07] Epoch: [063][4800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.314 (3.535) Prec@1 68.75 (64.20) Prec@5 86.72 (84.50) + train[2018-10-14-12:45:51] Epoch: [063][5000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.748 (3.536) Prec@1 58.59 (64.19) Prec@5 84.38 (84.50) + train[2018-10-14-12:47:35] Epoch: [063][5200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.764 (3.535) Prec@1 57.03 (64.20) Prec@5 81.25 (84.51) + train[2018-10-14-12:49:19] Epoch: [063][5400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.185 (3.535) Prec@1 67.19 (64.20) Prec@5 89.84 (84.51) + train[2018-10-14-12:51:04] Epoch: [063][5600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.653 (3.535) Prec@1 61.72 (64.20) Prec@5 85.16 (84.50) + train[2018-10-14-12:52:48] Epoch: [063][5800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.459 (3.536) Prec@1 66.41 (64.18) Prec@5 81.25 (84.49) + train[2018-10-14-12:54:33] Epoch: [063][6000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.877 (3.537) Prec@1 57.81 (64.17) Prec@5 79.69 (84.48) + train[2018-10-14-12:56:16] Epoch: [063][6200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.480 (3.538) Prec@1 63.28 (64.15) Prec@5 85.16 (84.48) + train[2018-10-14-12:58:00] Epoch: [063][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.459 (3.538) Prec@1 67.19 (64.15) Prec@5 84.38 (84.48) + train[2018-10-14-12:59:44] Epoch: [063][6600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.356 (3.538) Prec@1 67.97 (64.14) Prec@5 89.06 (84.47) + train[2018-10-14-13:01:28] Epoch: [063][6800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.556 (3.538) Prec@1 62.50 (64.16) Prec@5 82.03 (84.46) + train[2018-10-14-13:03:12] Epoch: [063][7000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.648 (3.538) Prec@1 62.50 (64.14) Prec@5 83.59 (84.46) + train[2018-10-14-13:04:56] Epoch: [063][7200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.593 (3.539) Prec@1 64.06 (64.12) Prec@5 87.50 (84.45) + train[2018-10-14-13:06:40] Epoch: [063][7400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.397 (3.540) Prec@1 60.94 (64.10) Prec@5 87.50 (84.44) + train[2018-10-14-13:08:26] Epoch: [063][7600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.488 (3.540) Prec@1 68.75 (64.08) Prec@5 82.81 (84.43) + train[2018-10-14-13:10:10] Epoch: [063][7800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.464 (3.541) Prec@1 61.72 (64.06) Prec@5 85.16 (84.43) + train[2018-10-14-13:11:55] Epoch: [063][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.851 (3.542) Prec@1 60.94 (64.05) Prec@5 80.47 (84.41) + train[2018-10-14-13:13:38] Epoch: [063][8200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.547 (3.542) Prec@1 64.84 (64.05) Prec@5 85.94 (84.40) + train[2018-10-14-13:15:23] Epoch: [063][8400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.790 (3.543) Prec@1 62.50 (64.05) Prec@5 84.38 (84.40) + train[2018-10-14-13:17:08] Epoch: [063][8600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.487 (3.543) Prec@1 59.38 (64.03) Prec@5 84.38 (84.39) + train[2018-10-14-13:18:54] Epoch: [063][8800/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.625 (3.544) Prec@1 65.62 (64.03) Prec@5 82.03 (84.38) + train[2018-10-14-13:20:40] Epoch: [063][9000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.729 (3.543) Prec@1 57.81 (64.03) Prec@5 82.81 (84.39) + train[2018-10-14-13:22:26] Epoch: [063][9200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.722 (3.543) Prec@1 58.59 (64.02) Prec@5 78.91 (84.38) + train[2018-10-14-13:24:11] Epoch: [063][9400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.567 (3.544) Prec@1 60.94 (64.00) Prec@5 81.25 (84.37) + train[2018-10-14-13:25:56] Epoch: [063][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.535 (3.545) Prec@1 65.62 (64.00) Prec@5 82.03 (84.37) + train[2018-10-14-13:27:40] Epoch: [063][9800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.633 (3.545) Prec@1 57.81 (63.99) Prec@5 87.50 (84.38) + train[2018-10-14-13:29:24] Epoch: [063][10000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.899 (3.546) Prec@1 58.59 (63.98) Prec@5 81.25 (84.37) + train[2018-10-14-13:29:28] Epoch: [063][10009/10010] Time 0.21 (0.52) Data 0.00 (0.00) Loss 5.136 (3.546) Prec@1 46.67 (63.98) Prec@5 73.33 (84.37) +[2018-10-14-13:29:28] **train** Prec@1 63.98 Prec@5 84.37 Error@1 36.02 Error@5 15.63 Loss:3.546 + test [2018-10-14-13:29:32] Epoch: [063][000/391] Time 4.01 (4.01) Data 3.88 (3.88) Loss 0.755 (0.755) Prec@1 82.81 (82.81) Prec@5 92.19 (92.19) + test [2018-10-14-13:29:58] Epoch: [063][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.752 (1.213) Prec@1 55.47 (71.78) Prec@5 85.94 (91.06) + test [2018-10-14-13:30:23] Epoch: [063][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.565 (1.404) Prec@1 38.75 (67.83) Prec@5 73.75 (88.31) +[2018-10-14-13:30:23] **test** Prec@1 67.83 Prec@5 88.31 Error@1 32.17 Error@5 11.69 Loss:1.404 +----> Best Accuracy : Acc@1=67.83, Acc@5=88.31, Error@1=32.17, Error@5=11.69 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-14-13:30:23] [Epoch=064/250] [Need: 272:58:54] LR=0.0142 ~ 0.0142, Batch=128 + train[2018-10-14-13:30:28] Epoch: [064][000/10010] Time 4.48 (4.48) Data 3.91 (3.91) Loss 3.700 (3.700) Prec@1 60.94 (60.94) Prec@5 82.03 (82.03) + train[2018-10-14-13:32:12] Epoch: [064][200/10010] Time 0.51 (0.54) Data 0.00 (0.02) Loss 3.663 (3.489) Prec@1 63.28 (64.90) Prec@5 78.91 (85.20) + train[2018-10-14-13:33:55] Epoch: [064][400/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.795 (3.498) Prec@1 63.28 (64.71) Prec@5 82.81 (85.01) + train[2018-10-14-13:35:40] Epoch: [064][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.389 (3.507) Prec@1 62.50 (64.66) Prec@5 89.84 (84.82) + train[2018-10-14-13:37:24] Epoch: [064][800/10010] Time 0.49 (0.52) Data 0.00 (0.01) Loss 3.256 (3.509) Prec@1 70.31 (64.66) Prec@5 86.72 (84.79) + train[2018-10-14-13:39:08] Epoch: [064][1000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.215 (3.503) Prec@1 71.88 (64.75) Prec@5 87.50 (84.84) + train[2018-10-14-13:40:51] Epoch: [064][1200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.371 (3.504) Prec@1 65.62 (64.71) Prec@5 84.38 (84.84) + train[2018-10-14-13:42:35] Epoch: [064][1400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.476 (3.504) Prec@1 64.06 (64.70) Prec@5 85.94 (84.87) + train[2018-10-14-13:44:20] Epoch: [064][1600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.459 (3.508) Prec@1 67.97 (64.61) Prec@5 82.81 (84.85) + train[2018-10-14-13:46:03] Epoch: [064][1800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.479 (3.513) Prec@1 64.06 (64.51) Prec@5 86.72 (84.80) + train[2018-10-14-13:47:47] Epoch: [064][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.574 (3.513) Prec@1 57.81 (64.51) Prec@5 85.16 (84.80) + train[2018-10-14-13:49:32] Epoch: [064][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.996 (3.513) Prec@1 75.78 (64.52) Prec@5 92.97 (84.79) + train[2018-10-14-13:51:16] Epoch: [064][2400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.556 (3.512) Prec@1 61.72 (64.53) Prec@5 85.16 (84.79) + train[2018-10-14-13:53:00] Epoch: [064][2600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.610 (3.513) Prec@1 64.06 (64.51) Prec@5 82.81 (84.77) + train[2018-10-14-13:54:45] Epoch: [064][2800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.847 (3.514) Prec@1 58.59 (64.50) Prec@5 80.47 (84.77) + train[2018-10-14-13:56:28] Epoch: [064][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.301 (3.514) Prec@1 69.53 (64.48) Prec@5 86.72 (84.76) + train[2018-10-14-13:58:13] Epoch: [064][3200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.112 (3.514) Prec@1 56.25 (64.48) Prec@5 78.91 (84.77) + train[2018-10-14-13:59:58] Epoch: [064][3400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.542 (3.515) Prec@1 73.44 (64.44) Prec@5 83.59 (84.76) + train[2018-10-14-14:01:44] Epoch: [064][3600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.790 (3.517) Prec@1 59.38 (64.43) Prec@5 81.25 (84.73) + train[2018-10-14-14:03:28] Epoch: [064][3800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.607 (3.517) Prec@1 64.84 (64.43) Prec@5 83.59 (84.73) + train[2018-10-14-14:05:12] Epoch: [064][4000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.738 (3.519) Prec@1 59.38 (64.39) Prec@5 86.72 (84.71) + train[2018-10-14-14:06:56] Epoch: [064][4200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.381 (3.521) Prec@1 67.97 (64.37) Prec@5 87.50 (84.70) + train[2018-10-14-14:08:42] Epoch: [064][4400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.732 (3.521) Prec@1 60.94 (64.36) Prec@5 81.25 (84.68) + train[2018-10-14-14:10:27] Epoch: [064][4600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.824 (3.523) Prec@1 59.38 (64.34) Prec@5 80.47 (84.66) + train[2018-10-14-14:12:12] Epoch: [064][4800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.381 (3.523) Prec@1 62.50 (64.33) Prec@5 86.72 (84.65) + train[2018-10-14-14:13:58] Epoch: [064][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.073 (3.523) Prec@1 68.75 (64.33) Prec@5 91.41 (84.65) + train[2018-10-14-14:15:44] Epoch: [064][5200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.259 (3.524) Prec@1 66.41 (64.31) Prec@5 88.28 (84.63) + train[2018-10-14-14:17:31] Epoch: [064][5400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.332 (3.525) Prec@1 68.75 (64.30) Prec@5 86.72 (84.63) + train[2018-10-14-14:19:18] Epoch: [064][5600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.488 (3.526) Prec@1 68.75 (64.29) Prec@5 85.16 (84.62) + train[2018-10-14-14:21:03] Epoch: [064][5800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.765 (3.526) Prec@1 59.38 (64.28) Prec@5 83.59 (84.62) + train[2018-10-14-14:22:50] Epoch: [064][6000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.473 (3.527) Prec@1 66.41 (64.28) Prec@5 82.81 (84.61) + train[2018-10-14-14:24:35] Epoch: [064][6200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.466 (3.526) Prec@1 65.62 (64.30) Prec@5 82.81 (84.61) + train[2018-10-14-14:26:21] Epoch: [064][6400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.647 (3.527) Prec@1 67.97 (64.29) Prec@5 82.81 (84.61) + train[2018-10-14-14:28:07] Epoch: [064][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.832 (3.528) Prec@1 58.59 (64.27) Prec@5 82.81 (84.60) + train[2018-10-14-14:29:53] Epoch: [064][6800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.514 (3.529) Prec@1 61.72 (64.25) Prec@5 84.38 (84.59) + train[2018-10-14-14:31:39] Epoch: [064][7000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.399 (3.529) Prec@1 67.19 (64.23) Prec@5 84.38 (84.58) + train[2018-10-14-14:33:24] Epoch: [064][7200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.226 (3.531) Prec@1 67.97 (64.21) Prec@5 89.06 (84.56) + train[2018-10-14-14:35:10] Epoch: [064][7400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.302 (3.531) Prec@1 67.19 (64.20) Prec@5 85.94 (84.56) + train[2018-10-14-14:36:55] Epoch: [064][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.340 (3.531) Prec@1 70.31 (64.19) Prec@5 84.38 (84.55) + train[2018-10-14-14:38:41] Epoch: [064][7800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.845 (3.532) Prec@1 60.94 (64.19) Prec@5 84.38 (84.55) + train[2018-10-14-14:40:25] Epoch: [064][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.745 (3.532) Prec@1 56.25 (64.19) Prec@5 80.47 (84.54) + train[2018-10-14-14:42:09] Epoch: [064][8200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 4.059 (3.533) Prec@1 56.25 (64.17) Prec@5 77.34 (84.53) + train[2018-10-14-14:43:53] Epoch: [064][8400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.470 (3.534) Prec@1 68.75 (64.16) Prec@5 83.59 (84.52) + train[2018-10-14-14:45:39] Epoch: [064][8600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.611 (3.534) Prec@1 62.50 (64.15) Prec@5 80.47 (84.51) + train[2018-10-14-14:47:23] Epoch: [064][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 4.086 (3.534) Prec@1 56.25 (64.15) Prec@5 76.56 (84.51) + train[2018-10-14-14:49:08] Epoch: [064][9000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.477 (3.535) Prec@1 57.03 (64.13) Prec@5 85.16 (84.50) + train[2018-10-14-14:50:53] Epoch: [064][9200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.445 (3.535) Prec@1 67.19 (64.13) Prec@5 88.28 (84.50) + train[2018-10-14-14:52:38] Epoch: [064][9400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.703 (3.536) Prec@1 60.16 (64.12) Prec@5 81.25 (84.49) + train[2018-10-14-14:54:23] Epoch: [064][9600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.533 (3.536) Prec@1 61.72 (64.12) Prec@5 84.38 (84.49) + train[2018-10-14-14:56:08] Epoch: [064][9800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.294 (3.536) Prec@1 67.97 (64.11) Prec@5 85.16 (84.48) + train[2018-10-14-14:57:52] Epoch: [064][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.417 (3.537) Prec@1 67.19 (64.11) Prec@5 85.94 (84.48) + train[2018-10-14-14:57:56] Epoch: [064][10009/10010] Time 0.18 (0.52) Data 0.00 (0.00) Loss 4.237 (3.537) Prec@1 46.67 (64.11) Prec@5 73.33 (84.48) +[2018-10-14-14:57:56] **train** Prec@1 64.11 Prec@5 84.48 Error@1 35.89 Error@5 15.52 Loss:3.537 + test [2018-10-14-14:58:00] Epoch: [064][000/391] Time 4.07 (4.07) Data 3.94 (3.94) Loss 0.738 (0.738) Prec@1 85.16 (85.16) Prec@5 97.66 (97.66) + test [2018-10-14-14:58:26] Epoch: [064][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.539 (1.239) Prec@1 57.81 (71.75) Prec@5 86.72 (90.80) + test [2018-10-14-14:58:51] Epoch: [064][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.659 (1.420) Prec@1 41.25 (67.90) Prec@5 68.75 (88.20) +[2018-10-14-14:58:51] **test** Prec@1 67.90 Prec@5 88.20 Error@1 32.10 Error@5 11.80 Loss:1.420 +----> Best Accuracy : Acc@1=67.90, Acc@5=88.20, Error@1=32.10, Error@5=11.80 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-14-14:58:51] [Epoch=065/250] [Need: 272:44:45] LR=0.0138 ~ 0.0138, Batch=128 + train[2018-10-14-14:58:55] Epoch: [065][000/10010] Time 4.43 (4.43) Data 3.85 (3.85) Loss 3.389 (3.389) Prec@1 60.94 (60.94) Prec@5 86.72 (86.72) + train[2018-10-14-15:00:40] Epoch: [065][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 3.677 (3.494) Prec@1 60.16 (64.75) Prec@5 85.16 (85.08) + train[2018-10-14-15:02:24] Epoch: [065][400/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.265 (3.499) Prec@1 67.97 (64.85) Prec@5 87.50 (84.96) + train[2018-10-14-15:04:08] Epoch: [065][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.611 (3.503) Prec@1 63.28 (64.61) Prec@5 83.59 (84.94) + train[2018-10-14-15:05:51] Epoch: [065][800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.601 (3.495) Prec@1 64.84 (64.78) Prec@5 84.38 (85.07) + train[2018-10-14-15:07:35] Epoch: [065][1000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 4.080 (3.500) Prec@1 52.34 (64.74) Prec@5 77.34 (84.98) + train[2018-10-14-15:09:19] Epoch: [065][1200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.215 (3.503) Prec@1 68.75 (64.73) Prec@5 90.62 (84.95) + train[2018-10-14-15:11:03] Epoch: [065][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.338 (3.501) Prec@1 66.41 (64.75) Prec@5 86.72 (84.98) + train[2018-10-14-15:12:47] Epoch: [065][1600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.564 (3.503) Prec@1 65.62 (64.69) Prec@5 85.94 (84.96) + train[2018-10-14-15:14:32] Epoch: [065][1800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.513 (3.504) Prec@1 64.06 (64.69) Prec@5 86.72 (84.95) + train[2018-10-14-15:16:16] Epoch: [065][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.355 (3.503) Prec@1 67.19 (64.73) Prec@5 86.72 (84.95) + train[2018-10-14-15:17:59] Epoch: [065][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.355 (3.504) Prec@1 70.31 (64.73) Prec@5 84.38 (84.92) + train[2018-10-14-15:19:43] Epoch: [065][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.730 (3.504) Prec@1 61.72 (64.72) Prec@5 81.25 (84.91) + train[2018-10-14-15:21:27] Epoch: [065][2600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.735 (3.504) Prec@1 61.72 (64.73) Prec@5 82.03 (84.91) + train[2018-10-14-15:23:11] Epoch: [065][2800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.105 (3.504) Prec@1 67.19 (64.73) Prec@5 87.50 (84.91) + train[2018-10-14-15:24:56] Epoch: [065][3000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.643 (3.506) Prec@1 57.03 (64.69) Prec@5 85.16 (84.88) + train[2018-10-14-15:26:41] Epoch: [065][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.720 (3.509) Prec@1 57.81 (64.65) Prec@5 82.81 (84.84) + train[2018-10-14-15:28:25] Epoch: [065][3400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.533 (3.509) Prec@1 64.84 (64.65) Prec@5 81.25 (84.83) + train[2018-10-14-15:30:09] Epoch: [065][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.239 (3.511) Prec@1 68.75 (64.62) Prec@5 86.72 (84.82) + train[2018-10-14-15:31:53] Epoch: [065][3800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.342 (3.512) Prec@1 65.62 (64.58) Prec@5 89.84 (84.79) + train[2018-10-14-15:33:37] Epoch: [065][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.601 (3.513) Prec@1 61.72 (64.60) Prec@5 83.59 (84.78) + train[2018-10-14-15:35:20] Epoch: [065][4200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.270 (3.513) Prec@1 66.41 (64.60) Prec@5 86.72 (84.77) + train[2018-10-14-15:37:05] Epoch: [065][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.628 (3.513) Prec@1 67.19 (64.60) Prec@5 80.47 (84.77) + train[2018-10-14-15:38:49] Epoch: [065][4600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.694 (3.514) Prec@1 63.28 (64.57) Prec@5 80.47 (84.75) + train[2018-10-14-15:40:33] Epoch: [065][4800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.659 (3.515) Prec@1 63.28 (64.57) Prec@5 82.81 (84.75) + train[2018-10-14-15:42:17] Epoch: [065][5000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.445 (3.515) Prec@1 67.19 (64.57) Prec@5 85.16 (84.74) + train[2018-10-14-15:44:02] Epoch: [065][5200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.631 (3.516) Prec@1 64.06 (64.57) Prec@5 84.38 (84.73) + train[2018-10-14-15:45:46] Epoch: [065][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.368 (3.516) Prec@1 64.84 (64.56) Prec@5 86.72 (84.73) + train[2018-10-14-15:47:30] Epoch: [065][5600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.755 (3.517) Prec@1 57.03 (64.55) Prec@5 84.38 (84.71) + train[2018-10-14-15:49:13] Epoch: [065][5800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.255 (3.518) Prec@1 71.88 (64.53) Prec@5 88.28 (84.70) + train[2018-10-14-15:50:57] Epoch: [065][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.799 (3.518) Prec@1 55.47 (64.53) Prec@5 81.25 (84.70) + train[2018-10-14-15:52:42] Epoch: [065][6200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.673 (3.518) Prec@1 64.84 (64.53) Prec@5 84.38 (84.69) + train[2018-10-14-15:54:26] Epoch: [065][6400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.715 (3.520) Prec@1 57.81 (64.50) Prec@5 75.78 (84.67) + train[2018-10-14-15:56:10] Epoch: [065][6600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.603 (3.520) Prec@1 63.28 (64.50) Prec@5 84.38 (84.67) + train[2018-10-14-15:57:54] Epoch: [065][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.502 (3.520) Prec@1 66.41 (64.49) Prec@5 85.94 (84.66) + train[2018-10-14-15:59:38] Epoch: [065][7000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.524 (3.521) Prec@1 64.06 (64.46) Prec@5 85.16 (84.65) + train[2018-10-14-16:01:21] Epoch: [065][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.317 (3.521) Prec@1 73.44 (64.44) Prec@5 86.72 (84.65) + train[2018-10-14-16:03:07] Epoch: [065][7400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.492 (3.522) Prec@1 65.62 (64.44) Prec@5 86.72 (84.64) + train[2018-10-14-16:04:53] Epoch: [065][7600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.387 (3.523) Prec@1 64.06 (64.42) Prec@5 86.72 (84.63) + train[2018-10-14-16:06:39] Epoch: [065][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.612 (3.524) Prec@1 64.84 (64.40) Prec@5 78.91 (84.62) + train[2018-10-14-16:08:22] Epoch: [065][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.486 (3.524) Prec@1 64.06 (64.38) Prec@5 86.72 (84.61) + train[2018-10-14-16:10:07] Epoch: [065][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.337 (3.525) Prec@1 65.62 (64.38) Prec@5 86.72 (84.61) + train[2018-10-14-16:11:51] Epoch: [065][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.358 (3.526) Prec@1 65.62 (64.36) Prec@5 84.38 (84.60) + train[2018-10-14-16:13:34] Epoch: [065][8600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.508 (3.526) Prec@1 60.94 (64.35) Prec@5 85.16 (84.60) + train[2018-10-14-16:15:18] Epoch: [065][8800/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.715 (3.526) Prec@1 62.50 (64.35) Prec@5 82.03 (84.59) + train[2018-10-14-16:17:02] Epoch: [065][9000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.663 (3.527) Prec@1 61.72 (64.34) Prec@5 82.81 (84.58) + train[2018-10-14-16:18:46] Epoch: [065][9200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.529 (3.527) Prec@1 65.62 (64.33) Prec@5 85.94 (84.58) + train[2018-10-14-16:20:30] Epoch: [065][9400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.387 (3.528) Prec@1 63.28 (64.32) Prec@5 86.72 (84.57) + train[2018-10-14-16:22:13] Epoch: [065][9600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.889 (3.528) Prec@1 53.91 (64.32) Prec@5 77.34 (84.57) + train[2018-10-14-16:23:57] Epoch: [065][9800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.859 (3.529) Prec@1 57.03 (64.31) Prec@5 81.25 (84.56) + train[2018-10-14-16:25:41] Epoch: [065][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.374 (3.529) Prec@1 71.88 (64.30) Prec@5 83.59 (84.56) + train[2018-10-14-16:25:45] Epoch: [065][10009/10010] Time 0.21 (0.52) Data 0.00 (0.00) Loss 5.056 (3.529) Prec@1 46.67 (64.30) Prec@5 60.00 (84.56) +[2018-10-14-16:25:45] **train** Prec@1 64.30 Prec@5 84.56 Error@1 35.70 Error@5 15.44 Loss:3.529 + test [2018-10-14-16:25:49] Epoch: [065][000/391] Time 3.85 (3.85) Data 3.72 (3.72) Loss 0.780 (0.780) Prec@1 83.59 (83.59) Prec@5 96.88 (96.88) + test [2018-10-14-16:26:15] Epoch: [065][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.471 (1.199) Prec@1 62.50 (71.90) Prec@5 89.06 (91.19) + test [2018-10-14-16:26:40] Epoch: [065][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.379 (1.392) Prec@1 41.25 (67.87) Prec@5 77.50 (88.35) +[2018-10-14-16:26:40] **test** Prec@1 67.87 Prec@5 88.35 Error@1 32.13 Error@5 11.65 Loss:1.392 +----> Best Accuracy : Acc@1=67.90, Acc@5=88.20, Error@1=32.10, Error@5=11.80 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-14-16:26:40] [Epoch=066/250] [Need: 269:19:30] LR=0.0134 ~ 0.0134, Batch=128 + train[2018-10-14-16:26:44] Epoch: [066][000/10010] Time 4.06 (4.06) Data 3.40 (3.40) Loss 3.514 (3.514) Prec@1 64.84 (64.84) Prec@5 84.38 (84.38) + train[2018-10-14-16:28:28] Epoch: [066][200/10010] Time 0.52 (0.54) Data 0.00 (0.02) Loss 3.375 (3.494) Prec@1 68.75 (64.80) Prec@5 89.06 (84.88) + train[2018-10-14-16:30:13] Epoch: [066][400/10010] Time 0.58 (0.53) Data 0.00 (0.01) Loss 3.441 (3.489) Prec@1 67.97 (64.89) Prec@5 85.94 (85.01) + train[2018-10-14-16:31:57] Epoch: [066][600/10010] Time 0.49 (0.53) Data 0.00 (0.01) Loss 3.884 (3.484) Prec@1 55.47 (64.94) Prec@5 79.69 (85.08) + train[2018-10-14-16:33:42] Epoch: [066][800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.629 (3.490) Prec@1 63.28 (64.83) Prec@5 82.81 (85.00) + train[2018-10-14-16:35:26] Epoch: [066][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.732 (3.489) Prec@1 61.72 (64.89) Prec@5 82.81 (85.03) + train[2018-10-14-16:37:10] Epoch: [066][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.768 (3.494) Prec@1 60.16 (64.84) Prec@5 81.25 (85.00) + train[2018-10-14-16:38:54] Epoch: [066][1400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.411 (3.491) Prec@1 70.31 (64.95) Prec@5 84.38 (85.00) + train[2018-10-14-16:40:38] Epoch: [066][1600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.178 (3.489) Prec@1 66.41 (64.97) Prec@5 87.50 (85.03) + train[2018-10-14-16:42:22] Epoch: [066][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.377 (3.492) Prec@1 68.75 (64.96) Prec@5 86.72 (85.01) + train[2018-10-14-16:44:07] Epoch: [066][2000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.389 (3.491) Prec@1 66.41 (64.96) Prec@5 87.50 (85.02) + train[2018-10-14-16:45:50] Epoch: [066][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.789 (3.491) Prec@1 57.03 (64.96) Prec@5 78.12 (85.01) + train[2018-10-14-16:47:35] Epoch: [066][2400/10010] Time 0.60 (0.52) Data 0.00 (0.00) Loss 4.075 (3.491) Prec@1 57.81 (64.95) Prec@5 77.34 (85.01) + train[2018-10-14-16:49:18] Epoch: [066][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.598 (3.493) Prec@1 60.16 (64.92) Prec@5 87.50 (85.00) + train[2018-10-14-16:51:02] Epoch: [066][2800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.441 (3.492) Prec@1 66.41 (64.92) Prec@5 88.28 (85.01) + train[2018-10-14-16:52:47] Epoch: [066][3000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.617 (3.493) Prec@1 59.38 (64.91) Prec@5 83.59 (84.98) + train[2018-10-14-16:54:30] Epoch: [066][3200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.913 (3.493) Prec@1 61.72 (64.89) Prec@5 77.34 (84.99) + train[2018-10-14-16:56:15] Epoch: [066][3400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.584 (3.494) Prec@1 64.84 (64.90) Prec@5 84.38 (84.98) + train[2018-10-14-16:57:59] Epoch: [066][3600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.343 (3.494) Prec@1 69.53 (64.90) Prec@5 83.59 (84.99) + train[2018-10-14-16:59:44] Epoch: [066][3800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.491 (3.495) Prec@1 65.62 (64.87) Prec@5 85.16 (84.97) + train[2018-10-14-17:01:29] Epoch: [066][4000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.332 (3.496) Prec@1 67.19 (64.86) Prec@5 85.94 (84.97) + train[2018-10-14-17:03:14] Epoch: [066][4200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.509 (3.496) Prec@1 64.06 (64.84) Prec@5 87.50 (84.97) + train[2018-10-14-17:04:59] Epoch: [066][4400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.382 (3.497) Prec@1 70.31 (64.82) Prec@5 86.72 (84.95) + train[2018-10-14-17:06:43] Epoch: [066][4600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.413 (3.498) Prec@1 65.62 (64.80) Prec@5 85.94 (84.95) + train[2018-10-14-17:08:27] Epoch: [066][4800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.672 (3.498) Prec@1 60.16 (64.79) Prec@5 83.59 (84.95) + train[2018-10-14-17:10:12] Epoch: [066][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.965 (3.498) Prec@1 74.22 (64.78) Prec@5 89.84 (84.95) + train[2018-10-14-17:11:56] Epoch: [066][5200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.687 (3.499) Prec@1 62.50 (64.77) Prec@5 84.38 (84.93) + train[2018-10-14-17:13:41] Epoch: [066][5400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.839 (3.500) Prec@1 57.03 (64.75) Prec@5 81.25 (84.92) + train[2018-10-14-17:15:25] Epoch: [066][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.766 (3.501) Prec@1 57.81 (64.73) Prec@5 84.38 (84.89) + train[2018-10-14-17:17:10] Epoch: [066][5800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.599 (3.502) Prec@1 62.50 (64.71) Prec@5 85.16 (84.89) + train[2018-10-14-17:18:53] Epoch: [066][6000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.513 (3.503) Prec@1 67.97 (64.70) Prec@5 84.38 (84.88) + train[2018-10-14-17:20:38] Epoch: [066][6200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.579 (3.504) Prec@1 58.59 (64.69) Prec@5 83.59 (84.88) + train[2018-10-14-17:22:23] Epoch: [066][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.481 (3.504) Prec@1 64.84 (64.67) Prec@5 82.81 (84.87) + train[2018-10-14-17:24:07] Epoch: [066][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.717 (3.504) Prec@1 63.28 (64.67) Prec@5 79.69 (84.87) + train[2018-10-14-17:25:51] Epoch: [066][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.142 (3.505) Prec@1 70.31 (64.65) Prec@5 89.06 (84.86) + train[2018-10-14-17:27:35] Epoch: [066][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.388 (3.506) Prec@1 66.41 (64.63) Prec@5 83.59 (84.84) + train[2018-10-14-17:29:19] Epoch: [066][7200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.313 (3.507) Prec@1 71.09 (64.62) Prec@5 83.59 (84.83) + train[2018-10-14-17:31:03] Epoch: [066][7400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.630 (3.507) Prec@1 64.06 (64.62) Prec@5 82.81 (84.81) + train[2018-10-14-17:32:46] Epoch: [066][7600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.695 (3.509) Prec@1 63.28 (64.59) Prec@5 85.16 (84.80) + train[2018-10-14-17:34:31] Epoch: [066][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.338 (3.510) Prec@1 69.53 (64.58) Prec@5 83.59 (84.77) + train[2018-10-14-17:36:15] Epoch: [066][8000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.725 (3.511) Prec@1 60.94 (64.57) Prec@5 83.59 (84.76) + train[2018-10-14-17:37:59] Epoch: [066][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.463 (3.512) Prec@1 64.06 (64.55) Prec@5 86.72 (84.74) + train[2018-10-14-17:39:43] Epoch: [066][8400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.316 (3.512) Prec@1 65.62 (64.55) Prec@5 91.41 (84.75) + train[2018-10-14-17:41:26] Epoch: [066][8600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.497 (3.513) Prec@1 67.97 (64.53) Prec@5 85.94 (84.73) + train[2018-10-14-17:43:10] Epoch: [066][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.601 (3.514) Prec@1 66.41 (64.53) Prec@5 85.16 (84.72) + train[2018-10-14-17:44:55] Epoch: [066][9000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.944 (3.515) Prec@1 60.16 (64.50) Prec@5 81.25 (84.70) + train[2018-10-14-17:46:40] Epoch: [066][9200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.361 (3.515) Prec@1 63.28 (64.50) Prec@5 88.28 (84.71) + train[2018-10-14-17:48:25] Epoch: [066][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.455 (3.515) Prec@1 62.50 (64.48) Prec@5 85.16 (84.70) + train[2018-10-14-17:50:10] Epoch: [066][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.194 (3.516) Prec@1 64.84 (64.46) Prec@5 88.28 (84.70) + train[2018-10-14-17:51:55] Epoch: [066][9800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.478 (3.516) Prec@1 65.62 (64.45) Prec@5 85.94 (84.69) + train[2018-10-14-17:53:39] Epoch: [066][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.478 (3.516) Prec@1 64.06 (64.45) Prec@5 86.72 (84.69) + train[2018-10-14-17:53:44] Epoch: [066][10009/10010] Time 0.21 (0.52) Data 0.00 (0.00) Loss 3.576 (3.516) Prec@1 66.67 (64.45) Prec@5 93.33 (84.69) +[2018-10-14-17:53:44] **train** Prec@1 64.45 Prec@5 84.69 Error@1 35.55 Error@5 15.31 Loss:3.516 + test [2018-10-14-17:53:48] Epoch: [066][000/391] Time 3.90 (3.90) Data 3.77 (3.77) Loss 0.784 (0.784) Prec@1 84.38 (84.38) Prec@5 96.09 (96.09) + test [2018-10-14-17:54:14] Epoch: [066][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.473 (1.204) Prec@1 65.62 (72.28) Prec@5 89.06 (91.31) + test [2018-10-14-17:54:38] Epoch: [066][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.658 (1.391) Prec@1 41.25 (68.28) Prec@5 70.00 (88.64) +[2018-10-14-17:54:38] **test** Prec@1 68.28 Prec@5 88.64 Error@1 31.72 Error@5 11.36 Loss:1.391 +----> Best Accuracy : Acc@1=68.28, Acc@5=88.64, Error@1=31.72, Error@5=11.36 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-14-17:54:38] [Epoch=067/250] [Need: 268:18:12] LR=0.0130 ~ 0.0130, Batch=128 + train[2018-10-14-17:54:44] Epoch: [067][000/10010] Time 5.70 (5.70) Data 5.14 (5.14) Loss 3.669 (3.669) Prec@1 60.94 (60.94) Prec@5 81.25 (81.25) + train[2018-10-14-17:56:28] Epoch: [067][200/10010] Time 0.51 (0.55) Data 0.00 (0.03) Loss 3.560 (3.473) Prec@1 65.62 (65.33) Prec@5 87.50 (85.47) + train[2018-10-14-17:58:12] Epoch: [067][400/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.643 (3.485) Prec@1 60.16 (65.15) Prec@5 85.16 (85.29) + train[2018-10-14-17:59:57] Epoch: [067][600/10010] Time 0.49 (0.53) Data 0.00 (0.01) Loss 3.517 (3.481) Prec@1 61.72 (65.16) Prec@5 86.72 (85.31) + train[2018-10-14-18:01:40] Epoch: [067][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.457 (3.481) Prec@1 61.72 (65.17) Prec@5 88.28 (85.28) + train[2018-10-14-18:03:25] Epoch: [067][1000/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.541 (3.480) Prec@1 64.84 (65.15) Prec@5 82.81 (85.25) + train[2018-10-14-18:05:09] Epoch: [067][1200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.698 (3.477) Prec@1 66.41 (65.22) Prec@5 82.03 (85.32) + train[2018-10-14-18:06:53] Epoch: [067][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.579 (3.478) Prec@1 62.50 (65.19) Prec@5 85.94 (85.27) + train[2018-10-14-18:08:37] Epoch: [067][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.496 (3.478) Prec@1 63.28 (65.18) Prec@5 86.72 (85.25) + train[2018-10-14-18:10:21] Epoch: [067][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.475 (3.480) Prec@1 64.84 (65.15) Prec@5 82.81 (85.23) + train[2018-10-14-18:12:05] Epoch: [067][2000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.234 (3.481) Prec@1 71.88 (65.14) Prec@5 87.50 (85.20) + train[2018-10-14-18:13:50] Epoch: [067][2200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.624 (3.482) Prec@1 61.72 (65.13) Prec@5 86.72 (85.16) + train[2018-10-14-18:15:34] Epoch: [067][2400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.748 (3.483) Prec@1 63.28 (65.11) Prec@5 82.03 (85.14) + train[2018-10-14-18:17:18] Epoch: [067][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.217 (3.483) Prec@1 71.09 (65.10) Prec@5 88.28 (85.13) + train[2018-10-14-18:19:02] Epoch: [067][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.516 (3.484) Prec@1 66.41 (65.11) Prec@5 82.81 (85.11) + train[2018-10-14-18:20:46] Epoch: [067][3000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.250 (3.485) Prec@1 71.88 (65.09) Prec@5 87.50 (85.11) + train[2018-10-14-18:22:29] Epoch: [067][3200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.290 (3.484) Prec@1 68.75 (65.11) Prec@5 88.28 (85.12) + train[2018-10-14-18:24:13] Epoch: [067][3400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.424 (3.484) Prec@1 64.06 (65.11) Prec@5 89.06 (85.10) + train[2018-10-14-18:25:57] Epoch: [067][3600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.647 (3.485) Prec@1 65.62 (65.11) Prec@5 85.16 (85.09) + train[2018-10-14-18:27:42] Epoch: [067][3800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.358 (3.485) Prec@1 63.28 (65.10) Prec@5 87.50 (85.09) + train[2018-10-14-18:29:26] Epoch: [067][4000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.372 (3.485) Prec@1 67.97 (65.09) Prec@5 86.72 (85.09) + train[2018-10-14-18:31:11] Epoch: [067][4200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.470 (3.487) Prec@1 60.16 (65.07) Prec@5 85.16 (85.08) + train[2018-10-14-18:32:55] Epoch: [067][4400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.388 (3.488) Prec@1 70.31 (65.04) Prec@5 84.38 (85.05) + train[2018-10-14-18:34:40] Epoch: [067][4600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.435 (3.489) Prec@1 67.19 (65.02) Prec@5 83.59 (85.04) + train[2018-10-14-18:36:25] Epoch: [067][4800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.368 (3.490) Prec@1 66.41 (64.98) Prec@5 81.25 (85.03) + train[2018-10-14-18:38:09] Epoch: [067][5000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.978 (3.491) Prec@1 53.12 (64.97) Prec@5 83.59 (85.02) + train[2018-10-14-18:39:54] Epoch: [067][5200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.224 (3.491) Prec@1 68.75 (64.98) Prec@5 87.50 (85.02) + train[2018-10-14-18:41:38] Epoch: [067][5400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.305 (3.491) Prec@1 70.31 (64.97) Prec@5 86.72 (85.01) + train[2018-10-14-18:43:22] Epoch: [067][5600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.407 (3.492) Prec@1 67.19 (64.95) Prec@5 87.50 (85.00) + train[2018-10-14-18:45:06] Epoch: [067][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.718 (3.493) Prec@1 61.72 (64.93) Prec@5 84.38 (85.00) + train[2018-10-14-18:46:51] Epoch: [067][6000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.284 (3.494) Prec@1 67.97 (64.91) Prec@5 86.72 (84.98) + train[2018-10-14-18:48:35] Epoch: [067][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.282 (3.495) Prec@1 64.84 (64.89) Prec@5 89.06 (84.97) + train[2018-10-14-18:50:18] Epoch: [067][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.258 (3.495) Prec@1 67.19 (64.89) Prec@5 85.16 (84.97) + train[2018-10-14-18:52:02] Epoch: [067][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.713 (3.497) Prec@1 59.38 (64.86) Prec@5 83.59 (84.95) + train[2018-10-14-18:53:46] Epoch: [067][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.027 (3.498) Prec@1 73.44 (64.84) Prec@5 91.41 (84.94) + train[2018-10-14-18:55:31] Epoch: [067][7000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.422 (3.499) Prec@1 59.38 (64.82) Prec@5 89.06 (84.93) + train[2018-10-14-18:57:15] Epoch: [067][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.238 (3.499) Prec@1 73.44 (64.81) Prec@5 89.06 (84.92) + train[2018-10-14-18:59:01] Epoch: [067][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.124 (3.500) Prec@1 67.97 (64.79) Prec@5 90.62 (84.91) + train[2018-10-14-19:00:47] Epoch: [067][7600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.450 (3.500) Prec@1 64.84 (64.78) Prec@5 85.16 (84.90) + train[2018-10-14-19:02:31] Epoch: [067][7800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.468 (3.501) Prec@1 64.06 (64.77) Prec@5 85.16 (84.89) + train[2018-10-14-19:04:15] Epoch: [067][8000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.230 (3.501) Prec@1 71.88 (64.75) Prec@5 89.06 (84.89) + train[2018-10-14-19:06:00] Epoch: [067][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.039 (3.501) Prec@1 72.66 (64.75) Prec@5 89.84 (84.89) + train[2018-10-14-19:07:44] Epoch: [067][8400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.338 (3.501) Prec@1 64.84 (64.75) Prec@5 86.72 (84.88) + train[2018-10-14-19:09:28] Epoch: [067][8600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.507 (3.502) Prec@1 61.72 (64.74) Prec@5 86.72 (84.87) + train[2018-10-14-19:11:12] Epoch: [067][8800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.548 (3.504) Prec@1 60.94 (64.71) Prec@5 85.94 (84.85) + train[2018-10-14-19:12:56] Epoch: [067][9000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.521 (3.504) Prec@1 62.50 (64.71) Prec@5 86.72 (84.85) + train[2018-10-14-19:14:40] Epoch: [067][9200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.406 (3.504) Prec@1 64.06 (64.70) Prec@5 88.28 (84.84) + train[2018-10-14-19:16:25] Epoch: [067][9400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.631 (3.505) Prec@1 64.06 (64.69) Prec@5 82.81 (84.84) + train[2018-10-14-19:18:09] Epoch: [067][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.637 (3.505) Prec@1 62.50 (64.70) Prec@5 82.81 (84.85) + train[2018-10-14-19:19:53] Epoch: [067][9800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.620 (3.505) Prec@1 62.50 (64.69) Prec@5 82.03 (84.84) + train[2018-10-14-19:21:37] Epoch: [067][10000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.599 (3.505) Prec@1 62.50 (64.68) Prec@5 83.59 (84.84) + train[2018-10-14-19:21:41] Epoch: [067][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.009 (3.505) Prec@1 66.67 (64.68) Prec@5 73.33 (84.84) +[2018-10-14-19:21:41] **train** Prec@1 64.68 Prec@5 84.84 Error@1 35.32 Error@5 15.16 Loss:3.505 + test [2018-10-14-19:21:45] Epoch: [067][000/391] Time 4.06 (4.06) Data 3.92 (3.92) Loss 0.831 (0.831) Prec@1 82.81 (82.81) Prec@5 95.31 (95.31) + test [2018-10-14-19:22:12] Epoch: [067][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.517 (1.227) Prec@1 63.28 (71.88) Prec@5 85.16 (91.06) + test [2018-10-14-19:22:37] Epoch: [067][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.289 (1.400) Prec@1 32.50 (68.13) Prec@5 80.00 (88.52) +[2018-10-14-19:22:37] **test** Prec@1 68.13 Prec@5 88.52 Error@1 31.87 Error@5 11.48 Loss:1.400 +----> Best Accuracy : Acc@1=68.28, Acc@5=88.64, Error@1=31.72, Error@5=11.36 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-14-19:22:37] [Epoch=068/250] [Need: 266:51:26] LR=0.0126 ~ 0.0126, Batch=128 + train[2018-10-14-19:22:41] Epoch: [068][000/10010] Time 4.28 (4.28) Data 3.68 (3.68) Loss 3.422 (3.422) Prec@1 65.62 (65.62) Prec@5 85.94 (85.94) + train[2018-10-14-19:24:26] Epoch: [068][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 3.347 (3.445) Prec@1 69.53 (65.68) Prec@5 88.28 (85.61) + train[2018-10-14-19:26:10] Epoch: [068][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.500 (3.457) Prec@1 68.75 (65.71) Prec@5 85.16 (85.40) + train[2018-10-14-19:27:54] Epoch: [068][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.560 (3.466) Prec@1 65.62 (65.57) Prec@5 85.94 (85.31) + train[2018-10-14-19:29:38] Epoch: [068][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.266 (3.465) Prec@1 68.75 (65.55) Prec@5 89.06 (85.30) + train[2018-10-14-19:31:22] Epoch: [068][1000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.404 (3.466) Prec@1 62.50 (65.45) Prec@5 83.59 (85.31) + train[2018-10-14-19:33:06] Epoch: [068][1200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.567 (3.467) Prec@1 66.41 (65.44) Prec@5 85.16 (85.34) + train[2018-10-14-19:34:50] Epoch: [068][1400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.294 (3.472) Prec@1 70.31 (65.33) Prec@5 88.28 (85.29) + train[2018-10-14-19:36:35] Epoch: [068][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.394 (3.472) Prec@1 67.97 (65.34) Prec@5 87.50 (85.29) + train[2018-10-14-19:38:19] Epoch: [068][1800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.344 (3.471) Prec@1 67.19 (65.31) Prec@5 87.50 (85.30) + train[2018-10-14-19:40:02] Epoch: [068][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.611 (3.473) Prec@1 60.16 (65.29) Prec@5 87.50 (85.28) + train[2018-10-14-19:41:47] Epoch: [068][2200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.386 (3.476) Prec@1 67.97 (65.25) Prec@5 85.16 (85.27) + train[2018-10-14-19:43:31] Epoch: [068][2400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.499 (3.475) Prec@1 67.19 (65.29) Prec@5 85.94 (85.28) + train[2018-10-14-19:45:16] Epoch: [068][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.622 (3.476) Prec@1 61.72 (65.23) Prec@5 82.81 (85.27) + train[2018-10-14-19:47:02] Epoch: [068][2800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.503 (3.478) Prec@1 60.94 (65.21) Prec@5 83.59 (85.24) + train[2018-10-14-19:48:47] Epoch: [068][3000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.754 (3.478) Prec@1 61.72 (65.20) Prec@5 82.03 (85.24) + train[2018-10-14-19:50:32] Epoch: [068][3200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.568 (3.478) Prec@1 61.72 (65.18) Prec@5 85.16 (85.22) + train[2018-10-14-19:52:17] Epoch: [068][3400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.777 (3.480) Prec@1 67.19 (65.17) Prec@5 82.81 (85.21) + train[2018-10-14-19:54:01] Epoch: [068][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.428 (3.480) Prec@1 65.62 (65.14) Prec@5 86.72 (85.20) + train[2018-10-14-19:55:46] Epoch: [068][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.575 (3.480) Prec@1 63.28 (65.12) Prec@5 87.50 (85.19) + train[2018-10-14-19:57:30] Epoch: [068][4000/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.403 (3.481) Prec@1 66.41 (65.13) Prec@5 85.94 (85.17) + train[2018-10-14-19:59:14] Epoch: [068][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.533 (3.482) Prec@1 64.84 (65.11) Prec@5 82.81 (85.16) + train[2018-10-14-20:00:58] Epoch: [068][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.398 (3.483) Prec@1 66.41 (65.09) Prec@5 85.16 (85.15) + train[2018-10-14-20:02:43] Epoch: [068][4600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.627 (3.483) Prec@1 55.47 (65.08) Prec@5 84.38 (85.15) + train[2018-10-14-20:04:27] Epoch: [068][4800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 4.126 (3.483) Prec@1 54.69 (65.09) Prec@5 76.56 (85.15) + train[2018-10-14-20:06:12] Epoch: [068][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.396 (3.484) Prec@1 64.84 (65.07) Prec@5 82.81 (85.14) + train[2018-10-14-20:07:56] Epoch: [068][5200/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.541 (3.485) Prec@1 62.50 (65.05) Prec@5 80.47 (85.12) + train[2018-10-14-20:09:40] Epoch: [068][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.572 (3.485) Prec@1 65.62 (65.04) Prec@5 85.16 (85.13) + train[2018-10-14-20:11:24] Epoch: [068][5600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.323 (3.485) Prec@1 64.06 (65.06) Prec@5 85.16 (85.12) + train[2018-10-14-20:13:08] Epoch: [068][5800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.666 (3.486) Prec@1 57.03 (65.03) Prec@5 82.03 (85.10) + train[2018-10-14-20:14:53] Epoch: [068][6000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.593 (3.486) Prec@1 63.28 (65.04) Prec@5 78.91 (85.10) + train[2018-10-14-20:16:37] Epoch: [068][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.633 (3.487) Prec@1 59.38 (65.01) Prec@5 81.25 (85.09) + train[2018-10-14-20:18:22] Epoch: [068][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.419 (3.487) Prec@1 69.53 (64.99) Prec@5 84.38 (85.08) + train[2018-10-14-20:20:06] Epoch: [068][6600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.707 (3.488) Prec@1 60.16 (64.97) Prec@5 80.47 (85.06) + train[2018-10-14-20:21:50] Epoch: [068][6800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.527 (3.489) Prec@1 65.62 (64.96) Prec@5 85.16 (85.06) + train[2018-10-14-20:23:34] Epoch: [068][7000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.395 (3.489) Prec@1 67.19 (64.96) Prec@5 85.16 (85.06) + train[2018-10-14-20:25:18] Epoch: [068][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.286 (3.490) Prec@1 71.88 (64.94) Prec@5 89.06 (85.05) + train[2018-10-14-20:27:03] Epoch: [068][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.561 (3.490) Prec@1 64.06 (64.93) Prec@5 84.38 (85.04) + train[2018-10-14-20:28:46] Epoch: [068][7600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.754 (3.490) Prec@1 63.28 (64.92) Prec@5 85.16 (85.04) + train[2018-10-14-20:30:31] Epoch: [068][7800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.394 (3.491) Prec@1 65.62 (64.92) Prec@5 84.38 (85.03) + train[2018-10-14-20:32:16] Epoch: [068][8000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.321 (3.491) Prec@1 67.97 (64.91) Prec@5 86.72 (85.02) + train[2018-10-14-20:34:01] Epoch: [068][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.147 (3.491) Prec@1 71.88 (64.91) Prec@5 88.28 (85.02) + train[2018-10-14-20:35:45] Epoch: [068][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.712 (3.493) Prec@1 56.25 (64.88) Prec@5 80.47 (84.99) + train[2018-10-14-20:37:29] Epoch: [068][8600/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.197 (3.493) Prec@1 68.75 (64.86) Prec@5 90.62 (84.99) + train[2018-10-14-20:39:13] Epoch: [068][8800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.428 (3.494) Prec@1 67.19 (64.85) Prec@5 84.38 (84.98) + train[2018-10-14-20:40:57] Epoch: [068][9000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.551 (3.494) Prec@1 57.03 (64.84) Prec@5 85.94 (84.98) + train[2018-10-14-20:42:41] Epoch: [068][9200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.585 (3.495) Prec@1 64.06 (64.82) Prec@5 82.81 (84.97) + train[2018-10-14-20:44:26] Epoch: [068][9400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.536 (3.495) Prec@1 62.50 (64.82) Prec@5 82.81 (84.96) + train[2018-10-14-20:46:10] Epoch: [068][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.649 (3.496) Prec@1 64.06 (64.81) Prec@5 81.25 (84.95) + train[2018-10-14-20:47:54] Epoch: [068][9800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.677 (3.497) Prec@1 59.38 (64.80) Prec@5 85.94 (84.95) + train[2018-10-14-20:49:39] Epoch: [068][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.577 (3.497) Prec@1 60.94 (64.78) Prec@5 85.16 (84.95) + train[2018-10-14-20:49:43] Epoch: [068][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 3.087 (3.497) Prec@1 66.67 (64.78) Prec@5 86.67 (84.95) +[2018-10-14-20:49:43] **train** Prec@1 64.78 Prec@5 84.95 Error@1 35.22 Error@5 15.05 Loss:3.497 + test [2018-10-14-20:49:47] Epoch: [068][000/391] Time 4.15 (4.15) Data 4.02 (4.02) Loss 0.765 (0.765) Prec@1 84.38 (84.38) Prec@5 94.53 (94.53) + test [2018-10-14-20:50:14] Epoch: [068][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.542 (1.187) Prec@1 59.38 (72.10) Prec@5 85.94 (91.22) + test [2018-10-14-20:50:38] Epoch: [068][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.304 (1.367) Prec@1 41.25 (68.45) Prec@5 78.75 (88.52) +[2018-10-14-20:50:38] **test** Prec@1 68.45 Prec@5 88.52 Error@1 31.55 Error@5 11.48 Loss:1.367 +----> Best Accuracy : Acc@1=68.45, Acc@5=88.52, Error@1=31.55, Error@5=11.48 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-14-20:50:38] [Epoch=069/250] [Need: 265:31:52] LR=0.0122 ~ 0.0122, Batch=128 + train[2018-10-14-20:50:43] Epoch: [069][000/10010] Time 4.51 (4.51) Data 3.91 (3.91) Loss 3.522 (3.522) Prec@1 61.72 (61.72) Prec@5 86.72 (86.72) + train[2018-10-14-20:52:27] Epoch: [069][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 3.690 (3.437) Prec@1 57.03 (65.81) Prec@5 82.03 (85.69) + train[2018-10-14-20:54:12] Epoch: [069][400/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.548 (3.452) Prec@1 61.72 (65.50) Prec@5 86.72 (85.53) + train[2018-10-14-20:55:56] Epoch: [069][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.392 (3.451) Prec@1 64.06 (65.49) Prec@5 89.06 (85.55) + train[2018-10-14-20:57:40] Epoch: [069][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.532 (3.455) Prec@1 64.06 (65.42) Prec@5 85.16 (85.51) + train[2018-10-14-20:59:24] Epoch: [069][1000/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.273 (3.453) Prec@1 69.53 (65.50) Prec@5 86.72 (85.51) + train[2018-10-14-21:01:08] Epoch: [069][1200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.393 (3.452) Prec@1 66.41 (65.51) Prec@5 87.50 (85.53) + train[2018-10-14-21:02:53] Epoch: [069][1400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.604 (3.455) Prec@1 62.50 (65.44) Prec@5 85.16 (85.49) + train[2018-10-14-21:04:38] Epoch: [069][1600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.324 (3.458) Prec@1 68.75 (65.40) Prec@5 85.16 (85.43) + train[2018-10-14-21:06:22] Epoch: [069][1800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.455 (3.461) Prec@1 65.62 (65.39) Prec@5 82.81 (85.38) + train[2018-10-14-21:08:06] Epoch: [069][2000/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.276 (3.462) Prec@1 67.19 (65.37) Prec@5 89.06 (85.37) + train[2018-10-14-21:09:50] Epoch: [069][2200/10010] Time 0.62 (0.52) Data 0.00 (0.00) Loss 3.743 (3.464) Prec@1 63.28 (65.32) Prec@5 83.59 (85.32) + train[2018-10-14-21:11:36] Epoch: [069][2400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.219 (3.466) Prec@1 69.53 (65.32) Prec@5 90.62 (85.30) + train[2018-10-14-21:13:21] Epoch: [069][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.343 (3.468) Prec@1 70.31 (65.33) Prec@5 86.72 (85.26) + train[2018-10-14-21:15:05] Epoch: [069][2800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.693 (3.467) Prec@1 57.81 (65.33) Prec@5 84.38 (85.26) + train[2018-10-14-21:16:49] Epoch: [069][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.131 (3.467) Prec@1 69.53 (65.34) Prec@5 89.06 (85.27) + train[2018-10-14-21:18:34] Epoch: [069][3200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.693 (3.469) Prec@1 63.28 (65.32) Prec@5 82.81 (85.24) + train[2018-10-14-21:20:17] Epoch: [069][3400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.492 (3.470) Prec@1 67.19 (65.31) Prec@5 82.81 (85.24) + train[2018-10-14-21:22:03] Epoch: [069][3600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.367 (3.471) Prec@1 61.72 (65.28) Prec@5 85.94 (85.23) + train[2018-10-14-21:23:48] Epoch: [069][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.932 (3.471) Prec@1 56.25 (65.28) Prec@5 77.34 (85.23) + train[2018-10-14-21:25:32] Epoch: [069][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.388 (3.472) Prec@1 65.62 (65.25) Prec@5 82.03 (85.21) + train[2018-10-14-21:27:17] Epoch: [069][4200/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.595 (3.472) Prec@1 66.41 (65.24) Prec@5 82.03 (85.22) + train[2018-10-14-21:29:01] Epoch: [069][4400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.138 (3.473) Prec@1 77.34 (65.25) Prec@5 89.84 (85.22) + train[2018-10-14-21:30:46] Epoch: [069][4600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.512 (3.473) Prec@1 61.72 (65.24) Prec@5 83.59 (85.21) + train[2018-10-14-21:32:31] Epoch: [069][4800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.620 (3.474) Prec@1 59.38 (65.22) Prec@5 83.59 (85.19) + train[2018-10-14-21:34:15] Epoch: [069][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.752 (3.475) Prec@1 61.72 (65.22) Prec@5 84.38 (85.18) + train[2018-10-14-21:35:59] Epoch: [069][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.642 (3.475) Prec@1 59.38 (65.21) Prec@5 84.38 (85.17) + train[2018-10-14-21:37:44] Epoch: [069][5400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.547 (3.475) Prec@1 60.16 (65.20) Prec@5 86.72 (85.17) + train[2018-10-14-21:39:28] Epoch: [069][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.213 (3.475) Prec@1 67.97 (65.21) Prec@5 87.50 (85.18) + train[2018-10-14-21:41:13] Epoch: [069][5800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.207 (3.476) Prec@1 67.19 (65.19) Prec@5 87.50 (85.18) + train[2018-10-14-21:42:57] Epoch: [069][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.647 (3.477) Prec@1 65.62 (65.16) Prec@5 83.59 (85.15) + train[2018-10-14-21:44:43] Epoch: [069][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.718 (3.478) Prec@1 60.94 (65.17) Prec@5 82.81 (85.14) + train[2018-10-14-21:46:27] Epoch: [069][6400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.157 (3.478) Prec@1 70.31 (65.17) Prec@5 91.41 (85.14) + train[2018-10-14-21:48:11] Epoch: [069][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.193 (3.479) Prec@1 68.75 (65.14) Prec@5 86.72 (85.14) + train[2018-10-14-21:49:56] Epoch: [069][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.557 (3.479) Prec@1 67.19 (65.14) Prec@5 83.59 (85.12) + train[2018-10-14-21:51:39] Epoch: [069][7000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.562 (3.480) Prec@1 68.75 (65.11) Prec@5 83.59 (85.11) + train[2018-10-14-21:53:25] Epoch: [069][7200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.825 (3.481) Prec@1 58.59 (65.10) Prec@5 76.56 (85.10) + train[2018-10-14-21:55:11] Epoch: [069][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.312 (3.481) Prec@1 64.06 (65.09) Prec@5 87.50 (85.09) + train[2018-10-14-21:56:57] Epoch: [069][7600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.425 (3.481) Prec@1 61.72 (65.09) Prec@5 85.16 (85.09) + train[2018-10-14-21:58:43] Epoch: [069][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.476 (3.482) Prec@1 61.72 (65.08) Prec@5 87.50 (85.09) + train[2018-10-14-22:00:30] Epoch: [069][8000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.733 (3.482) Prec@1 59.38 (65.06) Prec@5 82.03 (85.08) + train[2018-10-14-22:02:16] Epoch: [069][8200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.631 (3.483) Prec@1 64.06 (65.06) Prec@5 81.25 (85.08) + train[2018-10-14-22:04:03] Epoch: [069][8400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.307 (3.484) Prec@1 68.75 (65.04) Prec@5 85.94 (85.07) + train[2018-10-14-22:05:49] Epoch: [069][8600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.421 (3.484) Prec@1 64.84 (65.03) Prec@5 84.38 (85.06) + train[2018-10-14-22:07:36] Epoch: [069][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.529 (3.483) Prec@1 60.94 (65.03) Prec@5 86.72 (85.07) + train[2018-10-14-22:09:23] Epoch: [069][9000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.444 (3.484) Prec@1 62.50 (65.02) Prec@5 87.50 (85.07) + train[2018-10-14-22:11:09] Epoch: [069][9200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.512 (3.484) Prec@1 66.41 (65.01) Prec@5 85.16 (85.07) + train[2018-10-14-22:12:55] Epoch: [069][9400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.602 (3.484) Prec@1 62.50 (65.01) Prec@5 82.03 (85.07) + train[2018-10-14-22:14:41] Epoch: [069][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.548 (3.485) Prec@1 64.06 (64.99) Prec@5 83.59 (85.06) + train[2018-10-14-22:16:28] Epoch: [069][9800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.204 (3.486) Prec@1 66.41 (64.98) Prec@5 88.28 (85.05) + train[2018-10-14-22:18:15] Epoch: [069][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.257 (3.486) Prec@1 63.28 (64.97) Prec@5 87.50 (85.05) + train[2018-10-14-22:18:20] Epoch: [069][10009/10010] Time 0.21 (0.53) Data 0.00 (0.00) Loss 3.707 (3.486) Prec@1 66.67 (64.97) Prec@5 86.67 (85.05) +[2018-10-14-22:18:20] **train** Prec@1 64.97 Prec@5 85.05 Error@1 35.03 Error@5 14.95 Loss:3.486 + test [2018-10-14-22:18:24] Epoch: [069][000/391] Time 3.95 (3.95) Data 3.82 (3.82) Loss 0.868 (0.868) Prec@1 84.38 (84.38) Prec@5 93.75 (93.75) + test [2018-10-14-22:18:50] Epoch: [069][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.529 (1.180) Prec@1 60.94 (72.63) Prec@5 86.72 (91.26) + test [2018-10-14-22:19:15] Epoch: [069][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.563 (1.365) Prec@1 37.50 (68.52) Prec@5 75.00 (88.53) +[2018-10-14-22:19:15] **test** Prec@1 68.52 Prec@5 88.53 Error@1 31.48 Error@5 11.47 Loss:1.365 +----> Best Accuracy : Acc@1=68.52, Acc@5=88.53, Error@1=31.48, Error@5=11.47 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-14-22:19:15] [Epoch=070/250] [Need: 265:51:39] LR=0.0119 ~ 0.0119, Batch=128 + train[2018-10-14-22:19:21] Epoch: [070][000/10010] Time 5.56 (5.56) Data 4.95 (4.95) Loss 3.431 (3.431) Prec@1 64.84 (64.84) Prec@5 85.16 (85.16) + train[2018-10-14-22:21:05] Epoch: [070][200/10010] Time 0.54 (0.54) Data 0.00 (0.02) Loss 3.547 (3.442) Prec@1 64.06 (65.82) Prec@5 82.81 (85.70) + train[2018-10-14-22:22:49] Epoch: [070][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.290 (3.447) Prec@1 69.53 (65.70) Prec@5 87.50 (85.48) + train[2018-10-14-22:24:34] Epoch: [070][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.294 (3.448) Prec@1 66.41 (65.77) Prec@5 91.41 (85.54) + train[2018-10-14-22:26:18] Epoch: [070][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.638 (3.449) Prec@1 62.50 (65.78) Prec@5 81.25 (85.57) + train[2018-10-14-22:28:02] Epoch: [070][1000/10010] Time 0.49 (0.53) Data 0.00 (0.01) Loss 3.199 (3.447) Prec@1 71.09 (65.80) Prec@5 89.06 (85.61) + train[2018-10-14-22:29:46] Epoch: [070][1200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.735 (3.448) Prec@1 65.62 (65.80) Prec@5 82.81 (85.60) + train[2018-10-14-22:31:30] Epoch: [070][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.356 (3.449) Prec@1 67.19 (65.79) Prec@5 85.94 (85.56) + train[2018-10-14-22:33:14] Epoch: [070][1600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.715 (3.453) Prec@1 64.06 (65.73) Prec@5 78.91 (85.51) + train[2018-10-14-22:34:58] Epoch: [070][1800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.422 (3.454) Prec@1 68.75 (65.66) Prec@5 85.16 (85.48) + train[2018-10-14-22:36:43] Epoch: [070][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.319 (3.451) Prec@1 68.75 (65.74) Prec@5 84.38 (85.49) + train[2018-10-14-22:38:27] Epoch: [070][2200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.598 (3.451) Prec@1 56.25 (65.71) Prec@5 89.84 (85.50) + train[2018-10-14-22:40:11] Epoch: [070][2400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.801 (3.452) Prec@1 60.94 (65.68) Prec@5 82.03 (85.47) + train[2018-10-14-22:41:56] Epoch: [070][2600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.744 (3.452) Prec@1 58.59 (65.65) Prec@5 81.25 (85.47) + train[2018-10-14-22:43:41] Epoch: [070][2800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.587 (3.452) Prec@1 63.28 (65.65) Prec@5 83.59 (85.46) + train[2018-10-14-22:45:27] Epoch: [070][3000/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.431 (3.453) Prec@1 66.41 (65.62) Prec@5 82.81 (85.45) + train[2018-10-14-22:47:12] Epoch: [070][3200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.356 (3.453) Prec@1 67.19 (65.61) Prec@5 89.84 (85.45) + train[2018-10-14-22:48:58] Epoch: [070][3400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.823 (3.453) Prec@1 54.69 (65.57) Prec@5 82.03 (85.45) + train[2018-10-14-22:50:43] Epoch: [070][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.398 (3.455) Prec@1 68.75 (65.54) Prec@5 82.81 (85.41) + train[2018-10-14-22:52:30] Epoch: [070][3800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.817 (3.455) Prec@1 57.81 (65.53) Prec@5 80.47 (85.41) + train[2018-10-14-22:54:14] Epoch: [070][4000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.815 (3.456) Prec@1 60.94 (65.52) Prec@5 85.16 (85.40) + train[2018-10-14-22:55:58] Epoch: [070][4200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.397 (3.456) Prec@1 63.28 (65.51) Prec@5 88.28 (85.41) + train[2018-10-14-22:57:44] Epoch: [070][4400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.252 (3.457) Prec@1 65.62 (65.49) Prec@5 89.06 (85.40) + train[2018-10-14-22:59:30] Epoch: [070][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.313 (3.458) Prec@1 71.88 (65.49) Prec@5 87.50 (85.39) + train[2018-10-14-23:01:15] Epoch: [070][4800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.508 (3.459) Prec@1 60.16 (65.46) Prec@5 88.28 (85.37) + train[2018-10-14-23:03:01] Epoch: [070][5000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.507 (3.459) Prec@1 67.19 (65.46) Prec@5 81.25 (85.37) + train[2018-10-14-23:04:46] Epoch: [070][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.199 (3.460) Prec@1 71.09 (65.44) Prec@5 89.06 (85.37) + train[2018-10-14-23:06:30] Epoch: [070][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.759 (3.461) Prec@1 60.94 (65.42) Prec@5 81.25 (85.35) + train[2018-10-14-23:08:14] Epoch: [070][5600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.259 (3.461) Prec@1 71.88 (65.41) Prec@5 89.06 (85.34) + train[2018-10-14-23:09:59] Epoch: [070][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.414 (3.462) Prec@1 64.84 (65.40) Prec@5 85.94 (85.34) + train[2018-10-14-23:11:42] Epoch: [070][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.233 (3.462) Prec@1 68.75 (65.41) Prec@5 87.50 (85.33) + train[2018-10-14-23:13:25] Epoch: [070][6200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.388 (3.462) Prec@1 67.19 (65.41) Prec@5 87.50 (85.32) + train[2018-10-14-23:15:09] Epoch: [070][6400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.438 (3.463) Prec@1 62.50 (65.39) Prec@5 86.72 (85.32) + train[2018-10-14-23:16:54] Epoch: [070][6600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.342 (3.463) Prec@1 67.19 (65.37) Prec@5 84.38 (85.30) + train[2018-10-14-23:18:38] Epoch: [070][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.690 (3.463) Prec@1 64.84 (65.37) Prec@5 78.91 (85.30) + train[2018-10-14-23:20:22] Epoch: [070][7000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.276 (3.463) Prec@1 67.97 (65.36) Prec@5 89.06 (85.30) + train[2018-10-14-23:22:05] Epoch: [070][7200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.390 (3.464) Prec@1 63.28 (65.35) Prec@5 84.38 (85.29) + train[2018-10-14-23:23:49] Epoch: [070][7400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.485 (3.465) Prec@1 67.97 (65.34) Prec@5 85.16 (85.29) + train[2018-10-14-23:25:34] Epoch: [070][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.267 (3.466) Prec@1 64.84 (65.32) Prec@5 93.75 (85.28) + train[2018-10-14-23:27:18] Epoch: [070][7800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.518 (3.466) Prec@1 61.72 (65.31) Prec@5 86.72 (85.27) + train[2018-10-14-23:29:02] Epoch: [070][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.991 (3.467) Prec@1 71.88 (65.30) Prec@5 93.75 (85.26) + train[2018-10-14-23:30:47] Epoch: [070][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.428 (3.468) Prec@1 65.62 (65.28) Prec@5 84.38 (85.25) + train[2018-10-14-23:32:31] Epoch: [070][8400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.294 (3.469) Prec@1 71.88 (65.26) Prec@5 85.94 (85.23) + train[2018-10-14-23:34:16] Epoch: [070][8600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.660 (3.470) Prec@1 63.28 (65.25) Prec@5 83.59 (85.23) + train[2018-10-14-23:36:00] Epoch: [070][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.601 (3.470) Prec@1 67.19 (65.24) Prec@5 81.25 (85.22) + train[2018-10-14-23:37:44] Epoch: [070][9000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.775 (3.471) Prec@1 59.38 (65.24) Prec@5 81.25 (85.21) + train[2018-10-14-23:39:27] Epoch: [070][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.685 (3.471) Prec@1 58.59 (65.22) Prec@5 82.03 (85.20) + train[2018-10-14-23:41:11] Epoch: [070][9400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.375 (3.472) Prec@1 70.31 (65.21) Prec@5 88.28 (85.19) + train[2018-10-14-23:42:56] Epoch: [070][9600/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.385 (3.473) Prec@1 64.84 (65.19) Prec@5 86.72 (85.18) + train[2018-10-14-23:44:41] Epoch: [070][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.420 (3.474) Prec@1 67.19 (65.18) Prec@5 85.16 (85.17) + train[2018-10-14-23:46:25] Epoch: [070][10000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.488 (3.474) Prec@1 64.84 (65.18) Prec@5 85.94 (85.17) + train[2018-10-14-23:46:29] Epoch: [070][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.539 (3.475) Prec@1 46.67 (65.17) Prec@5 66.67 (85.17) +[2018-10-14-23:46:29] **train** Prec@1 65.17 Prec@5 85.17 Error@1 34.83 Error@5 14.83 Loss:3.475 + test [2018-10-14-23:46:33] Epoch: [070][000/391] Time 3.78 (3.78) Data 3.65 (3.65) Loss 0.894 (0.894) Prec@1 81.25 (81.25) Prec@5 95.31 (95.31) + test [2018-10-14-23:46:59] Epoch: [070][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.744 (1.196) Prec@1 57.03 (72.54) Prec@5 87.50 (91.38) + test [2018-10-14-23:47:23] Epoch: [070][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.380 (1.368) Prec@1 41.25 (68.99) Prec@5 81.25 (88.83) +[2018-10-14-23:47:23] **test** Prec@1 68.99 Prec@5 88.83 Error@1 31.01 Error@5 11.17 Loss:1.368 +----> Best Accuracy : Acc@1=68.99, Acc@5=88.83, Error@1=31.01, Error@5=11.17 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-14-23:47:24] [Epoch=071/250] [Need: 262:56:31] LR=0.0115 ~ 0.0115, Batch=128 + train[2018-10-14-23:47:29] Epoch: [071][000/10010] Time 5.54 (5.54) Data 4.97 (4.97) Loss 3.402 (3.402) Prec@1 63.28 (63.28) Prec@5 83.59 (83.59) + train[2018-10-14-23:49:14] Epoch: [071][200/10010] Time 0.51 (0.55) Data 0.00 (0.02) Loss 3.562 (3.443) Prec@1 62.50 (66.18) Prec@5 82.81 (85.74) + train[2018-10-14-23:50:58] Epoch: [071][400/10010] Time 0.56 (0.53) Data 0.00 (0.01) Loss 3.268 (3.438) Prec@1 67.97 (66.07) Prec@5 89.06 (85.79) + train[2018-10-14-23:52:41] Epoch: [071][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.096 (3.429) Prec@1 67.97 (66.13) Prec@5 88.28 (85.84) + train[2018-10-14-23:54:26] Epoch: [071][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.557 (3.433) Prec@1 65.62 (66.00) Prec@5 83.59 (85.77) + train[2018-10-14-23:56:10] Epoch: [071][1000/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.458 (3.436) Prec@1 66.41 (65.96) Prec@5 86.72 (85.72) + train[2018-10-14-23:57:54] Epoch: [071][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.480 (3.439) Prec@1 62.50 (65.93) Prec@5 87.50 (85.68) + train[2018-10-14-23:59:38] Epoch: [071][1400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.685 (3.441) Prec@1 58.59 (65.92) Prec@5 85.16 (85.66) + train[2018-10-15-00:01:23] Epoch: [071][1600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.466 (3.440) Prec@1 67.19 (65.88) Prec@5 86.72 (85.68) + train[2018-10-15-00:03:07] Epoch: [071][1800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.432 (3.443) Prec@1 71.09 (65.81) Prec@5 84.38 (85.62) + train[2018-10-15-00:04:51] Epoch: [071][2000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.620 (3.443) Prec@1 57.81 (65.81) Prec@5 85.94 (85.63) + train[2018-10-15-00:06:35] Epoch: [071][2200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.464 (3.444) Prec@1 65.62 (65.81) Prec@5 85.94 (85.61) + train[2018-10-15-00:08:20] Epoch: [071][2400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.050 (3.446) Prec@1 75.78 (65.79) Prec@5 89.84 (85.56) + train[2018-10-15-00:10:06] Epoch: [071][2600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.469 (3.445) Prec@1 66.41 (65.79) Prec@5 87.50 (85.58) + train[2018-10-15-00:11:50] Epoch: [071][2800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.648 (3.448) Prec@1 63.28 (65.73) Prec@5 82.81 (85.55) + train[2018-10-15-00:13:34] Epoch: [071][3000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.495 (3.449) Prec@1 69.53 (65.71) Prec@5 85.16 (85.50) + train[2018-10-15-00:15:18] Epoch: [071][3200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.169 (3.449) Prec@1 67.19 (65.71) Prec@5 89.06 (85.49) + train[2018-10-15-00:17:02] Epoch: [071][3400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.324 (3.450) Prec@1 67.97 (65.71) Prec@5 84.38 (85.48) + train[2018-10-15-00:18:45] Epoch: [071][3600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.578 (3.450) Prec@1 61.72 (65.72) Prec@5 82.81 (85.48) + train[2018-10-15-00:20:29] Epoch: [071][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.442 (3.451) Prec@1 68.75 (65.70) Prec@5 83.59 (85.47) + train[2018-10-15-00:22:14] Epoch: [071][4000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.754 (3.450) Prec@1 56.25 (65.71) Prec@5 82.81 (85.47) + train[2018-10-15-00:23:58] Epoch: [071][4200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.412 (3.452) Prec@1 67.19 (65.68) Prec@5 85.16 (85.45) + train[2018-10-15-00:25:42] Epoch: [071][4400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.346 (3.453) Prec@1 67.19 (65.65) Prec@5 85.16 (85.44) + train[2018-10-15-00:27:27] Epoch: [071][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.698 (3.453) Prec@1 62.50 (65.66) Prec@5 78.91 (85.45) + train[2018-10-15-00:29:11] Epoch: [071][4800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.388 (3.453) Prec@1 64.84 (65.64) Prec@5 88.28 (85.45) + train[2018-10-15-00:30:55] Epoch: [071][5000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.704 (3.454) Prec@1 62.50 (65.61) Prec@5 85.16 (85.44) + train[2018-10-15-00:32:39] Epoch: [071][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.841 (3.455) Prec@1 58.59 (65.58) Prec@5 80.47 (85.44) + train[2018-10-15-00:34:23] Epoch: [071][5400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.510 (3.456) Prec@1 67.97 (65.56) Prec@5 84.38 (85.42) + train[2018-10-15-00:36:07] Epoch: [071][5600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.452 (3.457) Prec@1 68.75 (65.54) Prec@5 84.38 (85.41) + train[2018-10-15-00:37:51] Epoch: [071][5800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.171 (3.458) Prec@1 71.88 (65.51) Prec@5 87.50 (85.41) + train[2018-10-15-00:39:35] Epoch: [071][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.227 (3.459) Prec@1 72.66 (65.49) Prec@5 86.72 (85.41) + train[2018-10-15-00:41:20] Epoch: [071][6200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.279 (3.460) Prec@1 66.41 (65.47) Prec@5 88.28 (85.40) + train[2018-10-15-00:43:04] Epoch: [071][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.509 (3.460) Prec@1 66.41 (65.46) Prec@5 82.81 (85.40) + train[2018-10-15-00:44:48] Epoch: [071][6600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.782 (3.460) Prec@1 60.16 (65.45) Prec@5 83.59 (85.39) + train[2018-10-15-00:46:33] Epoch: [071][6800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.524 (3.462) Prec@1 62.50 (65.43) Prec@5 82.81 (85.36) + train[2018-10-15-00:48:17] Epoch: [071][7000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.052 (3.462) Prec@1 71.09 (65.43) Prec@5 90.62 (85.36) + train[2018-10-15-00:50:00] Epoch: [071][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.439 (3.462) Prec@1 63.28 (65.44) Prec@5 85.94 (85.36) + train[2018-10-15-00:51:45] Epoch: [071][7400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.532 (3.462) Prec@1 60.16 (65.44) Prec@5 84.38 (85.35) + train[2018-10-15-00:53:30] Epoch: [071][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.677 (3.463) Prec@1 63.28 (65.42) Prec@5 82.03 (85.34) + train[2018-10-15-00:55:15] Epoch: [071][7800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.409 (3.463) Prec@1 63.28 (65.40) Prec@5 89.84 (85.34) + train[2018-10-15-00:57:00] Epoch: [071][8000/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.375 (3.464) Prec@1 64.84 (65.39) Prec@5 83.59 (85.33) + train[2018-10-15-00:58:45] Epoch: [071][8200/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.676 (3.465) Prec@1 60.16 (65.38) Prec@5 84.38 (85.32) + train[2018-10-15-01:00:29] Epoch: [071][8400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.724 (3.465) Prec@1 63.28 (65.36) Prec@5 81.25 (85.32) + train[2018-10-15-01:02:13] Epoch: [071][8600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.172 (3.466) Prec@1 71.09 (65.35) Prec@5 89.84 (85.31) + train[2018-10-15-01:03:58] Epoch: [071][8800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.485 (3.466) Prec@1 66.41 (65.34) Prec@5 85.94 (85.30) + train[2018-10-15-01:05:42] Epoch: [071][9000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.717 (3.467) Prec@1 61.72 (65.33) Prec@5 85.16 (85.29) + train[2018-10-15-01:07:26] Epoch: [071][9200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.327 (3.467) Prec@1 65.62 (65.33) Prec@5 86.72 (85.28) + train[2018-10-15-01:09:10] Epoch: [071][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.320 (3.468) Prec@1 67.97 (65.31) Prec@5 87.50 (85.27) + train[2018-10-15-01:10:55] Epoch: [071][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.531 (3.468) Prec@1 63.28 (65.31) Prec@5 82.81 (85.26) + train[2018-10-15-01:12:40] Epoch: [071][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.246 (3.469) Prec@1 67.19 (65.30) Prec@5 87.50 (85.26) + train[2018-10-15-01:14:25] Epoch: [071][10000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.606 (3.469) Prec@1 60.94 (65.30) Prec@5 82.81 (85.25) + train[2018-10-15-01:14:29] Epoch: [071][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 4.528 (3.469) Prec@1 60.00 (65.30) Prec@5 73.33 (85.25) +[2018-10-15-01:14:29] **train** Prec@1 65.30 Prec@5 85.25 Error@1 34.70 Error@5 14.75 Loss:3.469 + test [2018-10-15-01:14:34] Epoch: [071][000/391] Time 4.24 (4.24) Data 4.11 (4.11) Loss 0.862 (0.862) Prec@1 80.47 (80.47) Prec@5 95.31 (95.31) + test [2018-10-15-01:15:00] Epoch: [071][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.378 (1.197) Prec@1 64.84 (72.35) Prec@5 89.84 (91.35) + test [2018-10-15-01:15:24] Epoch: [071][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.360 (1.368) Prec@1 31.25 (68.74) Prec@5 81.25 (88.78) +[2018-10-15-01:15:24] **test** Prec@1 68.74 Prec@5 88.78 Error@1 31.26 Error@5 11.22 Loss:1.368 +----> Best Accuracy : Acc@1=68.99, Acc@5=88.83, Error@1=31.01, Error@5=11.17 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-15-01:15:25] [Epoch=072/250] [Need: 261:06:41] LR=0.0112 ~ 0.0112, Batch=128 + train[2018-10-15-01:15:30] Epoch: [072][000/10010] Time 5.08 (5.08) Data 4.46 (4.46) Loss 3.478 (3.478) Prec@1 62.50 (62.50) Prec@5 87.50 (87.50) + train[2018-10-15-01:17:14] Epoch: [072][200/10010] Time 0.49 (0.55) Data 0.00 (0.02) Loss 3.685 (3.446) Prec@1 62.50 (65.62) Prec@5 85.16 (85.57) + train[2018-10-15-01:18:59] Epoch: [072][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.062 (3.447) Prec@1 71.09 (65.68) Prec@5 89.84 (85.49) + train[2018-10-15-01:20:43] Epoch: [072][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.118 (3.432) Prec@1 75.00 (65.81) Prec@5 87.50 (85.76) + train[2018-10-15-01:22:26] Epoch: [072][800/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.505 (3.432) Prec@1 64.06 (65.83) Prec@5 87.50 (85.71) + train[2018-10-15-01:24:10] Epoch: [072][1000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.155 (3.433) Prec@1 69.53 (65.91) Prec@5 89.06 (85.68) + train[2018-10-15-01:25:54] Epoch: [072][1200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.311 (3.433) Prec@1 67.19 (65.93) Prec@5 90.62 (85.70) + train[2018-10-15-01:27:38] Epoch: [072][1400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.446 (3.433) Prec@1 66.41 (65.93) Prec@5 82.81 (85.72) + train[2018-10-15-01:29:22] Epoch: [072][1600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.108 (3.434) Prec@1 75.78 (65.91) Prec@5 89.84 (85.70) + train[2018-10-15-01:31:06] Epoch: [072][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.154 (3.436) Prec@1 67.19 (65.88) Prec@5 87.50 (85.66) + train[2018-10-15-01:32:50] Epoch: [072][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.469 (3.435) Prec@1 63.28 (65.88) Prec@5 84.38 (85.68) + train[2018-10-15-01:34:34] Epoch: [072][2200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.175 (3.435) Prec@1 71.09 (65.90) Prec@5 89.06 (85.68) + train[2018-10-15-01:36:17] Epoch: [072][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.433 (3.438) Prec@1 68.75 (65.85) Prec@5 84.38 (85.66) + train[2018-10-15-01:38:02] Epoch: [072][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.405 (3.437) Prec@1 64.84 (65.87) Prec@5 88.28 (85.66) + train[2018-10-15-01:39:46] Epoch: [072][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.335 (3.436) Prec@1 65.62 (65.88) Prec@5 86.72 (85.66) + train[2018-10-15-01:41:31] Epoch: [072][3000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.232 (3.438) Prec@1 68.75 (65.85) Prec@5 87.50 (85.64) + train[2018-10-15-01:43:15] Epoch: [072][3200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.716 (3.437) Prec@1 62.50 (65.86) Prec@5 79.69 (85.66) + train[2018-10-15-01:44:59] Epoch: [072][3400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.609 (3.438) Prec@1 60.16 (65.86) Prec@5 82.03 (85.65) + train[2018-10-15-01:46:43] Epoch: [072][3600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.418 (3.438) Prec@1 67.19 (65.84) Prec@5 85.16 (85.63) + train[2018-10-15-01:48:27] Epoch: [072][3800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.471 (3.439) Prec@1 64.06 (65.82) Prec@5 88.28 (85.62) + train[2018-10-15-01:50:12] Epoch: [072][4000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.549 (3.440) Prec@1 64.06 (65.81) Prec@5 85.16 (85.61) + train[2018-10-15-01:51:56] Epoch: [072][4200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.607 (3.440) Prec@1 63.28 (65.79) Prec@5 81.25 (85.61) + train[2018-10-15-01:53:39] Epoch: [072][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.585 (3.442) Prec@1 63.28 (65.77) Prec@5 82.81 (85.58) + train[2018-10-15-01:55:24] Epoch: [072][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.081 (3.443) Prec@1 75.78 (65.73) Prec@5 90.62 (85.56) + train[2018-10-15-01:57:08] Epoch: [072][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.290 (3.444) Prec@1 65.62 (65.72) Prec@5 87.50 (85.55) + train[2018-10-15-01:58:52] Epoch: [072][5000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.401 (3.444) Prec@1 67.97 (65.72) Prec@5 88.28 (85.55) + train[2018-10-15-02:00:35] Epoch: [072][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.420 (3.445) Prec@1 63.28 (65.72) Prec@5 85.16 (85.54) + train[2018-10-15-02:02:20] Epoch: [072][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.252 (3.444) Prec@1 68.75 (65.71) Prec@5 86.72 (85.54) + train[2018-10-15-02:04:04] Epoch: [072][5600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.201 (3.445) Prec@1 69.53 (65.71) Prec@5 88.28 (85.54) + train[2018-10-15-02:05:49] Epoch: [072][5800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.431 (3.445) Prec@1 64.06 (65.70) Prec@5 88.28 (85.54) + train[2018-10-15-02:07:35] Epoch: [072][6000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.196 (3.446) Prec@1 68.75 (65.69) Prec@5 90.62 (85.54) + train[2018-10-15-02:09:21] Epoch: [072][6200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.582 (3.447) Prec@1 66.41 (65.67) Prec@5 84.38 (85.52) + train[2018-10-15-02:11:06] Epoch: [072][6400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.367 (3.448) Prec@1 65.62 (65.66) Prec@5 85.16 (85.52) + train[2018-10-15-02:12:51] Epoch: [072][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.454 (3.448) Prec@1 66.41 (65.66) Prec@5 84.38 (85.51) + train[2018-10-15-02:14:36] Epoch: [072][6800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.266 (3.448) Prec@1 69.53 (65.65) Prec@5 87.50 (85.51) + train[2018-10-15-02:16:22] Epoch: [072][7000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.494 (3.448) Prec@1 65.62 (65.64) Prec@5 84.38 (85.50) + train[2018-10-15-02:18:08] Epoch: [072][7200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.809 (3.449) Prec@1 61.72 (65.63) Prec@5 85.16 (85.50) + train[2018-10-15-02:19:53] Epoch: [072][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.742 (3.449) Prec@1 55.47 (65.62) Prec@5 85.16 (85.50) + train[2018-10-15-02:21:38] Epoch: [072][7600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.577 (3.450) Prec@1 63.28 (65.61) Prec@5 83.59 (85.49) + train[2018-10-15-02:23:23] Epoch: [072][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.502 (3.450) Prec@1 65.62 (65.60) Prec@5 83.59 (85.48) + train[2018-10-15-02:25:09] Epoch: [072][8000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.279 (3.451) Prec@1 72.66 (65.60) Prec@5 87.50 (85.47) + train[2018-10-15-02:26:54] Epoch: [072][8200/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.132 (3.451) Prec@1 67.97 (65.59) Prec@5 91.41 (85.46) + train[2018-10-15-02:28:41] Epoch: [072][8400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.558 (3.452) Prec@1 65.62 (65.58) Prec@5 82.81 (85.45) + train[2018-10-15-02:30:27] Epoch: [072][8600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.499 (3.453) Prec@1 66.41 (65.56) Prec@5 82.81 (85.44) + train[2018-10-15-02:32:13] Epoch: [072][8800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.173 (3.453) Prec@1 71.09 (65.55) Prec@5 90.62 (85.43) + train[2018-10-15-02:33:59] Epoch: [072][9000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.040 (3.454) Prec@1 57.03 (65.54) Prec@5 78.12 (85.41) + train[2018-10-15-02:35:46] Epoch: [072][9200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.557 (3.455) Prec@1 61.72 (65.53) Prec@5 83.59 (85.41) + train[2018-10-15-02:37:32] Epoch: [072][9400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.182 (3.455) Prec@1 71.88 (65.52) Prec@5 87.50 (85.40) + train[2018-10-15-02:39:18] Epoch: [072][9600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.765 (3.456) Prec@1 64.06 (65.50) Prec@5 82.81 (85.38) + train[2018-10-15-02:41:03] Epoch: [072][9800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.578 (3.456) Prec@1 62.50 (65.50) Prec@5 83.59 (85.39) + train[2018-10-15-02:42:49] Epoch: [072][10000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.275 (3.456) Prec@1 67.19 (65.48) Prec@5 86.72 (85.38) + train[2018-10-15-02:42:54] Epoch: [072][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 2.999 (3.456) Prec@1 73.33 (65.48) Prec@5 86.67 (85.38) +[2018-10-15-02:42:54] **train** Prec@1 65.48 Prec@5 85.38 Error@1 34.52 Error@5 14.62 Loss:3.456 + test [2018-10-15-02:42:58] Epoch: [072][000/391] Time 3.98 (3.98) Data 3.85 (3.85) Loss 0.616 (0.616) Prec@1 89.06 (89.06) Prec@5 96.88 (96.88) + test [2018-10-15-02:43:24] Epoch: [072][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.404 (1.156) Prec@1 62.50 (73.03) Prec@5 90.62 (91.82) + test [2018-10-15-02:43:49] Epoch: [072][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.378 (1.341) Prec@1 36.25 (69.24) Prec@5 80.00 (89.06) +[2018-10-15-02:43:49] **test** Prec@1 69.24 Prec@5 89.06 Error@1 30.76 Error@5 10.94 Loss:1.341 +----> Best Accuracy : Acc@1=69.24, Acc@5=89.06, Error@1=30.76, Error@5=10.94 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-15-02:43:49] [Epoch=073/250] [Need: 260:48:53] LR=0.0108 ~ 0.0108, Batch=128 + train[2018-10-15-02:43:54] Epoch: [073][000/10010] Time 4.67 (4.67) Data 4.02 (4.02) Loss 3.558 (3.558) Prec@1 67.97 (67.97) Prec@5 79.69 (79.69) + train[2018-10-15-02:45:38] Epoch: [073][200/10010] Time 0.51 (0.54) Data 0.00 (0.02) Loss 3.379 (3.396) Prec@1 63.28 (66.51) Prec@5 87.50 (86.23) + train[2018-10-15-02:47:22] Epoch: [073][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.638 (3.417) Prec@1 60.94 (66.09) Prec@5 82.81 (85.91) + train[2018-10-15-02:49:06] Epoch: [073][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.603 (3.414) Prec@1 60.94 (66.38) Prec@5 80.47 (85.98) + train[2018-10-15-02:50:50] Epoch: [073][800/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.750 (3.418) Prec@1 61.72 (66.33) Prec@5 78.91 (85.89) + train[2018-10-15-02:52:34] Epoch: [073][1000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.665 (3.421) Prec@1 62.50 (66.33) Prec@5 80.47 (85.82) + train[2018-10-15-02:54:18] Epoch: [073][1200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.467 (3.421) Prec@1 68.75 (66.31) Prec@5 84.38 (85.80) + train[2018-10-15-02:56:02] Epoch: [073][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.665 (3.420) Prec@1 64.06 (66.35) Prec@5 83.59 (85.81) + train[2018-10-15-02:57:45] Epoch: [073][1600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.592 (3.423) Prec@1 62.50 (66.28) Prec@5 82.81 (85.76) + train[2018-10-15-02:59:29] Epoch: [073][1800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.331 (3.428) Prec@1 65.62 (66.19) Prec@5 86.72 (85.69) + train[2018-10-15-03:01:13] Epoch: [073][2000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.931 (3.427) Prec@1 77.34 (66.20) Prec@5 92.19 (85.71) + train[2018-10-15-03:02:57] Epoch: [073][2200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.478 (3.427) Prec@1 65.62 (66.18) Prec@5 86.72 (85.73) + train[2018-10-15-03:04:42] Epoch: [073][2400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.257 (3.428) Prec@1 67.19 (66.17) Prec@5 89.84 (85.71) + train[2018-10-15-03:06:28] Epoch: [073][2600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.418 (3.427) Prec@1 67.97 (66.16) Prec@5 88.28 (85.72) + train[2018-10-15-03:08:11] Epoch: [073][2800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.281 (3.427) Prec@1 67.97 (66.15) Prec@5 85.94 (85.72) + train[2018-10-15-03:09:56] Epoch: [073][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.317 (3.427) Prec@1 64.84 (66.14) Prec@5 84.38 (85.73) + train[2018-10-15-03:11:42] Epoch: [073][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.282 (3.427) Prec@1 66.41 (66.11) Prec@5 88.28 (85.74) + train[2018-10-15-03:13:26] Epoch: [073][3400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.483 (3.430) Prec@1 63.28 (66.07) Prec@5 83.59 (85.69) + train[2018-10-15-03:15:09] Epoch: [073][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.639 (3.431) Prec@1 61.72 (66.04) Prec@5 81.25 (85.69) + train[2018-10-15-03:16:53] Epoch: [073][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.751 (3.430) Prec@1 62.50 (66.04) Prec@5 78.91 (85.69) + train[2018-10-15-03:18:37] Epoch: [073][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.534 (3.431) Prec@1 68.75 (66.01) Prec@5 82.81 (85.67) + train[2018-10-15-03:20:21] Epoch: [073][4200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.916 (3.433) Prec@1 74.22 (65.97) Prec@5 92.97 (85.66) + train[2018-10-15-03:22:05] Epoch: [073][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.725 (3.434) Prec@1 57.03 (65.96) Prec@5 82.81 (85.66) + train[2018-10-15-03:23:49] Epoch: [073][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.048 (3.434) Prec@1 69.53 (65.93) Prec@5 88.28 (85.66) + train[2018-10-15-03:25:34] Epoch: [073][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.722 (3.436) Prec@1 61.72 (65.92) Prec@5 83.59 (85.64) + train[2018-10-15-03:27:18] Epoch: [073][5000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.443 (3.437) Prec@1 66.41 (65.90) Prec@5 85.16 (85.63) + train[2018-10-15-03:29:03] Epoch: [073][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.511 (3.438) Prec@1 67.97 (65.88) Prec@5 82.81 (85.60) + train[2018-10-15-03:30:47] Epoch: [073][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.277 (3.438) Prec@1 70.31 (65.86) Prec@5 86.72 (85.61) + train[2018-10-15-03:32:30] Epoch: [073][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.120 (3.438) Prec@1 73.44 (65.87) Prec@5 89.06 (85.62) + train[2018-10-15-03:34:15] Epoch: [073][5800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.941 (3.439) Prec@1 54.69 (65.84) Prec@5 82.81 (85.61) + train[2018-10-15-03:35:58] Epoch: [073][6000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.351 (3.440) Prec@1 67.19 (65.82) Prec@5 87.50 (85.61) + train[2018-10-15-03:37:43] Epoch: [073][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.576 (3.441) Prec@1 65.62 (65.80) Prec@5 85.16 (85.59) + train[2018-10-15-03:39:26] Epoch: [073][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.334 (3.441) Prec@1 65.62 (65.80) Prec@5 89.06 (85.59) + train[2018-10-15-03:41:10] Epoch: [073][6600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.782 (3.442) Prec@1 59.38 (65.77) Prec@5 82.81 (85.58) + train[2018-10-15-03:42:54] Epoch: [073][6800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.291 (3.443) Prec@1 67.19 (65.75) Prec@5 87.50 (85.57) + train[2018-10-15-03:44:38] Epoch: [073][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.317 (3.444) Prec@1 68.75 (65.74) Prec@5 87.50 (85.55) + train[2018-10-15-03:46:24] Epoch: [073][7200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.426 (3.444) Prec@1 68.75 (65.74) Prec@5 85.94 (85.55) + train[2018-10-15-03:48:09] Epoch: [073][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.382 (3.444) Prec@1 64.84 (65.74) Prec@5 89.06 (85.55) + train[2018-10-15-03:49:52] Epoch: [073][7600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.385 (3.444) Prec@1 65.62 (65.74) Prec@5 85.94 (85.55) + train[2018-10-15-03:51:38] Epoch: [073][7800/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.457 (3.445) Prec@1 64.06 (65.73) Prec@5 85.16 (85.55) + train[2018-10-15-03:53:22] Epoch: [073][8000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.213 (3.445) Prec@1 72.66 (65.73) Prec@5 87.50 (85.54) + train[2018-10-15-03:55:07] Epoch: [073][8200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.556 (3.446) Prec@1 66.41 (65.72) Prec@5 83.59 (85.53) + train[2018-10-15-03:56:52] Epoch: [073][8400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.393 (3.447) Prec@1 68.75 (65.71) Prec@5 87.50 (85.51) + train[2018-10-15-03:58:36] Epoch: [073][8600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.414 (3.447) Prec@1 64.84 (65.70) Prec@5 85.16 (85.50) + train[2018-10-15-04:00:20] Epoch: [073][8800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.614 (3.447) Prec@1 63.28 (65.70) Prec@5 81.25 (85.51) + train[2018-10-15-04:02:05] Epoch: [073][9000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.051 (3.448) Prec@1 70.31 (65.69) Prec@5 92.19 (85.50) + train[2018-10-15-04:03:48] Epoch: [073][9200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.308 (3.448) Prec@1 63.28 (65.69) Prec@5 88.28 (85.50) + train[2018-10-15-04:05:32] Epoch: [073][9400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.774 (3.448) Prec@1 56.25 (65.68) Prec@5 81.25 (85.49) + train[2018-10-15-04:07:17] Epoch: [073][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.197 (3.448) Prec@1 66.41 (65.68) Prec@5 89.84 (85.49) + train[2018-10-15-04:09:01] Epoch: [073][9800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.502 (3.449) Prec@1 60.16 (65.66) Prec@5 82.81 (85.48) + train[2018-10-15-04:10:44] Epoch: [073][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.673 (3.449) Prec@1 60.94 (65.65) Prec@5 84.38 (85.48) + train[2018-10-15-04:10:49] Epoch: [073][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 4.021 (3.449) Prec@1 46.67 (65.65) Prec@5 86.67 (85.48) +[2018-10-15-04:10:49] **train** Prec@1 65.65 Prec@5 85.48 Error@1 34.35 Error@5 14.52 Loss:3.449 + test [2018-10-15-04:10:53] Epoch: [073][000/391] Time 4.06 (4.06) Data 3.92 (3.92) Loss 0.651 (0.651) Prec@1 88.28 (88.28) Prec@5 95.31 (95.31) + test [2018-10-15-04:11:20] Epoch: [073][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.186 (1.181) Prec@1 73.44 (72.85) Prec@5 94.53 (91.65) + test [2018-10-15-04:11:44] Epoch: [073][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.281 (1.365) Prec@1 42.50 (69.04) Prec@5 77.50 (89.04) +[2018-10-15-04:11:44] **test** Prec@1 69.04 Prec@5 89.04 Error@1 30.96 Error@5 10.96 Loss:1.365 +----> Best Accuracy : Acc@1=69.24, Acc@5=89.06, Error@1=30.76, Error@5=10.94 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-15-04:11:44] [Epoch=074/250] [Need: 257:52:03] LR=0.0105 ~ 0.0105, Batch=128 + train[2018-10-15-04:11:49] Epoch: [074][000/10010] Time 5.63 (5.63) Data 5.06 (5.06) Loss 3.405 (3.405) Prec@1 64.84 (64.84) Prec@5 86.72 (86.72) + train[2018-10-15-04:13:33] Epoch: [074][200/10010] Time 0.54 (0.54) Data 0.00 (0.03) Loss 3.410 (3.396) Prec@1 63.28 (66.73) Prec@5 85.94 (86.38) + train[2018-10-15-04:15:17] Epoch: [074][400/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.038 (3.406) Prec@1 74.22 (66.53) Prec@5 92.19 (86.07) + train[2018-10-15-04:17:01] Epoch: [074][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.429 (3.404) Prec@1 64.06 (66.50) Prec@5 87.50 (86.05) + train[2018-10-15-04:18:45] Epoch: [074][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.284 (3.409) Prec@1 71.09 (66.44) Prec@5 85.94 (86.02) + train[2018-10-15-04:20:28] Epoch: [074][1000/10010] Time 0.53 (0.52) Data 0.00 (0.01) Loss 3.512 (3.411) Prec@1 62.50 (66.39) Prec@5 85.16 (86.01) + train[2018-10-15-04:22:11] Epoch: [074][1200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.180 (3.415) Prec@1 70.31 (66.29) Prec@5 89.06 (85.94) + train[2018-10-15-04:23:55] Epoch: [074][1400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.406 (3.416) Prec@1 66.41 (66.28) Prec@5 89.84 (85.93) + train[2018-10-15-04:25:39] Epoch: [074][1600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.651 (3.418) Prec@1 64.84 (66.25) Prec@5 82.81 (85.92) + train[2018-10-15-04:27:24] Epoch: [074][1800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.987 (3.420) Prec@1 76.56 (66.22) Prec@5 89.06 (85.87) + train[2018-10-15-04:29:08] Epoch: [074][2000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.463 (3.418) Prec@1 66.41 (66.28) Prec@5 85.16 (85.89) + train[2018-10-15-04:30:52] Epoch: [074][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.085 (3.417) Prec@1 71.09 (66.29) Prec@5 89.84 (85.90) + train[2018-10-15-04:32:36] Epoch: [074][2400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.310 (3.418) Prec@1 71.88 (66.25) Prec@5 89.84 (85.91) + train[2018-10-15-04:34:20] Epoch: [074][2600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.852 (3.419) Prec@1 58.59 (66.22) Prec@5 82.81 (85.89) + train[2018-10-15-04:36:03] Epoch: [074][2800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.366 (3.420) Prec@1 67.97 (66.22) Prec@5 81.25 (85.88) + train[2018-10-15-04:37:47] Epoch: [074][3000/10010] Time 0.59 (0.52) Data 0.00 (0.00) Loss 3.596 (3.421) Prec@1 57.81 (66.18) Prec@5 83.59 (85.86) + train[2018-10-15-04:39:31] Epoch: [074][3200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.410 (3.420) Prec@1 66.41 (66.21) Prec@5 82.03 (85.87) + train[2018-10-15-04:41:16] Epoch: [074][3400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.560 (3.420) Prec@1 66.41 (66.19) Prec@5 82.81 (85.87) + train[2018-10-15-04:43:00] Epoch: [074][3600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.027 (3.421) Prec@1 75.00 (66.16) Prec@5 89.84 (85.87) + train[2018-10-15-04:44:45] Epoch: [074][3800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.434 (3.422) Prec@1 66.41 (66.13) Prec@5 82.81 (85.85) + train[2018-10-15-04:46:29] Epoch: [074][4000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.377 (3.422) Prec@1 65.62 (66.12) Prec@5 88.28 (85.84) + train[2018-10-15-04:48:13] Epoch: [074][4200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.317 (3.423) Prec@1 64.84 (66.10) Prec@5 89.06 (85.82) + train[2018-10-15-04:49:57] Epoch: [074][4400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.385 (3.424) Prec@1 67.97 (66.11) Prec@5 87.50 (85.81) + train[2018-10-15-04:51:42] Epoch: [074][4600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.598 (3.426) Prec@1 69.53 (66.08) Prec@5 83.59 (85.79) + train[2018-10-15-04:53:26] Epoch: [074][4800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.647 (3.426) Prec@1 59.38 (66.07) Prec@5 82.03 (85.79) + train[2018-10-15-04:55:10] Epoch: [074][5000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.370 (3.426) Prec@1 62.50 (66.05) Prec@5 86.72 (85.79) + train[2018-10-15-04:56:55] Epoch: [074][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.576 (3.427) Prec@1 60.94 (66.03) Prec@5 83.59 (85.77) + train[2018-10-15-04:58:39] Epoch: [074][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.412 (3.429) Prec@1 64.06 (65.99) Prec@5 85.94 (85.74) + train[2018-10-15-05:00:24] Epoch: [074][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.271 (3.430) Prec@1 70.31 (65.98) Prec@5 89.06 (85.74) + train[2018-10-15-05:02:08] Epoch: [074][5800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.268 (3.431) Prec@1 67.19 (65.96) Prec@5 89.84 (85.72) + train[2018-10-15-05:03:52] Epoch: [074][6000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.467 (3.431) Prec@1 64.06 (65.96) Prec@5 85.16 (85.72) + train[2018-10-15-05:05:36] Epoch: [074][6200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.568 (3.431) Prec@1 62.50 (65.95) Prec@5 83.59 (85.70) + train[2018-10-15-05:07:20] Epoch: [074][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.535 (3.432) Prec@1 61.72 (65.94) Prec@5 87.50 (85.70) + train[2018-10-15-05:09:05] Epoch: [074][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.470 (3.432) Prec@1 70.31 (65.94) Prec@5 83.59 (85.69) + train[2018-10-15-05:10:49] Epoch: [074][6800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.384 (3.432) Prec@1 64.06 (65.92) Prec@5 84.38 (85.70) + train[2018-10-15-05:12:33] Epoch: [074][7000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.273 (3.432) Prec@1 65.62 (65.91) Prec@5 89.06 (85.69) + train[2018-10-15-05:14:17] Epoch: [074][7200/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.417 (3.433) Prec@1 66.41 (65.91) Prec@5 85.16 (85.68) + train[2018-10-15-05:16:02] Epoch: [074][7400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.501 (3.434) Prec@1 66.41 (65.89) Prec@5 85.16 (85.67) + train[2018-10-15-05:17:46] Epoch: [074][7600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.435 (3.435) Prec@1 65.62 (65.86) Prec@5 83.59 (85.65) + train[2018-10-15-05:19:30] Epoch: [074][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.433 (3.435) Prec@1 66.41 (65.85) Prec@5 78.91 (85.65) + train[2018-10-15-05:21:13] Epoch: [074][8000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.414 (3.435) Prec@1 63.28 (65.85) Prec@5 85.16 (85.65) + train[2018-10-15-05:22:57] Epoch: [074][8200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.109 (3.435) Prec@1 69.53 (65.85) Prec@5 91.41 (85.65) + train[2018-10-15-05:24:41] Epoch: [074][8400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.506 (3.435) Prec@1 62.50 (65.86) Prec@5 85.16 (85.64) + train[2018-10-15-05:26:25] Epoch: [074][8600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.332 (3.435) Prec@1 65.62 (65.86) Prec@5 84.38 (85.65) + train[2018-10-15-05:28:09] Epoch: [074][8800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.610 (3.436) Prec@1 62.50 (65.84) Prec@5 82.03 (85.63) + train[2018-10-15-05:29:53] Epoch: [074][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.171 (3.436) Prec@1 67.97 (65.83) Prec@5 89.06 (85.63) + train[2018-10-15-05:31:38] Epoch: [074][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.480 (3.436) Prec@1 64.06 (65.83) Prec@5 82.03 (85.63) + train[2018-10-15-05:33:25] Epoch: [074][9400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.614 (3.436) Prec@1 64.06 (65.83) Prec@5 84.38 (85.63) + train[2018-10-15-05:35:11] Epoch: [074][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.478 (3.437) Prec@1 64.84 (65.82) Prec@5 86.72 (85.62) + train[2018-10-15-05:36:58] Epoch: [074][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.538 (3.438) Prec@1 64.06 (65.81) Prec@5 82.81 (85.61) + train[2018-10-15-05:38:44] Epoch: [074][10000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.284 (3.437) Prec@1 68.75 (65.80) Prec@5 85.16 (85.61) + train[2018-10-15-05:38:49] Epoch: [074][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 3.709 (3.437) Prec@1 60.00 (65.80) Prec@5 86.67 (85.61) +[2018-10-15-05:38:49] **train** Prec@1 65.80 Prec@5 85.61 Error@1 34.20 Error@5 14.39 Loss:3.437 + test [2018-10-15-05:38:53] Epoch: [074][000/391] Time 4.09 (4.09) Data 3.95 (3.95) Loss 0.799 (0.799) Prec@1 79.69 (79.69) Prec@5 96.09 (96.09) + test [2018-10-15-05:39:19] Epoch: [074][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.424 (1.174) Prec@1 64.06 (72.81) Prec@5 89.06 (91.69) + test [2018-10-15-05:39:44] Epoch: [074][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.288 (1.355) Prec@1 38.75 (69.09) Prec@5 83.75 (88.97) +[2018-10-15-05:39:44] **test** Prec@1 69.09 Prec@5 88.97 Error@1 30.91 Error@5 11.03 Loss:1.355 +----> Best Accuracy : Acc@1=69.24, Acc@5=89.06, Error@1=30.76, Error@5=10.94 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-15-05:39:44] [Epoch=075/250] [Need: 256:39:57] LR=0.0102 ~ 0.0102, Batch=128 + train[2018-10-15-05:39:48] Epoch: [075][000/10010] Time 4.08 (4.08) Data 3.46 (3.46) Loss 3.740 (3.740) Prec@1 59.38 (59.38) Prec@5 80.47 (80.47) + train[2018-10-15-05:41:33] Epoch: [075][200/10010] Time 0.52 (0.54) Data 0.00 (0.02) Loss 2.991 (3.375) Prec@1 73.44 (67.05) Prec@5 92.19 (86.40) + train[2018-10-15-05:43:17] Epoch: [075][400/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.215 (3.391) Prec@1 67.97 (66.75) Prec@5 90.62 (86.22) + train[2018-10-15-05:45:00] Epoch: [075][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.494 (3.393) Prec@1 67.97 (66.70) Prec@5 84.38 (86.19) + train[2018-10-15-05:46:45] Epoch: [075][800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.843 (3.400) Prec@1 63.28 (66.60) Prec@5 82.81 (86.09) + train[2018-10-15-05:48:28] Epoch: [075][1000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.402 (3.403) Prec@1 66.41 (66.54) Prec@5 82.03 (86.07) + train[2018-10-15-05:50:12] Epoch: [075][1200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.407 (3.407) Prec@1 70.31 (66.43) Prec@5 82.81 (86.03) + train[2018-10-15-05:51:55] Epoch: [075][1400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.315 (3.407) Prec@1 68.75 (66.41) Prec@5 87.50 (86.02) + train[2018-10-15-05:53:39] Epoch: [075][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.600 (3.406) Prec@1 61.72 (66.45) Prec@5 86.72 (86.01) + train[2018-10-15-05:55:23] Epoch: [075][1800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.524 (3.409) Prec@1 63.28 (66.41) Prec@5 85.94 (85.98) + train[2018-10-15-05:57:06] Epoch: [075][2000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.201 (3.410) Prec@1 73.44 (66.35) Prec@5 85.16 (85.97) + train[2018-10-15-05:58:51] Epoch: [075][2200/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.358 (3.410) Prec@1 64.84 (66.35) Prec@5 87.50 (85.94) + train[2018-10-15-06:00:35] Epoch: [075][2400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.469 (3.411) Prec@1 65.62 (66.33) Prec@5 87.50 (85.95) + train[2018-10-15-06:02:21] Epoch: [075][2600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.275 (3.412) Prec@1 73.44 (66.31) Prec@5 90.62 (85.94) + train[2018-10-15-06:04:04] Epoch: [075][2800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.221 (3.412) Prec@1 71.88 (66.31) Prec@5 87.50 (85.91) + train[2018-10-15-06:05:48] Epoch: [075][3000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.262 (3.413) Prec@1 65.62 (66.32) Prec@5 85.94 (85.92) + train[2018-10-15-06:07:33] Epoch: [075][3200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.255 (3.412) Prec@1 74.22 (66.33) Prec@5 85.94 (85.93) + train[2018-10-15-06:09:18] Epoch: [075][3400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.513 (3.412) Prec@1 66.41 (66.33) Prec@5 87.50 (85.93) + train[2018-10-15-06:11:03] Epoch: [075][3600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.441 (3.411) Prec@1 65.62 (66.34) Prec@5 88.28 (85.94) + train[2018-10-15-06:12:47] Epoch: [075][3800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.302 (3.413) Prec@1 70.31 (66.30) Prec@5 86.72 (85.90) + train[2018-10-15-06:14:31] Epoch: [075][4000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.307 (3.414) Prec@1 64.06 (66.29) Prec@5 88.28 (85.90) + train[2018-10-15-06:16:17] Epoch: [075][4200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.515 (3.415) Prec@1 60.94 (66.26) Prec@5 84.38 (85.89) + train[2018-10-15-06:18:02] Epoch: [075][4400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.320 (3.414) Prec@1 67.19 (66.25) Prec@5 85.16 (85.89) + train[2018-10-15-06:19:46] Epoch: [075][4600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.148 (3.415) Prec@1 70.31 (66.24) Prec@5 85.94 (85.88) + train[2018-10-15-06:21:30] Epoch: [075][4800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.257 (3.416) Prec@1 71.09 (66.24) Prec@5 86.72 (85.88) + train[2018-10-15-06:23:14] Epoch: [075][5000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.334 (3.416) Prec@1 67.19 (66.22) Prec@5 88.28 (85.86) + train[2018-10-15-06:24:58] Epoch: [075][5200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.570 (3.417) Prec@1 64.84 (66.20) Prec@5 82.03 (85.85) + train[2018-10-15-06:26:42] Epoch: [075][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.788 (3.417) Prec@1 61.72 (66.19) Prec@5 79.69 (85.86) + train[2018-10-15-06:28:26] Epoch: [075][5600/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.565 (3.418) Prec@1 63.28 (66.16) Prec@5 82.03 (85.84) + train[2018-10-15-06:30:11] Epoch: [075][5800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.721 (3.420) Prec@1 60.94 (66.14) Prec@5 82.81 (85.83) + train[2018-10-15-06:31:55] Epoch: [075][6000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.443 (3.420) Prec@1 66.41 (66.14) Prec@5 86.72 (85.82) + train[2018-10-15-06:33:39] Epoch: [075][6200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.668 (3.420) Prec@1 60.16 (66.13) Prec@5 81.25 (85.82) + train[2018-10-15-06:35:22] Epoch: [075][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.458 (3.421) Prec@1 64.84 (66.13) Prec@5 87.50 (85.81) + train[2018-10-15-06:37:06] Epoch: [075][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.734 (3.422) Prec@1 61.72 (66.10) Prec@5 82.81 (85.79) + train[2018-10-15-06:38:51] Epoch: [075][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.436 (3.422) Prec@1 62.50 (66.09) Prec@5 88.28 (85.79) + train[2018-10-15-06:40:34] Epoch: [075][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.549 (3.423) Prec@1 64.84 (66.07) Prec@5 85.16 (85.78) + train[2018-10-15-06:42:19] Epoch: [075][7200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.450 (3.424) Prec@1 70.31 (66.06) Prec@5 84.38 (85.77) + train[2018-10-15-06:44:04] Epoch: [075][7400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.271 (3.424) Prec@1 67.19 (66.06) Prec@5 86.72 (85.77) + train[2018-10-15-06:45:48] Epoch: [075][7600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.547 (3.424) Prec@1 62.50 (66.05) Prec@5 85.94 (85.76) + train[2018-10-15-06:47:33] Epoch: [075][7800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.411 (3.425) Prec@1 69.53 (66.04) Prec@5 82.81 (85.77) + train[2018-10-15-06:49:16] Epoch: [075][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.656 (3.425) Prec@1 62.50 (66.02) Prec@5 85.16 (85.76) + train[2018-10-15-06:51:02] Epoch: [075][8200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.326 (3.426) Prec@1 71.88 (66.01) Prec@5 88.28 (85.75) + train[2018-10-15-06:52:46] Epoch: [075][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.591 (3.426) Prec@1 63.28 (66.01) Prec@5 82.81 (85.75) + train[2018-10-15-06:54:30] Epoch: [075][8600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.689 (3.426) Prec@1 59.38 (66.01) Prec@5 81.25 (85.74) + train[2018-10-15-06:56:14] Epoch: [075][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.412 (3.427) Prec@1 60.94 (66.00) Prec@5 85.94 (85.73) + train[2018-10-15-06:57:58] Epoch: [075][9000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.065 (3.427) Prec@1 75.00 (66.00) Prec@5 89.84 (85.73) + train[2018-10-15-06:59:41] Epoch: [075][9200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.132 (3.427) Prec@1 74.22 (66.00) Prec@5 88.28 (85.72) + train[2018-10-15-07:01:24] Epoch: [075][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.376 (3.428) Prec@1 69.53 (65.99) Prec@5 87.50 (85.71) + train[2018-10-15-07:03:09] Epoch: [075][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.567 (3.428) Prec@1 67.19 (65.99) Prec@5 84.38 (85.71) + train[2018-10-15-07:04:54] Epoch: [075][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.225 (3.428) Prec@1 63.28 (65.99) Prec@5 89.06 (85.71) + train[2018-10-15-07:06:38] Epoch: [075][10000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.507 (3.428) Prec@1 65.62 (65.99) Prec@5 82.03 (85.71) + train[2018-10-15-07:06:42] Epoch: [075][10009/10010] Time 0.18 (0.52) Data 0.00 (0.00) Loss 3.873 (3.428) Prec@1 66.67 (65.99) Prec@5 73.33 (85.71) +[2018-10-15-07:06:42] **train** Prec@1 65.99 Prec@5 85.71 Error@1 34.01 Error@5 14.29 Loss:3.428 + test [2018-10-15-07:06:46] Epoch: [075][000/391] Time 4.19 (4.19) Data 4.04 (4.04) Loss 0.771 (0.771) Prec@1 82.03 (82.03) Prec@5 94.53 (94.53) + test [2018-10-15-07:07:13] Epoch: [075][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.389 (1.163) Prec@1 68.75 (72.70) Prec@5 89.06 (91.76) + test [2018-10-15-07:07:38] Epoch: [075][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.320 (1.342) Prec@1 40.00 (69.04) Prec@5 80.00 (89.08) +[2018-10-15-07:07:38] **test** Prec@1 69.04 Prec@5 89.08 Error@1 30.96 Error@5 10.92 Loss:1.342 +----> Best Accuracy : Acc@1=69.24, Acc@5=89.06, Error@1=30.76, Error@5=10.94 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-15-07:07:38] [Epoch=076/250] [Need: 254:55:19] LR=0.0099 ~ 0.0099, Batch=128 + train[2018-10-15-07:07:43] Epoch: [076][000/10010] Time 4.66 (4.66) Data 4.06 (4.06) Loss 3.351 (3.351) Prec@1 67.97 (67.97) Prec@5 85.94 (85.94) + train[2018-10-15-07:09:27] Epoch: [076][200/10010] Time 0.52 (0.54) Data 0.00 (0.02) Loss 3.029 (3.372) Prec@1 78.91 (67.28) Prec@5 89.84 (86.28) + train[2018-10-15-07:11:11] Epoch: [076][400/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.673 (3.389) Prec@1 60.16 (66.91) Prec@5 82.03 (86.08) + train[2018-10-15-07:12:56] Epoch: [076][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.516 (3.395) Prec@1 65.62 (66.67) Prec@5 85.16 (86.11) + train[2018-10-15-07:14:40] Epoch: [076][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.196 (3.396) Prec@1 67.97 (66.60) Prec@5 87.50 (86.12) + train[2018-10-15-07:16:25] Epoch: [076][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.931 (3.391) Prec@1 75.00 (66.71) Prec@5 91.41 (86.18) + train[2018-10-15-07:18:08] Epoch: [076][1200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.310 (3.396) Prec@1 70.31 (66.62) Prec@5 85.16 (86.15) + train[2018-10-15-07:19:53] Epoch: [076][1400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.124 (3.396) Prec@1 70.31 (66.62) Prec@5 86.72 (86.16) + train[2018-10-15-07:21:37] Epoch: [076][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.169 (3.396) Prec@1 71.09 (66.62) Prec@5 86.72 (86.15) + train[2018-10-15-07:23:21] Epoch: [076][1800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.907 (3.396) Prec@1 76.56 (66.59) Prec@5 92.19 (86.12) + train[2018-10-15-07:25:05] Epoch: [076][2000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.513 (3.397) Prec@1 67.97 (66.58) Prec@5 82.03 (86.11) + train[2018-10-15-07:26:49] Epoch: [076][2200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.142 (3.396) Prec@1 68.75 (66.61) Prec@5 89.84 (86.10) + train[2018-10-15-07:28:33] Epoch: [076][2400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.314 (3.396) Prec@1 65.62 (66.62) Prec@5 86.72 (86.07) + train[2018-10-15-07:30:17] Epoch: [076][2600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.062 (3.398) Prec@1 72.66 (66.58) Prec@5 89.84 (86.05) + train[2018-10-15-07:32:01] Epoch: [076][2800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.390 (3.400) Prec@1 70.31 (66.54) Prec@5 85.94 (86.03) + train[2018-10-15-07:33:45] Epoch: [076][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.544 (3.399) Prec@1 65.62 (66.57) Prec@5 81.25 (86.05) + train[2018-10-15-07:35:29] Epoch: [076][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.294 (3.400) Prec@1 71.09 (66.55) Prec@5 86.72 (86.03) + train[2018-10-15-07:37:14] Epoch: [076][3400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.113 (3.401) Prec@1 67.97 (66.54) Prec@5 89.84 (86.03) + train[2018-10-15-07:38:59] Epoch: [076][3600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.322 (3.401) Prec@1 69.53 (66.51) Prec@5 89.84 (86.02) + train[2018-10-15-07:40:45] Epoch: [076][3800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.480 (3.402) Prec@1 63.28 (66.50) Prec@5 85.16 (86.00) + train[2018-10-15-07:42:30] Epoch: [076][4000/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.636 (3.405) Prec@1 67.19 (66.46) Prec@5 82.03 (85.97) + train[2018-10-15-07:44:15] Epoch: [076][4200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.266 (3.405) Prec@1 70.31 (66.46) Prec@5 86.72 (85.97) + train[2018-10-15-07:46:00] Epoch: [076][4400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.441 (3.406) Prec@1 60.94 (66.44) Prec@5 86.72 (85.96) + train[2018-10-15-07:47:44] Epoch: [076][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.142 (3.406) Prec@1 68.75 (66.42) Prec@5 90.62 (85.96) + train[2018-10-15-07:49:28] Epoch: [076][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.435 (3.406) Prec@1 67.19 (66.43) Prec@5 84.38 (85.97) + train[2018-10-15-07:51:12] Epoch: [076][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.411 (3.407) Prec@1 67.19 (66.41) Prec@5 83.59 (85.95) + train[2018-10-15-07:52:55] Epoch: [076][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.181 (3.408) Prec@1 69.53 (66.40) Prec@5 88.28 (85.93) + train[2018-10-15-07:54:39] Epoch: [076][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.625 (3.410) Prec@1 63.28 (66.37) Prec@5 84.38 (85.92) + train[2018-10-15-07:56:24] Epoch: [076][5600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.518 (3.409) Prec@1 63.28 (66.36) Prec@5 85.16 (85.92) + train[2018-10-15-07:58:08] Epoch: [076][5800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.709 (3.410) Prec@1 64.06 (66.35) Prec@5 78.91 (85.91) + train[2018-10-15-07:59:51] Epoch: [076][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.359 (3.411) Prec@1 66.41 (66.34) Prec@5 85.16 (85.91) + train[2018-10-15-08:01:35] Epoch: [076][6200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.386 (3.411) Prec@1 60.16 (66.31) Prec@5 91.41 (85.91) + train[2018-10-15-08:03:18] Epoch: [076][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.347 (3.412) Prec@1 68.75 (66.29) Prec@5 87.50 (85.89) + train[2018-10-15-08:05:02] Epoch: [076][6600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.459 (3.413) Prec@1 62.50 (66.27) Prec@5 85.94 (85.89) + train[2018-10-15-08:06:46] Epoch: [076][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.176 (3.413) Prec@1 71.09 (66.28) Prec@5 89.06 (85.89) + train[2018-10-15-08:08:30] Epoch: [076][7000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.500 (3.414) Prec@1 62.50 (66.27) Prec@5 82.81 (85.89) + train[2018-10-15-08:10:14] Epoch: [076][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.421 (3.415) Prec@1 72.66 (66.25) Prec@5 87.50 (85.88) + train[2018-10-15-08:11:58] Epoch: [076][7400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.388 (3.415) Prec@1 62.50 (66.24) Prec@5 86.72 (85.87) + train[2018-10-15-08:13:42] Epoch: [076][7600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 2.934 (3.416) Prec@1 75.78 (66.22) Prec@5 89.84 (85.87) + train[2018-10-15-08:15:26] Epoch: [076][7800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.330 (3.416) Prec@1 64.06 (66.21) Prec@5 87.50 (85.87) + train[2018-10-15-08:17:11] Epoch: [076][8000/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.212 (3.416) Prec@1 68.75 (66.21) Prec@5 91.41 (85.86) + train[2018-10-15-08:18:56] Epoch: [076][8200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.605 (3.416) Prec@1 64.84 (66.21) Prec@5 82.03 (85.86) + train[2018-10-15-08:20:41] Epoch: [076][8400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.445 (3.416) Prec@1 63.28 (66.20) Prec@5 85.94 (85.85) + train[2018-10-15-08:22:25] Epoch: [076][8600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.851 (3.417) Prec@1 60.16 (66.19) Prec@5 79.69 (85.85) + train[2018-10-15-08:24:10] Epoch: [076][8800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.242 (3.417) Prec@1 68.75 (66.19) Prec@5 92.19 (85.86) + train[2018-10-15-08:25:55] Epoch: [076][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.452 (3.417) Prec@1 64.84 (66.18) Prec@5 86.72 (85.86) + train[2018-10-15-08:27:40] Epoch: [076][9200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.142 (3.417) Prec@1 75.78 (66.16) Prec@5 86.72 (85.85) + train[2018-10-15-08:29:25] Epoch: [076][9400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.604 (3.418) Prec@1 61.72 (66.15) Prec@5 85.16 (85.85) + train[2018-10-15-08:31:11] Epoch: [076][9600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.285 (3.418) Prec@1 66.41 (66.15) Prec@5 92.97 (85.84) + train[2018-10-15-08:32:55] Epoch: [076][9800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.345 (3.419) Prec@1 67.19 (66.15) Prec@5 85.16 (85.83) + train[2018-10-15-08:34:39] Epoch: [076][10000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.309 (3.420) Prec@1 70.31 (66.13) Prec@5 91.41 (85.83) + train[2018-10-15-08:34:44] Epoch: [076][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.070 (3.420) Prec@1 46.67 (66.13) Prec@5 73.33 (85.83) +[2018-10-15-08:34:44] **train** Prec@1 66.13 Prec@5 85.83 Error@1 33.87 Error@5 14.17 Loss:3.420 + test [2018-10-15-08:34:48] Epoch: [076][000/391] Time 3.91 (3.91) Data 3.77 (3.77) Loss 0.777 (0.777) Prec@1 82.03 (82.03) Prec@5 96.88 (96.88) + test [2018-10-15-08:35:14] Epoch: [076][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.613 (1.154) Prec@1 57.03 (72.87) Prec@5 88.28 (91.75) + test [2018-10-15-08:35:40] Epoch: [076][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.268 (1.342) Prec@1 42.50 (69.10) Prec@5 77.50 (88.94) +[2018-10-15-08:35:40] **test** Prec@1 69.10 Prec@5 88.94 Error@1 30.90 Error@5 11.06 Loss:1.342 +----> Best Accuracy : Acc@1=69.24, Acc@5=89.06, Error@1=30.76, Error@5=10.94 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-15-08:35:40] [Epoch=077/250] [Need: 253:50:22] LR=0.0096 ~ 0.0096, Batch=128 + train[2018-10-15-08:35:46] Epoch: [077][000/10010] Time 5.50 (5.50) Data 4.89 (4.89) Loss 3.298 (3.298) Prec@1 63.28 (63.28) Prec@5 89.84 (89.84) + train[2018-10-15-08:37:30] Epoch: [077][200/10010] Time 0.52 (0.55) Data 0.00 (0.02) Loss 3.426 (3.375) Prec@1 61.72 (66.70) Prec@5 89.06 (86.28) + train[2018-10-15-08:39:14] Epoch: [077][400/10010] Time 0.57 (0.53) Data 0.00 (0.01) Loss 3.536 (3.381) Prec@1 62.50 (66.80) Prec@5 82.81 (86.22) + train[2018-10-15-08:40:58] Epoch: [077][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.321 (3.376) Prec@1 64.06 (66.89) Prec@5 89.84 (86.28) + train[2018-10-15-08:42:42] Epoch: [077][800/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.314 (3.379) Prec@1 67.97 (66.87) Prec@5 85.16 (86.19) + train[2018-10-15-08:44:25] Epoch: [077][1000/10010] Time 0.52 (0.52) Data 0.00 (0.01) Loss 3.392 (3.383) Prec@1 67.19 (66.83) Prec@5 84.38 (86.18) + train[2018-10-15-08:46:09] Epoch: [077][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.220 (3.380) Prec@1 69.53 (66.97) Prec@5 89.84 (86.22) + train[2018-10-15-08:47:53] Epoch: [077][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.096 (3.381) Prec@1 75.78 (66.94) Prec@5 89.06 (86.23) + train[2018-10-15-08:49:37] Epoch: [077][1600/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.317 (3.385) Prec@1 66.41 (66.90) Prec@5 89.84 (86.16) + train[2018-10-15-08:51:22] Epoch: [077][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.611 (3.384) Prec@1 64.84 (66.90) Prec@5 82.81 (86.16) + train[2018-10-15-08:53:07] Epoch: [077][2000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.362 (3.387) Prec@1 67.97 (66.84) Prec@5 83.59 (86.13) + train[2018-10-15-08:54:51] Epoch: [077][2200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.271 (3.386) Prec@1 64.84 (66.82) Prec@5 90.62 (86.17) + train[2018-10-15-08:56:35] Epoch: [077][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.507 (3.386) Prec@1 60.94 (66.80) Prec@5 84.38 (86.16) + train[2018-10-15-08:58:19] Epoch: [077][2600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.423 (3.387) Prec@1 65.62 (66.78) Prec@5 86.72 (86.14) + train[2018-10-15-09:00:03] Epoch: [077][2800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.923 (3.389) Prec@1 61.72 (66.74) Prec@5 75.78 (86.12) + train[2018-10-15-09:01:46] Epoch: [077][3000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.697 (3.390) Prec@1 63.28 (66.72) Prec@5 83.59 (86.10) + train[2018-10-15-09:03:31] Epoch: [077][3200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.428 (3.391) Prec@1 64.84 (66.70) Prec@5 89.06 (86.10) + train[2018-10-15-09:05:16] Epoch: [077][3400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.391 (3.391) Prec@1 69.53 (66.68) Prec@5 85.94 (86.10) + train[2018-10-15-09:07:00] Epoch: [077][3600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.732 (3.392) Prec@1 59.38 (66.66) Prec@5 80.47 (86.11) + train[2018-10-15-09:08:44] Epoch: [077][3800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.072 (3.393) Prec@1 72.66 (66.65) Prec@5 88.28 (86.09) + train[2018-10-15-09:10:28] Epoch: [077][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.644 (3.396) Prec@1 59.38 (66.60) Prec@5 82.81 (86.06) + train[2018-10-15-09:12:14] Epoch: [077][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.244 (3.398) Prec@1 66.41 (66.57) Prec@5 91.41 (86.05) + train[2018-10-15-09:14:00] Epoch: [077][4400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.402 (3.399) Prec@1 65.62 (66.54) Prec@5 85.94 (86.04) + train[2018-10-15-09:15:44] Epoch: [077][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.216 (3.400) Prec@1 67.19 (66.53) Prec@5 87.50 (86.02) + train[2018-10-15-09:17:29] Epoch: [077][4800/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.699 (3.401) Prec@1 65.62 (66.52) Prec@5 82.81 (86.02) + train[2018-10-15-09:19:13] Epoch: [077][5000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.459 (3.401) Prec@1 67.97 (66.51) Prec@5 82.03 (86.02) + train[2018-10-15-09:20:57] Epoch: [077][5200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.491 (3.402) Prec@1 66.41 (66.48) Prec@5 84.38 (86.01) + train[2018-10-15-09:22:42] Epoch: [077][5400/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.266 (3.404) Prec@1 62.50 (66.44) Prec@5 87.50 (85.98) + train[2018-10-15-09:24:26] Epoch: [077][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.300 (3.403) Prec@1 70.31 (66.45) Prec@5 88.28 (85.99) + train[2018-10-15-09:26:09] Epoch: [077][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.387 (3.404) Prec@1 66.41 (66.42) Prec@5 87.50 (85.98) + train[2018-10-15-09:27:53] Epoch: [077][6000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.527 (3.405) Prec@1 65.62 (66.40) Prec@5 84.38 (85.97) + train[2018-10-15-09:29:37] Epoch: [077][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.539 (3.405) Prec@1 64.84 (66.40) Prec@5 83.59 (85.98) + train[2018-10-15-09:31:22] Epoch: [077][6400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.190 (3.405) Prec@1 71.88 (66.40) Prec@5 86.72 (85.97) + train[2018-10-15-09:33:06] Epoch: [077][6600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.408 (3.405) Prec@1 67.97 (66.41) Prec@5 84.38 (85.97) + train[2018-10-15-09:34:50] Epoch: [077][6800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.182 (3.405) Prec@1 71.09 (66.41) Prec@5 88.28 (85.97) + train[2018-10-15-09:36:33] Epoch: [077][7000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.201 (3.405) Prec@1 66.41 (66.40) Prec@5 89.06 (85.97) + train[2018-10-15-09:38:18] Epoch: [077][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.567 (3.406) Prec@1 62.50 (66.40) Prec@5 83.59 (85.96) + train[2018-10-15-09:40:02] Epoch: [077][7400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.476 (3.407) Prec@1 62.50 (66.38) Prec@5 85.94 (85.95) + train[2018-10-15-09:41:46] Epoch: [077][7600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.492 (3.407) Prec@1 64.06 (66.38) Prec@5 85.94 (85.94) + train[2018-10-15-09:43:30] Epoch: [077][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.408 (3.407) Prec@1 66.41 (66.38) Prec@5 86.72 (85.93) + train[2018-10-15-09:45:13] Epoch: [077][8000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.257 (3.408) Prec@1 67.97 (66.38) Prec@5 87.50 (85.93) + train[2018-10-15-09:46:57] Epoch: [077][8200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.405 (3.408) Prec@1 64.84 (66.37) Prec@5 86.72 (85.92) + train[2018-10-15-09:48:42] Epoch: [077][8400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.555 (3.408) Prec@1 60.16 (66.36) Prec@5 84.38 (85.92) + train[2018-10-15-09:50:26] Epoch: [077][8600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.296 (3.409) Prec@1 64.84 (66.35) Prec@5 89.06 (85.92) + train[2018-10-15-09:52:11] Epoch: [077][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.586 (3.409) Prec@1 62.50 (66.33) Prec@5 85.16 (85.91) + train[2018-10-15-09:53:55] Epoch: [077][9000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.921 (3.410) Prec@1 59.38 (66.31) Prec@5 81.25 (85.90) + train[2018-10-15-09:55:41] Epoch: [077][9200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.133 (3.411) Prec@1 73.44 (66.30) Prec@5 92.97 (85.89) + train[2018-10-15-09:57:27] Epoch: [077][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.484 (3.412) Prec@1 65.62 (66.29) Prec@5 88.28 (85.88) + train[2018-10-15-09:59:13] Epoch: [077][9600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.118 (3.412) Prec@1 71.88 (66.28) Prec@5 87.50 (85.88) + train[2018-10-15-10:00:59] Epoch: [077][9800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.337 (3.413) Prec@1 62.50 (66.26) Prec@5 88.28 (85.87) + train[2018-10-15-10:02:43] Epoch: [077][10000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.091 (3.413) Prec@1 69.53 (66.26) Prec@5 92.19 (85.87) + train[2018-10-15-10:02:47] Epoch: [077][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 3.013 (3.413) Prec@1 73.33 (66.26) Prec@5 93.33 (85.87) +[2018-10-15-10:02:47] **train** Prec@1 66.26 Prec@5 85.87 Error@1 33.74 Error@5 14.13 Loss:3.413 + test [2018-10-15-10:02:51] Epoch: [077][000/391] Time 4.08 (4.08) Data 3.94 (3.94) Loss 0.759 (0.759) Prec@1 83.59 (83.59) Prec@5 97.66 (97.66) + test [2018-10-15-10:03:18] Epoch: [077][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.594 (1.164) Prec@1 57.03 (72.99) Prec@5 88.28 (91.73) + test [2018-10-15-10:03:43] Epoch: [077][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.526 (1.345) Prec@1 33.75 (69.25) Prec@5 76.25 (89.13) +[2018-10-15-10:03:43] **test** Prec@1 69.25 Prec@5 89.13 Error@1 30.75 Error@5 10.87 Loss:1.345 +----> Best Accuracy : Acc@1=69.25, Acc@5=89.13, Error@1=30.75, Error@5=10.87 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-15-10:03:43] [Epoch=078/250] [Need: 252:23:19] LR=0.0093 ~ 0.0093, Batch=128 + train[2018-10-15-10:03:48] Epoch: [078][000/10010] Time 5.14 (5.14) Data 4.59 (4.59) Loss 3.300 (3.300) Prec@1 66.41 (66.41) Prec@5 88.28 (88.28) + train[2018-10-15-10:05:33] Epoch: [078][200/10010] Time 0.52 (0.55) Data 0.00 (0.02) Loss 3.184 (3.382) Prec@1 71.09 (67.08) Prec@5 89.06 (85.94) + train[2018-10-15-10:07:17] Epoch: [078][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.304 (3.379) Prec@1 70.31 (67.09) Prec@5 86.72 (86.02) + train[2018-10-15-10:09:01] Epoch: [078][600/10010] Time 0.49 (0.53) Data 0.00 (0.01) Loss 3.463 (3.375) Prec@1 64.84 (67.17) Prec@5 83.59 (86.09) + train[2018-10-15-10:10:45] Epoch: [078][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.419 (3.374) Prec@1 71.09 (67.14) Prec@5 83.59 (86.18) + train[2018-10-15-10:12:29] Epoch: [078][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.003 (3.376) Prec@1 71.88 (67.04) Prec@5 89.84 (86.20) + train[2018-10-15-10:14:12] Epoch: [078][1200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.310 (3.378) Prec@1 72.66 (66.96) Prec@5 89.06 (86.19) + train[2018-10-15-10:15:57] Epoch: [078][1400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.271 (3.379) Prec@1 72.66 (67.00) Prec@5 85.94 (86.21) + train[2018-10-15-10:17:41] Epoch: [078][1600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.136 (3.382) Prec@1 69.53 (66.94) Prec@5 92.19 (86.20) + train[2018-10-15-10:19:25] Epoch: [078][1800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.216 (3.380) Prec@1 72.66 (66.94) Prec@5 88.28 (86.24) + train[2018-10-15-10:21:10] Epoch: [078][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.428 (3.380) Prec@1 68.75 (66.93) Prec@5 83.59 (86.24) + train[2018-10-15-10:22:54] Epoch: [078][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.499 (3.379) Prec@1 66.41 (66.93) Prec@5 85.94 (86.26) + train[2018-10-15-10:24:38] Epoch: [078][2400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.392 (3.380) Prec@1 65.62 (66.91) Prec@5 83.59 (86.26) + train[2018-10-15-10:26:24] Epoch: [078][2600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.364 (3.379) Prec@1 69.53 (66.89) Prec@5 88.28 (86.27) + train[2018-10-15-10:28:09] Epoch: [078][2800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.085 (3.383) Prec@1 68.75 (66.83) Prec@5 89.84 (86.21) + train[2018-10-15-10:29:55] Epoch: [078][3000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.459 (3.381) Prec@1 68.75 (66.86) Prec@5 82.81 (86.22) + train[2018-10-15-10:31:40] Epoch: [078][3200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.448 (3.382) Prec@1 64.06 (66.83) Prec@5 85.94 (86.22) + train[2018-10-15-10:33:25] Epoch: [078][3400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.218 (3.384) Prec@1 67.19 (66.79) Prec@5 86.72 (86.20) + train[2018-10-15-10:35:10] Epoch: [078][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.527 (3.384) Prec@1 63.28 (66.79) Prec@5 82.03 (86.21) + train[2018-10-15-10:36:56] Epoch: [078][3800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.384 (3.384) Prec@1 66.41 (66.77) Prec@5 89.84 (86.21) + train[2018-10-15-10:38:40] Epoch: [078][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.347 (3.384) Prec@1 71.09 (66.77) Prec@5 86.72 (86.20) + train[2018-10-15-10:40:25] Epoch: [078][4200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.439 (3.385) Prec@1 67.19 (66.76) Prec@5 88.28 (86.19) + train[2018-10-15-10:42:10] Epoch: [078][4400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.334 (3.385) Prec@1 68.75 (66.76) Prec@5 87.50 (86.20) + train[2018-10-15-10:43:55] Epoch: [078][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.472 (3.386) Prec@1 63.28 (66.74) Prec@5 86.72 (86.20) + train[2018-10-15-10:45:38] Epoch: [078][4800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.625 (3.388) Prec@1 66.41 (66.73) Prec@5 85.16 (86.17) + train[2018-10-15-10:47:23] Epoch: [078][5000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.305 (3.389) Prec@1 67.19 (66.70) Prec@5 86.72 (86.16) + train[2018-10-15-10:49:07] Epoch: [078][5200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.360 (3.389) Prec@1 60.94 (66.67) Prec@5 87.50 (86.16) + train[2018-10-15-10:50:51] Epoch: [078][5400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.353 (3.390) Prec@1 69.53 (66.67) Prec@5 87.50 (86.16) + train[2018-10-15-10:52:36] Epoch: [078][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.540 (3.390) Prec@1 65.62 (66.66) Prec@5 84.38 (86.15) + train[2018-10-15-10:54:19] Epoch: [078][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.183 (3.391) Prec@1 73.44 (66.65) Prec@5 88.28 (86.14) + train[2018-10-15-10:56:03] Epoch: [078][6000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.361 (3.391) Prec@1 67.19 (66.64) Prec@5 90.62 (86.13) + train[2018-10-15-10:57:48] Epoch: [078][6200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.323 (3.392) Prec@1 64.84 (66.62) Prec@5 88.28 (86.13) + train[2018-10-15-10:59:32] Epoch: [078][6400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.238 (3.393) Prec@1 69.53 (66.60) Prec@5 88.28 (86.12) + train[2018-10-15-11:01:15] Epoch: [078][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.350 (3.394) Prec@1 66.41 (66.59) Prec@5 90.62 (86.11) + train[2018-10-15-11:02:59] Epoch: [078][6800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.288 (3.394) Prec@1 73.44 (66.59) Prec@5 87.50 (86.11) + train[2018-10-15-11:04:44] Epoch: [078][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.236 (3.395) Prec@1 68.75 (66.59) Prec@5 87.50 (86.10) + train[2018-10-15-11:06:28] Epoch: [078][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.883 (3.395) Prec@1 56.25 (66.57) Prec@5 83.59 (86.09) + train[2018-10-15-11:08:13] Epoch: [078][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.522 (3.395) Prec@1 64.84 (66.57) Prec@5 85.16 (86.09) + train[2018-10-15-11:09:57] Epoch: [078][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.755 (3.396) Prec@1 56.25 (66.56) Prec@5 82.81 (86.07) + train[2018-10-15-11:11:42] Epoch: [078][7800/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.842 (3.397) Prec@1 66.41 (66.56) Prec@5 80.47 (86.06) + train[2018-10-15-11:13:25] Epoch: [078][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.471 (3.397) Prec@1 69.53 (66.55) Prec@5 82.81 (86.05) + train[2018-10-15-11:15:09] Epoch: [078][8200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.230 (3.398) Prec@1 70.31 (66.53) Prec@5 86.72 (86.04) + train[2018-10-15-11:16:53] Epoch: [078][8400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.053 (3.398) Prec@1 73.44 (66.53) Prec@5 91.41 (86.04) + train[2018-10-15-11:18:37] Epoch: [078][8600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.339 (3.399) Prec@1 67.19 (66.51) Prec@5 87.50 (86.04) + train[2018-10-15-11:20:23] Epoch: [078][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.632 (3.399) Prec@1 62.50 (66.51) Prec@5 85.16 (86.04) + train[2018-10-15-11:22:09] Epoch: [078][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.202 (3.399) Prec@1 70.31 (66.50) Prec@5 86.72 (86.04) + train[2018-10-15-11:23:55] Epoch: [078][9200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.420 (3.400) Prec@1 64.06 (66.49) Prec@5 86.72 (86.03) + train[2018-10-15-11:25:39] Epoch: [078][9400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.398 (3.400) Prec@1 69.53 (66.48) Prec@5 89.06 (86.02) + train[2018-10-15-11:27:24] Epoch: [078][9600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.517 (3.401) Prec@1 64.06 (66.47) Prec@5 82.81 (86.02) + train[2018-10-15-11:29:08] Epoch: [078][9800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.149 (3.401) Prec@1 67.97 (66.46) Prec@5 90.62 (86.02) + train[2018-10-15-11:30:51] Epoch: [078][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.491 (3.401) Prec@1 67.19 (66.45) Prec@5 84.38 (86.01) + train[2018-10-15-11:30:56] Epoch: [078][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 3.502 (3.401) Prec@1 73.33 (66.45) Prec@5 80.00 (86.01) +[2018-10-15-11:30:56] **train** Prec@1 66.45 Prec@5 86.01 Error@1 33.55 Error@5 13.99 Loss:3.401 + test [2018-10-15-11:31:00] Epoch: [078][000/391] Time 3.82 (3.82) Data 3.66 (3.66) Loss 0.778 (0.778) Prec@1 79.69 (79.69) Prec@5 95.31 (95.31) + test [2018-10-15-11:31:26] Epoch: [078][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.596 (1.140) Prec@1 58.59 (73.22) Prec@5 85.16 (91.79) + test [2018-10-15-11:31:51] Epoch: [078][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.396 (1.317) Prec@1 50.00 (69.58) Prec@5 73.75 (89.35) +[2018-10-15-11:31:51] **test** Prec@1 69.58 Prec@5 89.35 Error@1 30.42 Error@5 10.65 Loss:1.317 +----> Best Accuracy : Acc@1=69.58, Acc@5=89.35, Error@1=30.42, Error@5=10.65 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-15-11:31:51] [Epoch=079/250] [Need: 251:12:05] LR=0.0090 ~ 0.0090, Batch=128 + train[2018-10-15-11:31:57] Epoch: [079][000/10010] Time 5.32 (5.32) Data 4.71 (4.71) Loss 3.139 (3.139) Prec@1 69.53 (69.53) Prec@5 88.28 (88.28) + train[2018-10-15-11:33:41] Epoch: [079][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.395 (3.369) Prec@1 60.16 (67.15) Prec@5 87.50 (86.42) + train[2018-10-15-11:35:25] Epoch: [079][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.426 (3.365) Prec@1 62.50 (67.24) Prec@5 86.72 (86.41) + train[2018-10-15-11:37:09] Epoch: [079][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.472 (3.371) Prec@1 67.19 (67.21) Prec@5 85.94 (86.31) + train[2018-10-15-11:38:54] Epoch: [079][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.268 (3.366) Prec@1 68.75 (67.23) Prec@5 89.84 (86.40) + train[2018-10-15-11:40:39] Epoch: [079][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.410 (3.366) Prec@1 67.97 (67.25) Prec@5 86.72 (86.43) + train[2018-10-15-11:42:24] Epoch: [079][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.319 (3.365) Prec@1 67.19 (67.28) Prec@5 88.28 (86.43) + train[2018-10-15-11:44:08] Epoch: [079][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.465 (3.366) Prec@1 64.06 (67.22) Prec@5 87.50 (86.46) + train[2018-10-15-11:45:51] Epoch: [079][1600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.142 (3.363) Prec@1 68.75 (67.22) Prec@5 92.97 (86.50) + train[2018-10-15-11:47:36] Epoch: [079][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.185 (3.362) Prec@1 71.09 (67.19) Prec@5 90.62 (86.51) + train[2018-10-15-11:49:19] Epoch: [079][2000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.179 (3.361) Prec@1 71.09 (67.20) Prec@5 86.72 (86.52) + train[2018-10-15-11:51:04] Epoch: [079][2200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.961 (3.361) Prec@1 73.44 (67.18) Prec@5 90.62 (86.52) + train[2018-10-15-11:52:48] Epoch: [079][2400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.174 (3.363) Prec@1 71.09 (67.16) Prec@5 87.50 (86.47) + train[2018-10-15-11:54:34] Epoch: [079][2600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.350 (3.364) Prec@1 64.06 (67.13) Prec@5 85.16 (86.46) + train[2018-10-15-11:56:19] Epoch: [079][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.665 (3.367) Prec@1 63.28 (67.07) Prec@5 83.59 (86.42) + train[2018-10-15-11:58:05] Epoch: [079][3000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.704 (3.370) Prec@1 62.50 (67.04) Prec@5 80.47 (86.37) + train[2018-10-15-11:59:49] Epoch: [079][3200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.556 (3.371) Prec@1 63.28 (67.01) Prec@5 85.94 (86.35) + train[2018-10-15-12:01:35] Epoch: [079][3400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.210 (3.373) Prec@1 71.09 (66.99) Prec@5 91.41 (86.34) + train[2018-10-15-12:03:21] Epoch: [079][3600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.452 (3.373) Prec@1 65.62 (67.00) Prec@5 82.81 (86.33) + train[2018-10-15-12:05:07] Epoch: [079][3800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.289 (3.374) Prec@1 70.31 (66.97) Prec@5 85.94 (86.32) + train[2018-10-15-12:06:51] Epoch: [079][4000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.190 (3.375) Prec@1 74.22 (66.95) Prec@5 89.84 (86.30) + train[2018-10-15-12:08:36] Epoch: [079][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.461 (3.376) Prec@1 65.62 (66.93) Prec@5 85.16 (86.29) + train[2018-10-15-12:10:22] Epoch: [079][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.289 (3.377) Prec@1 66.41 (66.91) Prec@5 89.06 (86.29) + train[2018-10-15-12:12:07] Epoch: [079][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.626 (3.377) Prec@1 64.84 (66.91) Prec@5 83.59 (86.28) + train[2018-10-15-12:13:53] Epoch: [079][4800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.428 (3.378) Prec@1 68.75 (66.89) Prec@5 87.50 (86.26) + train[2018-10-15-12:15:39] Epoch: [079][5000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.453 (3.379) Prec@1 64.84 (66.87) Prec@5 84.38 (86.25) + train[2018-10-15-12:17:25] Epoch: [079][5200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.414 (3.380) Prec@1 69.53 (66.85) Prec@5 85.16 (86.24) + train[2018-10-15-12:19:11] Epoch: [079][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.395 (3.380) Prec@1 64.84 (66.84) Prec@5 85.94 (86.24) + train[2018-10-15-12:20:58] Epoch: [079][5600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.476 (3.380) Prec@1 67.97 (66.83) Prec@5 82.81 (86.24) + train[2018-10-15-12:22:45] Epoch: [079][5800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.353 (3.381) Prec@1 66.41 (66.82) Prec@5 88.28 (86.23) + train[2018-10-15-12:24:31] Epoch: [079][6000/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 3.308 (3.381) Prec@1 67.97 (66.82) Prec@5 89.06 (86.23) + train[2018-10-15-12:26:18] Epoch: [079][6200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.881 (3.383) Prec@1 59.38 (66.79) Prec@5 78.91 (86.21) + train[2018-10-15-12:28:03] Epoch: [079][6400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.223 (3.384) Prec@1 71.88 (66.78) Prec@5 90.62 (86.20) + train[2018-10-15-12:29:49] Epoch: [079][6600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.864 (3.385) Prec@1 60.16 (66.75) Prec@5 78.91 (86.19) + train[2018-10-15-12:31:35] Epoch: [079][6800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.223 (3.386) Prec@1 74.22 (66.74) Prec@5 90.62 (86.19) + train[2018-10-15-12:33:22] Epoch: [079][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.583 (3.386) Prec@1 59.38 (66.72) Prec@5 87.50 (86.18) + train[2018-10-15-12:35:07] Epoch: [079][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.134 (3.386) Prec@1 71.09 (66.72) Prec@5 88.28 (86.18) + train[2018-10-15-12:36:53] Epoch: [079][7400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.469 (3.387) Prec@1 66.41 (66.71) Prec@5 87.50 (86.17) + train[2018-10-15-12:38:38] Epoch: [079][7600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.413 (3.387) Prec@1 64.84 (66.70) Prec@5 85.94 (86.17) + train[2018-10-15-12:40:23] Epoch: [079][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.434 (3.388) Prec@1 62.50 (66.68) Prec@5 85.94 (86.16) + train[2018-10-15-12:42:08] Epoch: [079][8000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.660 (3.388) Prec@1 61.72 (66.68) Prec@5 86.72 (86.16) + train[2018-10-15-12:43:54] Epoch: [079][8200/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 3.452 (3.388) Prec@1 67.97 (66.68) Prec@5 87.50 (86.16) + train[2018-10-15-12:45:38] Epoch: [079][8400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.507 (3.388) Prec@1 68.75 (66.67) Prec@5 85.16 (86.16) + train[2018-10-15-12:47:23] Epoch: [079][8600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.188 (3.389) Prec@1 71.09 (66.65) Prec@5 89.06 (86.15) + train[2018-10-15-12:49:07] Epoch: [079][8800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.648 (3.390) Prec@1 62.50 (66.64) Prec@5 82.03 (86.14) + train[2018-10-15-12:50:53] Epoch: [079][9000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.488 (3.390) Prec@1 68.75 (66.64) Prec@5 82.81 (86.13) + train[2018-10-15-12:52:38] Epoch: [079][9200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.227 (3.390) Prec@1 67.19 (66.64) Prec@5 88.28 (86.13) + train[2018-10-15-12:54:24] Epoch: [079][9400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.522 (3.391) Prec@1 67.19 (66.63) Prec@5 87.50 (86.12) + train[2018-10-15-12:56:09] Epoch: [079][9600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.534 (3.391) Prec@1 61.72 (66.64) Prec@5 85.94 (86.12) + train[2018-10-15-12:57:55] Epoch: [079][9800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.363 (3.391) Prec@1 66.41 (66.63) Prec@5 87.50 (86.11) + train[2018-10-15-12:59:40] Epoch: [079][10000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.169 (3.391) Prec@1 71.88 (66.63) Prec@5 88.28 (86.12) + train[2018-10-15-12:59:44] Epoch: [079][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 3.331 (3.391) Prec@1 66.67 (66.63) Prec@5 86.67 (86.12) +[2018-10-15-12:59:44] **train** Prec@1 66.63 Prec@5 86.12 Error@1 33.37 Error@5 13.88 Loss:3.391 + test [2018-10-15-12:59:48] Epoch: [079][000/391] Time 3.75 (3.75) Data 3.60 (3.60) Loss 0.782 (0.782) Prec@1 82.03 (82.03) Prec@5 94.53 (94.53) + test [2018-10-15-13:00:15] Epoch: [079][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.584 (1.145) Prec@1 64.84 (73.34) Prec@5 85.94 (91.99) + test [2018-10-15-13:00:41] Epoch: [079][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.274 (1.325) Prec@1 45.00 (69.67) Prec@5 80.00 (89.36) +[2018-10-15-13:00:41] **test** Prec@1 69.67 Prec@5 89.36 Error@1 30.33 Error@5 10.64 Loss:1.325 +----> Best Accuracy : Acc@1=69.67, Acc@5=89.36, Error@1=30.33, Error@5=10.64 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-15-13:00:41] [Epoch=080/250] [Need: 251:40:15] LR=0.0087 ~ 0.0087, Batch=128 + train[2018-10-15-13:00:46] Epoch: [080][000/10010] Time 4.77 (4.77) Data 4.20 (4.20) Loss 3.087 (3.087) Prec@1 73.44 (73.44) Prec@5 90.62 (90.62) + train[2018-10-15-13:02:31] Epoch: [080][200/10010] Time 0.57 (0.55) Data 0.00 (0.02) Loss 3.433 (3.361) Prec@1 67.19 (67.49) Prec@5 84.38 (86.34) + train[2018-10-15-13:04:14] Epoch: [080][400/10010] Time 0.49 (0.53) Data 0.00 (0.01) Loss 3.418 (3.356) Prec@1 68.75 (67.45) Prec@5 85.16 (86.43) + train[2018-10-15-13:05:59] Epoch: [080][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.256 (3.351) Prec@1 70.31 (67.43) Prec@5 87.50 (86.54) + train[2018-10-15-13:07:43] Epoch: [080][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.979 (3.355) Prec@1 71.88 (67.30) Prec@5 90.62 (86.47) + train[2018-10-15-13:09:27] Epoch: [080][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.478 (3.355) Prec@1 61.72 (67.23) Prec@5 87.50 (86.48) + train[2018-10-15-13:11:11] Epoch: [080][1200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.599 (3.356) Prec@1 68.75 (67.17) Prec@5 82.03 (86.49) + train[2018-10-15-13:12:54] Epoch: [080][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.219 (3.356) Prec@1 67.97 (67.17) Prec@5 88.28 (86.50) + train[2018-10-15-13:14:39] Epoch: [080][1600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.636 (3.361) Prec@1 62.50 (67.09) Prec@5 84.38 (86.45) + train[2018-10-15-13:16:22] Epoch: [080][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.297 (3.363) Prec@1 64.84 (67.07) Prec@5 87.50 (86.41) + train[2018-10-15-13:18:06] Epoch: [080][2000/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.673 (3.363) Prec@1 63.28 (67.11) Prec@5 85.16 (86.42) + train[2018-10-15-13:19:50] Epoch: [080][2200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.658 (3.367) Prec@1 62.50 (67.02) Prec@5 80.47 (86.38) + train[2018-10-15-13:21:34] Epoch: [080][2400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.040 (3.369) Prec@1 75.00 (67.01) Prec@5 89.06 (86.35) + train[2018-10-15-13:23:19] Epoch: [080][2600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.268 (3.367) Prec@1 64.84 (67.04) Prec@5 87.50 (86.38) + train[2018-10-15-13:25:03] Epoch: [080][2800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.381 (3.367) Prec@1 67.97 (67.06) Prec@5 86.72 (86.38) + train[2018-10-15-13:26:47] Epoch: [080][3000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.270 (3.367) Prec@1 67.19 (67.08) Prec@5 87.50 (86.38) + train[2018-10-15-13:28:31] Epoch: [080][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.989 (3.367) Prec@1 76.56 (67.07) Prec@5 88.28 (86.38) + train[2018-10-15-13:30:15] Epoch: [080][3400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.341 (3.369) Prec@1 64.84 (67.04) Prec@5 88.28 (86.35) + train[2018-10-15-13:31:59] Epoch: [080][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.343 (3.369) Prec@1 64.84 (67.02) Prec@5 85.94 (86.35) + train[2018-10-15-13:33:44] Epoch: [080][3800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.406 (3.370) Prec@1 64.84 (66.99) Prec@5 83.59 (86.33) + train[2018-10-15-13:35:29] Epoch: [080][4000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.454 (3.372) Prec@1 64.84 (66.97) Prec@5 82.81 (86.31) + train[2018-10-15-13:37:14] Epoch: [080][4200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.409 (3.374) Prec@1 67.19 (66.93) Prec@5 85.94 (86.29) + train[2018-10-15-13:38:58] Epoch: [080][4400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.428 (3.374) Prec@1 65.62 (66.90) Prec@5 85.94 (86.29) + train[2018-10-15-13:40:42] Epoch: [080][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.227 (3.374) Prec@1 70.31 (66.92) Prec@5 87.50 (86.29) + train[2018-10-15-13:42:26] Epoch: [080][4800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.543 (3.374) Prec@1 62.50 (66.92) Prec@5 82.03 (86.28) + train[2018-10-15-13:44:10] Epoch: [080][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.466 (3.374) Prec@1 65.62 (66.93) Prec@5 84.38 (86.29) + train[2018-10-15-13:45:55] Epoch: [080][5200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.114 (3.375) Prec@1 74.22 (66.91) Prec@5 89.06 (86.27) + train[2018-10-15-13:47:39] Epoch: [080][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.288 (3.375) Prec@1 70.31 (66.90) Prec@5 85.16 (86.27) + train[2018-10-15-13:49:22] Epoch: [080][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.552 (3.376) Prec@1 61.72 (66.90) Prec@5 87.50 (86.28) + train[2018-10-15-13:51:06] Epoch: [080][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.388 (3.376) Prec@1 70.31 (66.91) Prec@5 89.84 (86.27) + train[2018-10-15-13:52:49] Epoch: [080][6000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.527 (3.377) Prec@1 64.06 (66.87) Prec@5 81.25 (86.25) + train[2018-10-15-13:54:33] Epoch: [080][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.435 (3.377) Prec@1 66.41 (66.87) Prec@5 84.38 (86.25) + train[2018-10-15-13:56:17] Epoch: [080][6400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.586 (3.377) Prec@1 64.84 (66.87) Prec@5 79.69 (86.26) + train[2018-10-15-13:58:03] Epoch: [080][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.574 (3.377) Prec@1 61.72 (66.87) Prec@5 84.38 (86.26) + train[2018-10-15-13:59:48] Epoch: [080][6800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.407 (3.377) Prec@1 71.88 (66.86) Prec@5 83.59 (86.24) + train[2018-10-15-14:01:34] Epoch: [080][7000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.374 (3.377) Prec@1 71.88 (66.86) Prec@5 85.16 (86.24) + train[2018-10-15-14:03:19] Epoch: [080][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.202 (3.378) Prec@1 67.97 (66.86) Prec@5 87.50 (86.23) + train[2018-10-15-14:05:03] Epoch: [080][7400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.843 (3.379) Prec@1 59.38 (66.84) Prec@5 78.91 (86.22) + train[2018-10-15-14:06:48] Epoch: [080][7600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.369 (3.380) Prec@1 63.28 (66.82) Prec@5 87.50 (86.21) + train[2018-10-15-14:08:34] Epoch: [080][7800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.198 (3.380) Prec@1 71.09 (66.82) Prec@5 88.28 (86.21) + train[2018-10-15-14:10:20] Epoch: [080][8000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.551 (3.381) Prec@1 61.72 (66.80) Prec@5 83.59 (86.20) + train[2018-10-15-14:12:03] Epoch: [080][8200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 4.003 (3.381) Prec@1 59.38 (66.80) Prec@5 78.12 (86.19) + train[2018-10-15-14:13:47] Epoch: [080][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.165 (3.381) Prec@1 66.41 (66.81) Prec@5 87.50 (86.19) + train[2018-10-15-14:15:33] Epoch: [080][8600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.485 (3.382) Prec@1 65.62 (66.80) Prec@5 82.03 (86.17) + train[2018-10-15-14:17:17] Epoch: [080][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.581 (3.382) Prec@1 61.72 (66.80) Prec@5 84.38 (86.17) + train[2018-10-15-14:19:01] Epoch: [080][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.517 (3.383) Prec@1 61.72 (66.80) Prec@5 85.94 (86.16) + train[2018-10-15-14:20:46] Epoch: [080][9200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.429 (3.383) Prec@1 67.19 (66.80) Prec@5 87.50 (86.17) + train[2018-10-15-14:22:31] Epoch: [080][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.456 (3.383) Prec@1 66.41 (66.79) Prec@5 87.50 (86.17) + train[2018-10-15-14:24:15] Epoch: [080][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.200 (3.383) Prec@1 71.09 (66.79) Prec@5 88.28 (86.17) + train[2018-10-15-14:25:58] Epoch: [080][9800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.331 (3.384) Prec@1 67.97 (66.78) Prec@5 85.16 (86.16) + train[2018-10-15-14:27:42] Epoch: [080][10000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.890 (3.385) Prec@1 59.38 (66.77) Prec@5 78.12 (86.16) + train[2018-10-15-14:27:46] Epoch: [080][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 3.034 (3.385) Prec@1 80.00 (66.77) Prec@5 86.67 (86.16) +[2018-10-15-14:27:46] **train** Prec@1 66.77 Prec@5 86.16 Error@1 33.23 Error@5 13.84 Loss:3.385 + test [2018-10-15-14:27:50] Epoch: [080][000/391] Time 3.21 (3.21) Data 3.07 (3.07) Loss 0.702 (0.702) Prec@1 82.81 (82.81) Prec@5 95.31 (95.31) + test [2018-10-15-14:28:17] Epoch: [080][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.413 (1.129) Prec@1 67.19 (73.52) Prec@5 89.06 (91.65) + test [2018-10-15-14:28:41] Epoch: [080][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.634 (1.310) Prec@1 28.75 (69.59) Prec@5 73.75 (89.16) +[2018-10-15-14:28:41] **test** Prec@1 69.59 Prec@5 89.16 Error@1 30.41 Error@5 10.84 Loss:1.310 +----> Best Accuracy : Acc@1=69.67, Acc@5=89.36, Error@1=30.33, Error@5=10.64 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-15-14:28:41] [Epoch=081/250] [Need: 247:52:59] LR=0.0085 ~ 0.0085, Batch=128 + train[2018-10-15-14:28:46] Epoch: [081][000/10010] Time 4.74 (4.74) Data 4.12 (4.12) Loss 3.662 (3.662) Prec@1 54.69 (54.69) Prec@5 84.38 (84.38) + train[2018-10-15-14:30:30] Epoch: [081][200/10010] Time 0.52 (0.54) Data 0.00 (0.02) Loss 3.452 (3.356) Prec@1 64.84 (67.67) Prec@5 82.81 (86.50) + train[2018-10-15-14:32:14] Epoch: [081][400/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.396 (3.355) Prec@1 67.19 (67.51) Prec@5 88.28 (86.52) + train[2018-10-15-14:33:58] Epoch: [081][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.838 (3.357) Prec@1 61.72 (67.45) Prec@5 84.38 (86.56) + train[2018-10-15-14:35:42] Epoch: [081][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.197 (3.355) Prec@1 68.75 (67.45) Prec@5 89.06 (86.53) + train[2018-10-15-14:37:26] Epoch: [081][1000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.270 (3.351) Prec@1 68.75 (67.49) Prec@5 87.50 (86.60) + train[2018-10-15-14:39:10] Epoch: [081][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.957 (3.348) Prec@1 58.59 (67.56) Prec@5 79.69 (86.65) + train[2018-10-15-14:40:55] Epoch: [081][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.214 (3.350) Prec@1 70.31 (67.51) Prec@5 90.62 (86.65) + train[2018-10-15-14:42:40] Epoch: [081][1600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.132 (3.349) Prec@1 71.09 (67.54) Prec@5 90.62 (86.66) + train[2018-10-15-14:44:23] Epoch: [081][1800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.292 (3.351) Prec@1 70.31 (67.52) Prec@5 84.38 (86.63) + train[2018-10-15-14:46:07] Epoch: [081][2000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.569 (3.353) Prec@1 66.41 (67.44) Prec@5 85.94 (86.60) + train[2018-10-15-14:47:51] Epoch: [081][2200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.393 (3.353) Prec@1 69.53 (67.45) Prec@5 86.72 (86.59) + train[2018-10-15-14:49:35] Epoch: [081][2400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.388 (3.355) Prec@1 71.88 (67.44) Prec@5 82.81 (86.56) + train[2018-10-15-14:51:19] Epoch: [081][2600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.454 (3.355) Prec@1 69.53 (67.44) Prec@5 85.94 (86.58) + train[2018-10-15-14:53:04] Epoch: [081][2800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.143 (3.355) Prec@1 70.31 (67.42) Prec@5 87.50 (86.57) + train[2018-10-15-14:54:47] Epoch: [081][3000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.293 (3.354) Prec@1 71.88 (67.41) Prec@5 85.94 (86.58) + train[2018-10-15-14:56:33] Epoch: [081][3200/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.160 (3.356) Prec@1 67.19 (67.37) Prec@5 86.72 (86.55) + train[2018-10-15-14:58:19] Epoch: [081][3400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.609 (3.357) Prec@1 65.62 (67.35) Prec@5 82.03 (86.53) + train[2018-10-15-15:00:05] Epoch: [081][3600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.968 (3.358) Prec@1 74.22 (67.33) Prec@5 92.97 (86.51) + train[2018-10-15-15:01:50] Epoch: [081][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.921 (3.359) Prec@1 75.00 (67.31) Prec@5 91.41 (86.49) + train[2018-10-15-15:03:34] Epoch: [081][4000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.443 (3.359) Prec@1 67.19 (67.32) Prec@5 86.72 (86.50) + train[2018-10-15-15:05:18] Epoch: [081][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.465 (3.359) Prec@1 67.97 (67.30) Prec@5 82.81 (86.49) + train[2018-10-15-15:07:02] Epoch: [081][4400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.571 (3.360) Prec@1 67.97 (67.29) Prec@5 82.81 (86.49) + train[2018-10-15-15:08:46] Epoch: [081][4600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.270 (3.360) Prec@1 71.88 (67.29) Prec@5 89.06 (86.48) + train[2018-10-15-15:10:31] Epoch: [081][4800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.576 (3.360) Prec@1 61.72 (67.27) Prec@5 86.72 (86.47) + train[2018-10-15-15:12:16] Epoch: [081][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.524 (3.361) Prec@1 61.72 (67.24) Prec@5 85.94 (86.46) + train[2018-10-15-15:14:01] Epoch: [081][5200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.693 (3.363) Prec@1 62.50 (67.21) Prec@5 83.59 (86.44) + train[2018-10-15-15:15:46] Epoch: [081][5400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.528 (3.364) Prec@1 65.62 (67.19) Prec@5 82.03 (86.43) + train[2018-10-15-15:17:32] Epoch: [081][5600/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.367 (3.365) Prec@1 68.75 (67.17) Prec@5 85.16 (86.42) + train[2018-10-15-15:19:18] Epoch: [081][5800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.396 (3.366) Prec@1 64.06 (67.16) Prec@5 87.50 (86.42) + train[2018-10-15-15:21:03] Epoch: [081][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.639 (3.366) Prec@1 63.28 (67.15) Prec@5 83.59 (86.42) + train[2018-10-15-15:22:48] Epoch: [081][6200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.199 (3.366) Prec@1 71.88 (67.15) Prec@5 85.94 (86.41) + train[2018-10-15-15:24:34] Epoch: [081][6400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.275 (3.366) Prec@1 70.31 (67.14) Prec@5 88.28 (86.41) + train[2018-10-15-15:26:20] Epoch: [081][6600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.619 (3.365) Prec@1 68.75 (67.15) Prec@5 82.81 (86.43) + train[2018-10-15-15:28:06] Epoch: [081][6800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.251 (3.365) Prec@1 72.66 (67.15) Prec@5 87.50 (86.44) + train[2018-10-15-15:29:51] Epoch: [081][7000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.446 (3.367) Prec@1 67.19 (67.13) Prec@5 86.72 (86.42) + train[2018-10-15-15:31:36] Epoch: [081][7200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.464 (3.367) Prec@1 64.06 (67.11) Prec@5 84.38 (86.41) + train[2018-10-15-15:33:22] Epoch: [081][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.390 (3.367) Prec@1 63.28 (67.10) Prec@5 86.72 (86.40) + train[2018-10-15-15:35:06] Epoch: [081][7600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.484 (3.369) Prec@1 67.97 (67.08) Prec@5 85.16 (86.39) + train[2018-10-15-15:36:52] Epoch: [081][7800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.217 (3.369) Prec@1 67.97 (67.08) Prec@5 87.50 (86.39) + train[2018-10-15-15:38:37] Epoch: [081][8000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.546 (3.369) Prec@1 65.62 (67.08) Prec@5 83.59 (86.39) + train[2018-10-15-15:40:23] Epoch: [081][8200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.355 (3.370) Prec@1 66.41 (67.05) Prec@5 92.97 (86.37) + train[2018-10-15-15:42:09] Epoch: [081][8400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.382 (3.370) Prec@1 69.53 (67.04) Prec@5 85.16 (86.37) + train[2018-10-15-15:43:55] Epoch: [081][8600/10010] Time 0.59 (0.52) Data 0.00 (0.00) Loss 3.581 (3.371) Prec@1 63.28 (67.03) Prec@5 88.28 (86.37) + train[2018-10-15-15:45:40] Epoch: [081][8800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.488 (3.372) Prec@1 64.84 (67.01) Prec@5 85.94 (86.36) + train[2018-10-15-15:47:26] Epoch: [081][9000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.270 (3.372) Prec@1 71.09 (67.01) Prec@5 89.84 (86.35) + train[2018-10-15-15:49:11] Epoch: [081][9200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.082 (3.373) Prec@1 70.31 (67.00) Prec@5 90.62 (86.34) + train[2018-10-15-15:50:56] Epoch: [081][9400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.503 (3.373) Prec@1 63.28 (66.99) Prec@5 84.38 (86.34) + train[2018-10-15-15:52:41] Epoch: [081][9600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.708 (3.374) Prec@1 60.94 (66.98) Prec@5 79.69 (86.33) + train[2018-10-15-15:54:27] Epoch: [081][9800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.063 (3.374) Prec@1 74.22 (66.98) Prec@5 87.50 (86.33) + train[2018-10-15-15:56:12] Epoch: [081][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.305 (3.375) Prec@1 70.31 (66.96) Prec@5 87.50 (86.32) + train[2018-10-15-15:56:17] Epoch: [081][10009/10010] Time 0.21 (0.53) Data 0.00 (0.00) Loss 3.708 (3.375) Prec@1 60.00 (66.96) Prec@5 93.33 (86.32) +[2018-10-15-15:56:17] **train** Prec@1 66.96 Prec@5 86.32 Error@1 33.04 Error@5 13.68 Loss:3.375 + test [2018-10-15-15:56:20] Epoch: [081][000/391] Time 3.80 (3.80) Data 3.67 (3.67) Loss 0.818 (0.818) Prec@1 80.47 (80.47) Prec@5 94.53 (94.53) + test [2018-10-15-15:56:47] Epoch: [081][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.227 (1.155) Prec@1 73.44 (73.22) Prec@5 91.41 (91.94) + test [2018-10-15-15:57:12] Epoch: [081][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.337 (1.320) Prec@1 36.25 (69.72) Prec@5 80.00 (89.42) +[2018-10-15-15:57:12] **test** Prec@1 69.72 Prec@5 89.42 Error@1 30.28 Error@5 10.58 Loss:1.320 +----> Best Accuracy : Acc@1=69.72, Acc@5=89.42, Error@1=30.28, Error@5=10.58 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-15-15:57:12] [Epoch=082/250] [Need: 247:49:23] LR=0.0082 ~ 0.0082, Batch=128 + train[2018-10-15-15:57:16] Epoch: [082][000/10010] Time 4.65 (4.65) Data 4.04 (4.04) Loss 3.078 (3.078) Prec@1 70.31 (70.31) Prec@5 88.28 (88.28) + train[2018-10-15-15:59:01] Epoch: [082][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 3.061 (3.322) Prec@1 71.09 (67.79) Prec@5 89.06 (86.86) + train[2018-10-15-16:00:45] Epoch: [082][400/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.376 (3.327) Prec@1 67.19 (67.91) Prec@5 86.72 (86.80) + train[2018-10-15-16:02:28] Epoch: [082][600/10010] Time 0.49 (0.53) Data 0.00 (0.01) Loss 3.098 (3.325) Prec@1 74.22 (67.99) Prec@5 85.94 (86.87) + train[2018-10-15-16:04:12] Epoch: [082][800/10010] Time 0.50 (0.52) Data 0.00 (0.01) Loss 3.088 (3.329) Prec@1 72.66 (67.87) Prec@5 89.06 (86.83) + train[2018-10-15-16:05:57] Epoch: [082][1000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.114 (3.324) Prec@1 69.53 (67.87) Prec@5 89.84 (86.92) + train[2018-10-15-16:07:42] Epoch: [082][1200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.437 (3.325) Prec@1 62.50 (67.86) Prec@5 83.59 (86.92) + train[2018-10-15-16:09:27] Epoch: [082][1400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.259 (3.330) Prec@1 68.75 (67.74) Prec@5 85.94 (86.87) + train[2018-10-15-16:11:12] Epoch: [082][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.292 (3.334) Prec@1 71.09 (67.64) Prec@5 86.72 (86.80) + train[2018-10-15-16:12:58] Epoch: [082][1800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.394 (3.340) Prec@1 64.06 (67.52) Prec@5 86.72 (86.73) + train[2018-10-15-16:14:44] Epoch: [082][2000/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.174 (3.339) Prec@1 75.00 (67.53) Prec@5 88.28 (86.74) + train[2018-10-15-16:16:28] Epoch: [082][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.281 (3.339) Prec@1 64.84 (67.52) Prec@5 86.72 (86.75) + train[2018-10-15-16:18:12] Epoch: [082][2400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.010 (3.338) Prec@1 75.78 (67.56) Prec@5 88.28 (86.79) + train[2018-10-15-16:19:56] Epoch: [082][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.293 (3.338) Prec@1 67.97 (67.54) Prec@5 89.06 (86.78) + train[2018-10-15-16:21:40] Epoch: [082][2800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.338 (3.339) Prec@1 63.28 (67.50) Prec@5 86.72 (86.77) + train[2018-10-15-16:23:24] Epoch: [082][3000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.416 (3.343) Prec@1 69.53 (67.43) Prec@5 85.94 (86.74) + train[2018-10-15-16:25:08] Epoch: [082][3200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.989 (3.345) Prec@1 72.66 (67.38) Prec@5 89.84 (86.71) + train[2018-10-15-16:26:53] Epoch: [082][3400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.202 (3.346) Prec@1 75.78 (67.36) Prec@5 87.50 (86.70) + train[2018-10-15-16:28:37] Epoch: [082][3600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.463 (3.346) Prec@1 65.62 (67.37) Prec@5 85.16 (86.70) + train[2018-10-15-16:30:21] Epoch: [082][3800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.382 (3.347) Prec@1 69.53 (67.33) Prec@5 85.94 (86.69) + train[2018-10-15-16:32:06] Epoch: [082][4000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.590 (3.349) Prec@1 66.41 (67.30) Prec@5 86.72 (86.66) + train[2018-10-15-16:33:50] Epoch: [082][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.188 (3.349) Prec@1 72.66 (67.30) Prec@5 89.84 (86.65) + train[2018-10-15-16:35:33] Epoch: [082][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.044 (3.350) Prec@1 73.44 (67.29) Prec@5 89.06 (86.65) + train[2018-10-15-16:37:18] Epoch: [082][4600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.442 (3.350) Prec@1 64.06 (67.28) Prec@5 82.03 (86.64) + train[2018-10-15-16:39:03] Epoch: [082][4800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.019 (3.352) Prec@1 75.78 (67.26) Prec@5 89.06 (86.63) + train[2018-10-15-16:40:47] Epoch: [082][5000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.479 (3.352) Prec@1 63.28 (67.26) Prec@5 85.16 (86.62) + train[2018-10-15-16:42:31] Epoch: [082][5200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.472 (3.353) Prec@1 64.06 (67.25) Prec@5 84.38 (86.61) + train[2018-10-15-16:44:16] Epoch: [082][5400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.057 (3.354) Prec@1 69.53 (67.23) Prec@5 91.41 (86.59) + train[2018-10-15-16:46:01] Epoch: [082][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.585 (3.355) Prec@1 63.28 (67.19) Prec@5 82.81 (86.57) + train[2018-10-15-16:47:45] Epoch: [082][5800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.331 (3.356) Prec@1 65.62 (67.19) Prec@5 84.38 (86.56) + train[2018-10-15-16:49:30] Epoch: [082][6000/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.078 (3.356) Prec@1 73.44 (67.20) Prec@5 91.41 (86.56) + train[2018-10-15-16:51:14] Epoch: [082][6200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.421 (3.356) Prec@1 64.06 (67.19) Prec@5 88.28 (86.55) + train[2018-10-15-16:52:58] Epoch: [082][6400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.460 (3.357) Prec@1 63.28 (67.18) Prec@5 85.94 (86.54) + train[2018-10-15-16:54:43] Epoch: [082][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.599 (3.357) Prec@1 67.97 (67.18) Prec@5 82.03 (86.54) + train[2018-10-15-16:56:27] Epoch: [082][6800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.437 (3.358) Prec@1 66.41 (67.16) Prec@5 85.94 (86.53) + train[2018-10-15-16:58:11] Epoch: [082][7000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.415 (3.359) Prec@1 64.84 (67.15) Prec@5 85.16 (86.53) + train[2018-10-15-16:59:55] Epoch: [082][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.886 (3.359) Prec@1 55.47 (67.14) Prec@5 82.03 (86.52) + train[2018-10-15-17:01:39] Epoch: [082][7400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.817 (3.360) Prec@1 58.59 (67.14) Prec@5 80.47 (86.51) + train[2018-10-15-17:03:25] Epoch: [082][7600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.443 (3.359) Prec@1 64.84 (67.15) Prec@5 85.94 (86.52) + train[2018-10-15-17:05:09] Epoch: [082][7800/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.449 (3.360) Prec@1 64.84 (67.14) Prec@5 84.38 (86.51) + train[2018-10-15-17:06:54] Epoch: [082][8000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.474 (3.360) Prec@1 67.19 (67.14) Prec@5 85.16 (86.51) + train[2018-10-15-17:08:39] Epoch: [082][8200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.513 (3.360) Prec@1 61.72 (67.13) Prec@5 86.72 (86.50) + train[2018-10-15-17:10:24] Epoch: [082][8400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.168 (3.361) Prec@1 69.53 (67.13) Prec@5 91.41 (86.49) + train[2018-10-15-17:12:09] Epoch: [082][8600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.441 (3.361) Prec@1 64.06 (67.13) Prec@5 83.59 (86.49) + train[2018-10-15-17:13:54] Epoch: [082][8800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.273 (3.362) Prec@1 69.53 (67.12) Prec@5 89.06 (86.48) + train[2018-10-15-17:15:39] Epoch: [082][9000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.325 (3.362) Prec@1 65.62 (67.11) Prec@5 85.94 (86.47) + train[2018-10-15-17:17:25] Epoch: [082][9200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.261 (3.363) Prec@1 69.53 (67.10) Prec@5 86.72 (86.47) + train[2018-10-15-17:19:10] Epoch: [082][9400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.341 (3.363) Prec@1 61.72 (67.09) Prec@5 88.28 (86.46) + train[2018-10-15-17:20:55] Epoch: [082][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.467 (3.363) Prec@1 68.75 (67.09) Prec@5 86.72 (86.46) + train[2018-10-15-17:22:39] Epoch: [082][9800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.228 (3.364) Prec@1 68.75 (67.08) Prec@5 86.72 (86.45) + train[2018-10-15-17:24:24] Epoch: [082][10000/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.187 (3.365) Prec@1 67.19 (67.08) Prec@5 89.84 (86.44) + train[2018-10-15-17:24:29] Epoch: [082][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 5.270 (3.365) Prec@1 46.67 (67.08) Prec@5 53.33 (86.44) +[2018-10-15-17:24:29] **train** Prec@1 67.08 Prec@5 86.44 Error@1 32.92 Error@5 13.56 Loss:3.365 + test [2018-10-15-17:24:33] Epoch: [082][000/391] Time 3.95 (3.95) Data 3.82 (3.82) Loss 0.664 (0.664) Prec@1 85.16 (85.16) Prec@5 97.66 (97.66) + test [2018-10-15-17:24:59] Epoch: [082][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.534 (1.163) Prec@1 58.59 (73.10) Prec@5 89.06 (91.95) + test [2018-10-15-17:25:24] Epoch: [082][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.223 (1.322) Prec@1 43.75 (69.78) Prec@5 78.75 (89.43) +[2018-10-15-17:25:24] **test** Prec@1 69.78 Prec@5 89.43 Error@1 30.22 Error@5 10.57 Loss:1.322 +----> Best Accuracy : Acc@1=69.78, Acc@5=89.43, Error@1=30.22, Error@5=10.57 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-15-17:25:25] [Epoch=083/250] [Need: 245:31:52] LR=0.0080 ~ 0.0080, Batch=128 + train[2018-10-15-17:25:29] Epoch: [083][000/10010] Time 4.42 (4.42) Data 3.86 (3.86) Loss 3.598 (3.598) Prec@1 64.84 (64.84) Prec@5 81.25 (81.25) + train[2018-10-15-17:27:13] Epoch: [083][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 3.391 (3.336) Prec@1 71.88 (67.70) Prec@5 86.72 (86.88) + train[2018-10-15-17:28:57] Epoch: [083][400/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.359 (3.338) Prec@1 67.19 (67.69) Prec@5 82.81 (86.83) + train[2018-10-15-17:30:42] Epoch: [083][600/10010] Time 0.49 (0.53) Data 0.00 (0.01) Loss 3.531 (3.337) Prec@1 65.62 (67.64) Prec@5 85.94 (86.79) + train[2018-10-15-17:32:27] Epoch: [083][800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.614 (3.332) Prec@1 65.62 (67.76) Prec@5 83.59 (86.79) + train[2018-10-15-17:34:11] Epoch: [083][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.184 (3.332) Prec@1 68.75 (67.82) Prec@5 90.62 (86.81) + train[2018-10-15-17:35:55] Epoch: [083][1200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.241 (3.335) Prec@1 69.53 (67.73) Prec@5 88.28 (86.76) + train[2018-10-15-17:37:38] Epoch: [083][1400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.011 (3.338) Prec@1 73.44 (67.69) Prec@5 88.28 (86.72) + train[2018-10-15-17:39:22] Epoch: [083][1600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.662 (3.338) Prec@1 61.72 (67.69) Prec@5 81.25 (86.71) + train[2018-10-15-17:41:06] Epoch: [083][1800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.381 (3.338) Prec@1 67.19 (67.69) Prec@5 87.50 (86.73) + train[2018-10-15-17:42:50] Epoch: [083][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.452 (3.337) Prec@1 65.62 (67.72) Prec@5 84.38 (86.74) + train[2018-10-15-17:44:34] Epoch: [083][2200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.640 (3.336) Prec@1 59.38 (67.75) Prec@5 84.38 (86.75) + train[2018-10-15-17:46:17] Epoch: [083][2400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.349 (3.337) Prec@1 64.06 (67.71) Prec@5 86.72 (86.73) + train[2018-10-15-17:48:01] Epoch: [083][2600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.444 (3.339) Prec@1 64.84 (67.66) Prec@5 85.16 (86.73) + train[2018-10-15-17:49:46] Epoch: [083][2800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.355 (3.341) Prec@1 66.41 (67.61) Prec@5 85.94 (86.69) + train[2018-10-15-17:51:30] Epoch: [083][3000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.342 (3.342) Prec@1 62.50 (67.60) Prec@5 89.84 (86.67) + train[2018-10-15-17:53:14] Epoch: [083][3200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.122 (3.343) Prec@1 69.53 (67.58) Prec@5 92.97 (86.67) + train[2018-10-15-17:54:59] Epoch: [083][3400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.025 (3.342) Prec@1 74.22 (67.59) Prec@5 89.06 (86.69) + train[2018-10-15-17:56:46] Epoch: [083][3600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.476 (3.343) Prec@1 66.41 (67.58) Prec@5 84.38 (86.67) + train[2018-10-15-17:58:30] Epoch: [083][3800/10010] Time 0.59 (0.52) Data 0.00 (0.00) Loss 3.498 (3.343) Prec@1 67.97 (67.56) Prec@5 86.72 (86.67) + train[2018-10-15-18:00:16] Epoch: [083][4000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.332 (3.345) Prec@1 67.97 (67.54) Prec@5 87.50 (86.65) + train[2018-10-15-18:02:02] Epoch: [083][4200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.248 (3.346) Prec@1 71.09 (67.50) Prec@5 87.50 (86.63) + train[2018-10-15-18:03:48] Epoch: [083][4400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.609 (3.347) Prec@1 67.19 (67.48) Prec@5 78.91 (86.62) + train[2018-10-15-18:05:34] Epoch: [083][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.284 (3.348) Prec@1 64.06 (67.46) Prec@5 89.06 (86.61) + train[2018-10-15-18:07:20] Epoch: [083][4800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.385 (3.349) Prec@1 67.19 (67.43) Prec@5 86.72 (86.59) + train[2018-10-15-18:09:05] Epoch: [083][5000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.163 (3.349) Prec@1 71.88 (67.42) Prec@5 89.84 (86.59) + train[2018-10-15-18:10:51] Epoch: [083][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.375 (3.351) Prec@1 67.97 (67.40) Prec@5 82.81 (86.56) + train[2018-10-15-18:12:36] Epoch: [083][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.430 (3.351) Prec@1 64.84 (67.40) Prec@5 86.72 (86.57) + train[2018-10-15-18:14:23] Epoch: [083][5600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.704 (3.351) Prec@1 61.72 (67.38) Prec@5 81.25 (86.56) + train[2018-10-15-18:16:08] Epoch: [083][5800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.413 (3.352) Prec@1 64.84 (67.38) Prec@5 88.28 (86.56) + train[2018-10-15-18:17:54] Epoch: [083][6000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.585 (3.352) Prec@1 64.06 (67.39) Prec@5 83.59 (86.57) + train[2018-10-15-18:19:39] Epoch: [083][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.220 (3.351) Prec@1 68.75 (67.38) Prec@5 88.28 (86.58) + train[2018-10-15-18:21:25] Epoch: [083][6400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.564 (3.351) Prec@1 64.06 (67.38) Prec@5 85.16 (86.58) + train[2018-10-15-18:23:11] Epoch: [083][6600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.787 (3.352) Prec@1 53.12 (67.36) Prec@5 80.47 (86.57) + train[2018-10-15-18:24:58] Epoch: [083][6800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.225 (3.352) Prec@1 66.41 (67.36) Prec@5 88.28 (86.57) + train[2018-10-15-18:26:43] Epoch: [083][7000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.333 (3.353) Prec@1 68.75 (67.35) Prec@5 84.38 (86.56) + train[2018-10-15-18:28:30] Epoch: [083][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.286 (3.354) Prec@1 67.97 (67.34) Prec@5 86.72 (86.55) + train[2018-10-15-18:30:15] Epoch: [083][7400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.617 (3.354) Prec@1 62.50 (67.32) Prec@5 81.25 (86.55) + train[2018-10-15-18:32:00] Epoch: [083][7600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.415 (3.354) Prec@1 69.53 (67.31) Prec@5 88.28 (86.55) + train[2018-10-15-18:33:46] Epoch: [083][7800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.137 (3.354) Prec@1 71.09 (67.30) Prec@5 89.84 (86.54) + train[2018-10-15-18:35:32] Epoch: [083][8000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.039 (3.354) Prec@1 72.66 (67.30) Prec@5 89.06 (86.54) + train[2018-10-15-18:37:18] Epoch: [083][8200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.266 (3.355) Prec@1 65.62 (67.28) Prec@5 88.28 (86.53) + train[2018-10-15-18:39:03] Epoch: [083][8400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.326 (3.355) Prec@1 70.31 (67.27) Prec@5 86.72 (86.52) + train[2018-10-15-18:40:48] Epoch: [083][8600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.779 (3.357) Prec@1 56.25 (67.24) Prec@5 78.91 (86.51) + train[2018-10-15-18:42:33] Epoch: [083][8800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.573 (3.357) Prec@1 64.84 (67.23) Prec@5 81.25 (86.50) + train[2018-10-15-18:44:19] Epoch: [083][9000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.325 (3.358) Prec@1 72.66 (67.22) Prec@5 85.94 (86.49) + train[2018-10-15-18:46:04] Epoch: [083][9200/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.188 (3.358) Prec@1 71.09 (67.21) Prec@5 85.94 (86.48) + train[2018-10-15-18:47:51] Epoch: [083][9400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.935 (3.359) Prec@1 74.22 (67.20) Prec@5 92.19 (86.48) + train[2018-10-15-18:49:36] Epoch: [083][9600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.282 (3.359) Prec@1 67.19 (67.19) Prec@5 86.72 (86.48) + train[2018-10-15-18:51:23] Epoch: [083][9800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.415 (3.360) Prec@1 64.84 (67.18) Prec@5 86.72 (86.47) + train[2018-10-15-18:53:08] Epoch: [083][10000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.366 (3.360) Prec@1 72.66 (67.17) Prec@5 87.50 (86.46) + train[2018-10-15-18:53:12] Epoch: [083][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 3.094 (3.360) Prec@1 66.67 (67.17) Prec@5 100.00 (86.46) +[2018-10-15-18:53:12] **train** Prec@1 67.17 Prec@5 86.46 Error@1 32.83 Error@5 13.54 Loss:3.360 + test [2018-10-15-18:53:16] Epoch: [083][000/391] Time 4.26 (4.26) Data 4.10 (4.10) Loss 0.802 (0.802) Prec@1 85.16 (85.16) Prec@5 91.41 (91.41) + test [2018-10-15-18:53:43] Epoch: [083][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.351 (1.130) Prec@1 64.06 (73.40) Prec@5 92.97 (91.89) + test [2018-10-15-18:54:08] Epoch: [083][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.389 (1.313) Prec@1 38.75 (69.70) Prec@5 76.25 (89.23) +[2018-10-15-18:54:08] **test** Prec@1 69.70 Prec@5 89.23 Error@1 30.30 Error@5 10.77 Loss:1.313 +----> Best Accuracy : Acc@1=69.78, Acc@5=89.43, Error@1=30.22, Error@5=10.57 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-15-18:54:09] [Epoch=084/250] [Need: 245:29:57] LR=0.0077 ~ 0.0077, Batch=128 + train[2018-10-15-18:54:14] Epoch: [084][000/10010] Time 5.29 (5.29) Data 4.74 (4.74) Loss 3.384 (3.384) Prec@1 65.62 (65.62) Prec@5 89.06 (89.06) + train[2018-10-15-18:55:58] Epoch: [084][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.269 (3.315) Prec@1 70.31 (68.19) Prec@5 85.16 (86.91) + train[2018-10-15-18:57:42] Epoch: [084][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.026 (3.316) Prec@1 75.00 (68.03) Prec@5 88.28 (86.95) + train[2018-10-15-18:59:27] Epoch: [084][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.353 (3.320) Prec@1 65.62 (67.96) Prec@5 88.28 (86.88) + train[2018-10-15-19:01:10] Epoch: [084][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.926 (3.323) Prec@1 69.53 (67.85) Prec@5 93.75 (86.88) + train[2018-10-15-19:02:55] Epoch: [084][1000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.239 (3.322) Prec@1 72.66 (67.93) Prec@5 87.50 (86.90) + train[2018-10-15-19:04:39] Epoch: [084][1200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.518 (3.323) Prec@1 66.41 (67.96) Prec@5 84.38 (86.90) + train[2018-10-15-19:06:23] Epoch: [084][1400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.750 (3.323) Prec@1 64.84 (68.00) Prec@5 82.81 (86.93) + train[2018-10-15-19:08:07] Epoch: [084][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.305 (3.324) Prec@1 70.31 (67.94) Prec@5 87.50 (86.90) + train[2018-10-15-19:09:51] Epoch: [084][1800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.079 (3.326) Prec@1 73.44 (67.91) Prec@5 89.84 (86.90) + train[2018-10-15-19:11:35] Epoch: [084][2000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.543 (3.327) Prec@1 67.19 (67.90) Prec@5 85.16 (86.89) + train[2018-10-15-19:13:18] Epoch: [084][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.306 (3.328) Prec@1 63.28 (67.83) Prec@5 86.72 (86.87) + train[2018-10-15-19:15:03] Epoch: [084][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.356 (3.328) Prec@1 64.06 (67.81) Prec@5 88.28 (86.86) + train[2018-10-15-19:16:48] Epoch: [084][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.599 (3.330) Prec@1 64.06 (67.76) Prec@5 84.38 (86.85) + train[2018-10-15-19:18:32] Epoch: [084][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.135 (3.330) Prec@1 71.88 (67.76) Prec@5 88.28 (86.85) + train[2018-10-15-19:20:16] Epoch: [084][3000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.533 (3.331) Prec@1 67.19 (67.72) Prec@5 83.59 (86.83) + train[2018-10-15-19:22:00] Epoch: [084][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.461 (3.333) Prec@1 70.31 (67.68) Prec@5 86.72 (86.81) + train[2018-10-15-19:23:46] Epoch: [084][3400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.711 (3.333) Prec@1 60.16 (67.69) Prec@5 81.25 (86.81) + train[2018-10-15-19:25:30] Epoch: [084][3600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.927 (3.334) Prec@1 73.44 (67.67) Prec@5 93.75 (86.78) + train[2018-10-15-19:27:14] Epoch: [084][3800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.049 (3.334) Prec@1 74.22 (67.66) Prec@5 89.84 (86.78) + train[2018-10-15-19:28:59] Epoch: [084][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.390 (3.334) Prec@1 67.97 (67.66) Prec@5 86.72 (86.77) + train[2018-10-15-19:30:42] Epoch: [084][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.292 (3.335) Prec@1 67.97 (67.65) Prec@5 89.84 (86.76) + train[2018-10-15-19:32:27] Epoch: [084][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.945 (3.336) Prec@1 60.94 (67.64) Prec@5 76.56 (86.75) + train[2018-10-15-19:34:11] Epoch: [084][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.163 (3.336) Prec@1 67.19 (67.63) Prec@5 87.50 (86.76) + train[2018-10-15-19:35:55] Epoch: [084][4800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.377 (3.335) Prec@1 71.09 (67.64) Prec@5 84.38 (86.76) + train[2018-10-15-19:37:40] Epoch: [084][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.360 (3.335) Prec@1 68.75 (67.65) Prec@5 87.50 (86.76) + train[2018-10-15-19:39:24] Epoch: [084][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.492 (3.337) Prec@1 67.19 (67.62) Prec@5 84.38 (86.74) + train[2018-10-15-19:41:08] Epoch: [084][5400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.321 (3.337) Prec@1 67.97 (67.62) Prec@5 86.72 (86.74) + train[2018-10-15-19:42:52] Epoch: [084][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.668 (3.338) Prec@1 62.50 (67.60) Prec@5 82.03 (86.73) + train[2018-10-15-19:44:36] Epoch: [084][5800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.202 (3.339) Prec@1 72.66 (67.57) Prec@5 88.28 (86.71) + train[2018-10-15-19:46:20] Epoch: [084][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.386 (3.339) Prec@1 64.06 (67.56) Prec@5 82.03 (86.71) + train[2018-10-15-19:48:04] Epoch: [084][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.393 (3.340) Prec@1 64.06 (67.55) Prec@5 86.72 (86.71) + train[2018-10-15-19:49:49] Epoch: [084][6400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.198 (3.340) Prec@1 68.75 (67.54) Prec@5 88.28 (86.70) + train[2018-10-15-19:51:33] Epoch: [084][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.108 (3.341) Prec@1 74.22 (67.53) Prec@5 90.62 (86.69) + train[2018-10-15-19:53:17] Epoch: [084][6800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.159 (3.342) Prec@1 71.09 (67.51) Prec@5 90.62 (86.68) + train[2018-10-15-19:55:01] Epoch: [084][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.180 (3.342) Prec@1 71.09 (67.51) Prec@5 85.16 (86.68) + train[2018-10-15-19:56:44] Epoch: [084][7200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.292 (3.342) Prec@1 70.31 (67.51) Prec@5 85.94 (86.68) + train[2018-10-15-19:58:29] Epoch: [084][7400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.409 (3.342) Prec@1 63.28 (67.49) Prec@5 85.16 (86.68) + train[2018-10-15-20:00:13] Epoch: [084][7600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.970 (3.343) Prec@1 75.78 (67.49) Prec@5 92.97 (86.67) + train[2018-10-15-20:01:57] Epoch: [084][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.683 (3.344) Prec@1 57.81 (67.47) Prec@5 82.81 (86.65) + train[2018-10-15-20:03:41] Epoch: [084][8000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.308 (3.344) Prec@1 67.19 (67.47) Prec@5 85.94 (86.65) + train[2018-10-15-20:05:25] Epoch: [084][8200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.145 (3.344) Prec@1 70.31 (67.47) Prec@5 93.75 (86.66) + train[2018-10-15-20:07:10] Epoch: [084][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.446 (3.344) Prec@1 69.53 (67.46) Prec@5 84.38 (86.65) + train[2018-10-15-20:08:54] Epoch: [084][8600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.328 (3.345) Prec@1 71.09 (67.45) Prec@5 87.50 (86.64) + train[2018-10-15-20:10:38] Epoch: [084][8800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.421 (3.346) Prec@1 67.97 (67.42) Prec@5 84.38 (86.62) + train[2018-10-15-20:12:23] Epoch: [084][9000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.565 (3.347) Prec@1 64.06 (67.41) Prec@5 85.94 (86.60) + train[2018-10-15-20:14:07] Epoch: [084][9200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.465 (3.347) Prec@1 66.41 (67.39) Prec@5 87.50 (86.60) + train[2018-10-15-20:15:51] Epoch: [084][9400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.997 (3.348) Prec@1 71.09 (67.38) Prec@5 92.19 (86.59) + train[2018-10-15-20:17:36] Epoch: [084][9600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.439 (3.348) Prec@1 64.06 (67.37) Prec@5 84.38 (86.59) + train[2018-10-15-20:19:20] Epoch: [084][9800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.535 (3.348) Prec@1 57.81 (67.37) Prec@5 85.94 (86.58) + train[2018-10-15-20:21:05] Epoch: [084][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.278 (3.348) Prec@1 67.97 (67.37) Prec@5 87.50 (86.57) + train[2018-10-15-20:21:09] Epoch: [084][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.585 (3.349) Prec@1 40.00 (67.37) Prec@5 60.00 (86.57) +[2018-10-15-20:21:09] **train** Prec@1 67.37 Prec@5 86.57 Error@1 32.63 Error@5 13.43 Loss:3.349 + test [2018-10-15-20:21:13] Epoch: [084][000/391] Time 3.71 (3.71) Data 3.58 (3.58) Loss 0.753 (0.753) Prec@1 84.38 (84.38) Prec@5 94.53 (94.53) + test [2018-10-15-20:21:40] Epoch: [084][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.484 (1.133) Prec@1 62.50 (73.59) Prec@5 90.62 (92.00) + test [2018-10-15-20:22:05] Epoch: [084][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.525 (1.301) Prec@1 31.25 (70.00) Prec@5 73.75 (89.53) +[2018-10-15-20:22:05] **test** Prec@1 70.00 Prec@5 89.53 Error@1 30.00 Error@5 10.47 Loss:1.301 +----> Best Accuracy : Acc@1=70.00, Acc@5=89.53, Error@1=30.00, Error@5=10.47 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-15-20:22:05] [Epoch=085/250] [Need: 241:50:31] LR=0.0075 ~ 0.0075, Batch=128 + train[2018-10-15-20:22:10] Epoch: [085][000/10010] Time 5.25 (5.25) Data 4.67 (4.67) Loss 3.214 (3.214) Prec@1 65.62 (65.62) Prec@5 89.84 (89.84) + train[2018-10-15-20:23:54] Epoch: [085][200/10010] Time 0.51 (0.54) Data 0.00 (0.02) Loss 3.458 (3.292) Prec@1 71.09 (68.57) Prec@5 87.50 (87.19) + train[2018-10-15-20:25:38] Epoch: [085][400/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.205 (3.313) Prec@1 71.88 (68.33) Prec@5 90.62 (86.98) + train[2018-10-15-20:27:22] Epoch: [085][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.057 (3.313) Prec@1 70.31 (68.24) Prec@5 91.41 (87.04) + train[2018-10-15-20:29:06] Epoch: [085][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.174 (3.313) Prec@1 74.22 (68.27) Prec@5 88.28 (86.95) + train[2018-10-15-20:30:49] Epoch: [085][1000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.340 (3.310) Prec@1 66.41 (68.26) Prec@5 89.06 (87.03) + train[2018-10-15-20:32:33] Epoch: [085][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.439 (3.305) Prec@1 62.50 (68.30) Prec@5 84.38 (87.09) + train[2018-10-15-20:34:17] Epoch: [085][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.451 (3.307) Prec@1 67.19 (68.33) Prec@5 88.28 (87.05) + train[2018-10-15-20:36:01] Epoch: [085][1600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.332 (3.308) Prec@1 67.19 (68.27) Prec@5 89.06 (87.03) + train[2018-10-15-20:37:45] Epoch: [085][1800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.608 (3.309) Prec@1 57.81 (68.22) Prec@5 81.25 (87.04) + train[2018-10-15-20:39:29] Epoch: [085][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.305 (3.310) Prec@1 64.84 (68.18) Prec@5 87.50 (87.02) + train[2018-10-15-20:41:13] Epoch: [085][2200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.337 (3.313) Prec@1 71.88 (68.12) Prec@5 88.28 (86.99) + train[2018-10-15-20:42:58] Epoch: [085][2400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.324 (3.312) Prec@1 66.41 (68.10) Prec@5 89.06 (87.01) + train[2018-10-15-20:44:44] Epoch: [085][2600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.060 (3.313) Prec@1 72.66 (68.05) Prec@5 88.28 (87.00) + train[2018-10-15-20:46:30] Epoch: [085][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.509 (3.314) Prec@1 63.28 (68.05) Prec@5 83.59 (86.99) + train[2018-10-15-20:48:17] Epoch: [085][3000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.346 (3.316) Prec@1 70.31 (68.00) Prec@5 87.50 (86.96) + train[2018-10-15-20:50:04] Epoch: [085][3200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.372 (3.317) Prec@1 67.19 (67.98) Prec@5 85.94 (86.97) + train[2018-10-15-20:51:50] Epoch: [085][3400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.727 (3.321) Prec@1 63.28 (67.89) Prec@5 84.38 (86.92) + train[2018-10-15-20:53:36] Epoch: [085][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.233 (3.322) Prec@1 73.44 (67.88) Prec@5 89.06 (86.91) + train[2018-10-15-20:55:24] Epoch: [085][3800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.313 (3.323) Prec@1 68.75 (67.87) Prec@5 89.06 (86.91) + train[2018-10-15-20:57:11] Epoch: [085][4000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.320 (3.324) Prec@1 65.62 (67.83) Prec@5 88.28 (86.89) + train[2018-10-15-20:58:58] Epoch: [085][4200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.375 (3.325) Prec@1 66.41 (67.82) Prec@5 89.06 (86.88) + train[2018-10-15-21:00:44] Epoch: [085][4400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.331 (3.326) Prec@1 63.28 (67.79) Prec@5 90.62 (86.87) + train[2018-10-15-21:02:30] Epoch: [085][4600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.193 (3.327) Prec@1 70.31 (67.79) Prec@5 88.28 (86.87) + train[2018-10-15-21:04:16] Epoch: [085][4800/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.387 (3.326) Prec@1 65.62 (67.78) Prec@5 88.28 (86.87) + train[2018-10-15-21:06:02] Epoch: [085][5000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.442 (3.326) Prec@1 64.06 (67.78) Prec@5 85.94 (86.87) + train[2018-10-15-21:07:48] Epoch: [085][5200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.521 (3.328) Prec@1 62.50 (67.75) Prec@5 84.38 (86.85) + train[2018-10-15-21:09:34] Epoch: [085][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.453 (3.329) Prec@1 63.28 (67.74) Prec@5 86.72 (86.83) + train[2018-10-15-21:11:19] Epoch: [085][5600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.496 (3.330) Prec@1 60.94 (67.72) Prec@5 83.59 (86.81) + train[2018-10-15-21:13:05] Epoch: [085][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.091 (3.331) Prec@1 72.66 (67.71) Prec@5 92.19 (86.81) + train[2018-10-15-21:14:51] Epoch: [085][6000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.017 (3.331) Prec@1 77.34 (67.70) Prec@5 90.62 (86.80) + train[2018-10-15-21:16:37] Epoch: [085][6200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.741 (3.332) Prec@1 60.16 (67.69) Prec@5 78.12 (86.79) + train[2018-10-15-21:18:22] Epoch: [085][6400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.436 (3.332) Prec@1 66.41 (67.68) Prec@5 84.38 (86.77) + train[2018-10-15-21:20:08] Epoch: [085][6600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.452 (3.333) Prec@1 66.41 (67.66) Prec@5 83.59 (86.76) + train[2018-10-15-21:21:54] Epoch: [085][6800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.269 (3.334) Prec@1 67.97 (67.64) Prec@5 87.50 (86.76) + train[2018-10-15-21:23:39] Epoch: [085][7000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.197 (3.334) Prec@1 74.22 (67.64) Prec@5 85.94 (86.76) + train[2018-10-15-21:25:23] Epoch: [085][7200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.229 (3.335) Prec@1 68.75 (67.62) Prec@5 87.50 (86.74) + train[2018-10-15-21:27:08] Epoch: [085][7400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.220 (3.336) Prec@1 68.75 (67.60) Prec@5 86.72 (86.73) + train[2018-10-15-21:28:54] Epoch: [085][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.332 (3.335) Prec@1 72.66 (67.61) Prec@5 83.59 (86.74) + train[2018-10-15-21:30:39] Epoch: [085][7800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.050 (3.336) Prec@1 71.88 (67.59) Prec@5 89.84 (86.73) + train[2018-10-15-21:32:24] Epoch: [085][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.048 (3.336) Prec@1 71.09 (67.59) Prec@5 90.62 (86.73) + train[2018-10-15-21:34:10] Epoch: [085][8200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.262 (3.337) Prec@1 70.31 (67.58) Prec@5 88.28 (86.72) + train[2018-10-15-21:35:56] Epoch: [085][8400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.229 (3.337) Prec@1 64.84 (67.58) Prec@5 91.41 (86.72) + train[2018-10-15-21:37:43] Epoch: [085][8600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.776 (3.337) Prec@1 60.16 (67.57) Prec@5 77.34 (86.73) + train[2018-10-15-21:39:29] Epoch: [085][8800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.329 (3.337) Prec@1 71.09 (67.57) Prec@5 86.72 (86.73) + train[2018-10-15-21:41:16] Epoch: [085][9000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.174 (3.338) Prec@1 71.09 (67.55) Prec@5 92.19 (86.72) + train[2018-10-15-21:43:02] Epoch: [085][9200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.263 (3.339) Prec@1 66.41 (67.53) Prec@5 88.28 (86.71) + train[2018-10-15-21:44:48] Epoch: [085][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.277 (3.339) Prec@1 69.53 (67.53) Prec@5 85.94 (86.70) + train[2018-10-15-21:46:34] Epoch: [085][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.282 (3.340) Prec@1 74.22 (67.51) Prec@5 87.50 (86.69) + train[2018-10-15-21:48:22] Epoch: [085][9800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.494 (3.340) Prec@1 68.75 (67.51) Prec@5 85.16 (86.69) + train[2018-10-15-21:50:08] Epoch: [085][10000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.529 (3.341) Prec@1 64.06 (67.50) Prec@5 84.38 (86.69) + train[2018-10-15-21:50:12] Epoch: [085][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 3.363 (3.341) Prec@1 66.67 (67.50) Prec@5 93.33 (86.69) +[2018-10-15-21:50:12] **train** Prec@1 67.50 Prec@5 86.69 Error@1 32.50 Error@5 13.31 Loss:3.341 + test [2018-10-15-21:50:16] Epoch: [085][000/391] Time 4.17 (4.17) Data 4.04 (4.04) Loss 0.725 (0.725) Prec@1 82.81 (82.81) Prec@5 96.09 (96.09) + test [2018-10-15-21:50:45] Epoch: [085][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.477 (1.122) Prec@1 60.94 (73.80) Prec@5 88.28 (92.15) + test [2018-10-15-21:51:09] Epoch: [085][390/391] Time 0.09 (0.15) Data 0.00 (0.02) Loss 2.483 (1.296) Prec@1 33.75 (70.21) Prec@5 73.75 (89.62) +[2018-10-15-21:51:09] **test** Prec@1 70.21 Prec@5 89.62 Error@1 29.79 Error@5 10.38 Loss:1.296 +----> Best Accuracy : Acc@1=70.21, Acc@5=89.62, Error@1=29.79, Error@5=10.38 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-15-21:51:10] [Epoch=086/250] [Need: 243:27:50] LR=0.0073 ~ 0.0073, Batch=128 + train[2018-10-15-21:51:14] Epoch: [086][000/10010] Time 4.30 (4.30) Data 3.68 (3.68) Loss 3.423 (3.423) Prec@1 65.62 (65.62) Prec@5 85.16 (85.16) + train[2018-10-15-21:52:58] Epoch: [086][200/10010] Time 0.54 (0.54) Data 0.00 (0.02) Loss 3.226 (3.306) Prec@1 67.19 (68.23) Prec@5 85.16 (87.04) + train[2018-10-15-21:54:43] Epoch: [086][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.557 (3.301) Prec@1 69.53 (68.37) Prec@5 84.38 (87.11) + train[2018-10-15-21:56:26] Epoch: [086][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.264 (3.308) Prec@1 69.53 (68.22) Prec@5 86.72 (87.01) + train[2018-10-15-21:58:10] Epoch: [086][800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.333 (3.314) Prec@1 65.62 (68.11) Prec@5 90.62 (86.99) + train[2018-10-15-21:59:55] Epoch: [086][1000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.165 (3.319) Prec@1 68.75 (68.01) Prec@5 88.28 (86.89) + train[2018-10-15-22:01:38] Epoch: [086][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.030 (3.313) Prec@1 71.88 (68.11) Prec@5 91.41 (86.98) + train[2018-10-15-22:03:21] Epoch: [086][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.457 (3.311) Prec@1 66.41 (68.11) Prec@5 85.16 (87.02) + train[2018-10-15-22:05:05] Epoch: [086][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.141 (3.312) Prec@1 71.09 (68.14) Prec@5 88.28 (86.98) + train[2018-10-15-22:06:49] Epoch: [086][1800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.586 (3.311) Prec@1 67.19 (68.15) Prec@5 81.25 (87.01) + train[2018-10-15-22:08:34] Epoch: [086][2000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.171 (3.309) Prec@1 71.09 (68.19) Prec@5 85.16 (87.00) + train[2018-10-15-22:10:18] Epoch: [086][2200/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.123 (3.311) Prec@1 66.41 (68.15) Prec@5 88.28 (86.98) + train[2018-10-15-22:12:04] Epoch: [086][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.256 (3.312) Prec@1 66.41 (68.10) Prec@5 89.06 (86.99) + train[2018-10-15-22:13:50] Epoch: [086][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.058 (3.311) Prec@1 72.66 (68.09) Prec@5 89.84 (87.03) + train[2018-10-15-22:15:35] Epoch: [086][2800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.570 (3.311) Prec@1 60.94 (68.08) Prec@5 82.81 (87.03) + train[2018-10-15-22:17:20] Epoch: [086][3000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.299 (3.311) Prec@1 65.62 (68.08) Prec@5 89.06 (87.02) + train[2018-10-15-22:19:05] Epoch: [086][3200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.297 (3.312) Prec@1 70.31 (68.06) Prec@5 84.38 (87.01) + train[2018-10-15-22:20:51] Epoch: [086][3400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.183 (3.312) Prec@1 68.75 (68.05) Prec@5 89.06 (87.01) + train[2018-10-15-22:22:36] Epoch: [086][3600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.286 (3.313) Prec@1 65.62 (68.03) Prec@5 84.38 (87.01) + train[2018-10-15-22:24:21] Epoch: [086][3800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.751 (3.315) Prec@1 63.28 (68.00) Prec@5 81.25 (86.99) + train[2018-10-15-22:26:05] Epoch: [086][4000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.637 (3.317) Prec@1 63.28 (67.96) Prec@5 82.03 (86.97) + train[2018-10-15-22:27:51] Epoch: [086][4200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.516 (3.318) Prec@1 67.97 (67.92) Prec@5 82.03 (86.95) + train[2018-10-15-22:29:36] Epoch: [086][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.379 (3.319) Prec@1 68.75 (67.90) Prec@5 85.16 (86.94) + train[2018-10-15-22:31:23] Epoch: [086][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.284 (3.320) Prec@1 71.88 (67.89) Prec@5 89.06 (86.93) + train[2018-10-15-22:33:09] Epoch: [086][4800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.309 (3.322) Prec@1 69.53 (67.86) Prec@5 87.50 (86.91) + train[2018-10-15-22:34:54] Epoch: [086][5000/10010] Time 0.62 (0.52) Data 0.00 (0.00) Loss 3.302 (3.322) Prec@1 68.75 (67.84) Prec@5 89.06 (86.90) + train[2018-10-15-22:36:41] Epoch: [086][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.266 (3.324) Prec@1 68.75 (67.83) Prec@5 89.06 (86.89) + train[2018-10-15-22:38:28] Epoch: [086][5400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.437 (3.324) Prec@1 67.19 (67.83) Prec@5 86.72 (86.89) + train[2018-10-15-22:40:14] Epoch: [086][5600/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.253 (3.325) Prec@1 71.09 (67.81) Prec@5 85.94 (86.87) + train[2018-10-15-22:42:00] Epoch: [086][5800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.984 (3.326) Prec@1 77.34 (67.79) Prec@5 89.84 (86.86) + train[2018-10-15-22:43:45] Epoch: [086][6000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.285 (3.326) Prec@1 65.62 (67.78) Prec@5 86.72 (86.86) + train[2018-10-15-22:45:31] Epoch: [086][6200/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.340 (3.326) Prec@1 66.41 (67.77) Prec@5 85.16 (86.86) + train[2018-10-15-22:47:17] Epoch: [086][6400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.424 (3.327) Prec@1 64.84 (67.77) Prec@5 87.50 (86.85) + train[2018-10-15-22:49:03] Epoch: [086][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.204 (3.328) Prec@1 71.88 (67.76) Prec@5 88.28 (86.84) + train[2018-10-15-22:50:48] Epoch: [086][6800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.221 (3.327) Prec@1 69.53 (67.76) Prec@5 87.50 (86.84) + train[2018-10-15-22:52:34] Epoch: [086][7000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.771 (3.328) Prec@1 60.16 (67.74) Prec@5 82.81 (86.83) + train[2018-10-15-22:54:19] Epoch: [086][7200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.247 (3.329) Prec@1 73.44 (67.73) Prec@5 85.16 (86.83) + train[2018-10-15-22:56:04] Epoch: [086][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.285 (3.329) Prec@1 68.75 (67.71) Prec@5 85.16 (86.82) + train[2018-10-15-22:57:49] Epoch: [086][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.587 (3.329) Prec@1 66.41 (67.71) Prec@5 82.03 (86.82) + train[2018-10-15-22:59:35] Epoch: [086][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.156 (3.330) Prec@1 71.09 (67.70) Prec@5 90.62 (86.82) + train[2018-10-15-23:01:20] Epoch: [086][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.332 (3.330) Prec@1 71.09 (67.70) Prec@5 88.28 (86.81) + train[2018-10-15-23:03:05] Epoch: [086][8200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.249 (3.331) Prec@1 64.84 (67.68) Prec@5 88.28 (86.81) + train[2018-10-15-23:04:51] Epoch: [086][8400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.216 (3.331) Prec@1 68.75 (67.68) Prec@5 87.50 (86.81) + train[2018-10-15-23:06:37] Epoch: [086][8600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.102 (3.332) Prec@1 71.09 (67.66) Prec@5 89.06 (86.80) + train[2018-10-15-23:08:23] Epoch: [086][8800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.528 (3.332) Prec@1 67.97 (67.65) Prec@5 85.16 (86.79) + train[2018-10-15-23:10:09] Epoch: [086][9000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.281 (3.331) Prec@1 72.66 (67.66) Prec@5 89.06 (86.80) + train[2018-10-15-23:11:55] Epoch: [086][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.329 (3.332) Prec@1 70.31 (67.65) Prec@5 89.84 (86.79) + train[2018-10-15-23:13:41] Epoch: [086][9400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.291 (3.332) Prec@1 66.41 (67.65) Prec@5 91.41 (86.79) + train[2018-10-15-23:15:26] Epoch: [086][9600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.326 (3.332) Prec@1 71.09 (67.65) Prec@5 85.94 (86.79) + train[2018-10-15-23:17:11] Epoch: [086][9800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.569 (3.333) Prec@1 61.72 (67.64) Prec@5 83.59 (86.78) + train[2018-10-15-23:18:57] Epoch: [086][10000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.355 (3.333) Prec@1 61.72 (67.63) Prec@5 91.41 (86.77) + train[2018-10-15-23:19:03] Epoch: [086][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 4.012 (3.333) Prec@1 46.67 (67.63) Prec@5 73.33 (86.77) +[2018-10-15-23:19:03] **train** Prec@1 67.63 Prec@5 86.77 Error@1 32.37 Error@5 13.23 Loss:3.333 + test [2018-10-15-23:19:07] Epoch: [086][000/391] Time 3.93 (3.93) Data 3.80 (3.80) Loss 0.625 (0.625) Prec@1 89.84 (89.84) Prec@5 96.88 (96.88) + test [2018-10-15-23:19:34] Epoch: [086][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.555 (1.143) Prec@1 64.84 (73.94) Prec@5 85.94 (92.07) + test [2018-10-15-23:19:59] Epoch: [086][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.078 (1.315) Prec@1 46.25 (70.31) Prec@5 80.00 (89.60) +[2018-10-15-23:19:59] **test** Prec@1 70.31 Prec@5 89.60 Error@1 29.69 Error@5 10.40 Loss:1.315 +----> Best Accuracy : Acc@1=70.31, Acc@5=89.60, Error@1=29.69, Error@5=10.40 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-15-23:19:59] [Epoch=087/250] [Need: 241:18:21] LR=0.0071 ~ 0.0071, Batch=128 + train[2018-10-15-23:20:04] Epoch: [087][000/10010] Time 5.02 (5.02) Data 4.41 (4.41) Loss 3.695 (3.695) Prec@1 61.72 (61.72) Prec@5 82.81 (82.81) + train[2018-10-15-23:21:48] Epoch: [087][200/10010] Time 0.52 (0.54) Data 0.00 (0.02) Loss 3.302 (3.304) Prec@1 71.09 (68.99) Prec@5 88.28 (87.11) + train[2018-10-15-23:23:32] Epoch: [087][400/10010] Time 0.56 (0.53) Data 0.00 (0.01) Loss 3.456 (3.308) Prec@1 67.19 (68.73) Prec@5 85.94 (87.08) + train[2018-10-15-23:25:15] Epoch: [087][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.334 (3.300) Prec@1 70.31 (68.72) Prec@5 89.06 (87.18) + train[2018-10-15-23:27:00] Epoch: [087][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.220 (3.302) Prec@1 65.62 (68.54) Prec@5 88.28 (87.15) + train[2018-10-15-23:28:43] Epoch: [087][1000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.334 (3.303) Prec@1 68.75 (68.52) Prec@5 85.16 (87.15) + train[2018-10-15-23:30:28] Epoch: [087][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.259 (3.303) Prec@1 68.75 (68.42) Prec@5 84.38 (87.13) + train[2018-10-15-23:32:12] Epoch: [087][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.608 (3.305) Prec@1 62.50 (68.37) Prec@5 81.25 (87.11) + train[2018-10-15-23:33:55] Epoch: [087][1600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.149 (3.310) Prec@1 70.31 (68.26) Prec@5 89.06 (87.06) + train[2018-10-15-23:35:39] Epoch: [087][1800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.325 (3.307) Prec@1 71.09 (68.30) Prec@5 86.72 (87.08) + train[2018-10-15-23:37:23] Epoch: [087][2000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.197 (3.306) Prec@1 65.62 (68.32) Prec@5 89.84 (87.09) + train[2018-10-15-23:39:07] Epoch: [087][2200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.364 (3.306) Prec@1 66.41 (68.33) Prec@5 86.72 (87.08) + train[2018-10-15-23:40:51] Epoch: [087][2400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.587 (3.306) Prec@1 64.06 (68.33) Prec@5 81.25 (87.06) + train[2018-10-15-23:42:36] Epoch: [087][2600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.519 (3.307) Prec@1 61.72 (68.34) Prec@5 82.81 (87.04) + train[2018-10-15-23:44:20] Epoch: [087][2800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.023 (3.307) Prec@1 75.78 (68.33) Prec@5 91.41 (87.04) + train[2018-10-15-23:46:05] Epoch: [087][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.596 (3.308) Prec@1 63.28 (68.32) Prec@5 84.38 (87.03) + train[2018-10-15-23:47:51] Epoch: [087][3200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.289 (3.308) Prec@1 72.66 (68.29) Prec@5 87.50 (87.02) + train[2018-10-15-23:49:36] Epoch: [087][3400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.584 (3.309) Prec@1 61.72 (68.28) Prec@5 86.72 (87.02) + train[2018-10-15-23:51:22] Epoch: [087][3600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.743 (3.310) Prec@1 60.16 (68.26) Prec@5 78.91 (87.00) + train[2018-10-15-23:53:07] Epoch: [087][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.380 (3.310) Prec@1 66.41 (68.24) Prec@5 85.16 (87.00) + train[2018-10-15-23:54:53] Epoch: [087][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.219 (3.310) Prec@1 70.31 (68.20) Prec@5 89.84 (86.99) + train[2018-10-15-23:56:38] Epoch: [087][4200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.618 (3.312) Prec@1 59.38 (68.17) Prec@5 83.59 (86.97) + train[2018-10-15-23:58:24] Epoch: [087][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.353 (3.313) Prec@1 70.31 (68.16) Prec@5 85.16 (86.98) + train[2018-10-16-00:00:10] Epoch: [087][4600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.400 (3.313) Prec@1 66.41 (68.15) Prec@5 85.16 (86.98) + train[2018-10-16-00:01:55] Epoch: [087][4800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.271 (3.314) Prec@1 67.19 (68.13) Prec@5 88.28 (86.98) + train[2018-10-16-00:03:39] Epoch: [087][5000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.221 (3.315) Prec@1 69.53 (68.10) Prec@5 89.06 (86.96) + train[2018-10-16-00:05:25] Epoch: [087][5200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.286 (3.316) Prec@1 67.19 (68.08) Prec@5 83.59 (86.96) + train[2018-10-16-00:07:11] Epoch: [087][5400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.202 (3.316) Prec@1 72.66 (68.05) Prec@5 88.28 (86.95) + train[2018-10-16-00:08:56] Epoch: [087][5600/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.313 (3.316) Prec@1 69.53 (68.05) Prec@5 85.16 (86.95) + train[2018-10-16-00:10:41] Epoch: [087][5800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.165 (3.317) Prec@1 71.88 (68.05) Prec@5 88.28 (86.94) + train[2018-10-16-00:12:25] Epoch: [087][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.158 (3.318) Prec@1 67.97 (68.03) Prec@5 89.84 (86.92) + train[2018-10-16-00:14:09] Epoch: [087][6200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.403 (3.319) Prec@1 63.28 (68.00) Prec@5 86.72 (86.92) + train[2018-10-16-00:15:54] Epoch: [087][6400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.321 (3.320) Prec@1 67.19 (67.99) Prec@5 87.50 (86.91) + train[2018-10-16-00:17:37] Epoch: [087][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.338 (3.320) Prec@1 58.59 (68.00) Prec@5 90.62 (86.92) + train[2018-10-16-00:19:21] Epoch: [087][6800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.978 (3.320) Prec@1 58.59 (67.99) Prec@5 80.47 (86.91) + train[2018-10-16-00:21:06] Epoch: [087][7000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.368 (3.321) Prec@1 62.50 (67.97) Prec@5 86.72 (86.90) + train[2018-10-16-00:22:51] Epoch: [087][7200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.314 (3.321) Prec@1 65.62 (67.96) Prec@5 84.38 (86.90) + train[2018-10-16-00:24:35] Epoch: [087][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.030 (3.321) Prec@1 76.56 (67.97) Prec@5 87.50 (86.89) + train[2018-10-16-00:26:19] Epoch: [087][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.234 (3.322) Prec@1 66.41 (67.95) Prec@5 88.28 (86.88) + train[2018-10-16-00:28:04] Epoch: [087][7800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.301 (3.322) Prec@1 67.19 (67.94) Prec@5 85.94 (86.88) + train[2018-10-16-00:29:50] Epoch: [087][8000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.120 (3.322) Prec@1 71.09 (67.94) Prec@5 89.84 (86.88) + train[2018-10-16-00:31:35] Epoch: [087][8200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.665 (3.322) Prec@1 66.41 (67.94) Prec@5 82.81 (86.88) + train[2018-10-16-00:33:20] Epoch: [087][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.506 (3.323) Prec@1 60.16 (67.92) Prec@5 86.72 (86.88) + train[2018-10-16-00:35:05] Epoch: [087][8600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.408 (3.322) Prec@1 65.62 (67.92) Prec@5 88.28 (86.88) + train[2018-10-16-00:36:51] Epoch: [087][8800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.512 (3.322) Prec@1 65.62 (67.91) Prec@5 85.16 (86.88) + train[2018-10-16-00:38:38] Epoch: [087][9000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.423 (3.323) Prec@1 61.72 (67.91) Prec@5 85.94 (86.87) + train[2018-10-16-00:40:23] Epoch: [087][9200/10010] Time 0.60 (0.52) Data 0.00 (0.00) Loss 3.379 (3.323) Prec@1 60.16 (67.90) Prec@5 86.72 (86.86) + train[2018-10-16-00:42:08] Epoch: [087][9400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.663 (3.324) Prec@1 61.72 (67.89) Prec@5 85.16 (86.86) + train[2018-10-16-00:43:53] Epoch: [087][9600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.613 (3.324) Prec@1 60.16 (67.88) Prec@5 85.94 (86.86) + train[2018-10-16-00:45:39] Epoch: [087][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.985 (3.324) Prec@1 73.44 (67.88) Prec@5 89.06 (86.86) + train[2018-10-16-00:47:24] Epoch: [087][10000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.639 (3.325) Prec@1 61.72 (67.86) Prec@5 82.81 (86.85) + train[2018-10-16-00:47:28] Epoch: [087][10009/10010] Time 0.14 (0.52) Data 0.00 (0.00) Loss 3.602 (3.325) Prec@1 60.00 (67.86) Prec@5 86.67 (86.85) +[2018-10-16-00:47:29] **train** Prec@1 67.86 Prec@5 86.85 Error@1 32.14 Error@5 13.15 Loss:3.325 + test [2018-10-16-00:47:33] Epoch: [087][000/391] Time 4.06 (4.06) Data 3.92 (3.92) Loss 0.789 (0.789) Prec@1 85.16 (85.16) Prec@5 95.31 (95.31) + test [2018-10-16-00:47:59] Epoch: [087][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.388 (1.123) Prec@1 68.75 (73.82) Prec@5 90.62 (92.26) + test [2018-10-16-00:48:24] Epoch: [087][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.290 (1.298) Prec@1 41.25 (70.23) Prec@5 80.00 (89.74) +[2018-10-16-00:48:24] **test** Prec@1 70.23 Prec@5 89.74 Error@1 29.77 Error@5 10.26 Loss:1.298 +----> Best Accuracy : Acc@1=70.31, Acc@5=89.60, Error@1=29.69, Error@5=10.40 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-16-00:48:24] [Epoch=088/250] [Need: 238:44:16] LR=0.0069 ~ 0.0069, Batch=128 + train[2018-10-16-00:48:29] Epoch: [088][000/10010] Time 4.72 (4.72) Data 4.12 (4.12) Loss 3.337 (3.337) Prec@1 67.19 (67.19) Prec@5 85.16 (85.16) + train[2018-10-16-00:50:13] Epoch: [088][200/10010] Time 0.58 (0.54) Data 0.00 (0.02) Loss 3.348 (3.292) Prec@1 65.62 (68.40) Prec@5 88.28 (87.46) + train[2018-10-16-00:51:57] Epoch: [088][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.279 (3.287) Prec@1 75.78 (68.60) Prec@5 85.16 (87.50) + train[2018-10-16-00:53:41] Epoch: [088][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.075 (3.289) Prec@1 69.53 (68.57) Prec@5 90.62 (87.40) + train[2018-10-16-00:55:24] Epoch: [088][800/10010] Time 0.54 (0.52) Data 0.00 (0.01) Loss 2.950 (3.284) Prec@1 71.09 (68.71) Prec@5 93.75 (87.46) + train[2018-10-16-00:57:08] Epoch: [088][1000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.875 (3.288) Prec@1 75.78 (68.57) Prec@5 94.53 (87.44) + train[2018-10-16-00:58:52] Epoch: [088][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.276 (3.288) Prec@1 66.41 (68.56) Prec@5 87.50 (87.38) + train[2018-10-16-01:00:37] Epoch: [088][1400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.589 (3.289) Prec@1 62.50 (68.56) Prec@5 80.47 (87.35) + train[2018-10-16-01:02:21] Epoch: [088][1600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.147 (3.290) Prec@1 70.31 (68.56) Prec@5 90.62 (87.33) + train[2018-10-16-01:04:05] Epoch: [088][1800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.284 (3.296) Prec@1 72.66 (68.43) Prec@5 85.94 (87.25) + train[2018-10-16-01:05:49] Epoch: [088][2000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.236 (3.294) Prec@1 72.66 (68.47) Prec@5 89.06 (87.26) + train[2018-10-16-01:07:33] Epoch: [088][2200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 2.936 (3.296) Prec@1 76.56 (68.44) Prec@5 89.84 (87.25) + train[2018-10-16-01:09:17] Epoch: [088][2400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.372 (3.297) Prec@1 68.75 (68.43) Prec@5 85.16 (87.23) + train[2018-10-16-01:11:02] Epoch: [088][2600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.994 (3.296) Prec@1 73.44 (68.44) Prec@5 86.72 (87.22) + train[2018-10-16-01:12:47] Epoch: [088][2800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.612 (3.297) Prec@1 60.94 (68.41) Prec@5 83.59 (87.20) + train[2018-10-16-01:14:33] Epoch: [088][3000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.093 (3.297) Prec@1 69.53 (68.39) Prec@5 90.62 (87.21) + train[2018-10-16-01:16:17] Epoch: [088][3200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.358 (3.297) Prec@1 66.41 (68.38) Prec@5 88.28 (87.21) + train[2018-10-16-01:18:01] Epoch: [088][3400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.379 (3.297) Prec@1 67.97 (68.37) Prec@5 85.94 (87.21) + train[2018-10-16-01:19:46] Epoch: [088][3600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.422 (3.300) Prec@1 64.84 (68.33) Prec@5 87.50 (87.17) + train[2018-10-16-01:21:32] Epoch: [088][3800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.260 (3.301) Prec@1 68.75 (68.30) Prec@5 86.72 (87.16) + train[2018-10-16-01:23:17] Epoch: [088][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.466 (3.301) Prec@1 67.97 (68.28) Prec@5 86.72 (87.15) + train[2018-10-16-01:25:03] Epoch: [088][4200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.147 (3.300) Prec@1 70.31 (68.30) Prec@5 88.28 (87.17) + train[2018-10-16-01:26:48] Epoch: [088][4400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.048 (3.300) Prec@1 70.31 (68.28) Prec@5 89.06 (87.17) + train[2018-10-16-01:28:33] Epoch: [088][4600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.992 (3.301) Prec@1 71.09 (68.25) Prec@5 89.84 (87.15) + train[2018-10-16-01:30:18] Epoch: [088][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.257 (3.302) Prec@1 68.75 (68.24) Prec@5 91.41 (87.15) + train[2018-10-16-01:32:03] Epoch: [088][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.078 (3.302) Prec@1 72.66 (68.24) Prec@5 92.19 (87.14) + train[2018-10-16-01:33:48] Epoch: [088][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.707 (3.303) Prec@1 59.38 (68.24) Prec@5 82.81 (87.14) + train[2018-10-16-01:35:34] Epoch: [088][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.325 (3.304) Prec@1 69.53 (68.21) Prec@5 85.16 (87.12) + train[2018-10-16-01:37:20] Epoch: [088][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.454 (3.304) Prec@1 63.28 (68.21) Prec@5 85.94 (87.12) + train[2018-10-16-01:39:06] Epoch: [088][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.374 (3.304) Prec@1 66.41 (68.20) Prec@5 85.94 (87.11) + train[2018-10-16-01:40:53] Epoch: [088][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.960 (3.305) Prec@1 55.47 (68.19) Prec@5 83.59 (87.11) + train[2018-10-16-01:42:39] Epoch: [088][6200/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.297 (3.305) Prec@1 71.88 (68.19) Prec@5 86.72 (87.10) + train[2018-10-16-01:44:24] Epoch: [088][6400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.529 (3.306) Prec@1 64.84 (68.17) Prec@5 84.38 (87.08) + train[2018-10-16-01:46:11] Epoch: [088][6600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.349 (3.307) Prec@1 67.97 (68.15) Prec@5 85.16 (87.06) + train[2018-10-16-01:47:57] Epoch: [088][6800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.180 (3.307) Prec@1 69.53 (68.15) Prec@5 90.62 (87.07) + train[2018-10-16-01:49:43] Epoch: [088][7000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.087 (3.308) Prec@1 67.19 (68.14) Prec@5 92.19 (87.05) + train[2018-10-16-01:51:28] Epoch: [088][7200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.412 (3.308) Prec@1 62.50 (68.13) Prec@5 86.72 (87.05) + train[2018-10-16-01:53:14] Epoch: [088][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.345 (3.308) Prec@1 69.53 (68.12) Prec@5 85.16 (87.04) + train[2018-10-16-01:55:00] Epoch: [088][7600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.125 (3.309) Prec@1 71.09 (68.11) Prec@5 89.84 (87.03) + train[2018-10-16-01:56:45] Epoch: [088][7800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.537 (3.310) Prec@1 65.62 (68.08) Prec@5 84.38 (87.02) + train[2018-10-16-01:58:30] Epoch: [088][8000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.359 (3.310) Prec@1 65.62 (68.08) Prec@5 88.28 (87.01) + train[2018-10-16-02:00:15] Epoch: [088][8200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.444 (3.311) Prec@1 67.19 (68.07) Prec@5 85.94 (87.00) + train[2018-10-16-02:02:00] Epoch: [088][8400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.451 (3.312) Prec@1 67.19 (68.05) Prec@5 85.94 (86.99) + train[2018-10-16-02:03:44] Epoch: [088][8600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.316 (3.313) Prec@1 70.31 (68.03) Prec@5 86.72 (86.98) + train[2018-10-16-02:05:29] Epoch: [088][8800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.611 (3.313) Prec@1 64.84 (68.03) Prec@5 82.03 (86.98) + train[2018-10-16-02:07:14] Epoch: [088][9000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.455 (3.314) Prec@1 66.41 (68.02) Prec@5 85.16 (86.96) + train[2018-10-16-02:08:59] Epoch: [088][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.180 (3.314) Prec@1 71.88 (68.01) Prec@5 87.50 (86.97) + train[2018-10-16-02:10:43] Epoch: [088][9400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.430 (3.314) Prec@1 66.41 (68.01) Prec@5 85.94 (86.96) + train[2018-10-16-02:12:29] Epoch: [088][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.700 (3.315) Prec@1 65.62 (68.00) Prec@5 84.38 (86.95) + train[2018-10-16-02:14:14] Epoch: [088][9800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.297 (3.316) Prec@1 67.97 (67.99) Prec@5 89.84 (86.95) + train[2018-10-16-02:16:00] Epoch: [088][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.356 (3.316) Prec@1 68.75 (67.97) Prec@5 86.72 (86.95) + train[2018-10-16-02:16:04] Epoch: [088][10009/10010] Time 0.21 (0.53) Data 0.00 (0.00) Loss 5.834 (3.316) Prec@1 33.33 (67.97) Prec@5 46.67 (86.94) +[2018-10-16-02:16:04] **train** Prec@1 67.97 Prec@5 86.94 Error@1 32.03 Error@5 13.06 Loss:3.316 + test [2018-10-16-02:16:08] Epoch: [088][000/391] Time 3.97 (3.97) Data 3.83 (3.83) Loss 0.670 (0.670) Prec@1 85.94 (85.94) Prec@5 97.66 (97.66) + test [2018-10-16-02:16:34] Epoch: [088][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.278 (1.100) Prec@1 66.41 (74.20) Prec@5 92.19 (92.45) + test [2018-10-16-02:17:00] Epoch: [088][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.392 (1.275) Prec@1 45.00 (70.73) Prec@5 80.00 (89.94) +[2018-10-16-02:17:00] **test** Prec@1 70.73 Prec@5 89.94 Error@1 29.27 Error@5 10.06 Loss:1.275 +----> Best Accuracy : Acc@1=70.73, Acc@5=89.94, Error@1=29.27, Error@5=10.06 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-16-02:17:00] [Epoch=089/250] [Need: 237:43:49] LR=0.0066 ~ 0.0066, Batch=128 + train[2018-10-16-02:17:04] Epoch: [089][000/10010] Time 4.30 (4.30) Data 3.64 (3.64) Loss 3.364 (3.364) Prec@1 65.62 (65.62) Prec@5 87.50 (87.50) + train[2018-10-16-02:18:50] Epoch: [089][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.355 (3.285) Prec@1 67.97 (68.86) Prec@5 86.72 (87.52) + train[2018-10-16-02:20:34] Epoch: [089][400/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 2.952 (3.275) Prec@1 65.62 (68.85) Prec@5 92.97 (87.57) + train[2018-10-16-02:22:19] Epoch: [089][600/10010] Time 0.58 (0.53) Data 0.00 (0.01) Loss 3.248 (3.275) Prec@1 69.53 (68.95) Prec@5 91.41 (87.53) + train[2018-10-16-02:24:03] Epoch: [089][800/10010] Time 0.58 (0.53) Data 0.00 (0.01) Loss 3.249 (3.274) Prec@1 73.44 (68.95) Prec@5 88.28 (87.55) + train[2018-10-16-02:25:47] Epoch: [089][1000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.287 (3.272) Prec@1 68.75 (68.94) Prec@5 89.84 (87.54) + train[2018-10-16-02:27:31] Epoch: [089][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.634 (3.272) Prec@1 60.16 (68.92) Prec@5 82.03 (87.55) + train[2018-10-16-02:29:15] Epoch: [089][1400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.356 (3.275) Prec@1 69.53 (68.85) Prec@5 84.38 (87.54) + train[2018-10-16-02:31:00] Epoch: [089][1600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.443 (3.278) Prec@1 63.28 (68.81) Prec@5 85.16 (87.51) + train[2018-10-16-02:32:44] Epoch: [089][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.004 (3.280) Prec@1 75.00 (68.74) Prec@5 88.28 (87.48) + train[2018-10-16-02:34:28] Epoch: [089][2000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.035 (3.283) Prec@1 78.91 (68.65) Prec@5 88.28 (87.44) + train[2018-10-16-02:36:12] Epoch: [089][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.666 (3.284) Prec@1 65.62 (68.62) Prec@5 82.81 (87.41) + train[2018-10-16-02:37:58] Epoch: [089][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.326 (3.287) Prec@1 66.41 (68.55) Prec@5 85.94 (87.37) + train[2018-10-16-02:39:44] Epoch: [089][2600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.609 (3.289) Prec@1 67.19 (68.51) Prec@5 80.47 (87.33) + train[2018-10-16-02:41:29] Epoch: [089][2800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.008 (3.291) Prec@1 75.00 (68.47) Prec@5 92.19 (87.31) + train[2018-10-16-02:43:16] Epoch: [089][3000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.474 (3.292) Prec@1 68.75 (68.46) Prec@5 82.81 (87.29) + train[2018-10-16-02:45:03] Epoch: [089][3200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.289 (3.293) Prec@1 67.19 (68.42) Prec@5 87.50 (87.26) + train[2018-10-16-02:46:49] Epoch: [089][3400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.185 (3.294) Prec@1 69.53 (68.41) Prec@5 89.06 (87.26) + train[2018-10-16-02:48:35] Epoch: [089][3600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.367 (3.294) Prec@1 67.97 (68.40) Prec@5 85.16 (87.25) + train[2018-10-16-02:50:21] Epoch: [089][3800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.154 (3.295) Prec@1 68.75 (68.38) Prec@5 86.72 (87.22) + train[2018-10-16-02:52:07] Epoch: [089][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.684 (3.295) Prec@1 61.72 (68.37) Prec@5 78.91 (87.21) + train[2018-10-16-02:53:54] Epoch: [089][4200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.491 (3.296) Prec@1 67.19 (68.38) Prec@5 83.59 (87.20) + train[2018-10-16-02:55:41] Epoch: [089][4400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.398 (3.295) Prec@1 71.09 (68.39) Prec@5 85.16 (87.21) + train[2018-10-16-02:57:27] Epoch: [089][4600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.464 (3.296) Prec@1 66.41 (68.37) Prec@5 87.50 (87.20) + train[2018-10-16-02:59:13] Epoch: [089][4800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.338 (3.297) Prec@1 67.19 (68.36) Prec@5 87.50 (87.19) + train[2018-10-16-03:00:59] Epoch: [089][5000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.063 (3.298) Prec@1 72.66 (68.36) Prec@5 87.50 (87.18) + train[2018-10-16-03:02:44] Epoch: [089][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.349 (3.298) Prec@1 62.50 (68.36) Prec@5 85.94 (87.18) + train[2018-10-16-03:04:29] Epoch: [089][5400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.240 (3.298) Prec@1 69.53 (68.36) Prec@5 85.16 (87.18) + train[2018-10-16-03:06:15] Epoch: [089][5600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.393 (3.298) Prec@1 65.62 (68.35) Prec@5 87.50 (87.18) + train[2018-10-16-03:08:02] Epoch: [089][5800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.202 (3.299) Prec@1 67.19 (68.33) Prec@5 89.06 (87.17) + train[2018-10-16-03:09:49] Epoch: [089][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.979 (3.299) Prec@1 75.00 (68.33) Prec@5 90.62 (87.17) + train[2018-10-16-03:11:35] Epoch: [089][6200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.147 (3.299) Prec@1 70.31 (68.33) Prec@5 87.50 (87.16) + train[2018-10-16-03:13:22] Epoch: [089][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.599 (3.300) Prec@1 64.84 (68.32) Prec@5 81.25 (87.16) + train[2018-10-16-03:15:09] Epoch: [089][6600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.360 (3.300) Prec@1 64.84 (68.31) Prec@5 85.16 (87.15) + train[2018-10-16-03:16:55] Epoch: [089][6800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.324 (3.301) Prec@1 64.84 (68.29) Prec@5 85.94 (87.14) + train[2018-10-16-03:18:42] Epoch: [089][7000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.316 (3.302) Prec@1 68.75 (68.28) Prec@5 83.59 (87.12) + train[2018-10-16-03:20:28] Epoch: [089][7200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.285 (3.303) Prec@1 71.09 (68.27) Prec@5 85.94 (87.11) + train[2018-10-16-03:22:13] Epoch: [089][7400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.306 (3.303) Prec@1 67.19 (68.26) Prec@5 88.28 (87.11) + train[2018-10-16-03:24:00] Epoch: [089][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.503 (3.304) Prec@1 65.62 (68.25) Prec@5 86.72 (87.11) + train[2018-10-16-03:25:46] Epoch: [089][7800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.463 (3.305) Prec@1 67.97 (68.23) Prec@5 85.94 (87.09) + train[2018-10-16-03:27:32] Epoch: [089][8000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.518 (3.305) Prec@1 64.06 (68.22) Prec@5 84.38 (87.09) + train[2018-10-16-03:29:17] Epoch: [089][8200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.330 (3.306) Prec@1 66.41 (68.21) Prec@5 87.50 (87.08) + train[2018-10-16-03:31:03] Epoch: [089][8400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.314 (3.306) Prec@1 66.41 (68.21) Prec@5 85.94 (87.08) + train[2018-10-16-03:32:48] Epoch: [089][8600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.631 (3.306) Prec@1 64.84 (68.20) Prec@5 84.38 (87.07) + train[2018-10-16-03:34:35] Epoch: [089][8800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.312 (3.306) Prec@1 67.97 (68.21) Prec@5 89.06 (87.07) + train[2018-10-16-03:36:21] Epoch: [089][9000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.349 (3.307) Prec@1 67.97 (68.21) Prec@5 83.59 (87.07) + train[2018-10-16-03:38:07] Epoch: [089][9200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.278 (3.307) Prec@1 71.88 (68.20) Prec@5 87.50 (87.06) + train[2018-10-16-03:39:52] Epoch: [089][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.517 (3.308) Prec@1 60.94 (68.19) Prec@5 84.38 (87.05) + train[2018-10-16-03:41:38] Epoch: [089][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.842 (3.308) Prec@1 59.38 (68.18) Prec@5 78.91 (87.04) + train[2018-10-16-03:43:24] Epoch: [089][9800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.603 (3.309) Prec@1 61.72 (68.17) Prec@5 83.59 (87.04) + train[2018-10-16-03:45:10] Epoch: [089][10000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.483 (3.309) Prec@1 67.19 (68.17) Prec@5 83.59 (87.04) + train[2018-10-16-03:45:14] Epoch: [089][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.707 (3.309) Prec@1 40.00 (68.17) Prec@5 86.67 (87.04) +[2018-10-16-03:45:14] **train** Prec@1 68.17 Prec@5 87.04 Error@1 31.83 Error@5 12.96 Loss:3.309 + test [2018-10-16-03:45:18] Epoch: [089][000/391] Time 4.11 (4.11) Data 3.98 (3.98) Loss 0.684 (0.684) Prec@1 85.94 (85.94) Prec@5 96.88 (96.88) + test [2018-10-16-03:45:44] Epoch: [089][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.333 (1.119) Prec@1 67.19 (74.18) Prec@5 89.84 (92.17) + test [2018-10-16-03:46:09] Epoch: [089][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.215 (1.289) Prec@1 45.00 (70.45) Prec@5 83.75 (89.90) +[2018-10-16-03:46:09] **test** Prec@1 70.45 Prec@5 89.90 Error@1 29.55 Error@5 10.10 Loss:1.289 +----> Best Accuracy : Acc@1=70.73, Acc@5=89.94, Error@1=29.27, Error@5=10.06 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-16-03:46:09] [Epoch=090/250] [Need: 237:44:17] LR=0.0064 ~ 0.0064, Batch=128 + train[2018-10-16-03:46:14] Epoch: [090][000/10010] Time 4.98 (4.98) Data 4.41 (4.41) Loss 3.556 (3.556) Prec@1 65.62 (65.62) Prec@5 85.16 (85.16) + train[2018-10-16-03:47:59] Epoch: [090][200/10010] Time 0.55 (0.55) Data 0.00 (0.02) Loss 3.159 (3.256) Prec@1 69.53 (69.12) Prec@5 92.19 (87.92) + train[2018-10-16-03:49:43] Epoch: [090][400/10010] Time 0.56 (0.53) Data 0.00 (0.01) Loss 3.434 (3.272) Prec@1 67.19 (68.80) Prec@5 83.59 (87.58) + train[2018-10-16-03:51:27] Epoch: [090][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.555 (3.269) Prec@1 61.72 (68.89) Prec@5 84.38 (87.50) + train[2018-10-16-03:53:10] Epoch: [090][800/10010] Time 0.57 (0.53) Data 0.00 (0.01) Loss 3.449 (3.271) Prec@1 67.19 (68.78) Prec@5 83.59 (87.45) + train[2018-10-16-03:54:54] Epoch: [090][1000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.336 (3.276) Prec@1 70.31 (68.68) Prec@5 85.94 (87.41) + train[2018-10-16-03:56:38] Epoch: [090][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.033 (3.275) Prec@1 70.31 (68.74) Prec@5 89.84 (87.44) + train[2018-10-16-03:58:22] Epoch: [090][1400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.179 (3.277) Prec@1 71.88 (68.72) Prec@5 88.28 (87.41) + train[2018-10-16-04:00:06] Epoch: [090][1600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.515 (3.276) Prec@1 64.84 (68.72) Prec@5 82.03 (87.41) + train[2018-10-16-04:01:50] Epoch: [090][1800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.893 (3.275) Prec@1 75.78 (68.73) Prec@5 92.19 (87.43) + train[2018-10-16-04:03:34] Epoch: [090][2000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.534 (3.277) Prec@1 58.59 (68.67) Prec@5 84.38 (87.43) + train[2018-10-16-04:05:18] Epoch: [090][2200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.143 (3.278) Prec@1 73.44 (68.62) Prec@5 89.06 (87.40) + train[2018-10-16-04:07:02] Epoch: [090][2400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.227 (3.279) Prec@1 71.09 (68.63) Prec@5 88.28 (87.38) + train[2018-10-16-04:08:46] Epoch: [090][2600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.695 (3.280) Prec@1 60.16 (68.62) Prec@5 83.59 (87.36) + train[2018-10-16-04:10:30] Epoch: [090][2800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.439 (3.282) Prec@1 67.97 (68.60) Prec@5 80.47 (87.35) + train[2018-10-16-04:12:14] Epoch: [090][3000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.392 (3.282) Prec@1 67.19 (68.61) Prec@5 85.94 (87.36) + train[2018-10-16-04:13:59] Epoch: [090][3200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.246 (3.282) Prec@1 69.53 (68.61) Prec@5 88.28 (87.35) + train[2018-10-16-04:15:43] Epoch: [090][3400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.063 (3.282) Prec@1 71.88 (68.60) Prec@5 89.06 (87.36) + train[2018-10-16-04:17:27] Epoch: [090][3600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.388 (3.284) Prec@1 64.84 (68.56) Prec@5 89.84 (87.34) + train[2018-10-16-04:19:11] Epoch: [090][3800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.170 (3.286) Prec@1 66.41 (68.52) Prec@5 90.62 (87.31) + train[2018-10-16-04:20:55] Epoch: [090][4000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.336 (3.287) Prec@1 67.19 (68.50) Prec@5 82.81 (87.28) + train[2018-10-16-04:22:39] Epoch: [090][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.003 (3.290) Prec@1 70.31 (68.47) Prec@5 93.75 (87.25) + train[2018-10-16-04:24:23] Epoch: [090][4400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.317 (3.291) Prec@1 64.84 (68.45) Prec@5 88.28 (87.24) + train[2018-10-16-04:26:07] Epoch: [090][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.423 (3.291) Prec@1 61.72 (68.44) Prec@5 85.94 (87.24) + train[2018-10-16-04:27:51] Epoch: [090][4800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.004 (3.291) Prec@1 75.00 (68.43) Prec@5 90.62 (87.24) + train[2018-10-16-04:29:35] Epoch: [090][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.151 (3.291) Prec@1 72.66 (68.44) Prec@5 88.28 (87.24) + train[2018-10-16-04:31:18] Epoch: [090][5200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.386 (3.292) Prec@1 66.41 (68.43) Prec@5 83.59 (87.22) + train[2018-10-16-04:33:02] Epoch: [090][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.422 (3.292) Prec@1 67.19 (68.44) Prec@5 86.72 (87.23) + train[2018-10-16-04:34:46] Epoch: [090][5600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.299 (3.292) Prec@1 71.88 (68.44) Prec@5 85.16 (87.22) + train[2018-10-16-04:36:30] Epoch: [090][5800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.181 (3.292) Prec@1 72.66 (68.42) Prec@5 89.06 (87.23) + train[2018-10-16-04:38:15] Epoch: [090][6000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.277 (3.292) Prec@1 68.75 (68.43) Prec@5 88.28 (87.24) + train[2018-10-16-04:39:59] Epoch: [090][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.081 (3.292) Prec@1 71.88 (68.42) Prec@5 90.62 (87.23) + train[2018-10-16-04:41:43] Epoch: [090][6400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.138 (3.293) Prec@1 71.88 (68.40) Prec@5 87.50 (87.21) + train[2018-10-16-04:43:28] Epoch: [090][6600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.078 (3.293) Prec@1 76.56 (68.40) Prec@5 88.28 (87.21) + train[2018-10-16-04:45:14] Epoch: [090][6800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.190 (3.293) Prec@1 67.97 (68.38) Prec@5 88.28 (87.21) + train[2018-10-16-04:46:59] Epoch: [090][7000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.337 (3.295) Prec@1 69.53 (68.37) Prec@5 83.59 (87.20) + train[2018-10-16-04:48:45] Epoch: [090][7200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.141 (3.295) Prec@1 73.44 (68.37) Prec@5 89.84 (87.19) + train[2018-10-16-04:50:29] Epoch: [090][7400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.457 (3.295) Prec@1 64.84 (68.37) Prec@5 86.72 (87.19) + train[2018-10-16-04:52:13] Epoch: [090][7600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.714 (3.297) Prec@1 63.28 (68.34) Prec@5 82.81 (87.17) + train[2018-10-16-04:53:57] Epoch: [090][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.157 (3.297) Prec@1 73.44 (68.34) Prec@5 90.62 (87.17) + train[2018-10-16-04:55:41] Epoch: [090][8000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.297 (3.297) Prec@1 68.75 (68.33) Prec@5 88.28 (87.17) + train[2018-10-16-04:57:25] Epoch: [090][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.928 (3.297) Prec@1 72.66 (68.32) Prec@5 89.06 (87.17) + train[2018-10-16-04:59:10] Epoch: [090][8400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.140 (3.297) Prec@1 75.78 (68.31) Prec@5 89.06 (87.17) + train[2018-10-16-05:00:53] Epoch: [090][8600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.152 (3.298) Prec@1 72.66 (68.30) Prec@5 87.50 (87.16) + train[2018-10-16-05:02:37] Epoch: [090][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.456 (3.298) Prec@1 66.41 (68.29) Prec@5 86.72 (87.15) + train[2018-10-16-05:04:21] Epoch: [090][9000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.460 (3.299) Prec@1 61.72 (68.27) Prec@5 84.38 (87.13) + train[2018-10-16-05:06:06] Epoch: [090][9200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.628 (3.299) Prec@1 62.50 (68.27) Prec@5 84.38 (87.13) + train[2018-10-16-05:07:50] Epoch: [090][9400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.638 (3.300) Prec@1 59.38 (68.25) Prec@5 85.94 (87.13) + train[2018-10-16-05:09:34] Epoch: [090][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.843 (3.301) Prec@1 60.16 (68.24) Prec@5 75.00 (87.12) + train[2018-10-16-05:11:17] Epoch: [090][9800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.465 (3.301) Prec@1 64.06 (68.24) Prec@5 82.03 (87.12) + train[2018-10-16-05:13:01] Epoch: [090][10000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.370 (3.301) Prec@1 67.19 (68.24) Prec@5 87.50 (87.11) + train[2018-10-16-05:13:05] Epoch: [090][10009/10010] Time 0.17 (0.52) Data 0.00 (0.00) Loss 3.132 (3.301) Prec@1 66.67 (68.24) Prec@5 93.33 (87.11) +[2018-10-16-05:13:05] **train** Prec@1 68.24 Prec@5 87.11 Error@1 31.76 Error@5 12.89 Loss:3.301 + test [2018-10-16-05:13:09] Epoch: [090][000/391] Time 3.58 (3.58) Data 3.45 (3.45) Loss 0.612 (0.612) Prec@1 87.50 (87.50) Prec@5 97.66 (97.66) + test [2018-10-16-05:13:35] Epoch: [090][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.321 (1.109) Prec@1 64.84 (74.13) Prec@5 89.84 (92.45) + test [2018-10-16-05:13:59] Epoch: [090][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.476 (1.276) Prec@1 35.00 (70.58) Prec@5 76.25 (89.98) +[2018-10-16-05:13:59] **test** Prec@1 70.58 Prec@5 89.98 Error@1 29.42 Error@5 10.02 Loss:1.276 +----> Best Accuracy : Acc@1=70.73, Acc@5=89.94, Error@1=29.27, Error@5=10.06 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-16-05:14:00] [Epoch=091/250] [Need: 232:46:41] LR=0.0063 ~ 0.0063, Batch=128 + train[2018-10-16-05:14:04] Epoch: [091][000/10010] Time 4.93 (4.93) Data 4.27 (4.27) Loss 2.877 (2.877) Prec@1 75.00 (75.00) Prec@5 92.97 (92.97) + train[2018-10-16-05:15:48] Epoch: [091][200/10010] Time 0.56 (0.54) Data 0.00 (0.02) Loss 3.351 (3.291) Prec@1 71.09 (68.45) Prec@5 85.16 (87.25) + train[2018-10-16-05:17:32] Epoch: [091][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.256 (3.290) Prec@1 69.53 (68.34) Prec@5 85.94 (87.29) + train[2018-10-16-05:19:16] Epoch: [091][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.295 (3.280) Prec@1 67.97 (68.53) Prec@5 86.72 (87.42) + train[2018-10-16-05:20:59] Epoch: [091][800/10010] Time 0.50 (0.52) Data 0.00 (0.01) Loss 3.379 (3.276) Prec@1 59.38 (68.62) Prec@5 89.84 (87.47) + train[2018-10-16-05:22:43] Epoch: [091][1000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.051 (3.272) Prec@1 71.09 (68.71) Prec@5 89.06 (87.54) + train[2018-10-16-05:24:27] Epoch: [091][1200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.077 (3.276) Prec@1 67.97 (68.63) Prec@5 91.41 (87.51) + train[2018-10-16-05:26:11] Epoch: [091][1400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.583 (3.278) Prec@1 68.75 (68.65) Prec@5 84.38 (87.48) + train[2018-10-16-05:27:55] Epoch: [091][1600/10010] Time 0.63 (0.52) Data 0.00 (0.00) Loss 3.489 (3.279) Prec@1 64.84 (68.60) Prec@5 84.38 (87.45) + train[2018-10-16-05:29:38] Epoch: [091][1800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.568 (3.282) Prec@1 64.84 (68.57) Prec@5 82.81 (87.41) + train[2018-10-16-05:31:22] Epoch: [091][2000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.984 (3.283) Prec@1 74.22 (68.58) Prec@5 88.28 (87.38) + train[2018-10-16-05:33:06] Epoch: [091][2200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.299 (3.283) Prec@1 71.09 (68.59) Prec@5 85.94 (87.37) + train[2018-10-16-05:34:50] Epoch: [091][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.110 (3.282) Prec@1 71.09 (68.56) Prec@5 89.06 (87.38) + train[2018-10-16-05:36:35] Epoch: [091][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.113 (3.282) Prec@1 69.53 (68.57) Prec@5 91.41 (87.39) + train[2018-10-16-05:38:20] Epoch: [091][2800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.480 (3.283) Prec@1 67.97 (68.55) Prec@5 84.38 (87.38) + train[2018-10-16-05:40:04] Epoch: [091][3000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.393 (3.284) Prec@1 66.41 (68.53) Prec@5 86.72 (87.36) + train[2018-10-16-05:41:48] Epoch: [091][3200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.772 (3.283) Prec@1 64.06 (68.55) Prec@5 82.81 (87.35) + train[2018-10-16-05:43:31] Epoch: [091][3400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.308 (3.283) Prec@1 73.44 (68.55) Prec@5 85.16 (87.36) + train[2018-10-16-05:45:15] Epoch: [091][3600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.492 (3.283) Prec@1 66.41 (68.54) Prec@5 86.72 (87.36) + train[2018-10-16-05:46:59] Epoch: [091][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.483 (3.284) Prec@1 64.06 (68.51) Prec@5 85.16 (87.35) + train[2018-10-16-05:48:43] Epoch: [091][4000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.378 (3.283) Prec@1 66.41 (68.53) Prec@5 85.16 (87.35) + train[2018-10-16-05:50:27] Epoch: [091][4200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.562 (3.283) Prec@1 66.41 (68.52) Prec@5 84.38 (87.35) + train[2018-10-16-05:52:12] Epoch: [091][4400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.954 (3.284) Prec@1 73.44 (68.51) Prec@5 91.41 (87.34) + train[2018-10-16-05:53:57] Epoch: [091][4600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.259 (3.284) Prec@1 67.97 (68.49) Prec@5 87.50 (87.32) + train[2018-10-16-05:55:41] Epoch: [091][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.371 (3.284) Prec@1 63.28 (68.49) Prec@5 87.50 (87.32) + train[2018-10-16-05:57:25] Epoch: [091][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.500 (3.285) Prec@1 62.50 (68.48) Prec@5 85.16 (87.31) + train[2018-10-16-05:59:09] Epoch: [091][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.058 (3.286) Prec@1 74.22 (68.46) Prec@5 88.28 (87.29) + train[2018-10-16-06:00:53] Epoch: [091][5400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.506 (3.287) Prec@1 67.97 (68.45) Prec@5 86.72 (87.29) + train[2018-10-16-06:02:37] Epoch: [091][5600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.022 (3.287) Prec@1 72.66 (68.45) Prec@5 91.41 (87.29) + train[2018-10-16-06:04:21] Epoch: [091][5800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.291 (3.287) Prec@1 67.19 (68.43) Prec@5 88.28 (87.29) + train[2018-10-16-06:06:06] Epoch: [091][6000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.175 (3.287) Prec@1 70.31 (68.43) Prec@5 89.84 (87.29) + train[2018-10-16-06:07:50] Epoch: [091][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.907 (3.287) Prec@1 75.00 (68.42) Prec@5 91.41 (87.29) + train[2018-10-16-06:09:35] Epoch: [091][6400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.000 (3.288) Prec@1 71.88 (68.41) Prec@5 89.84 (87.28) + train[2018-10-16-06:11:19] Epoch: [091][6600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.969 (3.289) Prec@1 75.00 (68.40) Prec@5 88.28 (87.27) + train[2018-10-16-06:13:04] Epoch: [091][6800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.105 (3.290) Prec@1 73.44 (68.38) Prec@5 87.50 (87.26) + train[2018-10-16-06:14:48] Epoch: [091][7000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.404 (3.291) Prec@1 69.53 (68.37) Prec@5 86.72 (87.24) + train[2018-10-16-06:16:31] Epoch: [091][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.144 (3.291) Prec@1 71.88 (68.37) Prec@5 85.94 (87.25) + train[2018-10-16-06:18:15] Epoch: [091][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.132 (3.291) Prec@1 67.97 (68.37) Prec@5 88.28 (87.24) + train[2018-10-16-06:20:00] Epoch: [091][7600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.709 (3.291) Prec@1 65.62 (68.37) Prec@5 85.94 (87.23) + train[2018-10-16-06:21:45] Epoch: [091][7800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.157 (3.291) Prec@1 70.31 (68.38) Prec@5 89.06 (87.24) + train[2018-10-16-06:23:30] Epoch: [091][8000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.309 (3.291) Prec@1 66.41 (68.38) Prec@5 88.28 (87.23) + train[2018-10-16-06:25:14] Epoch: [091][8200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.300 (3.292) Prec@1 67.19 (68.37) Prec@5 85.94 (87.23) + train[2018-10-16-06:26:59] Epoch: [091][8400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.227 (3.292) Prec@1 76.56 (68.36) Prec@5 85.94 (87.22) + train[2018-10-16-06:28:45] Epoch: [091][8600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.682 (3.292) Prec@1 64.06 (68.36) Prec@5 82.81 (87.21) + train[2018-10-16-06:30:31] Epoch: [091][8800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.032 (3.293) Prec@1 69.53 (68.35) Prec@5 91.41 (87.22) + train[2018-10-16-06:32:15] Epoch: [091][9000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.179 (3.294) Prec@1 69.53 (68.33) Prec@5 88.28 (87.21) + train[2018-10-16-06:33:59] Epoch: [091][9200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.320 (3.294) Prec@1 65.62 (68.33) Prec@5 88.28 (87.20) + train[2018-10-16-06:35:43] Epoch: [091][9400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.588 (3.294) Prec@1 64.06 (68.32) Prec@5 84.38 (87.20) + train[2018-10-16-06:37:27] Epoch: [091][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.448 (3.294) Prec@1 67.97 (68.32) Prec@5 85.16 (87.19) + train[2018-10-16-06:39:11] Epoch: [091][9800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.419 (3.295) Prec@1 64.84 (68.31) Prec@5 87.50 (87.19) + train[2018-10-16-06:40:55] Epoch: [091][10000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.279 (3.295) Prec@1 65.62 (68.31) Prec@5 89.84 (87.18) + train[2018-10-16-06:40:59] Epoch: [091][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 5.327 (3.295) Prec@1 40.00 (68.31) Prec@5 60.00 (87.18) +[2018-10-16-06:40:59] **train** Prec@1 68.31 Prec@5 87.18 Error@1 31.69 Error@5 12.82 Loss:3.295 + test [2018-10-16-06:41:04] Epoch: [091][000/391] Time 4.16 (4.16) Data 4.02 (4.02) Loss 0.692 (0.692) Prec@1 85.94 (85.94) Prec@5 96.88 (96.88) + test [2018-10-16-06:41:30] Epoch: [091][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.268 (1.141) Prec@1 68.75 (73.78) Prec@5 92.19 (92.15) + test [2018-10-16-06:41:55] Epoch: [091][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.121 (1.300) Prec@1 45.00 (70.31) Prec@5 85.00 (89.78) +[2018-10-16-06:41:55] **test** Prec@1 70.31 Prec@5 89.78 Error@1 29.69 Error@5 10.22 Loss:1.300 +----> Best Accuracy : Acc@1=70.73, Acc@5=89.94, Error@1=29.27, Error@5=10.06 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-16-06:41:55] [Epoch=092/250] [Need: 231:32:19] LR=0.0061 ~ 0.0061, Batch=128 + train[2018-10-16-06:41:59] Epoch: [092][000/10010] Time 4.21 (4.21) Data 3.62 (3.62) Loss 3.333 (3.333) Prec@1 68.75 (68.75) Prec@5 84.38 (84.38) + train[2018-10-16-06:43:44] Epoch: [092][200/10010] Time 0.54 (0.54) Data 0.00 (0.02) Loss 3.252 (3.252) Prec@1 68.75 (69.06) Prec@5 87.50 (87.71) + train[2018-10-16-06:45:28] Epoch: [092][400/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.271 (3.258) Prec@1 65.62 (69.07) Prec@5 85.16 (87.60) + train[2018-10-16-06:47:13] Epoch: [092][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.243 (3.256) Prec@1 68.75 (69.09) Prec@5 87.50 (87.63) + train[2018-10-16-06:48:57] Epoch: [092][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.169 (3.256) Prec@1 70.31 (69.08) Prec@5 87.50 (87.64) + train[2018-10-16-06:50:41] Epoch: [092][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.329 (3.259) Prec@1 68.75 (69.00) Prec@5 83.59 (87.61) + train[2018-10-16-06:52:25] Epoch: [092][1200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.277 (3.262) Prec@1 69.53 (68.96) Prec@5 84.38 (87.55) + train[2018-10-16-06:54:09] Epoch: [092][1400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.538 (3.264) Prec@1 64.84 (68.93) Prec@5 85.94 (87.57) + train[2018-10-16-06:55:54] Epoch: [092][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.196 (3.262) Prec@1 69.53 (68.98) Prec@5 87.50 (87.61) + train[2018-10-16-06:57:37] Epoch: [092][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.132 (3.263) Prec@1 71.88 (68.93) Prec@5 89.84 (87.60) + train[2018-10-16-06:59:21] Epoch: [092][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.334 (3.264) Prec@1 64.84 (68.91) Prec@5 85.16 (87.57) + train[2018-10-16-07:01:05] Epoch: [092][2200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.383 (3.266) Prec@1 64.06 (68.89) Prec@5 88.28 (87.54) + train[2018-10-16-07:02:50] Epoch: [092][2400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.301 (3.266) Prec@1 67.97 (68.90) Prec@5 89.06 (87.54) + train[2018-10-16-07:04:36] Epoch: [092][2600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.316 (3.265) Prec@1 68.75 (68.93) Prec@5 85.94 (87.54) + train[2018-10-16-07:06:21] Epoch: [092][2800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.014 (3.263) Prec@1 73.44 (68.97) Prec@5 92.19 (87.56) + train[2018-10-16-07:08:06] Epoch: [092][3000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.554 (3.265) Prec@1 61.72 (68.93) Prec@5 86.72 (87.53) + train[2018-10-16-07:09:50] Epoch: [092][3200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.390 (3.267) Prec@1 66.41 (68.89) Prec@5 89.06 (87.50) + train[2018-10-16-07:11:34] Epoch: [092][3400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.516 (3.268) Prec@1 66.41 (68.87) Prec@5 85.16 (87.50) + train[2018-10-16-07:13:19] Epoch: [092][3600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.300 (3.268) Prec@1 64.84 (68.87) Prec@5 86.72 (87.49) + train[2018-10-16-07:15:03] Epoch: [092][3800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.182 (3.269) Prec@1 68.75 (68.86) Prec@5 85.94 (87.49) + train[2018-10-16-07:16:47] Epoch: [092][4000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.208 (3.269) Prec@1 66.41 (68.84) Prec@5 89.06 (87.49) + train[2018-10-16-07:18:32] Epoch: [092][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.748 (3.270) Prec@1 59.38 (68.82) Prec@5 82.81 (87.48) + train[2018-10-16-07:20:16] Epoch: [092][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.943 (3.270) Prec@1 77.34 (68.81) Prec@5 93.75 (87.47) + train[2018-10-16-07:22:01] Epoch: [092][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.361 (3.271) Prec@1 71.09 (68.80) Prec@5 85.94 (87.46) + train[2018-10-16-07:23:46] Epoch: [092][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.513 (3.272) Prec@1 64.06 (68.79) Prec@5 82.81 (87.45) + train[2018-10-16-07:25:29] Epoch: [092][5000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.060 (3.272) Prec@1 66.41 (68.77) Prec@5 92.19 (87.45) + train[2018-10-16-07:27:14] Epoch: [092][5200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.400 (3.273) Prec@1 63.28 (68.76) Prec@5 83.59 (87.42) + train[2018-10-16-07:28:59] Epoch: [092][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.168 (3.274) Prec@1 70.31 (68.75) Prec@5 86.72 (87.42) + train[2018-10-16-07:30:43] Epoch: [092][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.211 (3.275) Prec@1 64.84 (68.71) Prec@5 89.06 (87.41) + train[2018-10-16-07:32:27] Epoch: [092][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.193 (3.276) Prec@1 67.97 (68.69) Prec@5 86.72 (87.39) + train[2018-10-16-07:34:11] Epoch: [092][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.440 (3.276) Prec@1 66.41 (68.69) Prec@5 85.94 (87.39) + train[2018-10-16-07:35:56] Epoch: [092][6200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.294 (3.277) Prec@1 68.75 (68.68) Prec@5 86.72 (87.37) + train[2018-10-16-07:37:40] Epoch: [092][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.250 (3.278) Prec@1 69.53 (68.66) Prec@5 87.50 (87.37) + train[2018-10-16-07:39:24] Epoch: [092][6600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.216 (3.279) Prec@1 67.97 (68.65) Prec@5 91.41 (87.36) + train[2018-10-16-07:41:11] Epoch: [092][6800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.903 (3.280) Prec@1 77.34 (68.63) Prec@5 85.94 (87.35) + train[2018-10-16-07:42:55] Epoch: [092][7000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.303 (3.281) Prec@1 67.97 (68.61) Prec@5 89.06 (87.34) + train[2018-10-16-07:44:40] Epoch: [092][7200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.379 (3.281) Prec@1 60.94 (68.60) Prec@5 86.72 (87.33) + train[2018-10-16-07:46:25] Epoch: [092][7400/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.280 (3.282) Prec@1 66.41 (68.59) Prec@5 86.72 (87.32) + train[2018-10-16-07:48:12] Epoch: [092][7600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.467 (3.282) Prec@1 65.62 (68.60) Prec@5 86.72 (87.32) + train[2018-10-16-07:49:58] Epoch: [092][7800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.374 (3.283) Prec@1 66.41 (68.59) Prec@5 85.16 (87.32) + train[2018-10-16-07:51:43] Epoch: [092][8000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.174 (3.283) Prec@1 68.75 (68.59) Prec@5 87.50 (87.31) + train[2018-10-16-07:53:27] Epoch: [092][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.618 (3.283) Prec@1 57.81 (68.58) Prec@5 82.03 (87.31) + train[2018-10-16-07:55:11] Epoch: [092][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.092 (3.284) Prec@1 71.09 (68.56) Prec@5 85.94 (87.29) + train[2018-10-16-07:56:57] Epoch: [092][8600/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.332 (3.285) Prec@1 64.84 (68.54) Prec@5 87.50 (87.28) + train[2018-10-16-07:58:42] Epoch: [092][8800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.099 (3.286) Prec@1 70.31 (68.52) Prec@5 88.28 (87.27) + train[2018-10-16-08:00:26] Epoch: [092][9000/10010] Time 0.60 (0.52) Data 0.00 (0.00) Loss 3.426 (3.286) Prec@1 70.31 (68.52) Prec@5 82.03 (87.26) + train[2018-10-16-08:02:10] Epoch: [092][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.267 (3.287) Prec@1 67.19 (68.51) Prec@5 87.50 (87.26) + train[2018-10-16-08:03:54] Epoch: [092][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.180 (3.286) Prec@1 66.41 (68.53) Prec@5 86.72 (87.26) + train[2018-10-16-08:05:39] Epoch: [092][9600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.228 (3.287) Prec@1 71.88 (68.52) Prec@5 89.84 (87.26) + train[2018-10-16-08:07:23] Epoch: [092][9800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.099 (3.287) Prec@1 68.75 (68.51) Prec@5 89.06 (87.25) + train[2018-10-16-08:09:07] Epoch: [092][10000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.935 (3.288) Prec@1 75.00 (68.49) Prec@5 89.84 (87.23) + train[2018-10-16-08:09:11] Epoch: [092][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.244 (3.288) Prec@1 66.67 (68.49) Prec@5 73.33 (87.23) +[2018-10-16-08:09:11] **train** Prec@1 68.49 Prec@5 87.23 Error@1 31.51 Error@5 12.77 Loss:3.288 + test [2018-10-16-08:09:15] Epoch: [092][000/391] Time 4.08 (4.08) Data 3.94 (3.94) Loss 0.582 (0.582) Prec@1 89.84 (89.84) Prec@5 96.88 (96.88) + test [2018-10-16-08:09:42] Epoch: [092][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.371 (1.096) Prec@1 67.97 (74.45) Prec@5 89.84 (92.44) + test [2018-10-16-08:10:06] Epoch: [092][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.291 (1.270) Prec@1 47.50 (70.81) Prec@5 80.00 (89.93) +[2018-10-16-08:10:06] **test** Prec@1 70.81 Prec@5 89.93 Error@1 29.19 Error@5 10.07 Loss:1.270 +----> Best Accuracy : Acc@1=70.81, Acc@5=89.93, Error@1=29.19, Error@5=10.07 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-16-08:10:06] [Epoch=093/250] [Need: 230:45:04] LR=0.0059 ~ 0.0059, Batch=128 + train[2018-10-16-08:10:11] Epoch: [093][000/10010] Time 5.06 (5.06) Data 4.38 (4.38) Loss 2.762 (2.762) Prec@1 79.69 (79.69) Prec@5 94.53 (94.53) + train[2018-10-16-08:11:56] Epoch: [093][200/10010] Time 0.54 (0.54) Data 0.00 (0.02) Loss 3.484 (3.251) Prec@1 67.19 (69.29) Prec@5 84.38 (87.60) + train[2018-10-16-08:13:40] Epoch: [093][400/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.070 (3.236) Prec@1 71.88 (69.33) Prec@5 89.06 (87.85) + train[2018-10-16-08:15:23] Epoch: [093][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 2.866 (3.239) Prec@1 74.22 (69.31) Prec@5 93.75 (87.87) + train[2018-10-16-08:17:08] Epoch: [093][800/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 2.919 (3.247) Prec@1 72.66 (69.18) Prec@5 92.97 (87.77) + train[2018-10-16-08:18:52] Epoch: [093][1000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.363 (3.254) Prec@1 67.97 (69.07) Prec@5 83.59 (87.69) + train[2018-10-16-08:20:36] Epoch: [093][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.320 (3.253) Prec@1 64.84 (69.06) Prec@5 88.28 (87.66) + train[2018-10-16-08:22:20] Epoch: [093][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.047 (3.252) Prec@1 75.78 (69.13) Prec@5 89.06 (87.70) + train[2018-10-16-08:24:03] Epoch: [093][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.347 (3.255) Prec@1 70.31 (69.10) Prec@5 85.16 (87.65) + train[2018-10-16-08:25:48] Epoch: [093][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.275 (3.256) Prec@1 67.97 (69.07) Prec@5 87.50 (87.63) + train[2018-10-16-08:27:31] Epoch: [093][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.931 (3.257) Prec@1 78.12 (69.06) Prec@5 92.97 (87.64) + train[2018-10-16-08:29:16] Epoch: [093][2200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.977 (3.258) Prec@1 75.00 (69.03) Prec@5 92.19 (87.63) + train[2018-10-16-08:30:59] Epoch: [093][2400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.383 (3.259) Prec@1 64.84 (69.02) Prec@5 82.81 (87.61) + train[2018-10-16-08:32:43] Epoch: [093][2600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.136 (3.261) Prec@1 71.88 (68.97) Prec@5 89.06 (87.58) + train[2018-10-16-08:34:27] Epoch: [093][2800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.248 (3.261) Prec@1 71.09 (68.96) Prec@5 88.28 (87.58) + train[2018-10-16-08:36:12] Epoch: [093][3000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.542 (3.263) Prec@1 60.94 (68.93) Prec@5 84.38 (87.56) + train[2018-10-16-08:37:56] Epoch: [093][3200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.207 (3.263) Prec@1 70.31 (68.92) Prec@5 86.72 (87.57) + train[2018-10-16-08:39:40] Epoch: [093][3400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.131 (3.264) Prec@1 71.09 (68.89) Prec@5 88.28 (87.54) + train[2018-10-16-08:41:24] Epoch: [093][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.576 (3.267) Prec@1 65.62 (68.86) Prec@5 82.03 (87.51) + train[2018-10-16-08:43:09] Epoch: [093][3800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.342 (3.267) Prec@1 74.22 (68.86) Prec@5 82.81 (87.51) + train[2018-10-16-08:44:53] Epoch: [093][4000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.351 (3.269) Prec@1 64.06 (68.82) Prec@5 88.28 (87.49) + train[2018-10-16-08:46:37] Epoch: [093][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.512 (3.270) Prec@1 63.28 (68.81) Prec@5 83.59 (87.49) + train[2018-10-16-08:48:21] Epoch: [093][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.268 (3.270) Prec@1 66.41 (68.80) Prec@5 87.50 (87.48) + train[2018-10-16-08:50:06] Epoch: [093][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.111 (3.270) Prec@1 73.44 (68.81) Prec@5 90.62 (87.48) + train[2018-10-16-08:51:50] Epoch: [093][4800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.312 (3.270) Prec@1 68.75 (68.81) Prec@5 86.72 (87.47) + train[2018-10-16-08:53:34] Epoch: [093][5000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.221 (3.270) Prec@1 73.44 (68.81) Prec@5 87.50 (87.47) + train[2018-10-16-08:55:18] Epoch: [093][5200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.490 (3.271) Prec@1 62.50 (68.79) Prec@5 87.50 (87.46) + train[2018-10-16-08:57:02] Epoch: [093][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.225 (3.272) Prec@1 70.31 (68.78) Prec@5 90.62 (87.45) + train[2018-10-16-08:58:46] Epoch: [093][5600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.243 (3.273) Prec@1 72.66 (68.75) Prec@5 88.28 (87.44) + train[2018-10-16-09:00:29] Epoch: [093][5800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.263 (3.274) Prec@1 68.75 (68.75) Prec@5 89.84 (87.44) + train[2018-10-16-09:02:13] Epoch: [093][6000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.135 (3.274) Prec@1 73.44 (68.74) Prec@5 87.50 (87.43) + train[2018-10-16-09:03:57] Epoch: [093][6200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.213 (3.275) Prec@1 71.09 (68.72) Prec@5 88.28 (87.42) + train[2018-10-16-09:05:42] Epoch: [093][6400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 2.980 (3.274) Prec@1 76.56 (68.73) Prec@5 92.97 (87.43) + train[2018-10-16-09:07:28] Epoch: [093][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.274 (3.275) Prec@1 70.31 (68.72) Prec@5 85.94 (87.43) + train[2018-10-16-09:09:13] Epoch: [093][6800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.216 (3.275) Prec@1 74.22 (68.70) Prec@5 86.72 (87.42) + train[2018-10-16-09:10:58] Epoch: [093][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.415 (3.276) Prec@1 68.75 (68.69) Prec@5 86.72 (87.41) + train[2018-10-16-09:12:44] Epoch: [093][7200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.327 (3.277) Prec@1 68.75 (68.68) Prec@5 85.94 (87.39) + train[2018-10-16-09:14:29] Epoch: [093][7400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.251 (3.277) Prec@1 67.97 (68.67) Prec@5 89.84 (87.40) + train[2018-10-16-09:16:14] Epoch: [093][7600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.235 (3.277) Prec@1 69.53 (68.67) Prec@5 87.50 (87.39) + train[2018-10-16-09:18:00] Epoch: [093][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.860 (3.278) Prec@1 75.78 (68.67) Prec@5 95.31 (87.39) + train[2018-10-16-09:19:45] Epoch: [093][8000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.406 (3.277) Prec@1 68.75 (68.67) Prec@5 87.50 (87.39) + train[2018-10-16-09:21:31] Epoch: [093][8200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.280 (3.278) Prec@1 67.19 (68.67) Prec@5 86.72 (87.39) + train[2018-10-16-09:23:17] Epoch: [093][8400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.291 (3.278) Prec@1 69.53 (68.66) Prec@5 87.50 (87.39) + train[2018-10-16-09:25:02] Epoch: [093][8600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.201 (3.279) Prec@1 69.53 (68.64) Prec@5 89.06 (87.37) + train[2018-10-16-09:26:48] Epoch: [093][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.516 (3.279) Prec@1 64.06 (68.64) Prec@5 84.38 (87.37) + train[2018-10-16-09:28:33] Epoch: [093][9000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.155 (3.280) Prec@1 69.53 (68.65) Prec@5 91.41 (87.37) + train[2018-10-16-09:30:17] Epoch: [093][9200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.330 (3.280) Prec@1 64.84 (68.64) Prec@5 86.72 (87.37) + train[2018-10-16-09:32:03] Epoch: [093][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.226 (3.280) Prec@1 67.19 (68.63) Prec@5 88.28 (87.36) + train[2018-10-16-09:33:49] Epoch: [093][9600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.195 (3.281) Prec@1 69.53 (68.62) Prec@5 91.41 (87.36) + train[2018-10-16-09:35:34] Epoch: [093][9800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.279 (3.280) Prec@1 70.31 (68.62) Prec@5 85.16 (87.36) + train[2018-10-16-09:37:19] Epoch: [093][10000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.532 (3.281) Prec@1 61.72 (68.61) Prec@5 85.94 (87.35) + train[2018-10-16-09:37:23] Epoch: [093][10009/10010] Time 0.18 (0.52) Data 0.00 (0.00) Loss 4.607 (3.281) Prec@1 40.00 (68.61) Prec@5 86.67 (87.35) +[2018-10-16-09:37:23] **train** Prec@1 68.61 Prec@5 87.35 Error@1 31.39 Error@5 12.65 Loss:3.281 + test [2018-10-16-09:37:27] Epoch: [093][000/391] Time 3.67 (3.67) Data 3.54 (3.54) Loss 0.676 (0.676) Prec@1 85.94 (85.94) Prec@5 96.09 (96.09) + test [2018-10-16-09:37:54] Epoch: [093][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.430 (1.103) Prec@1 66.41 (74.23) Prec@5 85.16 (92.33) + test [2018-10-16-09:38:18] Epoch: [093][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.182 (1.279) Prec@1 38.75 (70.60) Prec@5 82.50 (89.85) +[2018-10-16-09:38:18] **test** Prec@1 70.60 Prec@5 89.85 Error@1 29.40 Error@5 10.15 Loss:1.279 +----> Best Accuracy : Acc@1=70.81, Acc@5=89.93, Error@1=29.19, Error@5=10.07 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-16-09:38:18] [Epoch=094/250] [Need: 229:19:15] LR=0.0057 ~ 0.0057, Batch=128 + train[2018-10-16-09:38:23] Epoch: [094][000/10010] Time 4.91 (4.91) Data 4.28 (4.28) Loss 3.470 (3.470) Prec@1 66.41 (66.41) Prec@5 85.94 (85.94) + train[2018-10-16-09:40:07] Epoch: [094][200/10010] Time 0.54 (0.54) Data 0.00 (0.02) Loss 3.429 (3.228) Prec@1 69.53 (69.67) Prec@5 85.94 (88.04) + train[2018-10-16-09:41:51] Epoch: [094][400/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.489 (3.230) Prec@1 63.28 (69.59) Prec@5 86.72 (87.98) + train[2018-10-16-09:43:35] Epoch: [094][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.147 (3.246) Prec@1 71.88 (69.32) Prec@5 89.06 (87.75) + train[2018-10-16-09:45:19] Epoch: [094][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.098 (3.247) Prec@1 72.66 (69.28) Prec@5 87.50 (87.73) + train[2018-10-16-09:47:04] Epoch: [094][1000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.840 (3.250) Prec@1 75.00 (69.25) Prec@5 93.75 (87.71) + train[2018-10-16-09:48:47] Epoch: [094][1200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.482 (3.251) Prec@1 68.75 (69.21) Prec@5 83.59 (87.67) + train[2018-10-16-09:50:31] Epoch: [094][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.224 (3.251) Prec@1 71.09 (69.20) Prec@5 89.84 (87.70) + train[2018-10-16-09:52:15] Epoch: [094][1600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.327 (3.252) Prec@1 63.28 (69.20) Prec@5 85.16 (87.70) + train[2018-10-16-09:53:59] Epoch: [094][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.179 (3.250) Prec@1 66.41 (69.20) Prec@5 89.06 (87.74) + train[2018-10-16-09:55:43] Epoch: [094][2000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.299 (3.250) Prec@1 67.97 (69.19) Prec@5 84.38 (87.72) + train[2018-10-16-09:57:27] Epoch: [094][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.267 (3.249) Prec@1 67.19 (69.17) Prec@5 88.28 (87.73) + train[2018-10-16-09:59:11] Epoch: [094][2400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.613 (3.251) Prec@1 65.62 (69.13) Prec@5 82.03 (87.69) + train[2018-10-16-10:00:55] Epoch: [094][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.206 (3.250) Prec@1 72.66 (69.16) Prec@5 90.62 (87.70) + train[2018-10-16-10:02:40] Epoch: [094][2800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.312 (3.250) Prec@1 69.53 (69.17) Prec@5 89.06 (87.71) + train[2018-10-16-10:04:26] Epoch: [094][3000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.510 (3.251) Prec@1 64.84 (69.14) Prec@5 85.94 (87.68) + train[2018-10-16-10:06:11] Epoch: [094][3200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.036 (3.252) Prec@1 71.09 (69.14) Prec@5 91.41 (87.66) + train[2018-10-16-10:07:55] Epoch: [094][3400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.643 (3.253) Prec@1 67.19 (69.13) Prec@5 83.59 (87.66) + train[2018-10-16-10:09:40] Epoch: [094][3600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.257 (3.256) Prec@1 68.75 (69.08) Prec@5 88.28 (87.63) + train[2018-10-16-10:11:25] Epoch: [094][3800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.600 (3.257) Prec@1 63.28 (69.07) Prec@5 85.16 (87.61) + train[2018-10-16-10:13:09] Epoch: [094][4000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.884 (3.256) Prec@1 75.78 (69.08) Prec@5 92.97 (87.62) + train[2018-10-16-10:14:54] Epoch: [094][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.097 (3.256) Prec@1 71.09 (69.08) Prec@5 89.84 (87.62) + train[2018-10-16-10:16:39] Epoch: [094][4400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.274 (3.258) Prec@1 70.31 (69.05) Prec@5 85.94 (87.61) + train[2018-10-16-10:18:26] Epoch: [094][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.054 (3.259) Prec@1 71.88 (69.03) Prec@5 90.62 (87.60) + train[2018-10-16-10:20:12] Epoch: [094][4800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.328 (3.260) Prec@1 64.84 (69.03) Prec@5 90.62 (87.58) + train[2018-10-16-10:21:58] Epoch: [094][5000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.321 (3.260) Prec@1 66.41 (69.02) Prec@5 88.28 (87.58) + train[2018-10-16-10:23:45] Epoch: [094][5200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 2.963 (3.260) Prec@1 72.66 (69.01) Prec@5 94.53 (87.57) + train[2018-10-16-10:25:30] Epoch: [094][5400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.230 (3.261) Prec@1 69.53 (69.00) Prec@5 87.50 (87.57) + train[2018-10-16-10:27:16] Epoch: [094][5600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.306 (3.261) Prec@1 66.41 (68.99) Prec@5 88.28 (87.56) + train[2018-10-16-10:29:02] Epoch: [094][5800/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.442 (3.261) Prec@1 64.84 (69.00) Prec@5 85.16 (87.56) + train[2018-10-16-10:30:49] Epoch: [094][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.387 (3.262) Prec@1 68.75 (68.98) Prec@5 86.72 (87.54) + train[2018-10-16-10:32:34] Epoch: [094][6200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.199 (3.264) Prec@1 71.88 (68.95) Prec@5 87.50 (87.53) + train[2018-10-16-10:34:21] Epoch: [094][6400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.323 (3.265) Prec@1 67.19 (68.94) Prec@5 87.50 (87.53) + train[2018-10-16-10:36:07] Epoch: [094][6600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.014 (3.265) Prec@1 76.56 (68.93) Prec@5 91.41 (87.52) + train[2018-10-16-10:37:53] Epoch: [094][6800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.215 (3.265) Prec@1 72.66 (68.92) Prec@5 89.84 (87.52) + train[2018-10-16-10:39:38] Epoch: [094][7000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.584 (3.265) Prec@1 62.50 (68.93) Prec@5 83.59 (87.51) + train[2018-10-16-10:41:25] Epoch: [094][7200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.379 (3.266) Prec@1 66.41 (68.91) Prec@5 88.28 (87.50) + train[2018-10-16-10:43:10] Epoch: [094][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.208 (3.266) Prec@1 71.88 (68.91) Prec@5 86.72 (87.50) + train[2018-10-16-10:44:55] Epoch: [094][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.591 (3.266) Prec@1 63.28 (68.89) Prec@5 79.69 (87.49) + train[2018-10-16-10:46:40] Epoch: [094][7800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.261 (3.266) Prec@1 65.62 (68.89) Prec@5 87.50 (87.49) + train[2018-10-16-10:48:25] Epoch: [094][8000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.101 (3.267) Prec@1 71.09 (68.87) Prec@5 89.06 (87.49) + train[2018-10-16-10:50:11] Epoch: [094][8200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.709 (3.268) Prec@1 65.62 (68.86) Prec@5 82.03 (87.48) + train[2018-10-16-10:51:56] Epoch: [094][8400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.457 (3.268) Prec@1 68.75 (68.86) Prec@5 83.59 (87.49) + train[2018-10-16-10:53:41] Epoch: [094][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.179 (3.268) Prec@1 69.53 (68.85) Prec@5 89.06 (87.48) + train[2018-10-16-10:55:26] Epoch: [094][8800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.069 (3.268) Prec@1 75.78 (68.85) Prec@5 85.94 (87.48) + train[2018-10-16-10:57:12] Epoch: [094][9000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.275 (3.268) Prec@1 66.41 (68.83) Prec@5 85.94 (87.48) + train[2018-10-16-10:58:57] Epoch: [094][9200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.277 (3.268) Prec@1 68.75 (68.83) Prec@5 85.94 (87.48) + train[2018-10-16-11:00:44] Epoch: [094][9400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.572 (3.269) Prec@1 65.62 (68.82) Prec@5 82.81 (87.47) + train[2018-10-16-11:02:30] Epoch: [094][9600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.239 (3.269) Prec@1 67.97 (68.82) Prec@5 86.72 (87.47) + train[2018-10-16-11:04:17] Epoch: [094][9800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.040 (3.269) Prec@1 72.66 (68.81) Prec@5 89.06 (87.47) + train[2018-10-16-11:06:02] Epoch: [094][10000/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.151 (3.270) Prec@1 71.09 (68.80) Prec@5 91.41 (87.46) + train[2018-10-16-11:06:06] Epoch: [094][10009/10010] Time 0.14 (0.53) Data 0.00 (0.00) Loss 3.798 (3.269) Prec@1 53.33 (68.81) Prec@5 86.67 (87.46) +[2018-10-16-11:06:06] **train** Prec@1 68.81 Prec@5 87.46 Error@1 31.19 Error@5 12.54 Loss:3.269 + test [2018-10-16-11:06:11] Epoch: [094][000/391] Time 4.31 (4.31) Data 4.17 (4.17) Loss 0.703 (0.703) Prec@1 83.59 (83.59) Prec@5 95.31 (95.31) + test [2018-10-16-11:06:37] Epoch: [094][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.485 (1.095) Prec@1 60.94 (74.41) Prec@5 88.28 (92.31) + test [2018-10-16-11:07:01] Epoch: [094][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.202 (1.259) Prec@1 43.75 (70.94) Prec@5 82.50 (90.03) +[2018-10-16-11:07:01] **test** Prec@1 70.94 Prec@5 90.03 Error@1 29.06 Error@5 9.97 Loss:1.259 +----> Best Accuracy : Acc@1=70.94, Acc@5=90.03, Error@1=29.06, Error@5=9.97 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-16-11:07:02] [Epoch=095/250] [Need: 229:11:48] LR=0.0055 ~ 0.0055, Batch=128 + train[2018-10-16-11:07:07] Epoch: [095][000/10010] Time 5.68 (5.68) Data 5.13 (5.13) Loss 3.545 (3.545) Prec@1 62.50 (62.50) Prec@5 83.59 (83.59) + train[2018-10-16-11:08:52] Epoch: [095][200/10010] Time 0.52 (0.55) Data 0.00 (0.03) Loss 2.918 (3.215) Prec@1 71.88 (69.83) Prec@5 92.97 (88.18) + train[2018-10-16-11:10:36] Epoch: [095][400/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 3.333 (3.231) Prec@1 67.97 (69.72) Prec@5 85.16 (87.94) + train[2018-10-16-11:12:20] Epoch: [095][600/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.175 (3.229) Prec@1 72.66 (69.78) Prec@5 87.50 (87.96) + train[2018-10-16-11:14:04] Epoch: [095][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.287 (3.234) Prec@1 68.75 (69.74) Prec@5 87.50 (87.84) + train[2018-10-16-11:15:49] Epoch: [095][1000/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.057 (3.235) Prec@1 74.22 (69.68) Prec@5 89.84 (87.83) + train[2018-10-16-11:17:32] Epoch: [095][1200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.346 (3.237) Prec@1 67.97 (69.57) Prec@5 83.59 (87.86) + train[2018-10-16-11:19:16] Epoch: [095][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.850 (3.238) Prec@1 77.34 (69.55) Prec@5 90.62 (87.83) + train[2018-10-16-11:21:00] Epoch: [095][1600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.982 (3.238) Prec@1 72.66 (69.52) Prec@5 94.53 (87.83) + train[2018-10-16-11:22:44] Epoch: [095][1800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.268 (3.239) Prec@1 71.09 (69.52) Prec@5 86.72 (87.81) + train[2018-10-16-11:24:28] Epoch: [095][2000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.198 (3.241) Prec@1 69.53 (69.48) Prec@5 86.72 (87.78) + train[2018-10-16-11:26:12] Epoch: [095][2200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.460 (3.239) Prec@1 72.66 (69.50) Prec@5 84.38 (87.80) + train[2018-10-16-11:27:56] Epoch: [095][2400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.921 (3.241) Prec@1 63.28 (69.46) Prec@5 82.03 (87.79) + train[2018-10-16-11:29:42] Epoch: [095][2600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.986 (3.242) Prec@1 75.78 (69.44) Prec@5 90.62 (87.76) + train[2018-10-16-11:31:27] Epoch: [095][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.388 (3.244) Prec@1 67.97 (69.38) Prec@5 88.28 (87.74) + train[2018-10-16-11:33:12] Epoch: [095][3000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.220 (3.244) Prec@1 65.62 (69.35) Prec@5 86.72 (87.75) + train[2018-10-16-11:34:57] Epoch: [095][3200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.296 (3.245) Prec@1 72.66 (69.34) Prec@5 87.50 (87.74) + train[2018-10-16-11:36:42] Epoch: [095][3400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.388 (3.246) Prec@1 67.19 (69.32) Prec@5 85.16 (87.73) + train[2018-10-16-11:38:26] Epoch: [095][3600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.136 (3.246) Prec@1 71.09 (69.32) Prec@5 90.62 (87.74) + train[2018-10-16-11:40:10] Epoch: [095][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.225 (3.246) Prec@1 66.41 (69.32) Prec@5 90.62 (87.75) + train[2018-10-16-11:41:53] Epoch: [095][4000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.210 (3.248) Prec@1 74.22 (69.27) Prec@5 87.50 (87.73) + train[2018-10-16-11:43:37] Epoch: [095][4200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.257 (3.248) Prec@1 73.44 (69.25) Prec@5 87.50 (87.73) + train[2018-10-16-11:45:21] Epoch: [095][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.981 (3.249) Prec@1 72.66 (69.23) Prec@5 89.84 (87.72) + train[2018-10-16-11:47:06] Epoch: [095][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.314 (3.249) Prec@1 65.62 (69.22) Prec@5 85.94 (87.72) + train[2018-10-16-11:48:50] Epoch: [095][4800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.858 (3.249) Prec@1 78.91 (69.23) Prec@5 92.19 (87.72) + train[2018-10-16-11:50:35] Epoch: [095][5000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.222 (3.249) Prec@1 67.97 (69.22) Prec@5 89.84 (87.71) + train[2018-10-16-11:52:20] Epoch: [095][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.261 (3.250) Prec@1 68.75 (69.22) Prec@5 85.16 (87.70) + train[2018-10-16-11:54:03] Epoch: [095][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.613 (3.251) Prec@1 62.50 (69.20) Prec@5 84.38 (87.68) + train[2018-10-16-11:55:48] Epoch: [095][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.360 (3.250) Prec@1 64.06 (69.21) Prec@5 88.28 (87.68) + train[2018-10-16-11:57:32] Epoch: [095][5800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.108 (3.251) Prec@1 72.66 (69.20) Prec@5 87.50 (87.67) + train[2018-10-16-11:59:16] Epoch: [095][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.337 (3.252) Prec@1 66.41 (69.18) Prec@5 87.50 (87.66) + train[2018-10-16-12:01:00] Epoch: [095][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.090 (3.253) Prec@1 70.31 (69.17) Prec@5 89.84 (87.66) + train[2018-10-16-12:02:45] Epoch: [095][6400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.255 (3.253) Prec@1 67.97 (69.16) Prec@5 90.62 (87.66) + train[2018-10-16-12:04:30] Epoch: [095][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.449 (3.254) Prec@1 65.62 (69.15) Prec@5 87.50 (87.65) + train[2018-10-16-12:06:15] Epoch: [095][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.281 (3.254) Prec@1 69.53 (69.14) Prec@5 86.72 (87.64) + train[2018-10-16-12:07:59] Epoch: [095][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.318 (3.254) Prec@1 66.41 (69.14) Prec@5 85.94 (87.63) + train[2018-10-16-12:09:44] Epoch: [095][7200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.396 (3.255) Prec@1 68.75 (69.13) Prec@5 84.38 (87.63) + train[2018-10-16-12:11:27] Epoch: [095][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.333 (3.255) Prec@1 68.75 (69.12) Prec@5 88.28 (87.63) + train[2018-10-16-12:13:11] Epoch: [095][7600/10010] Time 0.59 (0.52) Data 0.00 (0.00) Loss 2.951 (3.255) Prec@1 72.66 (69.12) Prec@5 91.41 (87.63) + train[2018-10-16-12:14:55] Epoch: [095][7800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.083 (3.255) Prec@1 74.22 (69.10) Prec@5 89.06 (87.62) + train[2018-10-16-12:16:39] Epoch: [095][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.049 (3.256) Prec@1 69.53 (69.09) Prec@5 89.84 (87.62) + train[2018-10-16-12:18:23] Epoch: [095][8200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.334 (3.257) Prec@1 72.66 (69.07) Prec@5 85.94 (87.61) + train[2018-10-16-12:20:08] Epoch: [095][8400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.099 (3.257) Prec@1 71.88 (69.05) Prec@5 86.72 (87.60) + train[2018-10-16-12:21:54] Epoch: [095][8600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.514 (3.257) Prec@1 66.41 (69.04) Prec@5 82.81 (87.61) + train[2018-10-16-12:23:40] Epoch: [095][8800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.583 (3.258) Prec@1 67.97 (69.04) Prec@5 81.25 (87.59) + train[2018-10-16-12:25:27] Epoch: [095][9000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.947 (3.259) Prec@1 75.00 (69.03) Prec@5 90.62 (87.59) + train[2018-10-16-12:27:13] Epoch: [095][9200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.200 (3.259) Prec@1 71.88 (69.02) Prec@5 89.06 (87.58) + train[2018-10-16-12:29:00] Epoch: [095][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.397 (3.259) Prec@1 68.75 (69.01) Prec@5 85.16 (87.58) + train[2018-10-16-12:30:47] Epoch: [095][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.484 (3.260) Prec@1 69.53 (69.01) Prec@5 84.38 (87.58) + train[2018-10-16-12:32:34] Epoch: [095][9800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.349 (3.260) Prec@1 67.19 (69.00) Prec@5 86.72 (87.57) + train[2018-10-16-12:34:19] Epoch: [095][10000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.190 (3.261) Prec@1 75.00 (68.99) Prec@5 86.72 (87.56) + train[2018-10-16-12:34:24] Epoch: [095][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 3.302 (3.261) Prec@1 73.33 (68.99) Prec@5 80.00 (87.56) +[2018-10-16-12:34:24] **train** Prec@1 68.99 Prec@5 87.56 Error@1 31.01 Error@5 12.44 Loss:3.261 + test [2018-10-16-12:34:28] Epoch: [095][000/391] Time 4.12 (4.12) Data 3.98 (3.98) Loss 0.634 (0.634) Prec@1 89.84 (89.84) Prec@5 97.66 (97.66) + test [2018-10-16-12:34:54] Epoch: [095][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.247 (1.096) Prec@1 66.41 (74.38) Prec@5 92.19 (92.47) + test [2018-10-16-12:35:19] Epoch: [095][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.423 (1.267) Prec@1 42.50 (70.98) Prec@5 75.00 (90.05) +[2018-10-16-12:35:19] **test** Prec@1 70.98 Prec@5 90.05 Error@1 29.02 Error@5 9.95 Loss:1.267 +----> Best Accuracy : Acc@1=70.98, Acc@5=90.05, Error@1=29.02, Error@5=9.95 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-16-12:35:19] [Epoch=096/250] [Need: 226:36:17] LR=0.0054 ~ 0.0054, Batch=128 + train[2018-10-16-12:35:23] Epoch: [096][000/10010] Time 4.57 (4.57) Data 3.96 (3.96) Loss 3.618 (3.618) Prec@1 63.28 (63.28) Prec@5 85.94 (85.94) + train[2018-10-16-12:37:07] Epoch: [096][200/10010] Time 0.54 (0.54) Data 0.00 (0.02) Loss 3.202 (3.232) Prec@1 72.66 (69.34) Prec@5 87.50 (88.11) + train[2018-10-16-12:38:50] Epoch: [096][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.898 (3.226) Prec@1 75.00 (69.58) Prec@5 92.19 (88.11) + train[2018-10-16-12:40:34] Epoch: [096][600/10010] Time 0.54 (0.52) Data 0.00 (0.01) Loss 3.836 (3.225) Prec@1 60.94 (69.65) Prec@5 80.47 (88.06) + train[2018-10-16-12:42:18] Epoch: [096][800/10010] Time 0.50 (0.52) Data 0.00 (0.01) Loss 3.346 (3.223) Prec@1 69.53 (69.65) Prec@5 86.72 (88.06) + train[2018-10-16-12:44:02] Epoch: [096][1000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.123 (3.223) Prec@1 74.22 (69.62) Prec@5 89.84 (88.05) + train[2018-10-16-12:45:47] Epoch: [096][1200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.165 (3.225) Prec@1 69.53 (69.58) Prec@5 90.62 (88.02) + train[2018-10-16-12:47:31] Epoch: [096][1400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.030 (3.228) Prec@1 67.97 (69.53) Prec@5 89.06 (87.99) + train[2018-10-16-12:49:14] Epoch: [096][1600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.215 (3.229) Prec@1 70.31 (69.52) Prec@5 87.50 (87.99) + train[2018-10-16-12:50:58] Epoch: [096][1800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.147 (3.228) Prec@1 70.31 (69.53) Prec@5 90.62 (88.01) + train[2018-10-16-12:52:43] Epoch: [096][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.579 (3.228) Prec@1 64.06 (69.55) Prec@5 85.16 (88.00) + train[2018-10-16-12:54:27] Epoch: [096][2200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.275 (3.230) Prec@1 72.66 (69.50) Prec@5 88.28 (87.98) + train[2018-10-16-12:56:11] Epoch: [096][2400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.223 (3.230) Prec@1 68.75 (69.53) Prec@5 89.06 (87.98) + train[2018-10-16-12:57:55] Epoch: [096][2600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.090 (3.231) Prec@1 77.34 (69.52) Prec@5 92.19 (87.97) + train[2018-10-16-12:59:40] Epoch: [096][2800/10010] Time 0.59 (0.52) Data 0.00 (0.00) Loss 3.461 (3.232) Prec@1 63.28 (69.51) Prec@5 85.94 (87.96) + train[2018-10-16-13:01:24] Epoch: [096][3000/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.146 (3.234) Prec@1 70.31 (69.48) Prec@5 89.06 (87.94) + train[2018-10-16-13:03:09] Epoch: [096][3200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.166 (3.236) Prec@1 68.75 (69.46) Prec@5 92.97 (87.92) + train[2018-10-16-13:04:53] Epoch: [096][3400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.355 (3.236) Prec@1 67.97 (69.45) Prec@5 84.38 (87.90) + train[2018-10-16-13:06:37] Epoch: [096][3600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.391 (3.238) Prec@1 64.84 (69.44) Prec@5 87.50 (87.88) + train[2018-10-16-13:08:21] Epoch: [096][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.228 (3.240) Prec@1 71.09 (69.40) Prec@5 87.50 (87.87) + train[2018-10-16-13:10:05] Epoch: [096][4000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.806 (3.240) Prec@1 78.12 (69.39) Prec@5 90.62 (87.87) + train[2018-10-16-13:11:49] Epoch: [096][4200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.866 (3.241) Prec@1 76.56 (69.36) Prec@5 92.97 (87.85) + train[2018-10-16-13:13:33] Epoch: [096][4400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.240 (3.242) Prec@1 67.97 (69.34) Prec@5 88.28 (87.85) + train[2018-10-16-13:15:17] Epoch: [096][4600/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.374 (3.242) Prec@1 64.84 (69.34) Prec@5 85.94 (87.85) + train[2018-10-16-13:17:02] Epoch: [096][4800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.831 (3.242) Prec@1 79.69 (69.32) Prec@5 91.41 (87.84) + train[2018-10-16-13:18:48] Epoch: [096][5000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.238 (3.243) Prec@1 70.31 (69.29) Prec@5 87.50 (87.83) + train[2018-10-16-13:20:34] Epoch: [096][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.230 (3.245) Prec@1 69.53 (69.27) Prec@5 87.50 (87.82) + train[2018-10-16-13:22:19] Epoch: [096][5400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.337 (3.245) Prec@1 66.41 (69.26) Prec@5 89.84 (87.81) + train[2018-10-16-13:24:05] Epoch: [096][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.171 (3.246) Prec@1 71.09 (69.26) Prec@5 89.84 (87.79) + train[2018-10-16-13:25:51] Epoch: [096][5800/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.501 (3.247) Prec@1 65.62 (69.22) Prec@5 85.16 (87.78) + train[2018-10-16-13:27:36] Epoch: [096][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.262 (3.248) Prec@1 70.31 (69.22) Prec@5 85.94 (87.77) + train[2018-10-16-13:29:22] Epoch: [096][6200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.157 (3.248) Prec@1 71.09 (69.21) Prec@5 88.28 (87.76) + train[2018-10-16-13:31:07] Epoch: [096][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.066 (3.248) Prec@1 70.31 (69.20) Prec@5 90.62 (87.76) + train[2018-10-16-13:32:53] Epoch: [096][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.584 (3.249) Prec@1 61.72 (69.18) Prec@5 82.03 (87.75) + train[2018-10-16-13:34:39] Epoch: [096][6800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.512 (3.249) Prec@1 66.41 (69.18) Prec@5 84.38 (87.75) + train[2018-10-16-13:36:24] Epoch: [096][7000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.515 (3.250) Prec@1 67.19 (69.17) Prec@5 84.38 (87.74) + train[2018-10-16-13:38:10] Epoch: [096][7200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 2.860 (3.251) Prec@1 74.22 (69.16) Prec@5 89.84 (87.73) + train[2018-10-16-13:39:55] Epoch: [096][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.817 (3.251) Prec@1 78.91 (69.14) Prec@5 92.97 (87.72) + train[2018-10-16-13:41:40] Epoch: [096][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.315 (3.252) Prec@1 65.62 (69.14) Prec@5 87.50 (87.72) + train[2018-10-16-13:43:25] Epoch: [096][7800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.458 (3.252) Prec@1 63.28 (69.14) Prec@5 86.72 (87.71) + train[2018-10-16-13:45:11] Epoch: [096][8000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.392 (3.253) Prec@1 69.53 (69.11) Prec@5 85.94 (87.70) + train[2018-10-16-13:46:54] Epoch: [096][8200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.334 (3.254) Prec@1 65.62 (69.10) Prec@5 87.50 (87.69) + train[2018-10-16-13:48:39] Epoch: [096][8400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.333 (3.254) Prec@1 65.62 (69.09) Prec@5 86.72 (87.69) + train[2018-10-16-13:50:23] Epoch: [096][8600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.398 (3.254) Prec@1 67.19 (69.09) Prec@5 83.59 (87.68) + train[2018-10-16-13:52:08] Epoch: [096][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.120 (3.254) Prec@1 71.09 (69.08) Prec@5 91.41 (87.68) + train[2018-10-16-13:53:53] Epoch: [096][9000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.515 (3.255) Prec@1 65.62 (69.08) Prec@5 82.81 (87.67) + train[2018-10-16-13:55:37] Epoch: [096][9200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.363 (3.255) Prec@1 66.41 (69.08) Prec@5 85.16 (87.66) + train[2018-10-16-13:57:22] Epoch: [096][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.347 (3.255) Prec@1 66.41 (69.08) Prec@5 83.59 (87.66) + train[2018-10-16-13:59:07] Epoch: [096][9600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.209 (3.256) Prec@1 68.75 (69.07) Prec@5 86.72 (87.65) + train[2018-10-16-14:00:50] Epoch: [096][9800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.912 (3.256) Prec@1 71.09 (69.07) Prec@5 92.19 (87.65) + train[2018-10-16-14:02:34] Epoch: [096][10000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.042 (3.257) Prec@1 75.78 (69.06) Prec@5 89.84 (87.64) + train[2018-10-16-14:02:39] Epoch: [096][10009/10010] Time 0.30 (0.52) Data 0.00 (0.00) Loss 4.391 (3.257) Prec@1 53.33 (69.06) Prec@5 80.00 (87.64) +[2018-10-16-14:02:39] **train** Prec@1 69.06 Prec@5 87.64 Error@1 30.94 Error@5 12.36 Loss:3.257 + test [2018-10-16-14:02:43] Epoch: [096][000/391] Time 4.16 (4.16) Data 4.03 (4.03) Loss 0.667 (0.667) Prec@1 88.28 (88.28) Prec@5 97.66 (97.66) + test [2018-10-16-14:03:09] Epoch: [096][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.386 (1.090) Prec@1 61.72 (74.76) Prec@5 90.62 (92.72) + test [2018-10-16-14:03:33] Epoch: [096][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.205 (1.264) Prec@1 42.50 (71.16) Prec@5 83.75 (90.12) +[2018-10-16-14:03:33] **test** Prec@1 71.16 Prec@5 90.12 Error@1 28.84 Error@5 9.88 Loss:1.264 +----> Best Accuracy : Acc@1=71.16, Acc@5=90.12, Error@1=28.84, Error@5=9.88 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-16-14:03:34] [Epoch=097/250] [Need: 225:01:43] LR=0.0052 ~ 0.0052, Batch=128 + train[2018-10-16-14:03:38] Epoch: [097][000/10010] Time 4.65 (4.65) Data 4.04 (4.04) Loss 2.702 (2.702) Prec@1 84.38 (84.38) Prec@5 96.09 (96.09) + train[2018-10-16-14:05:23] Epoch: [097][200/10010] Time 0.56 (0.54) Data 0.00 (0.02) Loss 3.503 (3.226) Prec@1 63.28 (69.90) Prec@5 87.50 (88.01) + train[2018-10-16-14:07:07] Epoch: [097][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.494 (3.223) Prec@1 64.06 (69.99) Prec@5 86.72 (87.94) + train[2018-10-16-14:08:50] Epoch: [097][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.141 (3.221) Prec@1 67.97 (69.90) Prec@5 88.28 (88.00) + train[2018-10-16-14:10:34] Epoch: [097][800/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.344 (3.229) Prec@1 66.41 (69.74) Prec@5 85.94 (87.87) + train[2018-10-16-14:12:18] Epoch: [097][1000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.159 (3.230) Prec@1 75.78 (69.65) Prec@5 86.72 (87.89) + train[2018-10-16-14:14:03] Epoch: [097][1200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.215 (3.232) Prec@1 70.31 (69.63) Prec@5 83.59 (87.87) + train[2018-10-16-14:15:47] Epoch: [097][1400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.360 (3.233) Prec@1 67.19 (69.56) Prec@5 88.28 (87.87) + train[2018-10-16-14:17:31] Epoch: [097][1600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.414 (3.233) Prec@1 66.41 (69.55) Prec@5 85.16 (87.88) + train[2018-10-16-14:19:15] Epoch: [097][1800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.216 (3.232) Prec@1 64.06 (69.54) Prec@5 92.97 (87.87) + train[2018-10-16-14:20:59] Epoch: [097][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.433 (3.235) Prec@1 68.75 (69.50) Prec@5 84.38 (87.82) + train[2018-10-16-14:22:43] Epoch: [097][2200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.209 (3.237) Prec@1 66.41 (69.45) Prec@5 87.50 (87.80) + train[2018-10-16-14:24:27] Epoch: [097][2400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.410 (3.237) Prec@1 67.19 (69.46) Prec@5 89.06 (87.80) + train[2018-10-16-14:26:11] Epoch: [097][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.456 (3.237) Prec@1 63.28 (69.44) Prec@5 85.94 (87.80) + train[2018-10-16-14:27:56] Epoch: [097][2800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 2.974 (3.236) Prec@1 71.09 (69.45) Prec@5 89.06 (87.82) + train[2018-10-16-14:29:40] Epoch: [097][3000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.095 (3.237) Prec@1 71.88 (69.44) Prec@5 90.62 (87.82) + train[2018-10-16-14:31:25] Epoch: [097][3200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.244 (3.236) Prec@1 68.75 (69.44) Prec@5 85.94 (87.84) + train[2018-10-16-14:33:11] Epoch: [097][3400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.093 (3.235) Prec@1 69.53 (69.44) Prec@5 87.50 (87.85) + train[2018-10-16-14:34:56] Epoch: [097][3600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.940 (3.236) Prec@1 78.12 (69.43) Prec@5 92.19 (87.83) + train[2018-10-16-14:36:42] Epoch: [097][3800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.014 (3.237) Prec@1 77.34 (69.42) Prec@5 86.72 (87.82) + train[2018-10-16-14:38:27] Epoch: [097][4000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.271 (3.237) Prec@1 69.53 (69.42) Prec@5 85.94 (87.82) + train[2018-10-16-14:40:11] Epoch: [097][4200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.129 (3.238) Prec@1 70.31 (69.41) Prec@5 88.28 (87.82) + train[2018-10-16-14:41:56] Epoch: [097][4400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.410 (3.237) Prec@1 64.06 (69.41) Prec@5 89.84 (87.83) + train[2018-10-16-14:43:40] Epoch: [097][4600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.413 (3.238) Prec@1 64.84 (69.41) Prec@5 85.94 (87.82) + train[2018-10-16-14:45:25] Epoch: [097][4800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.136 (3.238) Prec@1 71.88 (69.42) Prec@5 87.50 (87.81) + train[2018-10-16-14:47:09] Epoch: [097][5000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.282 (3.238) Prec@1 71.09 (69.41) Prec@5 87.50 (87.81) + train[2018-10-16-14:48:53] Epoch: [097][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.208 (3.238) Prec@1 68.75 (69.41) Prec@5 85.94 (87.82) + train[2018-10-16-14:50:37] Epoch: [097][5400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.246 (3.239) Prec@1 73.44 (69.39) Prec@5 85.16 (87.81) + train[2018-10-16-14:52:21] Epoch: [097][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.110 (3.239) Prec@1 73.44 (69.39) Prec@5 89.84 (87.80) + train[2018-10-16-14:54:06] Epoch: [097][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.571 (3.240) Prec@1 62.50 (69.38) Prec@5 82.81 (87.79) + train[2018-10-16-14:55:50] Epoch: [097][6000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.133 (3.240) Prec@1 67.97 (69.37) Prec@5 91.41 (87.79) + train[2018-10-16-14:57:34] Epoch: [097][6200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.671 (3.241) Prec@1 64.84 (69.36) Prec@5 84.38 (87.77) + train[2018-10-16-14:59:20] Epoch: [097][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.266 (3.241) Prec@1 66.41 (69.35) Prec@5 84.38 (87.77) + train[2018-10-16-15:01:03] Epoch: [097][6600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.858 (3.242) Prec@1 72.66 (69.32) Prec@5 92.97 (87.76) + train[2018-10-16-15:02:48] Epoch: [097][6800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.128 (3.243) Prec@1 70.31 (69.32) Prec@5 89.06 (87.76) + train[2018-10-16-15:04:32] Epoch: [097][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.232 (3.243) Prec@1 70.31 (69.30) Prec@5 86.72 (87.75) + train[2018-10-16-15:06:17] Epoch: [097][7200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.227 (3.244) Prec@1 69.53 (69.29) Prec@5 84.38 (87.74) + train[2018-10-16-15:08:03] Epoch: [097][7400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.197 (3.243) Prec@1 65.62 (69.28) Prec@5 88.28 (87.75) + train[2018-10-16-15:09:49] Epoch: [097][7600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.084 (3.244) Prec@1 71.09 (69.28) Prec@5 88.28 (87.74) + train[2018-10-16-15:11:34] Epoch: [097][7800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.203 (3.244) Prec@1 70.31 (69.26) Prec@5 85.94 (87.74) + train[2018-10-16-15:13:22] Epoch: [097][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.795 (3.245) Prec@1 65.62 (69.25) Prec@5 80.47 (87.73) + train[2018-10-16-15:15:08] Epoch: [097][8200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.448 (3.246) Prec@1 63.28 (69.24) Prec@5 82.81 (87.72) + train[2018-10-16-15:16:55] Epoch: [097][8400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.990 (3.246) Prec@1 75.78 (69.24) Prec@5 89.06 (87.71) + train[2018-10-16-15:18:42] Epoch: [097][8600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.151 (3.247) Prec@1 66.41 (69.23) Prec@5 90.62 (87.71) + train[2018-10-16-15:20:30] Epoch: [097][8800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.467 (3.247) Prec@1 64.06 (69.23) Prec@5 85.16 (87.71) + train[2018-10-16-15:22:16] Epoch: [097][9000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.365 (3.247) Prec@1 67.19 (69.23) Prec@5 88.28 (87.70) + train[2018-10-16-15:24:02] Epoch: [097][9200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.383 (3.248) Prec@1 66.41 (69.21) Prec@5 87.50 (87.69) + train[2018-10-16-15:25:49] Epoch: [097][9400/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 3.179 (3.248) Prec@1 69.53 (69.21) Prec@5 90.62 (87.69) + train[2018-10-16-15:27:36] Epoch: [097][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.104 (3.249) Prec@1 77.34 (69.20) Prec@5 89.06 (87.69) + train[2018-10-16-15:29:23] Epoch: [097][9800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.372 (3.249) Prec@1 65.62 (69.19) Prec@5 86.72 (87.68) + train[2018-10-16-15:31:09] Epoch: [097][10000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.205 (3.250) Prec@1 67.19 (69.18) Prec@5 88.28 (87.68) + train[2018-10-16-15:31:14] Epoch: [097][10009/10010] Time 0.21 (0.53) Data 0.00 (0.00) Loss 3.447 (3.250) Prec@1 66.67 (69.18) Prec@5 86.67 (87.68) +[2018-10-16-15:31:14] **train** Prec@1 69.18 Prec@5 87.68 Error@1 30.82 Error@5 12.32 Loss:3.250 + test [2018-10-16-15:31:18] Epoch: [097][000/391] Time 4.28 (4.28) Data 4.12 (4.12) Loss 0.677 (0.677) Prec@1 87.50 (87.50) Prec@5 94.53 (94.53) + test [2018-10-16-15:31:44] Epoch: [097][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.373 (1.095) Prec@1 65.62 (74.39) Prec@5 89.84 (92.41) + test [2018-10-16-15:32:09] Epoch: [097][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.119 (1.264) Prec@1 40.00 (70.86) Prec@5 81.25 (90.05) +[2018-10-16-15:32:09] **test** Prec@1 70.86 Prec@5 90.05 Error@1 29.14 Error@5 9.95 Loss:1.264 +----> Best Accuracy : Acc@1=71.16, Acc@5=90.12, Error@1=28.84, Error@5=9.88 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-16-15:32:10] [Epoch=098/250] [Need: 224:27:21] LR=0.0051 ~ 0.0051, Batch=128 + train[2018-10-16-15:32:14] Epoch: [098][000/10010] Time 4.21 (4.21) Data 3.63 (3.63) Loss 3.252 (3.252) Prec@1 71.09 (71.09) Prec@5 88.28 (88.28) + train[2018-10-16-15:33:58] Epoch: [098][200/10010] Time 0.51 (0.54) Data 0.00 (0.02) Loss 3.129 (3.222) Prec@1 72.66 (69.86) Prec@5 90.62 (88.09) + train[2018-10-16-15:35:42] Epoch: [098][400/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.750 (3.234) Prec@1 78.91 (69.61) Prec@5 92.19 (87.90) + train[2018-10-16-15:37:26] Epoch: [098][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.398 (3.232) Prec@1 65.62 (69.54) Prec@5 85.94 (87.93) + train[2018-10-16-15:39:10] Epoch: [098][800/10010] Time 0.55 (0.52) Data 0.00 (0.01) Loss 3.115 (3.233) Prec@1 74.22 (69.58) Prec@5 91.41 (87.90) + train[2018-10-16-15:40:54] Epoch: [098][1000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.402 (3.229) Prec@1 69.53 (69.67) Prec@5 85.16 (88.01) + train[2018-10-16-15:42:38] Epoch: [098][1200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.983 (3.235) Prec@1 71.88 (69.53) Prec@5 93.75 (87.94) + train[2018-10-16-15:44:23] Epoch: [098][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.205 (3.232) Prec@1 70.31 (69.53) Prec@5 89.06 (87.98) + train[2018-10-16-15:46:08] Epoch: [098][1600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.114 (3.232) Prec@1 70.31 (69.56) Prec@5 87.50 (87.98) + train[2018-10-16-15:47:52] Epoch: [098][1800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.068 (3.229) Prec@1 69.53 (69.60) Prec@5 89.06 (87.98) + train[2018-10-16-15:49:36] Epoch: [098][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.440 (3.229) Prec@1 61.72 (69.58) Prec@5 90.62 (87.98) + train[2018-10-16-15:51:20] Epoch: [098][2200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.153 (3.231) Prec@1 70.31 (69.56) Prec@5 86.72 (87.96) + train[2018-10-16-15:53:04] Epoch: [098][2400/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.102 (3.231) Prec@1 68.75 (69.55) Prec@5 91.41 (87.95) + train[2018-10-16-15:54:49] Epoch: [098][2600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.463 (3.230) Prec@1 65.62 (69.54) Prec@5 84.38 (87.96) + train[2018-10-16-15:56:32] Epoch: [098][2800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.380 (3.232) Prec@1 65.62 (69.52) Prec@5 86.72 (87.93) + train[2018-10-16-15:58:17] Epoch: [098][3000/10010] Time 0.59 (0.52) Data 0.00 (0.00) Loss 3.138 (3.232) Prec@1 71.88 (69.51) Prec@5 89.84 (87.93) + train[2018-10-16-16:00:03] Epoch: [098][3200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.364 (3.234) Prec@1 65.62 (69.49) Prec@5 88.28 (87.91) + train[2018-10-16-16:01:50] Epoch: [098][3400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.076 (3.235) Prec@1 71.88 (69.48) Prec@5 91.41 (87.91) + train[2018-10-16-16:03:35] Epoch: [098][3600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.363 (3.237) Prec@1 62.50 (69.44) Prec@5 87.50 (87.88) + train[2018-10-16-16:05:21] Epoch: [098][3800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.206 (3.237) Prec@1 70.31 (69.43) Prec@5 89.84 (87.88) + train[2018-10-16-16:07:09] Epoch: [098][4000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.471 (3.237) Prec@1 60.94 (69.43) Prec@5 85.16 (87.89) + train[2018-10-16-16:08:56] Epoch: [098][4200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.154 (3.235) Prec@1 71.88 (69.43) Prec@5 91.41 (87.92) + train[2018-10-16-16:10:42] Epoch: [098][4400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.437 (3.236) Prec@1 69.53 (69.42) Prec@5 84.38 (87.91) + train[2018-10-16-16:12:29] Epoch: [098][4600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.231 (3.236) Prec@1 69.53 (69.41) Prec@5 87.50 (87.91) + train[2018-10-16-16:14:15] Epoch: [098][4800/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.135 (3.236) Prec@1 72.66 (69.41) Prec@5 87.50 (87.90) + train[2018-10-16-16:16:01] Epoch: [098][5000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.328 (3.237) Prec@1 67.19 (69.40) Prec@5 88.28 (87.89) + train[2018-10-16-16:17:48] Epoch: [098][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.364 (3.237) Prec@1 67.97 (69.39) Prec@5 81.25 (87.89) + train[2018-10-16-16:19:35] Epoch: [098][5400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.214 (3.236) Prec@1 71.88 (69.39) Prec@5 86.72 (87.89) + train[2018-10-16-16:21:22] Epoch: [098][5600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.288 (3.237) Prec@1 68.75 (69.39) Prec@5 85.94 (87.88) + train[2018-10-16-16:23:08] Epoch: [098][5800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.354 (3.237) Prec@1 61.72 (69.38) Prec@5 88.28 (87.88) + train[2018-10-16-16:24:55] Epoch: [098][6000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.236 (3.236) Prec@1 66.41 (69.39) Prec@5 88.28 (87.88) + train[2018-10-16-16:26:43] Epoch: [098][6200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.150 (3.237) Prec@1 74.22 (69.37) Prec@5 89.84 (87.88) + train[2018-10-16-16:28:29] Epoch: [098][6400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.258 (3.238) Prec@1 66.41 (69.36) Prec@5 85.94 (87.87) + train[2018-10-16-16:30:15] Epoch: [098][6600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.278 (3.238) Prec@1 66.41 (69.37) Prec@5 89.84 (87.87) + train[2018-10-16-16:32:01] Epoch: [098][6800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.489 (3.238) Prec@1 64.84 (69.36) Prec@5 84.38 (87.86) + train[2018-10-16-16:33:46] Epoch: [098][7000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.416 (3.238) Prec@1 63.28 (69.34) Prec@5 85.94 (87.85) + train[2018-10-16-16:35:33] Epoch: [098][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.584 (3.238) Prec@1 60.16 (69.35) Prec@5 83.59 (87.85) + train[2018-10-16-16:37:19] Epoch: [098][7400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.541 (3.238) Prec@1 59.38 (69.35) Prec@5 84.38 (87.85) + train[2018-10-16-16:39:05] Epoch: [098][7600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.388 (3.239) Prec@1 64.06 (69.35) Prec@5 86.72 (87.85) + train[2018-10-16-16:40:51] Epoch: [098][7800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.163 (3.239) Prec@1 67.97 (69.35) Prec@5 89.06 (87.84) + train[2018-10-16-16:42:37] Epoch: [098][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.429 (3.239) Prec@1 63.28 (69.34) Prec@5 85.16 (87.84) + train[2018-10-16-16:44:23] Epoch: [098][8200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.140 (3.239) Prec@1 69.53 (69.32) Prec@5 92.19 (87.83) + train[2018-10-16-16:46:08] Epoch: [098][8400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.231 (3.240) Prec@1 65.62 (69.31) Prec@5 91.41 (87.82) + train[2018-10-16-16:47:55] Epoch: [098][8600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.840 (3.241) Prec@1 74.22 (69.30) Prec@5 90.62 (87.82) + train[2018-10-16-16:49:42] Epoch: [098][8800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.367 (3.240) Prec@1 71.09 (69.31) Prec@5 86.72 (87.82) + train[2018-10-16-16:51:29] Epoch: [098][9000/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 3.487 (3.240) Prec@1 64.06 (69.31) Prec@5 84.38 (87.82) + train[2018-10-16-16:53:15] Epoch: [098][9200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.389 (3.241) Prec@1 67.97 (69.30) Prec@5 84.38 (87.81) + train[2018-10-16-16:55:01] Epoch: [098][9400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.294 (3.242) Prec@1 64.06 (69.28) Prec@5 89.84 (87.80) + train[2018-10-16-16:56:48] Epoch: [098][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.184 (3.242) Prec@1 71.09 (69.28) Prec@5 90.62 (87.79) + train[2018-10-16-16:58:35] Epoch: [098][9800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.271 (3.243) Prec@1 68.75 (69.27) Prec@5 86.72 (87.78) + train[2018-10-16-17:00:21] Epoch: [098][10000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.282 (3.244) Prec@1 70.31 (69.25) Prec@5 85.16 (87.77) + train[2018-10-16-17:00:25] Epoch: [098][10009/10010] Time 0.21 (0.53) Data 0.00 (0.00) Loss 4.902 (3.244) Prec@1 40.00 (69.25) Prec@5 60.00 (87.77) +[2018-10-16-17:00:25] **train** Prec@1 69.25 Prec@5 87.77 Error@1 30.75 Error@5 12.23 Loss:3.244 + test [2018-10-16-17:00:29] Epoch: [098][000/391] Time 3.96 (3.96) Data 3.80 (3.80) Loss 0.647 (0.647) Prec@1 89.06 (89.06) Prec@5 95.31 (95.31) + test [2018-10-16-17:00:57] Epoch: [098][200/391] Time 0.14 (0.16) Data 0.00 (0.02) Loss 1.409 (1.106) Prec@1 61.72 (74.83) Prec@5 90.62 (92.53) + test [2018-10-16-17:01:21] Epoch: [098][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.359 (1.273) Prec@1 41.25 (71.24) Prec@5 78.75 (90.16) +[2018-10-16-17:01:21] **test** Prec@1 71.24 Prec@5 90.16 Error@1 28.76 Error@5 9.84 Loss:1.273 +----> Best Accuracy : Acc@1=71.24, Acc@5=90.16, Error@1=28.76, Error@5=9.84 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-16-17:01:21] [Epoch=099/250] [Need: 224:28:26] LR=0.0049 ~ 0.0049, Batch=128 + train[2018-10-16-17:01:26] Epoch: [099][000/10010] Time 4.48 (4.48) Data 3.90 (3.90) Loss 3.376 (3.376) Prec@1 67.19 (67.19) Prec@5 87.50 (87.50) + train[2018-10-16-17:03:10] Epoch: [099][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 3.479 (3.206) Prec@1 67.19 (70.15) Prec@5 84.38 (88.17) + train[2018-10-16-17:04:54] Epoch: [099][400/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 2.865 (3.195) Prec@1 78.91 (70.37) Prec@5 90.62 (88.35) + train[2018-10-16-17:06:39] Epoch: [099][600/10010] Time 0.58 (0.53) Data 0.00 (0.01) Loss 3.154 (3.197) Prec@1 74.22 (70.36) Prec@5 89.06 (88.35) + train[2018-10-16-17:08:22] Epoch: [099][800/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.078 (3.203) Prec@1 68.75 (70.23) Prec@5 92.97 (88.26) + train[2018-10-16-17:10:06] Epoch: [099][1000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.066 (3.207) Prec@1 73.44 (70.10) Prec@5 87.50 (88.23) + train[2018-10-16-17:11:51] Epoch: [099][1200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.254 (3.210) Prec@1 71.88 (70.04) Prec@5 86.72 (88.18) + train[2018-10-16-17:13:36] Epoch: [099][1400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.211 (3.214) Prec@1 67.19 (69.91) Prec@5 89.06 (88.15) + train[2018-10-16-17:15:20] Epoch: [099][1600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.395 (3.215) Prec@1 67.97 (69.84) Prec@5 85.16 (88.15) + train[2018-10-16-17:17:04] Epoch: [099][1800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.198 (3.217) Prec@1 72.66 (69.80) Prec@5 86.72 (88.11) + train[2018-10-16-17:18:48] Epoch: [099][2000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.358 (3.219) Prec@1 60.94 (69.73) Prec@5 88.28 (88.10) + train[2018-10-16-17:20:33] Epoch: [099][2200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.001 (3.221) Prec@1 71.88 (69.71) Prec@5 93.75 (88.08) + train[2018-10-16-17:22:18] Epoch: [099][2400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.093 (3.220) Prec@1 71.09 (69.70) Prec@5 91.41 (88.07) + train[2018-10-16-17:24:02] Epoch: [099][2600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.201 (3.220) Prec@1 70.31 (69.71) Prec@5 89.06 (88.07) + train[2018-10-16-17:25:47] Epoch: [099][2800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.203 (3.220) Prec@1 70.31 (69.69) Prec@5 87.50 (88.09) + train[2018-10-16-17:27:32] Epoch: [099][3000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.930 (3.221) Prec@1 75.00 (69.67) Prec@5 89.84 (88.06) + train[2018-10-16-17:29:16] Epoch: [099][3200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.383 (3.223) Prec@1 61.72 (69.62) Prec@5 87.50 (88.03) + train[2018-10-16-17:31:00] Epoch: [099][3400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.145 (3.223) Prec@1 71.88 (69.61) Prec@5 92.19 (88.05) + train[2018-10-16-17:32:45] Epoch: [099][3600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.433 (3.225) Prec@1 67.97 (69.58) Prec@5 83.59 (88.02) + train[2018-10-16-17:34:30] Epoch: [099][3800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.078 (3.225) Prec@1 72.66 (69.58) Prec@5 89.84 (88.01) + train[2018-10-16-17:36:15] Epoch: [099][4000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.360 (3.226) Prec@1 69.53 (69.57) Prec@5 82.03 (87.99) + train[2018-10-16-17:38:00] Epoch: [099][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.320 (3.227) Prec@1 64.06 (69.57) Prec@5 89.84 (87.98) + train[2018-10-16-17:39:45] Epoch: [099][4400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 2.898 (3.227) Prec@1 75.00 (69.58) Prec@5 90.62 (87.98) + train[2018-10-16-17:41:31] Epoch: [099][4600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.290 (3.227) Prec@1 67.19 (69.56) Prec@5 85.16 (87.96) + train[2018-10-16-17:43:16] Epoch: [099][4800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.313 (3.227) Prec@1 69.53 (69.57) Prec@5 85.16 (87.96) + train[2018-10-16-17:45:01] Epoch: [099][5000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.499 (3.228) Prec@1 67.97 (69.55) Prec@5 85.16 (87.94) + train[2018-10-16-17:46:47] Epoch: [099][5200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.244 (3.228) Prec@1 73.44 (69.56) Prec@5 90.62 (87.94) + train[2018-10-16-17:48:34] Epoch: [099][5400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.565 (3.229) Prec@1 68.75 (69.55) Prec@5 82.81 (87.92) + train[2018-10-16-17:50:21] Epoch: [099][5600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.882 (3.230) Prec@1 78.12 (69.53) Prec@5 92.19 (87.91) + train[2018-10-16-17:52:07] Epoch: [099][5800/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 2.886 (3.229) Prec@1 73.44 (69.53) Prec@5 92.19 (87.91) + train[2018-10-16-17:53:54] Epoch: [099][6000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.026 (3.230) Prec@1 73.44 (69.52) Prec@5 92.19 (87.90) + train[2018-10-16-17:55:40] Epoch: [099][6200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.070 (3.230) Prec@1 75.00 (69.52) Prec@5 89.06 (87.90) + train[2018-10-16-17:57:26] Epoch: [099][6400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.557 (3.231) Prec@1 64.06 (69.50) Prec@5 85.16 (87.90) + train[2018-10-16-17:59:13] Epoch: [099][6600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.126 (3.231) Prec@1 71.88 (69.49) Prec@5 89.06 (87.89) + train[2018-10-16-18:01:00] Epoch: [099][6800/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.448 (3.232) Prec@1 69.53 (69.48) Prec@5 84.38 (87.88) + train[2018-10-16-18:02:46] Epoch: [099][7000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.353 (3.232) Prec@1 70.31 (69.47) Prec@5 83.59 (87.87) + train[2018-10-16-18:04:32] Epoch: [099][7200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.652 (3.232) Prec@1 62.50 (69.47) Prec@5 83.59 (87.88) + train[2018-10-16-18:06:16] Epoch: [099][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.364 (3.232) Prec@1 66.41 (69.47) Prec@5 86.72 (87.87) + train[2018-10-16-18:08:02] Epoch: [099][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.455 (3.231) Prec@1 70.31 (69.48) Prec@5 82.03 (87.87) + train[2018-10-16-18:09:48] Epoch: [099][7800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.440 (3.231) Prec@1 66.41 (69.48) Prec@5 84.38 (87.87) + train[2018-10-16-18:11:33] Epoch: [099][8000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.413 (3.232) Prec@1 70.31 (69.47) Prec@5 85.16 (87.86) + train[2018-10-16-18:13:18] Epoch: [099][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.964 (3.232) Prec@1 76.56 (69.47) Prec@5 90.62 (87.86) + train[2018-10-16-18:15:04] Epoch: [099][8400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.061 (3.232) Prec@1 74.22 (69.47) Prec@5 90.62 (87.86) + train[2018-10-16-18:16:50] Epoch: [099][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.122 (3.232) Prec@1 70.31 (69.49) Prec@5 89.84 (87.87) + train[2018-10-16-18:18:36] Epoch: [099][8800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.336 (3.232) Prec@1 66.41 (69.49) Prec@5 85.94 (87.86) + train[2018-10-16-18:20:22] Epoch: [099][9000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.455 (3.232) Prec@1 60.94 (69.49) Prec@5 87.50 (87.85) + train[2018-10-16-18:22:08] Epoch: [099][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.385 (3.232) Prec@1 66.41 (69.49) Prec@5 83.59 (87.86) + train[2018-10-16-18:23:54] Epoch: [099][9400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.254 (3.233) Prec@1 71.09 (69.48) Prec@5 87.50 (87.86) + train[2018-10-16-18:25:40] Epoch: [099][9600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.107 (3.233) Prec@1 73.44 (69.48) Prec@5 88.28 (87.85) + train[2018-10-16-18:27:25] Epoch: [099][9800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.039 (3.233) Prec@1 73.44 (69.48) Prec@5 90.62 (87.85) + train[2018-10-16-18:29:12] Epoch: [099][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.923 (3.233) Prec@1 71.88 (69.48) Prec@5 94.53 (87.85) + train[2018-10-16-18:29:16] Epoch: [099][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 4.608 (3.233) Prec@1 46.67 (69.48) Prec@5 73.33 (87.85) +[2018-10-16-18:29:16] **train** Prec@1 69.48 Prec@5 87.85 Error@1 30.52 Error@5 12.15 Loss:3.233 + test [2018-10-16-18:29:20] Epoch: [099][000/391] Time 3.88 (3.88) Data 3.75 (3.75) Loss 0.699 (0.699) Prec@1 89.06 (89.06) Prec@5 96.88 (96.88) + test [2018-10-16-18:29:47] Epoch: [099][200/391] Time 0.13 (0.15) Data 0.01 (0.02) Loss 1.187 (1.098) Prec@1 72.66 (74.93) Prec@5 92.19 (92.68) + test [2018-10-16-18:30:12] Epoch: [099][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.473 (1.277) Prec@1 43.75 (71.31) Prec@5 80.00 (90.13) +[2018-10-16-18:30:12] **test** Prec@1 71.31 Prec@5 90.13 Error@1 28.69 Error@5 9.87 Loss:1.277 +----> Best Accuracy : Acc@1=71.31, Acc@5=90.13, Error@1=28.69, Error@5=9.87 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-16-18:30:12] [Epoch=100/250] [Need: 222:06:13] LR=0.0048 ~ 0.0048, Batch=128 + train[2018-10-16-18:30:16] Epoch: [100][000/10010] Time 4.37 (4.37) Data 3.80 (3.80) Loss 3.003 (3.003) Prec@1 77.34 (77.34) Prec@5 90.62 (90.62) + train[2018-10-16-18:32:01] Epoch: [100][200/10010] Time 0.54 (0.54) Data 0.00 (0.02) Loss 3.104 (3.186) Prec@1 75.78 (70.39) Prec@5 88.28 (88.26) + train[2018-10-16-18:33:45] Epoch: [100][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.857 (3.194) Prec@1 76.56 (70.26) Prec@5 92.19 (88.23) + train[2018-10-16-18:35:29] Epoch: [100][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.051 (3.197) Prec@1 75.00 (70.22) Prec@5 85.94 (88.18) + train[2018-10-16-18:37:13] Epoch: [100][800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.379 (3.202) Prec@1 66.41 (70.08) Prec@5 83.59 (88.20) + train[2018-10-16-18:38:58] Epoch: [100][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.090 (3.205) Prec@1 72.66 (70.06) Prec@5 91.41 (88.18) + train[2018-10-16-18:40:41] Epoch: [100][1200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.068 (3.210) Prec@1 75.78 (69.99) Prec@5 89.06 (88.11) + train[2018-10-16-18:42:24] Epoch: [100][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.282 (3.209) Prec@1 66.41 (70.01) Prec@5 87.50 (88.14) + train[2018-10-16-18:44:09] Epoch: [100][1600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.173 (3.208) Prec@1 68.75 (70.07) Prec@5 90.62 (88.16) + train[2018-10-16-18:45:53] Epoch: [100][1800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.013 (3.208) Prec@1 74.22 (70.06) Prec@5 91.41 (88.15) + train[2018-10-16-18:47:37] Epoch: [100][2000/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 2.961 (3.211) Prec@1 75.78 (70.02) Prec@5 89.84 (88.14) + train[2018-10-16-18:49:22] Epoch: [100][2200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.928 (3.210) Prec@1 72.66 (70.00) Prec@5 89.06 (88.15) + train[2018-10-16-18:51:06] Epoch: [100][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.402 (3.209) Prec@1 67.97 (70.02) Prec@5 86.72 (88.17) + train[2018-10-16-18:52:52] Epoch: [100][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.155 (3.210) Prec@1 69.53 (69.98) Prec@5 87.50 (88.15) + train[2018-10-16-18:54:37] Epoch: [100][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.542 (3.210) Prec@1 66.41 (69.96) Prec@5 84.38 (88.15) + train[2018-10-16-18:56:22] Epoch: [100][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.959 (3.209) Prec@1 73.44 (69.98) Prec@5 89.84 (88.15) + train[2018-10-16-18:58:06] Epoch: [100][3200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.231 (3.212) Prec@1 71.88 (69.94) Prec@5 87.50 (88.11) + train[2018-10-16-18:59:50] Epoch: [100][3400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.043 (3.212) Prec@1 71.88 (69.91) Prec@5 90.62 (88.11) + train[2018-10-16-19:01:34] Epoch: [100][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.482 (3.213) Prec@1 66.41 (69.89) Prec@5 81.25 (88.10) + train[2018-10-16-19:03:19] Epoch: [100][3800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.855 (3.214) Prec@1 73.44 (69.86) Prec@5 92.19 (88.09) + train[2018-10-16-19:05:04] Epoch: [100][4000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.932 (3.215) Prec@1 75.00 (69.85) Prec@5 92.19 (88.09) + train[2018-10-16-19:06:50] Epoch: [100][4200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.624 (3.216) Prec@1 62.50 (69.83) Prec@5 85.16 (88.06) + train[2018-10-16-19:08:35] Epoch: [100][4400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.795 (3.216) Prec@1 63.28 (69.84) Prec@5 82.03 (88.05) + train[2018-10-16-19:10:20] Epoch: [100][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.309 (3.217) Prec@1 68.75 (69.83) Prec@5 85.94 (88.06) + train[2018-10-16-19:12:05] Epoch: [100][4800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.486 (3.217) Prec@1 66.41 (69.84) Prec@5 82.81 (88.05) + train[2018-10-16-19:13:51] Epoch: [100][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.155 (3.218) Prec@1 67.97 (69.83) Prec@5 90.62 (88.03) + train[2018-10-16-19:15:37] Epoch: [100][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.002 (3.219) Prec@1 74.22 (69.82) Prec@5 87.50 (88.02) + train[2018-10-16-19:17:23] Epoch: [100][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.133 (3.220) Prec@1 73.44 (69.81) Prec@5 87.50 (88.01) + train[2018-10-16-19:19:09] Epoch: [100][5600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.479 (3.220) Prec@1 60.94 (69.80) Prec@5 85.16 (87.99) + train[2018-10-16-19:20:55] Epoch: [100][5800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.215 (3.221) Prec@1 71.88 (69.79) Prec@5 89.84 (87.99) + train[2018-10-16-19:22:41] Epoch: [100][6000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.329 (3.222) Prec@1 67.19 (69.76) Prec@5 87.50 (87.97) + train[2018-10-16-19:24:28] Epoch: [100][6200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.032 (3.222) Prec@1 74.22 (69.76) Prec@5 88.28 (87.98) + train[2018-10-16-19:26:13] Epoch: [100][6400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.032 (3.222) Prec@1 72.66 (69.77) Prec@5 89.84 (87.98) + train[2018-10-16-19:27:59] Epoch: [100][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.212 (3.223) Prec@1 69.53 (69.74) Prec@5 92.97 (87.96) + train[2018-10-16-19:29:46] Epoch: [100][6800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.320 (3.224) Prec@1 65.62 (69.72) Prec@5 85.94 (87.95) + train[2018-10-16-19:31:31] Epoch: [100][7000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.464 (3.225) Prec@1 63.28 (69.71) Prec@5 86.72 (87.95) + train[2018-10-16-19:33:18] Epoch: [100][7200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.462 (3.225) Prec@1 66.41 (69.70) Prec@5 82.81 (87.94) + train[2018-10-16-19:35:03] Epoch: [100][7400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.970 (3.225) Prec@1 74.22 (69.69) Prec@5 88.28 (87.94) + train[2018-10-16-19:36:49] Epoch: [100][7600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.738 (3.226) Prec@1 61.72 (69.69) Prec@5 82.03 (87.93) + train[2018-10-16-19:38:34] Epoch: [100][7800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.231 (3.225) Prec@1 71.88 (69.69) Prec@5 90.62 (87.93) + train[2018-10-16-19:40:20] Epoch: [100][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.464 (3.226) Prec@1 66.41 (69.68) Prec@5 83.59 (87.93) + train[2018-10-16-19:42:05] Epoch: [100][8200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.167 (3.226) Prec@1 70.31 (69.67) Prec@5 91.41 (87.92) + train[2018-10-16-19:43:51] Epoch: [100][8400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.224 (3.226) Prec@1 68.75 (69.67) Prec@5 85.94 (87.92) + train[2018-10-16-19:45:36] Epoch: [100][8600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.151 (3.227) Prec@1 71.09 (69.66) Prec@5 88.28 (87.91) + train[2018-10-16-19:47:21] Epoch: [100][8800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.185 (3.227) Prec@1 71.09 (69.65) Prec@5 89.06 (87.90) + train[2018-10-16-19:49:07] Epoch: [100][9000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.162 (3.228) Prec@1 70.31 (69.64) Prec@5 88.28 (87.90) + train[2018-10-16-19:50:53] Epoch: [100][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.123 (3.228) Prec@1 71.09 (69.64) Prec@5 89.84 (87.90) + train[2018-10-16-19:52:38] Epoch: [100][9400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.944 (3.228) Prec@1 72.66 (69.64) Prec@5 92.97 (87.91) + train[2018-10-16-19:54:24] Epoch: [100][9600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.426 (3.228) Prec@1 65.62 (69.63) Prec@5 84.38 (87.90) + train[2018-10-16-19:56:10] Epoch: [100][9800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.957 (3.228) Prec@1 76.56 (69.63) Prec@5 92.97 (87.89) + train[2018-10-16-19:57:56] Epoch: [100][10000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.023 (3.228) Prec@1 71.09 (69.62) Prec@5 89.84 (87.90) + train[2018-10-16-19:58:00] Epoch: [100][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 4.207 (3.228) Prec@1 53.33 (69.62) Prec@5 73.33 (87.89) +[2018-10-16-19:58:00] **train** Prec@1 69.62 Prec@5 87.89 Error@1 30.38 Error@5 12.11 Loss:3.228 + test [2018-10-16-19:58:04] Epoch: [100][000/391] Time 3.89 (3.89) Data 3.76 (3.76) Loss 0.729 (0.729) Prec@1 85.94 (85.94) Prec@5 97.66 (97.66) + test [2018-10-16-19:58:30] Epoch: [100][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.261 (1.092) Prec@1 66.41 (74.63) Prec@5 92.19 (92.58) + test [2018-10-16-19:58:55] Epoch: [100][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.360 (1.258) Prec@1 41.25 (71.05) Prec@5 78.75 (90.22) +[2018-10-16-19:58:55] **test** Prec@1 71.05 Prec@5 90.22 Error@1 28.95 Error@5 9.78 Loss:1.258 +----> Best Accuracy : Acc@1=71.31, Acc@5=90.13, Error@1=28.69, Error@5=9.87 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-16-19:58:56] [Epoch=101/250] [Need: 220:21:01] LR=0.0046 ~ 0.0046, Batch=128 + train[2018-10-16-19:59:01] Epoch: [101][000/10010] Time 5.55 (5.55) Data 4.99 (4.99) Loss 3.537 (3.537) Prec@1 65.62 (65.62) Prec@5 82.03 (82.03) + train[2018-10-16-20:00:45] Epoch: [101][200/10010] Time 0.53 (0.54) Data 0.00 (0.02) Loss 3.356 (3.192) Prec@1 66.41 (70.28) Prec@5 86.72 (88.32) + train[2018-10-16-20:02:29] Epoch: [101][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.823 (3.194) Prec@1 72.66 (70.32) Prec@5 92.97 (88.28) + train[2018-10-16-20:04:13] Epoch: [101][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 2.956 (3.191) Prec@1 75.00 (70.34) Prec@5 91.41 (88.33) + train[2018-10-16-20:05:56] Epoch: [101][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.048 (3.194) Prec@1 71.09 (70.25) Prec@5 92.19 (88.34) + train[2018-10-16-20:07:40] Epoch: [101][1000/10010] Time 0.52 (0.52) Data 0.00 (0.01) Loss 3.142 (3.194) Prec@1 64.06 (70.24) Prec@5 91.41 (88.31) + train[2018-10-16-20:09:24] Epoch: [101][1200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.795 (3.192) Prec@1 78.12 (70.30) Prec@5 90.62 (88.35) + train[2018-10-16-20:11:08] Epoch: [101][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.126 (3.196) Prec@1 68.75 (70.23) Prec@5 91.41 (88.32) + train[2018-10-16-20:12:52] Epoch: [101][1600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 2.990 (3.200) Prec@1 70.31 (70.15) Prec@5 92.97 (88.29) + train[2018-10-16-20:14:36] Epoch: [101][1800/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.454 (3.200) Prec@1 62.50 (70.13) Prec@5 85.16 (88.30) + train[2018-10-16-20:16:21] Epoch: [101][2000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.271 (3.200) Prec@1 67.97 (70.11) Prec@5 85.16 (88.29) + train[2018-10-16-20:18:05] Epoch: [101][2200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.117 (3.201) Prec@1 71.88 (70.08) Prec@5 89.84 (88.27) + train[2018-10-16-20:19:49] Epoch: [101][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.910 (3.202) Prec@1 76.56 (70.03) Prec@5 92.19 (88.26) + train[2018-10-16-20:21:34] Epoch: [101][2600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.240 (3.203) Prec@1 69.53 (70.03) Prec@5 86.72 (88.25) + train[2018-10-16-20:23:18] Epoch: [101][2800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.042 (3.205) Prec@1 74.22 (69.98) Prec@5 87.50 (88.23) + train[2018-10-16-20:25:03] Epoch: [101][3000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.437 (3.206) Prec@1 67.97 (69.96) Prec@5 85.94 (88.22) + train[2018-10-16-20:26:48] Epoch: [101][3200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.131 (3.206) Prec@1 74.22 (69.95) Prec@5 86.72 (88.20) + train[2018-10-16-20:28:33] Epoch: [101][3400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.300 (3.206) Prec@1 65.62 (69.95) Prec@5 84.38 (88.19) + train[2018-10-16-20:30:17] Epoch: [101][3600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.345 (3.207) Prec@1 61.72 (69.95) Prec@5 86.72 (88.20) + train[2018-10-16-20:32:02] Epoch: [101][3800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.122 (3.207) Prec@1 72.66 (69.96) Prec@5 90.62 (88.18) + train[2018-10-16-20:33:46] Epoch: [101][4000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.189 (3.207) Prec@1 71.09 (69.97) Prec@5 89.06 (88.18) + train[2018-10-16-20:35:32] Epoch: [101][4200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.427 (3.207) Prec@1 67.97 (69.97) Prec@5 85.94 (88.17) + train[2018-10-16-20:37:17] Epoch: [101][4400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.196 (3.207) Prec@1 72.66 (69.95) Prec@5 87.50 (88.17) + train[2018-10-16-20:39:03] Epoch: [101][4600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.908 (3.206) Prec@1 74.22 (69.96) Prec@5 91.41 (88.17) + train[2018-10-16-20:40:49] Epoch: [101][4800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.194 (3.207) Prec@1 71.88 (69.95) Prec@5 87.50 (88.16) + train[2018-10-16-20:42:34] Epoch: [101][5000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.245 (3.208) Prec@1 71.09 (69.95) Prec@5 89.06 (88.15) + train[2018-10-16-20:44:20] Epoch: [101][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.175 (3.209) Prec@1 69.53 (69.92) Prec@5 88.28 (88.14) + train[2018-10-16-20:46:06] Epoch: [101][5400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.276 (3.209) Prec@1 70.31 (69.92) Prec@5 89.84 (88.14) + train[2018-10-16-20:47:52] Epoch: [101][5600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.217 (3.209) Prec@1 75.00 (69.92) Prec@5 89.84 (88.13) + train[2018-10-16-20:49:38] Epoch: [101][5800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.038 (3.209) Prec@1 74.22 (69.91) Prec@5 86.72 (88.13) + train[2018-10-16-20:51:24] Epoch: [101][6000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.210 (3.209) Prec@1 71.88 (69.91) Prec@5 89.06 (88.12) + train[2018-10-16-20:53:09] Epoch: [101][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.106 (3.210) Prec@1 70.31 (69.89) Prec@5 88.28 (88.11) + train[2018-10-16-20:54:55] Epoch: [101][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.631 (3.211) Prec@1 64.06 (69.88) Prec@5 83.59 (88.11) + train[2018-10-16-20:56:41] Epoch: [101][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.070 (3.211) Prec@1 71.88 (69.87) Prec@5 90.62 (88.11) + train[2018-10-16-20:58:27] Epoch: [101][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.072 (3.212) Prec@1 66.41 (69.87) Prec@5 90.62 (88.10) + train[2018-10-16-21:00:11] Epoch: [101][7000/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 2.975 (3.212) Prec@1 74.22 (69.87) Prec@5 89.84 (88.09) + train[2018-10-16-21:01:57] Epoch: [101][7200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.349 (3.212) Prec@1 67.97 (69.86) Prec@5 85.94 (88.08) + train[2018-10-16-21:03:41] Epoch: [101][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.348 (3.213) Prec@1 67.97 (69.85) Prec@5 85.16 (88.07) + train[2018-10-16-21:05:28] Epoch: [101][7600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.025 (3.214) Prec@1 74.22 (69.83) Prec@5 88.28 (88.06) + train[2018-10-16-21:07:13] Epoch: [101][7800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.489 (3.214) Prec@1 64.06 (69.82) Prec@5 84.38 (88.05) + train[2018-10-16-21:08:58] Epoch: [101][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.345 (3.215) Prec@1 65.62 (69.81) Prec@5 85.94 (88.05) + train[2018-10-16-21:10:42] Epoch: [101][8200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.957 (3.215) Prec@1 71.88 (69.80) Prec@5 92.97 (88.05) + train[2018-10-16-21:12:28] Epoch: [101][8400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.989 (3.215) Prec@1 75.00 (69.79) Prec@5 89.84 (88.05) + train[2018-10-16-21:14:13] Epoch: [101][8600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.039 (3.216) Prec@1 75.00 (69.79) Prec@5 88.28 (88.04) + train[2018-10-16-21:15:58] Epoch: [101][8800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.282 (3.216) Prec@1 66.41 (69.78) Prec@5 89.06 (88.04) + train[2018-10-16-21:17:43] Epoch: [101][9000/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.248 (3.217) Prec@1 69.53 (69.76) Prec@5 88.28 (88.04) + train[2018-10-16-21:19:29] Epoch: [101][9200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.344 (3.217) Prec@1 69.53 (69.75) Prec@5 86.72 (88.03) + train[2018-10-16-21:21:14] Epoch: [101][9400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.184 (3.217) Prec@1 71.88 (69.75) Prec@5 87.50 (88.03) + train[2018-10-16-21:22:59] Epoch: [101][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.971 (3.218) Prec@1 71.88 (69.74) Prec@5 92.19 (88.03) + train[2018-10-16-21:24:46] Epoch: [101][9800/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.428 (3.218) Prec@1 63.28 (69.74) Prec@5 85.16 (88.03) + train[2018-10-16-21:26:30] Epoch: [101][10000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.528 (3.219) Prec@1 67.97 (69.73) Prec@5 82.03 (88.01) + train[2018-10-16-21:26:35] Epoch: [101][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 3.226 (3.219) Prec@1 66.67 (69.73) Prec@5 100.00 (88.01) +[2018-10-16-21:26:35] **train** Prec@1 69.73 Prec@5 88.01 Error@1 30.27 Error@5 11.99 Loss:3.219 + test [2018-10-16-21:26:38] Epoch: [101][000/391] Time 3.67 (3.67) Data 3.53 (3.53) Loss 0.629 (0.629) Prec@1 84.38 (84.38) Prec@5 98.44 (98.44) + test [2018-10-16-21:27:05] Epoch: [101][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.285 (1.073) Prec@1 68.75 (75.25) Prec@5 91.41 (92.66) + test [2018-10-16-21:27:30] Epoch: [101][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.237 (1.246) Prec@1 47.50 (71.46) Prec@5 77.50 (90.15) +[2018-10-16-21:27:30] **test** Prec@1 71.46 Prec@5 90.15 Error@1 28.54 Error@5 9.85 Loss:1.246 +----> Best Accuracy : Acc@1=71.46, Acc@5=90.15, Error@1=28.54, Error@5=9.85 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-16-21:27:30] [Epoch=102/250] [Need: 218:28:20] LR=0.0045 ~ 0.0045, Batch=128 + train[2018-10-16-21:27:35] Epoch: [102][000/10010] Time 5.06 (5.06) Data 4.40 (4.40) Loss 3.162 (3.162) Prec@1 71.88 (71.88) Prec@5 88.28 (88.28) + train[2018-10-16-21:29:19] Epoch: [102][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 3.236 (3.187) Prec@1 71.09 (70.39) Prec@5 88.28 (88.60) + train[2018-10-16-21:31:03] Epoch: [102][400/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.051 (3.190) Prec@1 72.66 (70.32) Prec@5 92.97 (88.38) + train[2018-10-16-21:32:48] Epoch: [102][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.094 (3.186) Prec@1 75.00 (70.39) Prec@5 85.94 (88.41) + train[2018-10-16-21:34:33] Epoch: [102][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.058 (3.187) Prec@1 75.78 (70.35) Prec@5 88.28 (88.39) + train[2018-10-16-21:36:17] Epoch: [102][1000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.113 (3.189) Prec@1 67.97 (70.34) Prec@5 88.28 (88.34) + train[2018-10-16-21:38:01] Epoch: [102][1200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.331 (3.190) Prec@1 67.19 (70.34) Prec@5 85.94 (88.34) + train[2018-10-16-21:39:46] Epoch: [102][1400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.141 (3.189) Prec@1 68.75 (70.38) Prec@5 90.62 (88.33) + train[2018-10-16-21:41:31] Epoch: [102][1600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.146 (3.188) Prec@1 67.97 (70.36) Prec@5 91.41 (88.38) + train[2018-10-16-21:43:15] Epoch: [102][1800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.069 (3.188) Prec@1 71.09 (70.36) Prec@5 87.50 (88.36) + train[2018-10-16-21:44:59] Epoch: [102][2000/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.299 (3.189) Prec@1 71.09 (70.31) Prec@5 85.94 (88.36) + train[2018-10-16-21:46:44] Epoch: [102][2200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.322 (3.189) Prec@1 67.19 (70.29) Prec@5 88.28 (88.37) + train[2018-10-16-21:48:28] Epoch: [102][2400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.321 (3.191) Prec@1 67.97 (70.24) Prec@5 89.06 (88.33) + train[2018-10-16-21:50:14] Epoch: [102][2600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.327 (3.193) Prec@1 67.97 (70.24) Prec@5 85.16 (88.32) + train[2018-10-16-21:51:59] Epoch: [102][2800/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.299 (3.195) Prec@1 73.44 (70.20) Prec@5 84.38 (88.29) + train[2018-10-16-21:53:43] Epoch: [102][3000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.379 (3.196) Prec@1 61.72 (70.17) Prec@5 89.06 (88.28) + train[2018-10-16-21:55:28] Epoch: [102][3200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.619 (3.195) Prec@1 62.50 (70.18) Prec@5 82.81 (88.29) + train[2018-10-16-21:57:13] Epoch: [102][3400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.096 (3.195) Prec@1 73.44 (70.20) Prec@5 89.06 (88.29) + train[2018-10-16-21:59:00] Epoch: [102][3600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.486 (3.195) Prec@1 65.62 (70.16) Prec@5 84.38 (88.28) + train[2018-10-16-22:00:46] Epoch: [102][3800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.477 (3.196) Prec@1 63.28 (70.17) Prec@5 85.16 (88.28) + train[2018-10-16-22:02:33] Epoch: [102][4000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.236 (3.197) Prec@1 71.88 (70.16) Prec@5 85.94 (88.26) + train[2018-10-16-22:04:20] Epoch: [102][4200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.367 (3.198) Prec@1 63.28 (70.14) Prec@5 89.84 (88.25) + train[2018-10-16-22:06:06] Epoch: [102][4400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.627 (3.198) Prec@1 64.06 (70.14) Prec@5 79.69 (88.25) + train[2018-10-16-22:07:52] Epoch: [102][4600/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.915 (3.198) Prec@1 75.78 (70.13) Prec@5 92.97 (88.26) + train[2018-10-16-22:09:38] Epoch: [102][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.227 (3.199) Prec@1 71.09 (70.12) Prec@5 87.50 (88.24) + train[2018-10-16-22:11:24] Epoch: [102][5000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.128 (3.199) Prec@1 67.19 (70.10) Prec@5 89.84 (88.25) + train[2018-10-16-22:13:10] Epoch: [102][5200/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.120 (3.200) Prec@1 73.44 (70.07) Prec@5 86.72 (88.23) + train[2018-10-16-22:14:56] Epoch: [102][5400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.243 (3.201) Prec@1 67.97 (70.07) Prec@5 89.84 (88.23) + train[2018-10-16-22:16:42] Epoch: [102][5600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.341 (3.201) Prec@1 71.09 (70.06) Prec@5 85.94 (88.22) + train[2018-10-16-22:18:29] Epoch: [102][5800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.407 (3.203) Prec@1 65.62 (70.04) Prec@5 88.28 (88.21) + train[2018-10-16-22:20:15] Epoch: [102][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.496 (3.203) Prec@1 61.72 (70.04) Prec@5 83.59 (88.21) + train[2018-10-16-22:22:00] Epoch: [102][6200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.244 (3.204) Prec@1 72.66 (70.03) Prec@5 85.94 (88.20) + train[2018-10-16-22:23:46] Epoch: [102][6400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.127 (3.205) Prec@1 71.09 (70.00) Prec@5 89.06 (88.19) + train[2018-10-16-22:25:32] Epoch: [102][6600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.160 (3.205) Prec@1 72.66 (69.99) Prec@5 90.62 (88.20) + train[2018-10-16-22:27:18] Epoch: [102][6800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.986 (3.206) Prec@1 75.78 (69.97) Prec@5 91.41 (88.18) + train[2018-10-16-22:29:03] Epoch: [102][7000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.369 (3.205) Prec@1 69.53 (69.98) Prec@5 84.38 (88.19) + train[2018-10-16-22:30:49] Epoch: [102][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.445 (3.206) Prec@1 63.28 (69.98) Prec@5 86.72 (88.19) + train[2018-10-16-22:32:35] Epoch: [102][7400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.107 (3.206) Prec@1 67.97 (69.98) Prec@5 91.41 (88.18) + train[2018-10-16-22:34:21] Epoch: [102][7600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.157 (3.207) Prec@1 70.31 (69.96) Prec@5 86.72 (88.17) + train[2018-10-16-22:36:08] Epoch: [102][7800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.453 (3.206) Prec@1 64.06 (69.97) Prec@5 86.72 (88.17) + train[2018-10-16-22:37:54] Epoch: [102][8000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.202 (3.207) Prec@1 72.66 (69.94) Prec@5 92.19 (88.16) + train[2018-10-16-22:39:41] Epoch: [102][8200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.905 (3.208) Prec@1 71.09 (69.93) Prec@5 91.41 (88.15) + train[2018-10-16-22:41:28] Epoch: [102][8400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.290 (3.208) Prec@1 71.09 (69.92) Prec@5 87.50 (88.15) + train[2018-10-16-22:43:15] Epoch: [102][8600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.295 (3.209) Prec@1 74.22 (69.90) Prec@5 83.59 (88.14) + train[2018-10-16-22:45:00] Epoch: [102][8800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.093 (3.209) Prec@1 68.75 (69.90) Prec@5 89.06 (88.14) + train[2018-10-16-22:46:47] Epoch: [102][9000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.415 (3.209) Prec@1 67.97 (69.90) Prec@5 84.38 (88.13) + train[2018-10-16-22:48:34] Epoch: [102][9200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.604 (3.209) Prec@1 60.94 (69.90) Prec@5 82.03 (88.14) + train[2018-10-16-22:50:20] Epoch: [102][9400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.239 (3.210) Prec@1 67.19 (69.88) Prec@5 85.94 (88.13) + train[2018-10-16-22:52:07] Epoch: [102][9600/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.141 (3.210) Prec@1 72.66 (69.89) Prec@5 86.72 (88.13) + train[2018-10-16-22:53:53] Epoch: [102][9800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.186 (3.210) Prec@1 71.09 (69.88) Prec@5 85.94 (88.13) + train[2018-10-16-22:55:39] Epoch: [102][10000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.487 (3.211) Prec@1 64.06 (69.88) Prec@5 82.03 (88.12) + train[2018-10-16-22:55:43] Epoch: [102][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.663 (3.211) Prec@1 60.00 (69.88) Prec@5 86.67 (88.12) +[2018-10-16-22:55:43] **train** Prec@1 69.88 Prec@5 88.12 Error@1 30.12 Error@5 11.88 Loss:3.211 + test [2018-10-16-22:55:47] Epoch: [102][000/391] Time 3.69 (3.69) Data 3.55 (3.55) Loss 0.768 (0.768) Prec@1 83.59 (83.59) Prec@5 96.88 (96.88) + test [2018-10-16-22:56:14] Epoch: [102][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.366 (1.084) Prec@1 67.19 (74.94) Prec@5 90.62 (92.69) + test [2018-10-16-22:56:38] Epoch: [102][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.226 (1.254) Prec@1 40.00 (71.29) Prec@5 81.25 (90.32) +[2018-10-16-22:56:38] **test** Prec@1 71.29 Prec@5 90.32 Error@1 28.71 Error@5 9.68 Loss:1.254 +----> Best Accuracy : Acc@1=71.46, Acc@5=90.15, Error@1=28.54, Error@5=9.85 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-16-22:56:39] [Epoch=103/250] [Need: 218:24:21] LR=0.0043 ~ 0.0043, Batch=128 + train[2018-10-16-22:56:44] Epoch: [103][000/10010] Time 5.32 (5.32) Data 4.70 (4.70) Loss 3.086 (3.086) Prec@1 75.00 (75.00) Prec@5 88.28 (88.28) + train[2018-10-16-22:58:28] Epoch: [103][200/10010] Time 0.54 (0.55) Data 0.00 (0.02) Loss 3.104 (3.186) Prec@1 71.88 (70.39) Prec@5 86.72 (88.55) + train[2018-10-16-23:00:13] Epoch: [103][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.842 (3.182) Prec@1 75.78 (70.55) Prec@5 89.84 (88.45) + train[2018-10-16-23:01:56] Epoch: [103][600/10010] Time 0.49 (0.53) Data 0.00 (0.01) Loss 3.234 (3.183) Prec@1 67.19 (70.55) Prec@5 87.50 (88.41) + train[2018-10-16-23:03:41] Epoch: [103][800/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.579 (3.189) Prec@1 60.94 (70.45) Prec@5 85.94 (88.38) + train[2018-10-16-23:05:25] Epoch: [103][1000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.269 (3.191) Prec@1 72.66 (70.38) Prec@5 88.28 (88.34) + train[2018-10-16-23:07:09] Epoch: [103][1200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.062 (3.188) Prec@1 70.31 (70.41) Prec@5 90.62 (88.38) + train[2018-10-16-23:08:53] Epoch: [103][1400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.365 (3.188) Prec@1 67.19 (70.38) Prec@5 86.72 (88.39) + train[2018-10-16-23:10:37] Epoch: [103][1600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.454 (3.189) Prec@1 65.62 (70.37) Prec@5 85.94 (88.38) + train[2018-10-16-23:12:22] Epoch: [103][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.210 (3.191) Prec@1 67.97 (70.33) Prec@5 89.84 (88.37) + train[2018-10-16-23:14:05] Epoch: [103][2000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.297 (3.191) Prec@1 66.41 (70.30) Prec@5 85.94 (88.36) + train[2018-10-16-23:15:49] Epoch: [103][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.157 (3.193) Prec@1 71.88 (70.28) Prec@5 87.50 (88.34) + train[2018-10-16-23:17:33] Epoch: [103][2400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.539 (3.195) Prec@1 64.84 (70.23) Prec@5 85.16 (88.32) + train[2018-10-16-23:19:19] Epoch: [103][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.270 (3.197) Prec@1 67.97 (70.18) Prec@5 87.50 (88.30) + train[2018-10-16-23:21:02] Epoch: [103][2800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.271 (3.197) Prec@1 69.53 (70.17) Prec@5 89.06 (88.29) + train[2018-10-16-23:22:47] Epoch: [103][3000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.021 (3.197) Prec@1 75.78 (70.18) Prec@5 90.62 (88.30) + train[2018-10-16-23:24:31] Epoch: [103][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.011 (3.197) Prec@1 75.00 (70.19) Prec@5 92.97 (88.30) + train[2018-10-16-23:26:15] Epoch: [103][3400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.251 (3.197) Prec@1 58.59 (70.18) Prec@5 88.28 (88.29) + train[2018-10-16-23:27:59] Epoch: [103][3600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.921 (3.197) Prec@1 74.22 (70.18) Prec@5 92.97 (88.27) + train[2018-10-16-23:29:44] Epoch: [103][3800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.187 (3.199) Prec@1 64.84 (70.17) Prec@5 88.28 (88.25) + train[2018-10-16-23:31:29] Epoch: [103][4000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.445 (3.198) Prec@1 68.75 (70.17) Prec@5 86.72 (88.25) + train[2018-10-16-23:33:15] Epoch: [103][4200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.461 (3.200) Prec@1 67.19 (70.13) Prec@5 82.81 (88.24) + train[2018-10-16-23:35:00] Epoch: [103][4400/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.082 (3.200) Prec@1 71.88 (70.15) Prec@5 89.06 (88.24) + train[2018-10-16-23:36:46] Epoch: [103][4600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.414 (3.200) Prec@1 59.38 (70.14) Prec@5 84.38 (88.24) + train[2018-10-16-23:38:32] Epoch: [103][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.274 (3.201) Prec@1 70.31 (70.13) Prec@5 87.50 (88.23) + train[2018-10-16-23:40:17] Epoch: [103][5000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.952 (3.201) Prec@1 72.66 (70.12) Prec@5 91.41 (88.22) + train[2018-10-16-23:42:02] Epoch: [103][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.964 (3.201) Prec@1 69.53 (70.11) Prec@5 89.84 (88.22) + train[2018-10-16-23:43:48] Epoch: [103][5400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.686 (3.201) Prec@1 64.84 (70.11) Prec@5 86.72 (88.23) + train[2018-10-16-23:45:33] Epoch: [103][5600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.259 (3.201) Prec@1 66.41 (70.09) Prec@5 88.28 (88.23) + train[2018-10-16-23:47:18] Epoch: [103][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.911 (3.202) Prec@1 75.00 (70.08) Prec@5 92.97 (88.23) + train[2018-10-16-23:49:04] Epoch: [103][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.263 (3.202) Prec@1 66.41 (70.08) Prec@5 86.72 (88.22) + train[2018-10-16-23:50:49] Epoch: [103][6200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.719 (3.202) Prec@1 81.25 (70.08) Prec@5 94.53 (88.22) + train[2018-10-16-23:52:34] Epoch: [103][6400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.328 (3.202) Prec@1 64.84 (70.08) Prec@5 88.28 (88.21) + train[2018-10-16-23:54:18] Epoch: [103][6600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.097 (3.203) Prec@1 71.09 (70.06) Prec@5 89.84 (88.21) + train[2018-10-16-23:56:03] Epoch: [103][6800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.416 (3.202) Prec@1 64.84 (70.07) Prec@5 86.72 (88.20) + train[2018-10-16-23:57:48] Epoch: [103][7000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.110 (3.204) Prec@1 69.53 (70.04) Prec@5 87.50 (88.18) + train[2018-10-16-23:59:32] Epoch: [103][7200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.170 (3.204) Prec@1 69.53 (70.04) Prec@5 90.62 (88.18) + train[2018-10-17-00:01:16] Epoch: [103][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.184 (3.204) Prec@1 71.09 (70.03) Prec@5 87.50 (88.17) + train[2018-10-17-00:03:00] Epoch: [103][7600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.016 (3.204) Prec@1 74.22 (70.03) Prec@5 90.62 (88.17) + train[2018-10-17-00:04:44] Epoch: [103][7800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.320 (3.205) Prec@1 70.31 (70.02) Prec@5 87.50 (88.16) + train[2018-10-17-00:06:29] Epoch: [103][8000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.028 (3.205) Prec@1 72.66 (70.01) Prec@5 87.50 (88.16) + train[2018-10-17-00:08:12] Epoch: [103][8200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.284 (3.205) Prec@1 71.88 (70.02) Prec@5 85.94 (88.16) + train[2018-10-17-00:09:56] Epoch: [103][8400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.768 (3.205) Prec@1 75.78 (70.02) Prec@5 91.41 (88.15) + train[2018-10-17-00:11:40] Epoch: [103][8600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.300 (3.204) Prec@1 69.53 (70.03) Prec@5 84.38 (88.16) + train[2018-10-17-00:13:24] Epoch: [103][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.592 (3.205) Prec@1 64.06 (70.02) Prec@5 79.69 (88.16) + train[2018-10-17-00:15:08] Epoch: [103][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.194 (3.205) Prec@1 73.44 (70.01) Prec@5 86.72 (88.16) + train[2018-10-17-00:16:52] Epoch: [103][9200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.051 (3.205) Prec@1 72.66 (70.00) Prec@5 92.97 (88.15) + train[2018-10-17-00:18:39] Epoch: [103][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.240 (3.205) Prec@1 67.97 (70.00) Prec@5 87.50 (88.15) + train[2018-10-17-00:20:23] Epoch: [103][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.403 (3.206) Prec@1 59.38 (69.99) Prec@5 89.06 (88.15) + train[2018-10-17-00:22:09] Epoch: [103][9800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 2.991 (3.206) Prec@1 73.44 (69.98) Prec@5 92.19 (88.14) + train[2018-10-17-00:23:54] Epoch: [103][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.943 (3.207) Prec@1 71.88 (69.96) Prec@5 90.62 (88.13) + train[2018-10-17-00:23:58] Epoch: [103][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 5.345 (3.207) Prec@1 40.00 (69.96) Prec@5 73.33 (88.13) +[2018-10-17-00:23:58] **train** Prec@1 69.96 Prec@5 88.13 Error@1 30.04 Error@5 11.87 Loss:3.207 + test [2018-10-17-00:24:02] Epoch: [103][000/391] Time 4.21 (4.21) Data 4.07 (4.07) Loss 0.689 (0.689) Prec@1 87.50 (87.50) Prec@5 96.09 (96.09) + test [2018-10-17-00:24:29] Epoch: [103][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.419 (1.069) Prec@1 60.16 (75.05) Prec@5 92.19 (92.57) + test [2018-10-17-00:24:54] Epoch: [103][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 1.823 (1.238) Prec@1 53.75 (71.51) Prec@5 85.00 (90.28) +[2018-10-17-00:24:54] **test** Prec@1 71.51 Prec@5 90.28 Error@1 28.49 Error@5 9.72 Loss:1.238 +----> Best Accuracy : Acc@1=71.51, Acc@5=90.28, Error@1=28.49, Error@5=9.72 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-17-00:24:54] [Epoch=104/250] [Need: 214:44:55] LR=0.0042 ~ 0.0042, Batch=128 + train[2018-10-17-00:24:58] Epoch: [104][000/10010] Time 4.28 (4.28) Data 3.58 (3.58) Loss 3.329 (3.329) Prec@1 69.53 (69.53) Prec@5 85.94 (85.94) + train[2018-10-17-00:26:43] Epoch: [104][200/10010] Time 0.49 (0.54) Data 0.00 (0.02) Loss 3.323 (3.175) Prec@1 64.84 (70.65) Prec@5 86.72 (88.56) + train[2018-10-17-00:28:27] Epoch: [104][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.149 (3.173) Prec@1 75.00 (70.65) Prec@5 85.94 (88.66) + train[2018-10-17-00:30:11] Epoch: [104][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.499 (3.180) Prec@1 63.28 (70.51) Prec@5 86.72 (88.57) + train[2018-10-17-00:31:55] Epoch: [104][800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.059 (3.178) Prec@1 75.78 (70.57) Prec@5 88.28 (88.61) + train[2018-10-17-00:33:39] Epoch: [104][1000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.331 (3.181) Prec@1 68.75 (70.45) Prec@5 83.59 (88.54) + train[2018-10-17-00:35:23] Epoch: [104][1200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.243 (3.182) Prec@1 71.09 (70.44) Prec@5 87.50 (88.50) + train[2018-10-17-00:37:07] Epoch: [104][1400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.517 (3.182) Prec@1 64.84 (70.46) Prec@5 85.16 (88.49) + train[2018-10-17-00:38:52] Epoch: [104][1600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.156 (3.181) Prec@1 75.00 (70.47) Prec@5 88.28 (88.50) + train[2018-10-17-00:40:36] Epoch: [104][1800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.408 (3.183) Prec@1 65.62 (70.43) Prec@5 85.94 (88.46) + train[2018-10-17-00:42:20] Epoch: [104][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.125 (3.182) Prec@1 67.19 (70.43) Prec@5 89.84 (88.50) + train[2018-10-17-00:44:04] Epoch: [104][2200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.050 (3.181) Prec@1 73.44 (70.44) Prec@5 90.62 (88.49) + train[2018-10-17-00:45:49] Epoch: [104][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.080 (3.181) Prec@1 70.31 (70.46) Prec@5 89.06 (88.50) + train[2018-10-17-00:47:34] Epoch: [104][2600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.238 (3.180) Prec@1 68.75 (70.47) Prec@5 87.50 (88.51) + train[2018-10-17-00:49:18] Epoch: [104][2800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.255 (3.181) Prec@1 71.09 (70.46) Prec@5 87.50 (88.49) + train[2018-10-17-00:51:04] Epoch: [104][3000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.176 (3.180) Prec@1 67.97 (70.46) Prec@5 87.50 (88.49) + train[2018-10-17-00:52:51] Epoch: [104][3200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.271 (3.179) Prec@1 71.09 (70.46) Prec@5 88.28 (88.52) + train[2018-10-17-00:54:38] Epoch: [104][3400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.271 (3.182) Prec@1 68.75 (70.41) Prec@5 88.28 (88.48) + train[2018-10-17-00:56:25] Epoch: [104][3600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.174 (3.184) Prec@1 70.31 (70.38) Prec@5 85.94 (88.46) + train[2018-10-17-00:58:12] Epoch: [104][3800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.890 (3.185) Prec@1 75.78 (70.37) Prec@5 91.41 (88.45) + train[2018-10-17-00:59:59] Epoch: [104][4000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.589 (3.186) Prec@1 67.97 (70.35) Prec@5 84.38 (88.43) + train[2018-10-17-01:01:46] Epoch: [104][4200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.617 (3.186) Prec@1 62.50 (70.34) Prec@5 82.81 (88.42) + train[2018-10-17-01:03:32] Epoch: [104][4400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.984 (3.186) Prec@1 74.22 (70.33) Prec@5 92.19 (88.41) + train[2018-10-17-01:05:17] Epoch: [104][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.037 (3.188) Prec@1 69.53 (70.31) Prec@5 92.19 (88.39) + train[2018-10-17-01:07:01] Epoch: [104][4800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.217 (3.188) Prec@1 74.22 (70.30) Prec@5 89.06 (88.38) + train[2018-10-17-01:08:45] Epoch: [104][5000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.244 (3.189) Prec@1 69.53 (70.29) Prec@5 87.50 (88.37) + train[2018-10-17-01:10:30] Epoch: [104][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.312 (3.190) Prec@1 70.31 (70.27) Prec@5 85.16 (88.35) + train[2018-10-17-01:12:14] Epoch: [104][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.045 (3.190) Prec@1 73.44 (70.27) Prec@5 90.62 (88.36) + train[2018-10-17-01:13:58] Epoch: [104][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.818 (3.191) Prec@1 76.56 (70.25) Prec@5 94.53 (88.34) + train[2018-10-17-01:15:43] Epoch: [104][5800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.238 (3.190) Prec@1 70.31 (70.26) Prec@5 88.28 (88.34) + train[2018-10-17-01:17:28] Epoch: [104][6000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.071 (3.191) Prec@1 66.41 (70.25) Prec@5 92.19 (88.33) + train[2018-10-17-01:19:15] Epoch: [104][6200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.096 (3.191) Prec@1 68.75 (70.24) Prec@5 90.62 (88.33) + train[2018-10-17-01:21:01] Epoch: [104][6400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.097 (3.192) Prec@1 76.56 (70.22) Prec@5 86.72 (88.31) + train[2018-10-17-01:22:48] Epoch: [104][6600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.430 (3.192) Prec@1 62.50 (70.22) Prec@5 83.59 (88.32) + train[2018-10-17-01:24:36] Epoch: [104][6800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.559 (3.192) Prec@1 67.19 (70.22) Prec@5 83.59 (88.33) + train[2018-10-17-01:26:23] Epoch: [104][7000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.121 (3.193) Prec@1 71.09 (70.21) Prec@5 88.28 (88.31) + train[2018-10-17-01:28:09] Epoch: [104][7200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.883 (3.193) Prec@1 75.78 (70.21) Prec@5 92.97 (88.31) + train[2018-10-17-01:29:57] Epoch: [104][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.027 (3.193) Prec@1 72.66 (70.20) Prec@5 89.84 (88.30) + train[2018-10-17-01:31:44] Epoch: [104][7600/10010] Time 0.62 (0.53) Data 0.00 (0.00) Loss 3.576 (3.195) Prec@1 62.50 (70.18) Prec@5 82.03 (88.29) + train[2018-10-17-01:33:30] Epoch: [104][7800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.084 (3.195) Prec@1 68.75 (70.16) Prec@5 92.19 (88.28) + train[2018-10-17-01:35:17] Epoch: [104][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.201 (3.196) Prec@1 73.44 (70.16) Prec@5 86.72 (88.28) + train[2018-10-17-01:37:04] Epoch: [104][8200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.191 (3.196) Prec@1 66.41 (70.15) Prec@5 87.50 (88.27) + train[2018-10-17-01:38:52] Epoch: [104][8400/10010] Time 0.61 (0.53) Data 0.00 (0.00) Loss 3.174 (3.196) Prec@1 73.44 (70.14) Prec@5 88.28 (88.27) + train[2018-10-17-01:40:40] Epoch: [104][8600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.130 (3.197) Prec@1 72.66 (70.14) Prec@5 88.28 (88.26) + train[2018-10-17-01:42:28] Epoch: [104][8800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.957 (3.197) Prec@1 76.56 (70.14) Prec@5 91.41 (88.26) + train[2018-10-17-01:44:14] Epoch: [104][9000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.392 (3.198) Prec@1 69.53 (70.12) Prec@5 88.28 (88.25) + train[2018-10-17-01:46:00] Epoch: [104][9200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.115 (3.198) Prec@1 69.53 (70.12) Prec@5 90.62 (88.26) + train[2018-10-17-01:47:45] Epoch: [104][9400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.380 (3.198) Prec@1 71.09 (70.11) Prec@5 84.38 (88.25) + train[2018-10-17-01:49:31] Epoch: [104][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.528 (3.199) Prec@1 64.06 (70.10) Prec@5 80.47 (88.24) + train[2018-10-17-01:51:16] Epoch: [104][9800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.868 (3.199) Prec@1 74.22 (70.08) Prec@5 90.62 (88.23) + train[2018-10-17-01:53:03] Epoch: [104][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.150 (3.199) Prec@1 71.88 (70.07) Prec@5 89.84 (88.24) + train[2018-10-17-01:53:07] Epoch: [104][10009/10010] Time 0.18 (0.53) Data 0.00 (0.00) Loss 3.316 (3.199) Prec@1 80.00 (70.07) Prec@5 86.67 (88.24) +[2018-10-17-01:53:07] **train** Prec@1 70.07 Prec@5 88.24 Error@1 29.93 Error@5 11.76 Loss:3.199 + test [2018-10-17-01:53:11] Epoch: [104][000/391] Time 3.98 (3.98) Data 3.82 (3.82) Loss 0.592 (0.592) Prec@1 89.84 (89.84) Prec@5 95.31 (95.31) + test [2018-10-17-01:53:38] Epoch: [104][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.263 (1.072) Prec@1 67.97 (74.97) Prec@5 91.41 (92.53) + test [2018-10-17-01:54:02] Epoch: [104][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.131 (1.233) Prec@1 42.50 (71.54) Prec@5 81.25 (90.28) +[2018-10-17-01:54:02] **test** Prec@1 71.54 Prec@5 90.28 Error@1 28.46 Error@5 9.72 Loss:1.233 +----> Best Accuracy : Acc@1=71.54, Acc@5=90.28, Error@1=28.46, Error@5=9.72 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-17-01:54:02] [Epoch=105/250] [Need: 215:26:00] LR=0.0041 ~ 0.0041, Batch=128 + train[2018-10-17-01:54:07] Epoch: [105][000/10010] Time 4.65 (4.65) Data 4.03 (4.03) Loss 3.249 (3.249) Prec@1 68.75 (68.75) Prec@5 89.84 (89.84) + train[2018-10-17-01:55:52] Epoch: [105][200/10010] Time 0.51 (0.55) Data 0.00 (0.02) Loss 3.365 (3.184) Prec@1 67.19 (70.55) Prec@5 84.38 (88.33) + train[2018-10-17-01:57:36] Epoch: [105][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.983 (3.178) Prec@1 71.09 (70.72) Prec@5 89.06 (88.42) + train[2018-10-17-01:59:21] Epoch: [105][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.968 (3.173) Prec@1 73.44 (70.65) Prec@5 91.41 (88.55) + train[2018-10-17-02:01:05] Epoch: [105][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.242 (3.179) Prec@1 66.41 (70.59) Prec@5 87.50 (88.50) + train[2018-10-17-02:02:49] Epoch: [105][1000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.123 (3.179) Prec@1 74.22 (70.60) Prec@5 88.28 (88.45) + train[2018-10-17-02:04:33] Epoch: [105][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.867 (3.181) Prec@1 77.34 (70.53) Prec@5 89.84 (88.46) + train[2018-10-17-02:06:17] Epoch: [105][1400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.181 (3.179) Prec@1 71.09 (70.59) Prec@5 88.28 (88.47) + train[2018-10-17-02:08:00] Epoch: [105][1600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.390 (3.179) Prec@1 71.09 (70.60) Prec@5 87.50 (88.48) + train[2018-10-17-02:09:44] Epoch: [105][1800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.276 (3.177) Prec@1 71.09 (70.63) Prec@5 89.06 (88.51) + train[2018-10-17-02:11:28] Epoch: [105][2000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.422 (3.177) Prec@1 62.50 (70.63) Prec@5 85.94 (88.52) + train[2018-10-17-02:13:13] Epoch: [105][2200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.188 (3.175) Prec@1 64.84 (70.66) Prec@5 90.62 (88.52) + train[2018-10-17-02:14:58] Epoch: [105][2400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.246 (3.176) Prec@1 64.84 (70.66) Prec@5 89.06 (88.52) + train[2018-10-17-02:16:43] Epoch: [105][2600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.952 (3.177) Prec@1 69.53 (70.65) Prec@5 91.41 (88.51) + train[2018-10-17-02:18:27] Epoch: [105][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.301 (3.177) Prec@1 64.84 (70.64) Prec@5 85.94 (88.51) + train[2018-10-17-02:20:13] Epoch: [105][3000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.870 (3.178) Prec@1 77.34 (70.64) Prec@5 93.75 (88.49) + train[2018-10-17-02:21:57] Epoch: [105][3200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.399 (3.178) Prec@1 67.19 (70.62) Prec@5 89.84 (88.48) + train[2018-10-17-02:23:43] Epoch: [105][3400/10010] Time 0.59 (0.52) Data 0.00 (0.00) Loss 3.126 (3.180) Prec@1 67.97 (70.58) Prec@5 90.62 (88.46) + train[2018-10-17-02:25:28] Epoch: [105][3600/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.057 (3.180) Prec@1 76.56 (70.57) Prec@5 91.41 (88.46) + train[2018-10-17-02:27:13] Epoch: [105][3800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.273 (3.181) Prec@1 68.75 (70.53) Prec@5 88.28 (88.45) + train[2018-10-17-02:28:59] Epoch: [105][4000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.382 (3.182) Prec@1 64.84 (70.50) Prec@5 88.28 (88.45) + train[2018-10-17-02:30:44] Epoch: [105][4200/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.502 (3.182) Prec@1 64.84 (70.50) Prec@5 82.03 (88.44) + train[2018-10-17-02:32:31] Epoch: [105][4400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.039 (3.184) Prec@1 72.66 (70.47) Prec@5 92.19 (88.42) + train[2018-10-17-02:34:17] Epoch: [105][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.119 (3.184) Prec@1 71.88 (70.46) Prec@5 89.06 (88.42) + train[2018-10-17-02:36:03] Epoch: [105][4800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.151 (3.184) Prec@1 69.53 (70.45) Prec@5 89.06 (88.42) + train[2018-10-17-02:37:48] Epoch: [105][5000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.303 (3.185) Prec@1 65.62 (70.44) Prec@5 85.94 (88.40) + train[2018-10-17-02:39:35] Epoch: [105][5200/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 2.912 (3.186) Prec@1 71.09 (70.42) Prec@5 92.19 (88.40) + train[2018-10-17-02:41:21] Epoch: [105][5400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.168 (3.186) Prec@1 71.09 (70.42) Prec@5 89.06 (88.39) + train[2018-10-17-02:43:06] Epoch: [105][5600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.556 (3.187) Prec@1 60.16 (70.39) Prec@5 82.81 (88.37) + train[2018-10-17-02:44:52] Epoch: [105][5800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.178 (3.187) Prec@1 71.09 (70.41) Prec@5 86.72 (88.37) + train[2018-10-17-02:46:37] Epoch: [105][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.274 (3.187) Prec@1 66.41 (70.40) Prec@5 85.16 (88.36) + train[2018-10-17-02:48:23] Epoch: [105][6200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.167 (3.189) Prec@1 68.75 (70.38) Prec@5 88.28 (88.35) + train[2018-10-17-02:50:08] Epoch: [105][6400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.245 (3.188) Prec@1 68.75 (70.36) Prec@5 86.72 (88.35) + train[2018-10-17-02:51:53] Epoch: [105][6600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.330 (3.188) Prec@1 65.62 (70.37) Prec@5 85.94 (88.35) + train[2018-10-17-02:53:38] Epoch: [105][6800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.093 (3.188) Prec@1 70.31 (70.37) Prec@5 88.28 (88.35) + train[2018-10-17-02:55:23] Epoch: [105][7000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.300 (3.188) Prec@1 67.19 (70.37) Prec@5 88.28 (88.35) + train[2018-10-17-02:57:07] Epoch: [105][7200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.296 (3.188) Prec@1 68.75 (70.37) Prec@5 82.81 (88.34) + train[2018-10-17-02:58:51] Epoch: [105][7400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.097 (3.189) Prec@1 68.75 (70.36) Prec@5 89.06 (88.34) + train[2018-10-17-03:00:35] Epoch: [105][7600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.084 (3.189) Prec@1 67.97 (70.35) Prec@5 89.06 (88.33) + train[2018-10-17-03:02:20] Epoch: [105][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.027 (3.189) Prec@1 74.22 (70.35) Prec@5 90.62 (88.33) + train[2018-10-17-03:04:05] Epoch: [105][8000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.159 (3.190) Prec@1 72.66 (70.33) Prec@5 85.94 (88.32) + train[2018-10-17-03:05:50] Epoch: [105][8200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.978 (3.189) Prec@1 73.44 (70.34) Prec@5 88.28 (88.33) + train[2018-10-17-03:07:36] Epoch: [105][8400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.035 (3.189) Prec@1 71.09 (70.34) Prec@5 89.06 (88.33) + train[2018-10-17-03:09:22] Epoch: [105][8600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.283 (3.189) Prec@1 71.09 (70.33) Prec@5 83.59 (88.32) + train[2018-10-17-03:11:08] Epoch: [105][8800/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.071 (3.190) Prec@1 69.53 (70.31) Prec@5 88.28 (88.31) + train[2018-10-17-03:12:52] Epoch: [105][9000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.447 (3.191) Prec@1 64.84 (70.30) Prec@5 86.72 (88.31) + train[2018-10-17-03:14:37] Epoch: [105][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.198 (3.190) Prec@1 67.19 (70.31) Prec@5 86.72 (88.31) + train[2018-10-17-03:16:21] Epoch: [105][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.513 (3.191) Prec@1 64.84 (70.31) Prec@5 85.94 (88.30) + train[2018-10-17-03:18:05] Epoch: [105][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.269 (3.192) Prec@1 70.31 (70.30) Prec@5 87.50 (88.30) + train[2018-10-17-03:19:51] Epoch: [105][9800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.233 (3.192) Prec@1 68.75 (70.29) Prec@5 84.38 (88.30) + train[2018-10-17-03:21:35] Epoch: [105][10000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.184 (3.193) Prec@1 67.97 (70.27) Prec@5 85.16 (88.29) + train[2018-10-17-03:21:39] Epoch: [105][10009/10010] Time 0.21 (0.53) Data 0.00 (0.00) Loss 2.991 (3.193) Prec@1 73.33 (70.27) Prec@5 86.67 (88.29) +[2018-10-17-03:21:39] **train** Prec@1 70.27 Prec@5 88.29 Error@1 29.73 Error@5 11.71 Loss:3.193 + test [2018-10-17-03:21:44] Epoch: [105][000/391] Time 4.29 (4.29) Data 4.15 (4.15) Loss 0.580 (0.580) Prec@1 91.41 (91.41) Prec@5 96.88 (96.88) + test [2018-10-17-03:22:10] Epoch: [105][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.380 (1.073) Prec@1 64.06 (75.22) Prec@5 90.62 (92.77) + test [2018-10-17-03:22:34] Epoch: [105][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.146 (1.240) Prec@1 45.00 (71.50) Prec@5 82.50 (90.36) +[2018-10-17-03:22:34] **test** Prec@1 71.50 Prec@5 90.36 Error@1 28.50 Error@5 9.64 Loss:1.240 +----> Best Accuracy : Acc@1=71.54, Acc@5=90.28, Error@1=28.46, Error@5=9.72 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-17-03:22:34] [Epoch=106/250] [Need: 212:28:43] LR=0.0040 ~ 0.0040, Batch=128 + train[2018-10-17-03:22:39] Epoch: [106][000/10010] Time 4.50 (4.50) Data 3.89 (3.89) Loss 3.384 (3.384) Prec@1 70.31 (70.31) Prec@5 86.72 (86.72) + train[2018-10-17-03:24:24] Epoch: [106][200/10010] Time 0.51 (0.54) Data 0.00 (0.02) Loss 3.088 (3.152) Prec@1 72.66 (71.02) Prec@5 87.50 (88.61) + train[2018-10-17-03:26:08] Epoch: [106][400/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.026 (3.160) Prec@1 71.88 (70.79) Prec@5 89.06 (88.69) + train[2018-10-17-03:27:53] Epoch: [106][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.146 (3.169) Prec@1 71.09 (70.60) Prec@5 90.62 (88.59) + train[2018-10-17-03:29:38] Epoch: [106][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.017 (3.175) Prec@1 75.78 (70.58) Prec@5 88.28 (88.57) + train[2018-10-17-03:31:21] Epoch: [106][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.176 (3.173) Prec@1 71.88 (70.57) Prec@5 86.72 (88.57) + train[2018-10-17-03:33:06] Epoch: [106][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.079 (3.176) Prec@1 71.09 (70.50) Prec@5 89.84 (88.51) + train[2018-10-17-03:34:50] Epoch: [106][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.982 (3.175) Prec@1 75.78 (70.51) Prec@5 92.97 (88.53) + train[2018-10-17-03:36:34] Epoch: [106][1600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.579 (3.175) Prec@1 62.50 (70.55) Prec@5 78.12 (88.51) + train[2018-10-17-03:38:19] Epoch: [106][1800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.162 (3.175) Prec@1 71.88 (70.53) Prec@5 89.06 (88.48) + train[2018-10-17-03:40:03] Epoch: [106][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.281 (3.174) Prec@1 66.41 (70.59) Prec@5 86.72 (88.51) + train[2018-10-17-03:41:48] Epoch: [106][2200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.319 (3.175) Prec@1 69.53 (70.58) Prec@5 85.16 (88.49) + train[2018-10-17-03:43:32] Epoch: [106][2400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.276 (3.176) Prec@1 67.97 (70.58) Prec@5 86.72 (88.49) + train[2018-10-17-03:45:17] Epoch: [106][2600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.424 (3.177) Prec@1 62.50 (70.59) Prec@5 85.16 (88.46) + train[2018-10-17-03:47:01] Epoch: [106][2800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.162 (3.176) Prec@1 75.00 (70.61) Prec@5 91.41 (88.47) + train[2018-10-17-03:48:46] Epoch: [106][3000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.275 (3.176) Prec@1 67.19 (70.61) Prec@5 85.16 (88.47) + train[2018-10-17-03:50:32] Epoch: [106][3200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.135 (3.175) Prec@1 73.44 (70.63) Prec@5 90.62 (88.49) + train[2018-10-17-03:52:16] Epoch: [106][3400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.319 (3.174) Prec@1 69.53 (70.65) Prec@5 87.50 (88.49) + train[2018-10-17-03:54:02] Epoch: [106][3600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.326 (3.177) Prec@1 66.41 (70.59) Prec@5 87.50 (88.43) + train[2018-10-17-03:55:47] Epoch: [106][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.188 (3.178) Prec@1 70.31 (70.56) Prec@5 85.94 (88.43) + train[2018-10-17-03:57:31] Epoch: [106][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.222 (3.179) Prec@1 66.41 (70.56) Prec@5 88.28 (88.43) + train[2018-10-17-03:59:16] Epoch: [106][4200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.243 (3.179) Prec@1 69.53 (70.56) Prec@5 87.50 (88.43) + train[2018-10-17-04:01:00] Epoch: [106][4400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.416 (3.179) Prec@1 64.84 (70.55) Prec@5 84.38 (88.43) + train[2018-10-17-04:02:44] Epoch: [106][4600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.209 (3.180) Prec@1 71.09 (70.54) Prec@5 88.28 (88.44) + train[2018-10-17-04:04:29] Epoch: [106][4800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.253 (3.180) Prec@1 69.53 (70.52) Prec@5 91.41 (88.43) + train[2018-10-17-04:06:14] Epoch: [106][5000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.333 (3.180) Prec@1 66.41 (70.52) Prec@5 87.50 (88.44) + train[2018-10-17-04:07:58] Epoch: [106][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.205 (3.181) Prec@1 75.00 (70.50) Prec@5 89.06 (88.43) + train[2018-10-17-04:09:42] Epoch: [106][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.128 (3.181) Prec@1 68.75 (70.51) Prec@5 89.84 (88.42) + train[2018-10-17-04:11:26] Epoch: [106][5600/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.253 (3.181) Prec@1 70.31 (70.50) Prec@5 85.94 (88.43) + train[2018-10-17-04:13:10] Epoch: [106][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.304 (3.183) Prec@1 69.53 (70.49) Prec@5 85.16 (88.41) + train[2018-10-17-04:14:55] Epoch: [106][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.279 (3.182) Prec@1 70.31 (70.50) Prec@5 87.50 (88.41) + train[2018-10-17-04:16:39] Epoch: [106][6200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.605 (3.182) Prec@1 60.16 (70.50) Prec@5 83.59 (88.42) + train[2018-10-17-04:18:24] Epoch: [106][6400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.543 (3.183) Prec@1 64.06 (70.49) Prec@5 86.72 (88.41) + train[2018-10-17-04:20:09] Epoch: [106][6600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.139 (3.183) Prec@1 69.53 (70.48) Prec@5 87.50 (88.41) + train[2018-10-17-04:21:53] Epoch: [106][6800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.291 (3.183) Prec@1 67.19 (70.47) Prec@5 88.28 (88.41) + train[2018-10-17-04:23:38] Epoch: [106][7000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.769 (3.183) Prec@1 80.47 (70.46) Prec@5 95.31 (88.41) + train[2018-10-17-04:25:21] Epoch: [106][7200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.439 (3.183) Prec@1 67.97 (70.47) Prec@5 85.16 (88.41) + train[2018-10-17-04:27:06] Epoch: [106][7400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.111 (3.183) Prec@1 71.09 (70.47) Prec@5 87.50 (88.41) + train[2018-10-17-04:28:51] Epoch: [106][7600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.077 (3.183) Prec@1 72.66 (70.46) Prec@5 91.41 (88.42) + train[2018-10-17-04:30:35] Epoch: [106][7800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.169 (3.183) Prec@1 73.44 (70.46) Prec@5 86.72 (88.41) + train[2018-10-17-04:32:20] Epoch: [106][8000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.306 (3.184) Prec@1 66.41 (70.45) Prec@5 87.50 (88.41) + train[2018-10-17-04:34:04] Epoch: [106][8200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.898 (3.183) Prec@1 75.78 (70.45) Prec@5 91.41 (88.41) + train[2018-10-17-04:35:49] Epoch: [106][8400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.170 (3.184) Prec@1 66.41 (70.44) Prec@5 92.19 (88.41) + train[2018-10-17-04:37:34] Epoch: [106][8600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.384 (3.184) Prec@1 71.88 (70.44) Prec@5 86.72 (88.41) + train[2018-10-17-04:39:20] Epoch: [106][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.268 (3.184) Prec@1 68.75 (70.42) Prec@5 88.28 (88.40) + train[2018-10-17-04:41:05] Epoch: [106][9000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.542 (3.184) Prec@1 70.31 (70.42) Prec@5 81.25 (88.40) + train[2018-10-17-04:42:49] Epoch: [106][9200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 2.965 (3.185) Prec@1 73.44 (70.41) Prec@5 89.84 (88.39) + train[2018-10-17-04:44:35] Epoch: [106][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.392 (3.185) Prec@1 69.53 (70.39) Prec@5 85.94 (88.39) + train[2018-10-17-04:46:20] Epoch: [106][9600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.598 (3.185) Prec@1 79.69 (70.39) Prec@5 95.31 (88.38) + train[2018-10-17-04:48:04] Epoch: [106][9800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.333 (3.185) Prec@1 67.97 (70.38) Prec@5 88.28 (88.38) + train[2018-10-17-04:49:48] Epoch: [106][10000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.073 (3.185) Prec@1 68.75 (70.38) Prec@5 86.72 (88.38) + train[2018-10-17-04:49:52] Epoch: [106][10009/10010] Time 0.19 (0.52) Data 0.00 (0.00) Loss 4.326 (3.185) Prec@1 53.33 (70.38) Prec@5 80.00 (88.38) +[2018-10-17-04:49:52] **train** Prec@1 70.38 Prec@5 88.38 Error@1 29.62 Error@5 11.62 Loss:3.185 + test [2018-10-17-04:49:56] Epoch: [106][000/391] Time 3.82 (3.82) Data 3.68 (3.68) Loss 0.546 (0.546) Prec@1 89.06 (89.06) Prec@5 96.88 (96.88) + test [2018-10-17-04:50:23] Epoch: [106][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.485 (1.067) Prec@1 60.16 (75.31) Prec@5 90.62 (92.87) + test [2018-10-17-04:50:48] Epoch: [106][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.294 (1.231) Prec@1 38.75 (71.74) Prec@5 82.50 (90.64) +[2018-10-17-04:50:48] **test** Prec@1 71.74 Prec@5 90.64 Error@1 28.26 Error@5 9.36 Loss:1.231 +----> Best Accuracy : Acc@1=71.74, Acc@5=90.64, Error@1=28.26, Error@5=9.36 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-17-04:50:48] [Epoch=107/250] [Need: 210:16:17] LR=0.0038 ~ 0.0038, Batch=128 + train[2018-10-17-04:50:52] Epoch: [107][000/10010] Time 4.37 (4.37) Data 3.79 (3.79) Loss 3.496 (3.496) Prec@1 67.19 (67.19) Prec@5 84.38 (84.38) + train[2018-10-17-04:52:37] Epoch: [107][200/10010] Time 0.51 (0.54) Data 0.00 (0.02) Loss 3.245 (3.155) Prec@1 71.09 (71.14) Prec@5 88.28 (88.70) + train[2018-10-17-04:54:21] Epoch: [107][400/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.442 (3.154) Prec@1 64.06 (71.08) Prec@5 85.94 (88.66) + train[2018-10-17-04:56:06] Epoch: [107][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.068 (3.150) Prec@1 73.44 (71.13) Prec@5 90.62 (88.75) + train[2018-10-17-04:57:50] Epoch: [107][800/10010] Time 0.56 (0.53) Data 0.00 (0.01) Loss 3.002 (3.151) Prec@1 74.22 (71.17) Prec@5 92.97 (88.74) + train[2018-10-17-04:59:34] Epoch: [107][1000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.233 (3.156) Prec@1 67.97 (71.07) Prec@5 88.28 (88.69) + train[2018-10-17-05:01:18] Epoch: [107][1200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.826 (3.158) Prec@1 75.78 (71.00) Prec@5 92.97 (88.66) + train[2018-10-17-05:03:03] Epoch: [107][1400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.224 (3.156) Prec@1 67.19 (71.01) Prec@5 85.16 (88.68) + train[2018-10-17-05:04:47] Epoch: [107][1600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.819 (3.157) Prec@1 79.69 (70.98) Prec@5 92.19 (88.67) + train[2018-10-17-05:06:31] Epoch: [107][1800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.537 (3.155) Prec@1 64.84 (70.99) Prec@5 82.81 (88.69) + train[2018-10-17-05:08:16] Epoch: [107][2000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.906 (3.159) Prec@1 76.56 (70.94) Prec@5 93.75 (88.66) + train[2018-10-17-05:10:00] Epoch: [107][2200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.088 (3.162) Prec@1 70.31 (70.85) Prec@5 88.28 (88.62) + train[2018-10-17-05:11:44] Epoch: [107][2400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.223 (3.162) Prec@1 70.31 (70.87) Prec@5 88.28 (88.62) + train[2018-10-17-05:13:28] Epoch: [107][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.333 (3.162) Prec@1 69.53 (70.87) Prec@5 84.38 (88.63) + train[2018-10-17-05:15:12] Epoch: [107][2800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.267 (3.163) Prec@1 59.38 (70.83) Prec@5 92.19 (88.63) + train[2018-10-17-05:16:56] Epoch: [107][3000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.059 (3.164) Prec@1 69.53 (70.81) Prec@5 91.41 (88.61) + train[2018-10-17-05:18:41] Epoch: [107][3200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.817 (3.165) Prec@1 74.22 (70.79) Prec@5 92.19 (88.60) + train[2018-10-17-05:20:25] Epoch: [107][3400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.312 (3.165) Prec@1 69.53 (70.78) Prec@5 87.50 (88.60) + train[2018-10-17-05:22:09] Epoch: [107][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.237 (3.164) Prec@1 67.97 (70.78) Prec@5 87.50 (88.61) + train[2018-10-17-05:23:54] Epoch: [107][3800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.929 (3.164) Prec@1 76.56 (70.80) Prec@5 92.19 (88.63) + train[2018-10-17-05:25:38] Epoch: [107][4000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.202 (3.164) Prec@1 71.09 (70.79) Prec@5 89.06 (88.61) + train[2018-10-17-05:27:22] Epoch: [107][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.457 (3.165) Prec@1 67.97 (70.78) Prec@5 82.81 (88.60) + train[2018-10-17-05:29:07] Epoch: [107][4400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.372 (3.166) Prec@1 69.53 (70.76) Prec@5 86.72 (88.60) + train[2018-10-17-05:30:52] Epoch: [107][4600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.322 (3.166) Prec@1 67.19 (70.75) Prec@5 88.28 (88.59) + train[2018-10-17-05:32:36] Epoch: [107][4800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.234 (3.166) Prec@1 68.75 (70.74) Prec@5 89.84 (88.59) + train[2018-10-17-05:34:20] Epoch: [107][5000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.416 (3.167) Prec@1 66.41 (70.72) Prec@5 85.94 (88.58) + train[2018-10-17-05:36:04] Epoch: [107][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.426 (3.168) Prec@1 67.97 (70.70) Prec@5 86.72 (88.57) + train[2018-10-17-05:37:48] Epoch: [107][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.049 (3.168) Prec@1 74.22 (70.70) Prec@5 93.75 (88.57) + train[2018-10-17-05:39:32] Epoch: [107][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.144 (3.168) Prec@1 72.66 (70.69) Prec@5 88.28 (88.58) + train[2018-10-17-05:41:16] Epoch: [107][5800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.225 (3.169) Prec@1 65.62 (70.67) Prec@5 91.41 (88.56) + train[2018-10-17-05:43:00] Epoch: [107][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.972 (3.171) Prec@1 76.56 (70.65) Prec@5 90.62 (88.55) + train[2018-10-17-05:44:45] Epoch: [107][6200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.962 (3.170) Prec@1 71.88 (70.66) Prec@5 91.41 (88.55) + train[2018-10-17-05:46:29] Epoch: [107][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.387 (3.172) Prec@1 65.62 (70.63) Prec@5 85.16 (88.53) + train[2018-10-17-05:48:13] Epoch: [107][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.186 (3.172) Prec@1 75.00 (70.64) Prec@5 89.06 (88.52) + train[2018-10-17-05:49:58] Epoch: [107][6800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.806 (3.172) Prec@1 80.47 (70.63) Prec@5 92.19 (88.52) + train[2018-10-17-05:51:41] Epoch: [107][7000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.092 (3.173) Prec@1 70.31 (70.61) Prec@5 89.06 (88.51) + train[2018-10-17-05:53:25] Epoch: [107][7200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.855 (3.173) Prec@1 75.00 (70.61) Prec@5 92.97 (88.51) + train[2018-10-17-05:55:08] Epoch: [107][7400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.109 (3.173) Prec@1 71.88 (70.61) Prec@5 87.50 (88.50) + train[2018-10-17-05:56:53] Epoch: [107][7600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.082 (3.174) Prec@1 74.22 (70.59) Prec@5 92.19 (88.49) + train[2018-10-17-05:58:37] Epoch: [107][7800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.235 (3.174) Prec@1 71.88 (70.58) Prec@5 87.50 (88.49) + train[2018-10-17-06:00:22] Epoch: [107][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.113 (3.175) Prec@1 72.66 (70.57) Prec@5 92.19 (88.48) + train[2018-10-17-06:02:07] Epoch: [107][8200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.167 (3.175) Prec@1 70.31 (70.57) Prec@5 85.94 (88.48) + train[2018-10-17-06:03:51] Epoch: [107][8400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.609 (3.175) Prec@1 60.94 (70.56) Prec@5 80.47 (88.48) + train[2018-10-17-06:05:35] Epoch: [107][8600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.399 (3.176) Prec@1 62.50 (70.54) Prec@5 88.28 (88.48) + train[2018-10-17-06:07:19] Epoch: [107][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.288 (3.176) Prec@1 75.00 (70.54) Prec@5 85.16 (88.48) + train[2018-10-17-06:09:03] Epoch: [107][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.414 (3.177) Prec@1 67.97 (70.53) Prec@5 86.72 (88.47) + train[2018-10-17-06:10:47] Epoch: [107][9200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.159 (3.177) Prec@1 71.09 (70.53) Prec@5 89.84 (88.46) + train[2018-10-17-06:12:32] Epoch: [107][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.299 (3.177) Prec@1 71.09 (70.52) Prec@5 85.16 (88.46) + train[2018-10-17-06:14:15] Epoch: [107][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.356 (3.178) Prec@1 64.06 (70.52) Prec@5 84.38 (88.45) + train[2018-10-17-06:16:00] Epoch: [107][9800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.127 (3.178) Prec@1 65.62 (70.52) Prec@5 92.19 (88.46) + train[2018-10-17-06:17:44] Epoch: [107][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.221 (3.178) Prec@1 69.53 (70.51) Prec@5 88.28 (88.45) + train[2018-10-17-06:17:48] Epoch: [107][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 3.173 (3.178) Prec@1 73.33 (70.51) Prec@5 86.67 (88.45) +[2018-10-17-06:17:48] **train** Prec@1 70.51 Prec@5 88.45 Error@1 29.49 Error@5 11.55 Loss:3.178 + test [2018-10-17-06:17:52] Epoch: [107][000/391] Time 3.76 (3.76) Data 3.63 (3.63) Loss 0.520 (0.520) Prec@1 90.62 (90.62) Prec@5 98.44 (98.44) + test [2018-10-17-06:18:18] Epoch: [107][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.251 (1.061) Prec@1 71.09 (75.47) Prec@5 92.97 (92.80) + test [2018-10-17-06:18:43] Epoch: [107][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.173 (1.227) Prec@1 46.25 (71.77) Prec@5 82.50 (90.49) +[2018-10-17-06:18:43] **test** Prec@1 71.77 Prec@5 90.49 Error@1 28.23 Error@5 9.51 Loss:1.227 +----> Best Accuracy : Acc@1=71.77, Acc@5=90.49, Error@1=28.23, Error@5=9.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-17-06:18:43] [Epoch=108/250] [Need: 208:04:12] LR=0.0037 ~ 0.0037, Batch=128 + train[2018-10-17-06:18:49] Epoch: [108][000/10010] Time 5.65 (5.65) Data 5.05 (5.05) Loss 3.110 (3.110) Prec@1 71.09 (71.09) Prec@5 89.06 (89.06) + train[2018-10-17-06:20:32] Epoch: [108][200/10010] Time 0.54 (0.54) Data 0.00 (0.03) Loss 2.969 (3.160) Prec@1 76.56 (71.12) Prec@5 89.84 (88.76) + train[2018-10-17-06:22:17] Epoch: [108][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.217 (3.168) Prec@1 75.00 (71.00) Prec@5 86.72 (88.57) + train[2018-10-17-06:24:00] Epoch: [108][600/10010] Time 0.49 (0.53) Data 0.00 (0.01) Loss 3.396 (3.170) Prec@1 61.72 (70.92) Prec@5 86.72 (88.55) + train[2018-10-17-06:25:45] Epoch: [108][800/10010] Time 0.57 (0.53) Data 0.00 (0.01) Loss 3.229 (3.166) Prec@1 72.66 (70.93) Prec@5 91.41 (88.59) + train[2018-10-17-06:27:29] Epoch: [108][1000/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.028 (3.162) Prec@1 75.00 (70.99) Prec@5 88.28 (88.63) + train[2018-10-17-06:29:13] Epoch: [108][1200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.188 (3.162) Prec@1 67.19 (70.94) Prec@5 87.50 (88.61) + train[2018-10-17-06:30:57] Epoch: [108][1400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.220 (3.162) Prec@1 67.19 (70.92) Prec@5 85.94 (88.62) + train[2018-10-17-06:32:43] Epoch: [108][1600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.197 (3.160) Prec@1 70.31 (70.97) Prec@5 87.50 (88.64) + train[2018-10-17-06:34:28] Epoch: [108][1800/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.269 (3.159) Prec@1 65.62 (70.96) Prec@5 87.50 (88.68) + train[2018-10-17-06:36:14] Epoch: [108][2000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.038 (3.160) Prec@1 70.31 (70.95) Prec@5 91.41 (88.66) + train[2018-10-17-06:38:00] Epoch: [108][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.160 (3.159) Prec@1 71.09 (70.95) Prec@5 89.06 (88.67) + train[2018-10-17-06:39:47] Epoch: [108][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.324 (3.160) Prec@1 68.75 (70.96) Prec@5 87.50 (88.67) + train[2018-10-17-06:41:31] Epoch: [108][2600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.232 (3.158) Prec@1 70.31 (70.97) Prec@5 90.62 (88.70) + train[2018-10-17-06:43:15] Epoch: [108][2800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.342 (3.158) Prec@1 63.28 (70.98) Prec@5 88.28 (88.70) + train[2018-10-17-06:45:01] Epoch: [108][3000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.401 (3.157) Prec@1 69.53 (70.99) Prec@5 85.94 (88.70) + train[2018-10-17-06:46:45] Epoch: [108][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.278 (3.159) Prec@1 70.31 (70.95) Prec@5 84.38 (88.70) + train[2018-10-17-06:48:30] Epoch: [108][3400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.119 (3.158) Prec@1 67.19 (70.96) Prec@5 89.06 (88.71) + train[2018-10-17-06:50:16] Epoch: [108][3600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.404 (3.159) Prec@1 61.72 (70.95) Prec@5 84.38 (88.70) + train[2018-10-17-06:52:02] Epoch: [108][3800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.218 (3.158) Prec@1 71.09 (70.95) Prec@5 85.94 (88.70) + train[2018-10-17-06:53:48] Epoch: [108][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.099 (3.158) Prec@1 70.31 (70.95) Prec@5 88.28 (88.70) + train[2018-10-17-06:55:34] Epoch: [108][4200/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.111 (3.158) Prec@1 69.53 (70.94) Prec@5 87.50 (88.71) + train[2018-10-17-06:57:19] Epoch: [108][4400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.192 (3.159) Prec@1 71.88 (70.92) Prec@5 89.06 (88.69) + train[2018-10-17-06:59:03] Epoch: [108][4600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.903 (3.159) Prec@1 75.00 (70.92) Prec@5 89.06 (88.70) + train[2018-10-17-07:00:48] Epoch: [108][4800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.248 (3.160) Prec@1 70.31 (70.89) Prec@5 86.72 (88.68) + train[2018-10-17-07:02:33] Epoch: [108][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.124 (3.161) Prec@1 71.09 (70.87) Prec@5 92.97 (88.68) + train[2018-10-17-07:04:18] Epoch: [108][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.504 (3.161) Prec@1 64.84 (70.85) Prec@5 82.81 (88.67) + train[2018-10-17-07:06:02] Epoch: [108][5400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.007 (3.162) Prec@1 71.88 (70.83) Prec@5 89.84 (88.66) + train[2018-10-17-07:07:45] Epoch: [108][5600/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.340 (3.164) Prec@1 68.75 (70.80) Prec@5 85.94 (88.64) + train[2018-10-17-07:09:30] Epoch: [108][5800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.910 (3.164) Prec@1 78.12 (70.79) Prec@5 91.41 (88.64) + train[2018-10-17-07:11:14] Epoch: [108][6000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.833 (3.164) Prec@1 78.12 (70.80) Prec@5 89.84 (88.64) + train[2018-10-17-07:12:59] Epoch: [108][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.400 (3.164) Prec@1 64.06 (70.80) Prec@5 85.16 (88.64) + train[2018-10-17-07:14:45] Epoch: [108][6400/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.361 (3.165) Prec@1 68.75 (70.79) Prec@5 85.16 (88.63) + train[2018-10-17-07:16:31] Epoch: [108][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.350 (3.165) Prec@1 68.75 (70.80) Prec@5 85.16 (88.62) + train[2018-10-17-07:18:17] Epoch: [108][6800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.278 (3.166) Prec@1 64.84 (70.77) Prec@5 86.72 (88.60) + train[2018-10-17-07:20:04] Epoch: [108][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.307 (3.167) Prec@1 65.62 (70.76) Prec@5 85.16 (88.60) + train[2018-10-17-07:21:50] Epoch: [108][7200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.078 (3.167) Prec@1 75.00 (70.75) Prec@5 92.19 (88.60) + train[2018-10-17-07:23:36] Epoch: [108][7400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.985 (3.167) Prec@1 77.34 (70.75) Prec@5 89.84 (88.61) + train[2018-10-17-07:25:20] Epoch: [108][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.548 (3.167) Prec@1 64.84 (70.74) Prec@5 80.47 (88.59) + train[2018-10-17-07:27:05] Epoch: [108][7800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.087 (3.168) Prec@1 75.00 (70.73) Prec@5 89.84 (88.59) + train[2018-10-17-07:28:50] Epoch: [108][8000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.600 (3.168) Prec@1 62.50 (70.72) Prec@5 84.38 (88.58) + train[2018-10-17-07:30:35] Epoch: [108][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.170 (3.168) Prec@1 70.31 (70.72) Prec@5 93.75 (88.58) + train[2018-10-17-07:32:20] Epoch: [108][8400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.184 (3.169) Prec@1 70.31 (70.70) Prec@5 87.50 (88.57) + train[2018-10-17-07:34:04] Epoch: [108][8600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.196 (3.169) Prec@1 69.53 (70.70) Prec@5 88.28 (88.57) + train[2018-10-17-07:35:48] Epoch: [108][8800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.081 (3.169) Prec@1 72.66 (70.70) Prec@5 89.84 (88.57) + train[2018-10-17-07:37:32] Epoch: [108][9000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.434 (3.169) Prec@1 68.75 (70.69) Prec@5 84.38 (88.56) + train[2018-10-17-07:39:16] Epoch: [108][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.296 (3.170) Prec@1 67.97 (70.68) Prec@5 88.28 (88.55) + train[2018-10-17-07:41:02] Epoch: [108][9400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.264 (3.170) Prec@1 72.66 (70.67) Prec@5 88.28 (88.55) + train[2018-10-17-07:42:48] Epoch: [108][9600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.005 (3.170) Prec@1 70.31 (70.67) Prec@5 87.50 (88.55) + train[2018-10-17-07:44:34] Epoch: [108][9800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.015 (3.170) Prec@1 75.00 (70.66) Prec@5 90.62 (88.55) + train[2018-10-17-07:46:20] Epoch: [108][10000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.230 (3.170) Prec@1 70.31 (70.65) Prec@5 87.50 (88.55) + train[2018-10-17-07:46:24] Epoch: [108][10009/10010] Time 0.21 (0.53) Data 0.00 (0.00) Loss 4.579 (3.170) Prec@1 66.67 (70.65) Prec@5 73.33 (88.55) +[2018-10-17-07:46:24] **train** Prec@1 70.65 Prec@5 88.55 Error@1 29.35 Error@5 11.45 Loss:3.170 + test [2018-10-17-07:46:28] Epoch: [108][000/391] Time 3.72 (3.72) Data 3.59 (3.59) Loss 0.728 (0.728) Prec@1 82.03 (82.03) Prec@5 96.88 (96.88) + test [2018-10-17-07:46:54] Epoch: [108][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.448 (1.073) Prec@1 60.16 (75.26) Prec@5 89.84 (92.81) + test [2018-10-17-07:47:19] Epoch: [108][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.386 (1.246) Prec@1 45.00 (71.65) Prec@5 81.25 (90.48) +[2018-10-17-07:47:19] **test** Prec@1 71.65 Prec@5 90.48 Error@1 28.35 Error@5 9.52 Loss:1.246 +----> Best Accuracy : Acc@1=71.77, Acc@5=90.49, Error@1=28.23, Error@5=9.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-17-07:47:19] [Epoch=109/250] [Need: 208:12:43] LR=0.0036 ~ 0.0036, Batch=128 + train[2018-10-17-07:47:24] Epoch: [109][000/10010] Time 5.22 (5.22) Data 4.65 (4.65) Loss 2.889 (2.889) Prec@1 76.56 (76.56) Prec@5 92.97 (92.97) + train[2018-10-17-07:49:10] Epoch: [109][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.560 (3.172) Prec@1 65.62 (70.94) Prec@5 83.59 (88.57) + train[2018-10-17-07:50:54] Epoch: [109][400/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 3.150 (3.162) Prec@1 78.12 (70.93) Prec@5 88.28 (88.56) + train[2018-10-17-07:52:38] Epoch: [109][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.217 (3.160) Prec@1 75.78 (70.98) Prec@5 85.16 (88.60) + train[2018-10-17-07:54:22] Epoch: [109][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.438 (3.152) Prec@1 68.75 (71.08) Prec@5 83.59 (88.67) + train[2018-10-17-07:56:06] Epoch: [109][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.406 (3.153) Prec@1 69.53 (71.08) Prec@5 85.16 (88.73) + train[2018-10-17-07:57:50] Epoch: [109][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.191 (3.158) Prec@1 66.41 (70.98) Prec@5 91.41 (88.68) + train[2018-10-17-07:59:34] Epoch: [109][1400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.129 (3.155) Prec@1 71.88 (71.01) Prec@5 87.50 (88.70) + train[2018-10-17-08:01:18] Epoch: [109][1600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.933 (3.155) Prec@1 77.34 (71.02) Prec@5 94.53 (88.71) + train[2018-10-17-08:03:02] Epoch: [109][1800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.366 (3.156) Prec@1 67.19 (70.98) Prec@5 88.28 (88.70) + train[2018-10-17-08:04:46] Epoch: [109][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.486 (3.156) Prec@1 63.28 (71.00) Prec@5 86.72 (88.70) + train[2018-10-17-08:06:30] Epoch: [109][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.276 (3.155) Prec@1 68.75 (70.99) Prec@5 89.06 (88.70) + train[2018-10-17-08:08:14] Epoch: [109][2400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.202 (3.156) Prec@1 71.88 (70.96) Prec@5 88.28 (88.69) + train[2018-10-17-08:09:59] Epoch: [109][2600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.909 (3.157) Prec@1 71.09 (70.96) Prec@5 89.84 (88.67) + train[2018-10-17-08:11:44] Epoch: [109][2800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.861 (3.158) Prec@1 74.22 (70.94) Prec@5 92.97 (88.67) + train[2018-10-17-08:13:28] Epoch: [109][3000/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.361 (3.158) Prec@1 64.84 (70.95) Prec@5 87.50 (88.68) + train[2018-10-17-08:15:12] Epoch: [109][3200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.107 (3.158) Prec@1 69.53 (70.93) Prec@5 91.41 (88.68) + train[2018-10-17-08:16:56] Epoch: [109][3400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.863 (3.158) Prec@1 78.91 (70.92) Prec@5 89.06 (88.68) + train[2018-10-17-08:18:41] Epoch: [109][3600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.390 (3.159) Prec@1 67.19 (70.91) Prec@5 83.59 (88.67) + train[2018-10-17-08:20:25] Epoch: [109][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.300 (3.160) Prec@1 70.31 (70.88) Prec@5 84.38 (88.64) + train[2018-10-17-08:22:10] Epoch: [109][4000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.025 (3.159) Prec@1 76.56 (70.90) Prec@5 91.41 (88.66) + train[2018-10-17-08:23:54] Epoch: [109][4200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.322 (3.159) Prec@1 67.19 (70.89) Prec@5 85.94 (88.65) + train[2018-10-17-08:25:39] Epoch: [109][4400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.883 (3.159) Prec@1 75.00 (70.90) Prec@5 91.41 (88.65) + train[2018-10-17-08:27:24] Epoch: [109][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.219 (3.159) Prec@1 73.44 (70.89) Prec@5 88.28 (88.65) + train[2018-10-17-08:29:08] Epoch: [109][4800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.757 (3.159) Prec@1 76.56 (70.89) Prec@5 94.53 (88.65) + train[2018-10-17-08:30:51] Epoch: [109][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.229 (3.158) Prec@1 69.53 (70.90) Prec@5 89.84 (88.66) + train[2018-10-17-08:32:37] Epoch: [109][5200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.394 (3.159) Prec@1 67.19 (70.89) Prec@5 87.50 (88.66) + train[2018-10-17-08:34:24] Epoch: [109][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.295 (3.159) Prec@1 71.09 (70.87) Prec@5 86.72 (88.65) + train[2018-10-17-08:36:11] Epoch: [109][5600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.020 (3.160) Prec@1 72.66 (70.86) Prec@5 89.06 (88.65) + train[2018-10-17-08:37:58] Epoch: [109][5800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.420 (3.161) Prec@1 64.84 (70.85) Prec@5 84.38 (88.64) + train[2018-10-17-08:39:43] Epoch: [109][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.122 (3.160) Prec@1 69.53 (70.85) Prec@5 89.84 (88.64) + train[2018-10-17-08:41:29] Epoch: [109][6200/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.255 (3.161) Prec@1 67.19 (70.82) Prec@5 90.62 (88.63) + train[2018-10-17-08:43:16] Epoch: [109][6400/10010] Time 0.59 (0.52) Data 0.00 (0.00) Loss 3.396 (3.162) Prec@1 67.97 (70.80) Prec@5 84.38 (88.62) + train[2018-10-17-08:45:03] Epoch: [109][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.984 (3.163) Prec@1 75.00 (70.79) Prec@5 92.97 (88.62) + train[2018-10-17-08:46:50] Epoch: [109][6800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.083 (3.163) Prec@1 71.09 (70.78) Prec@5 92.19 (88.60) + train[2018-10-17-08:48:37] Epoch: [109][7000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.937 (3.163) Prec@1 72.66 (70.77) Prec@5 90.62 (88.60) + train[2018-10-17-08:50:23] Epoch: [109][7200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.983 (3.164) Prec@1 74.22 (70.77) Prec@5 88.28 (88.59) + train[2018-10-17-08:52:10] Epoch: [109][7400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.380 (3.164) Prec@1 64.84 (70.76) Prec@5 86.72 (88.58) + train[2018-10-17-08:53:58] Epoch: [109][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.272 (3.165) Prec@1 64.84 (70.75) Prec@5 88.28 (88.58) + train[2018-10-17-08:55:44] Epoch: [109][7800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.847 (3.165) Prec@1 76.56 (70.74) Prec@5 90.62 (88.57) + train[2018-10-17-08:57:31] Epoch: [109][8000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.694 (3.166) Prec@1 80.47 (70.73) Prec@5 96.88 (88.57) + train[2018-10-17-08:59:18] Epoch: [109][8200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.141 (3.167) Prec@1 71.88 (70.72) Prec@5 88.28 (88.56) + train[2018-10-17-09:01:04] Epoch: [109][8400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.164 (3.167) Prec@1 74.22 (70.72) Prec@5 91.41 (88.57) + train[2018-10-17-09:02:51] Epoch: [109][8600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.203 (3.166) Prec@1 71.88 (70.72) Prec@5 87.50 (88.57) + train[2018-10-17-09:04:37] Epoch: [109][8800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.182 (3.167) Prec@1 70.31 (70.72) Prec@5 89.06 (88.56) + train[2018-10-17-09:06:25] Epoch: [109][9000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.258 (3.167) Prec@1 71.09 (70.71) Prec@5 87.50 (88.56) + train[2018-10-17-09:08:13] Epoch: [109][9200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.131 (3.167) Prec@1 70.31 (70.70) Prec@5 89.06 (88.56) + train[2018-10-17-09:10:00] Epoch: [109][9400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.139 (3.168) Prec@1 69.53 (70.70) Prec@5 89.06 (88.55) + train[2018-10-17-09:11:47] Epoch: [109][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.029 (3.168) Prec@1 71.88 (70.69) Prec@5 92.97 (88.55) + train[2018-10-17-09:13:34] Epoch: [109][9800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.084 (3.168) Prec@1 68.75 (70.68) Prec@5 91.41 (88.55) + train[2018-10-17-09:15:20] Epoch: [109][10000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.116 (3.169) Prec@1 71.09 (70.67) Prec@5 91.41 (88.55) + train[2018-10-17-09:15:25] Epoch: [109][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.382 (3.169) Prec@1 73.33 (70.68) Prec@5 93.33 (88.55) +[2018-10-17-09:15:25] **train** Prec@1 70.68 Prec@5 88.55 Error@1 29.32 Error@5 11.45 Loss:3.169 + test [2018-10-17-09:15:29] Epoch: [109][000/391] Time 4.26 (4.26) Data 4.13 (4.13) Loss 0.653 (0.653) Prec@1 86.72 (86.72) Prec@5 97.66 (97.66) + test [2018-10-17-09:15:55] Epoch: [109][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.246 (1.070) Prec@1 67.19 (75.38) Prec@5 94.53 (92.89) + test [2018-10-17-09:16:20] Epoch: [109][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.127 (1.237) Prec@1 46.25 (71.85) Prec@5 82.50 (90.54) +[2018-10-17-09:16:20] **test** Prec@1 71.85 Prec@5 90.54 Error@1 28.15 Error@5 9.46 Loss:1.237 +----> Best Accuracy : Acc@1=71.85, Acc@5=90.54, Error@1=28.15, Error@5=9.46 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-17-09:16:20] [Epoch=110/250] [Need: 207:41:36] LR=0.0035 ~ 0.0035, Batch=128 + train[2018-10-17-09:16:24] Epoch: [110][000/10010] Time 4.59 (4.59) Data 3.92 (3.92) Loss 2.964 (2.964) Prec@1 73.44 (73.44) Prec@5 95.31 (95.31) + train[2018-10-17-09:18:09] Epoch: [110][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.189 (3.163) Prec@1 71.88 (70.90) Prec@5 88.28 (88.79) + train[2018-10-17-09:19:53] Epoch: [110][400/10010] Time 0.58 (0.53) Data 0.00 (0.01) Loss 3.176 (3.149) Prec@1 69.53 (71.07) Prec@5 85.94 (88.89) + train[2018-10-17-09:21:38] Epoch: [110][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.364 (3.142) Prec@1 68.75 (71.28) Prec@5 85.94 (88.93) + train[2018-10-17-09:23:24] Epoch: [110][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.244 (3.144) Prec@1 66.41 (71.28) Prec@5 86.72 (88.89) + train[2018-10-17-09:25:08] Epoch: [110][1000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.157 (3.144) Prec@1 67.97 (71.19) Prec@5 89.06 (88.90) + train[2018-10-17-09:26:52] Epoch: [110][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.066 (3.148) Prec@1 78.91 (71.19) Prec@5 89.84 (88.81) + train[2018-10-17-09:28:36] Epoch: [110][1400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.111 (3.146) Prec@1 73.44 (71.27) Prec@5 89.06 (88.80) + train[2018-10-17-09:30:21] Epoch: [110][1600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.113 (3.149) Prec@1 73.44 (71.21) Prec@5 89.84 (88.78) + train[2018-10-17-09:32:06] Epoch: [110][1800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.080 (3.146) Prec@1 72.66 (71.23) Prec@5 89.06 (88.83) + train[2018-10-17-09:33:51] Epoch: [110][2000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.039 (3.145) Prec@1 75.78 (71.22) Prec@5 89.84 (88.83) + train[2018-10-17-09:35:36] Epoch: [110][2200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.201 (3.145) Prec@1 72.66 (71.21) Prec@5 89.06 (88.84) + train[2018-10-17-09:37:21] Epoch: [110][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.111 (3.145) Prec@1 71.09 (71.23) Prec@5 89.06 (88.84) + train[2018-10-17-09:39:05] Epoch: [110][2600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.082 (3.146) Prec@1 70.31 (71.22) Prec@5 91.41 (88.81) + train[2018-10-17-09:40:51] Epoch: [110][2800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.927 (3.147) Prec@1 77.34 (71.20) Prec@5 89.06 (88.80) + train[2018-10-17-09:42:35] Epoch: [110][3000/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.002 (3.146) Prec@1 73.44 (71.19) Prec@5 91.41 (88.81) + train[2018-10-17-09:44:19] Epoch: [110][3200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.996 (3.147) Prec@1 77.34 (71.19) Prec@5 87.50 (88.81) + train[2018-10-17-09:46:03] Epoch: [110][3400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.237 (3.148) Prec@1 70.31 (71.15) Prec@5 87.50 (88.79) + train[2018-10-17-09:47:49] Epoch: [110][3600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.702 (3.147) Prec@1 60.94 (71.17) Prec@5 85.16 (88.81) + train[2018-10-17-09:49:34] Epoch: [110][3800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.174 (3.148) Prec@1 70.31 (71.15) Prec@5 89.84 (88.80) + train[2018-10-17-09:51:19] Epoch: [110][4000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.162 (3.148) Prec@1 67.97 (71.14) Prec@5 88.28 (88.80) + train[2018-10-17-09:53:05] Epoch: [110][4200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 2.876 (3.149) Prec@1 71.09 (71.13) Prec@5 90.62 (88.79) + train[2018-10-17-09:54:50] Epoch: [110][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.911 (3.149) Prec@1 72.66 (71.12) Prec@5 93.75 (88.79) + train[2018-10-17-09:56:34] Epoch: [110][4600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.869 (3.148) Prec@1 75.78 (71.13) Prec@5 92.19 (88.80) + train[2018-10-17-09:58:19] Epoch: [110][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.757 (3.148) Prec@1 78.91 (71.13) Prec@5 92.19 (88.80) + train[2018-10-17-10:00:03] Epoch: [110][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.016 (3.149) Prec@1 76.56 (71.11) Prec@5 90.62 (88.79) + train[2018-10-17-10:01:48] Epoch: [110][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.939 (3.150) Prec@1 78.91 (71.10) Prec@5 92.97 (88.79) + train[2018-10-17-10:03:31] Epoch: [110][5400/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.040 (3.150) Prec@1 75.78 (71.09) Prec@5 89.84 (88.78) + train[2018-10-17-10:05:16] Epoch: [110][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.510 (3.151) Prec@1 60.94 (71.08) Prec@5 86.72 (88.77) + train[2018-10-17-10:07:00] Epoch: [110][5800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.811 (3.151) Prec@1 77.34 (71.08) Prec@5 92.97 (88.76) + train[2018-10-17-10:08:45] Epoch: [110][6000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.540 (3.152) Prec@1 64.06 (71.06) Prec@5 82.03 (88.74) + train[2018-10-17-10:10:32] Epoch: [110][6200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.450 (3.152) Prec@1 64.84 (71.07) Prec@5 82.81 (88.74) + train[2018-10-17-10:12:19] Epoch: [110][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.238 (3.152) Prec@1 71.88 (71.06) Prec@5 88.28 (88.74) + train[2018-10-17-10:14:06] Epoch: [110][6600/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 3.460 (3.152) Prec@1 64.06 (71.05) Prec@5 85.16 (88.74) + train[2018-10-17-10:15:52] Epoch: [110][6800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.527 (3.153) Prec@1 62.50 (71.03) Prec@5 83.59 (88.73) + train[2018-10-17-10:17:37] Epoch: [110][7000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.415 (3.153) Prec@1 70.31 (71.03) Prec@5 85.94 (88.73) + train[2018-10-17-10:19:23] Epoch: [110][7200/10010] Time 0.61 (0.53) Data 0.00 (0.00) Loss 3.173 (3.153) Prec@1 68.75 (71.03) Prec@5 88.28 (88.72) + train[2018-10-17-10:21:09] Epoch: [110][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.185 (3.153) Prec@1 74.22 (71.01) Prec@5 85.16 (88.72) + train[2018-10-17-10:22:56] Epoch: [110][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.980 (3.153) Prec@1 71.09 (71.01) Prec@5 92.19 (88.72) + train[2018-10-17-10:24:43] Epoch: [110][7800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.333 (3.154) Prec@1 65.62 (70.99) Prec@5 90.62 (88.71) + train[2018-10-17-10:26:28] Epoch: [110][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.189 (3.154) Prec@1 71.09 (70.98) Prec@5 88.28 (88.71) + train[2018-10-17-10:28:15] Epoch: [110][8200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.206 (3.155) Prec@1 73.44 (70.97) Prec@5 86.72 (88.70) + train[2018-10-17-10:30:01] Epoch: [110][8400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.003 (3.155) Prec@1 76.56 (70.97) Prec@5 90.62 (88.70) + train[2018-10-17-10:31:48] Epoch: [110][8600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.198 (3.156) Prec@1 70.31 (70.95) Prec@5 88.28 (88.70) + train[2018-10-17-10:33:35] Epoch: [110][8800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.904 (3.156) Prec@1 74.22 (70.94) Prec@5 90.62 (88.69) + train[2018-10-17-10:35:22] Epoch: [110][9000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.630 (3.156) Prec@1 65.62 (70.94) Prec@5 81.25 (88.68) + train[2018-10-17-10:37:09] Epoch: [110][9200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.789 (3.157) Prec@1 78.12 (70.93) Prec@5 93.75 (88.68) + train[2018-10-17-10:38:55] Epoch: [110][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.336 (3.157) Prec@1 65.62 (70.92) Prec@5 90.62 (88.68) + train[2018-10-17-10:40:41] Epoch: [110][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.279 (3.157) Prec@1 66.41 (70.91) Prec@5 85.94 (88.68) + train[2018-10-17-10:42:28] Epoch: [110][9800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.049 (3.158) Prec@1 75.00 (70.91) Prec@5 90.62 (88.67) + train[2018-10-17-10:44:14] Epoch: [110][10000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.179 (3.158) Prec@1 69.53 (70.90) Prec@5 87.50 (88.66) + train[2018-10-17-10:44:19] Epoch: [110][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 2.725 (3.158) Prec@1 73.33 (70.90) Prec@5 93.33 (88.66) +[2018-10-17-10:44:19] **train** Prec@1 70.90 Prec@5 88.66 Error@1 29.10 Error@5 11.34 Loss:3.158 + test [2018-10-17-10:44:23] Epoch: [110][000/391] Time 3.93 (3.93) Data 3.80 (3.80) Loss 0.615 (0.615) Prec@1 89.06 (89.06) Prec@5 97.66 (97.66) + test [2018-10-17-10:44:49] Epoch: [110][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.325 (1.066) Prec@1 64.84 (75.56) Prec@5 92.19 (92.87) + test [2018-10-17-10:45:14] Epoch: [110][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.074 (1.230) Prec@1 46.25 (72.05) Prec@5 81.25 (90.54) +[2018-10-17-10:45:14] **test** Prec@1 72.05 Prec@5 90.54 Error@1 27.95 Error@5 9.46 Loss:1.230 +----> Best Accuracy : Acc@1=72.05, Acc@5=90.54, Error@1=27.95, Error@5=9.46 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-17-10:45:14] [Epoch=111/250] [Need: 205:58:14] LR=0.0034 ~ 0.0034, Batch=128 + train[2018-10-17-10:45:19] Epoch: [111][000/10010] Time 5.05 (5.05) Data 4.49 (4.49) Loss 3.180 (3.180) Prec@1 70.31 (70.31) Prec@5 85.94 (85.94) + train[2018-10-17-10:47:03] Epoch: [111][200/10010] Time 0.56 (0.54) Data 0.00 (0.02) Loss 2.991 (3.108) Prec@1 73.44 (71.66) Prec@5 90.62 (89.46) + train[2018-10-17-10:48:48] Epoch: [111][400/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.132 (3.120) Prec@1 71.09 (71.48) Prec@5 90.62 (89.18) + train[2018-10-17-10:50:33] Epoch: [111][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 2.589 (3.125) Prec@1 76.56 (71.44) Prec@5 95.31 (89.09) + train[2018-10-17-10:52:17] Epoch: [111][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.335 (3.129) Prec@1 70.31 (71.52) Prec@5 88.28 (89.05) + train[2018-10-17-10:54:01] Epoch: [111][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.283 (3.130) Prec@1 71.09 (71.48) Prec@5 88.28 (89.07) + train[2018-10-17-10:55:47] Epoch: [111][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.135 (3.130) Prec@1 71.88 (71.51) Prec@5 88.28 (89.07) + train[2018-10-17-10:57:33] Epoch: [111][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.829 (3.131) Prec@1 75.78 (71.52) Prec@5 90.62 (89.05) + train[2018-10-17-10:59:18] Epoch: [111][1600/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 2.928 (3.133) Prec@1 76.56 (71.46) Prec@5 92.97 (89.04) + train[2018-10-17-11:01:03] Epoch: [111][1800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.819 (3.132) Prec@1 76.56 (71.44) Prec@5 92.97 (89.03) + train[2018-10-17-11:02:49] Epoch: [111][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.987 (3.131) Prec@1 78.12 (71.48) Prec@5 88.28 (89.03) + train[2018-10-17-11:04:34] Epoch: [111][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.831 (3.134) Prec@1 75.78 (71.44) Prec@5 89.84 (89.00) + train[2018-10-17-11:06:19] Epoch: [111][2400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.448 (3.135) Prec@1 64.84 (71.44) Prec@5 82.03 (88.99) + train[2018-10-17-11:08:05] Epoch: [111][2600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.505 (3.137) Prec@1 66.41 (71.40) Prec@5 85.94 (88.95) + train[2018-10-17-11:09:49] Epoch: [111][2800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.241 (3.137) Prec@1 71.88 (71.41) Prec@5 89.06 (88.96) + train[2018-10-17-11:11:35] Epoch: [111][3000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.058 (3.139) Prec@1 73.44 (71.37) Prec@5 87.50 (88.95) + train[2018-10-17-11:13:22] Epoch: [111][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.420 (3.140) Prec@1 60.94 (71.33) Prec@5 89.84 (88.92) + train[2018-10-17-11:15:07] Epoch: [111][3400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.958 (3.141) Prec@1 73.44 (71.30) Prec@5 90.62 (88.91) + train[2018-10-17-11:16:53] Epoch: [111][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.774 (3.142) Prec@1 81.25 (71.29) Prec@5 92.97 (88.90) + train[2018-10-17-11:18:39] Epoch: [111][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.808 (3.142) Prec@1 78.12 (71.28) Prec@5 92.19 (88.91) + train[2018-10-17-11:20:26] Epoch: [111][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.236 (3.142) Prec@1 68.75 (71.26) Prec@5 88.28 (88.90) + train[2018-10-17-11:22:12] Epoch: [111][4200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.966 (3.142) Prec@1 71.88 (71.24) Prec@5 89.84 (88.90) + train[2018-10-17-11:23:58] Epoch: [111][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.245 (3.142) Prec@1 68.75 (71.24) Prec@5 88.28 (88.89) + train[2018-10-17-11:25:45] Epoch: [111][4600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.037 (3.143) Prec@1 71.88 (71.23) Prec@5 91.41 (88.89) + train[2018-10-17-11:27:31] Epoch: [111][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.281 (3.143) Prec@1 68.75 (71.22) Prec@5 87.50 (88.89) + train[2018-10-17-11:29:16] Epoch: [111][5000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.121 (3.143) Prec@1 71.88 (71.21) Prec@5 89.06 (88.87) + train[2018-10-17-11:31:02] Epoch: [111][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.244 (3.144) Prec@1 66.41 (71.20) Prec@5 90.62 (88.86) + train[2018-10-17-11:32:46] Epoch: [111][5400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.247 (3.144) Prec@1 67.19 (71.19) Prec@5 90.62 (88.86) + train[2018-10-17-11:34:32] Epoch: [111][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.243 (3.145) Prec@1 69.53 (71.18) Prec@5 88.28 (88.85) + train[2018-10-17-11:36:19] Epoch: [111][5800/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 3.152 (3.145) Prec@1 71.09 (71.17) Prec@5 88.28 (88.85) + train[2018-10-17-11:38:06] Epoch: [111][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.082 (3.145) Prec@1 72.66 (71.17) Prec@5 92.19 (88.85) + train[2018-10-17-11:39:53] Epoch: [111][6200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.358 (3.145) Prec@1 67.19 (71.16) Prec@5 82.81 (88.84) + train[2018-10-17-11:41:39] Epoch: [111][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.769 (3.146) Prec@1 61.72 (71.14) Prec@5 80.47 (88.83) + train[2018-10-17-11:43:25] Epoch: [111][6600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.981 (3.147) Prec@1 75.00 (71.13) Prec@5 89.06 (88.83) + train[2018-10-17-11:45:11] Epoch: [111][6800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.982 (3.147) Prec@1 74.22 (71.12) Prec@5 90.62 (88.82) + train[2018-10-17-11:46:58] Epoch: [111][7000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.165 (3.148) Prec@1 71.09 (71.11) Prec@5 89.06 (88.81) + train[2018-10-17-11:48:44] Epoch: [111][7200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.052 (3.149) Prec@1 69.53 (71.10) Prec@5 89.84 (88.80) + train[2018-10-17-11:50:30] Epoch: [111][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.402 (3.149) Prec@1 66.41 (71.09) Prec@5 83.59 (88.79) + train[2018-10-17-11:52:16] Epoch: [111][7600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.865 (3.149) Prec@1 75.78 (71.08) Prec@5 91.41 (88.79) + train[2018-10-17-11:54:02] Epoch: [111][7800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.376 (3.150) Prec@1 70.31 (71.06) Prec@5 86.72 (88.79) + train[2018-10-17-11:55:47] Epoch: [111][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.168 (3.150) Prec@1 70.31 (71.05) Prec@5 89.06 (88.78) + train[2018-10-17-11:57:33] Epoch: [111][8200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.808 (3.151) Prec@1 77.34 (71.04) Prec@5 92.19 (88.77) + train[2018-10-17-11:59:19] Epoch: [111][8400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.708 (3.152) Prec@1 79.69 (71.02) Prec@5 94.53 (88.77) + train[2018-10-17-12:01:05] Epoch: [111][8600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.185 (3.152) Prec@1 71.88 (71.01) Prec@5 88.28 (88.76) + train[2018-10-17-12:02:50] Epoch: [111][8800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.168 (3.152) Prec@1 71.09 (71.02) Prec@5 87.50 (88.76) + train[2018-10-17-12:04:34] Epoch: [111][9000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.147 (3.152) Prec@1 64.06 (71.02) Prec@5 90.62 (88.76) + train[2018-10-17-12:06:20] Epoch: [111][9200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.052 (3.153) Prec@1 73.44 (71.01) Prec@5 88.28 (88.75) + train[2018-10-17-12:08:07] Epoch: [111][9400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.385 (3.153) Prec@1 67.19 (71.01) Prec@5 89.06 (88.75) + train[2018-10-17-12:09:53] Epoch: [111][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.274 (3.154) Prec@1 69.53 (71.00) Prec@5 87.50 (88.74) + train[2018-10-17-12:11:38] Epoch: [111][9800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.158 (3.154) Prec@1 69.53 (70.99) Prec@5 89.06 (88.73) + train[2018-10-17-12:13:23] Epoch: [111][10000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.051 (3.154) Prec@1 70.31 (70.98) Prec@5 91.41 (88.72) + train[2018-10-17-12:13:27] Epoch: [111][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.875 (3.154) Prec@1 60.00 (70.98) Prec@5 80.00 (88.72) +[2018-10-17-12:13:27] **train** Prec@1 70.98 Prec@5 88.72 Error@1 29.02 Error@5 11.28 Loss:3.154 + test [2018-10-17-12:13:31] Epoch: [111][000/391] Time 3.82 (3.82) Data 3.68 (3.68) Loss 0.549 (0.549) Prec@1 92.97 (92.97) Prec@5 99.22 (99.22) + test [2018-10-17-12:13:57] Epoch: [111][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.341 (1.059) Prec@1 64.06 (75.60) Prec@5 92.19 (93.03) + test [2018-10-17-12:14:21] Epoch: [111][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.319 (1.226) Prec@1 43.75 (72.07) Prec@5 81.25 (90.59) +[2018-10-17-12:14:21] **test** Prec@1 72.07 Prec@5 90.59 Error@1 27.93 Error@5 9.41 Loss:1.226 +----> Best Accuracy : Acc@1=72.07, Acc@5=90.59, Error@1=27.93, Error@5=9.41 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-17-12:14:22] [Epoch=112/250] [Need: 204:58:55] LR=0.0033 ~ 0.0033, Batch=128 + train[2018-10-17-12:14:26] Epoch: [112][000/10010] Time 4.41 (4.41) Data 3.76 (3.76) Loss 3.111 (3.111) Prec@1 71.88 (71.88) Prec@5 92.19 (92.19) + train[2018-10-17-12:16:11] Epoch: [112][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 3.095 (3.118) Prec@1 75.00 (71.40) Prec@5 87.50 (89.19) + train[2018-10-17-12:17:55] Epoch: [112][400/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 2.807 (3.116) Prec@1 78.12 (71.55) Prec@5 92.19 (89.16) + train[2018-10-17-12:19:42] Epoch: [112][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 2.959 (3.117) Prec@1 73.44 (71.66) Prec@5 91.41 (89.15) + train[2018-10-17-12:21:29] Epoch: [112][800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.113 (3.120) Prec@1 71.88 (71.60) Prec@5 89.06 (89.13) + train[2018-10-17-12:23:15] Epoch: [112][1000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.134 (3.122) Prec@1 75.00 (71.56) Prec@5 88.28 (89.08) + train[2018-10-17-12:25:02] Epoch: [112][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.130 (3.127) Prec@1 71.09 (71.45) Prec@5 89.84 (88.98) + train[2018-10-17-12:26:48] Epoch: [112][1400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.160 (3.131) Prec@1 69.53 (71.36) Prec@5 88.28 (88.97) + train[2018-10-17-12:28:34] Epoch: [112][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.088 (3.132) Prec@1 67.97 (71.35) Prec@5 91.41 (88.97) + train[2018-10-17-12:30:20] Epoch: [112][1800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.895 (3.130) Prec@1 77.34 (71.38) Prec@5 89.06 (89.00) + train[2018-10-17-12:32:05] Epoch: [112][2000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.175 (3.131) Prec@1 74.22 (71.39) Prec@5 87.50 (88.97) + train[2018-10-17-12:33:51] Epoch: [112][2200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.384 (3.132) Prec@1 69.53 (71.37) Prec@5 85.94 (88.93) + train[2018-10-17-12:35:38] Epoch: [112][2400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.974 (3.133) Prec@1 70.31 (71.37) Prec@5 93.75 (88.92) + train[2018-10-17-12:37:24] Epoch: [112][2600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.274 (3.134) Prec@1 69.53 (71.33) Prec@5 89.84 (88.91) + train[2018-10-17-12:39:09] Epoch: [112][2800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.083 (3.136) Prec@1 71.09 (71.30) Prec@5 90.62 (88.90) + train[2018-10-17-12:40:55] Epoch: [112][3000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.935 (3.137) Prec@1 70.31 (71.28) Prec@5 94.53 (88.90) + train[2018-10-17-12:42:42] Epoch: [112][3200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.317 (3.137) Prec@1 64.06 (71.27) Prec@5 89.84 (88.91) + train[2018-10-17-12:44:28] Epoch: [112][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.143 (3.138) Prec@1 72.66 (71.27) Prec@5 83.59 (88.88) + train[2018-10-17-12:46:15] Epoch: [112][3600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.083 (3.138) Prec@1 71.88 (71.27) Prec@5 89.84 (88.88) + train[2018-10-17-12:48:00] Epoch: [112][3800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.609 (3.138) Prec@1 59.38 (71.25) Prec@5 85.94 (88.88) + train[2018-10-17-12:49:47] Epoch: [112][4000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.934 (3.138) Prec@1 76.56 (71.24) Prec@5 92.97 (88.89) + train[2018-10-17-12:51:33] Epoch: [112][4200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.591 (3.137) Prec@1 63.28 (71.26) Prec@5 83.59 (88.90) + train[2018-10-17-12:53:19] Epoch: [112][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.129 (3.137) Prec@1 75.00 (71.28) Prec@5 89.06 (88.89) + train[2018-10-17-12:55:05] Epoch: [112][4600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.226 (3.137) Prec@1 65.62 (71.27) Prec@5 86.72 (88.89) + train[2018-10-17-12:56:51] Epoch: [112][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.114 (3.138) Prec@1 69.53 (71.26) Prec@5 89.06 (88.89) + train[2018-10-17-12:58:37] Epoch: [112][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.031 (3.139) Prec@1 70.31 (71.23) Prec@5 89.06 (88.86) + train[2018-10-17-13:00:23] Epoch: [112][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.029 (3.140) Prec@1 72.66 (71.20) Prec@5 86.72 (88.86) + train[2018-10-17-13:02:10] Epoch: [112][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.356 (3.140) Prec@1 67.97 (71.19) Prec@5 86.72 (88.85) + train[2018-10-17-13:03:57] Epoch: [112][5600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.053 (3.141) Prec@1 71.09 (71.18) Prec@5 89.84 (88.85) + train[2018-10-17-13:05:44] Epoch: [112][5800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.128 (3.142) Prec@1 72.66 (71.17) Prec@5 89.06 (88.83) + train[2018-10-17-13:07:30] Epoch: [112][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.471 (3.143) Prec@1 67.97 (71.16) Prec@5 87.50 (88.82) + train[2018-10-17-13:09:16] Epoch: [112][6200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.172 (3.144) Prec@1 66.41 (71.16) Prec@5 89.06 (88.81) + train[2018-10-17-13:11:00] Epoch: [112][6400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.849 (3.144) Prec@1 74.22 (71.17) Prec@5 94.53 (88.81) + train[2018-10-17-13:12:47] Epoch: [112][6600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.298 (3.144) Prec@1 68.75 (71.17) Prec@5 89.06 (88.80) + train[2018-10-17-13:14:34] Epoch: [112][6800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.885 (3.145) Prec@1 74.22 (71.16) Prec@5 92.19 (88.79) + train[2018-10-17-13:16:20] Epoch: [112][7000/10010] Time 0.61 (0.53) Data 0.00 (0.00) Loss 3.168 (3.145) Prec@1 71.88 (71.16) Prec@5 86.72 (88.79) + train[2018-10-17-13:18:06] Epoch: [112][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.793 (3.145) Prec@1 76.56 (71.16) Prec@5 96.09 (88.79) + train[2018-10-17-13:19:52] Epoch: [112][7400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.371 (3.145) Prec@1 67.19 (71.15) Prec@5 88.28 (88.79) + train[2018-10-17-13:21:38] Epoch: [112][7600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.269 (3.145) Prec@1 67.97 (71.15) Prec@5 87.50 (88.80) + train[2018-10-17-13:23:24] Epoch: [112][7800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.928 (3.145) Prec@1 73.44 (71.15) Prec@5 91.41 (88.80) + train[2018-10-17-13:25:12] Epoch: [112][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.154 (3.146) Prec@1 67.97 (71.14) Prec@5 85.94 (88.79) + train[2018-10-17-13:26:59] Epoch: [112][8200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.044 (3.146) Prec@1 71.09 (71.13) Prec@5 89.84 (88.79) + train[2018-10-17-13:28:46] Epoch: [112][8400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.063 (3.146) Prec@1 72.66 (71.13) Prec@5 92.97 (88.80) + train[2018-10-17-13:30:34] Epoch: [112][8600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.254 (3.147) Prec@1 68.75 (71.12) Prec@5 87.50 (88.79) + train[2018-10-17-13:32:21] Epoch: [112][8800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.950 (3.147) Prec@1 73.44 (71.12) Prec@5 91.41 (88.79) + train[2018-10-17-13:34:08] Epoch: [112][9000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.141 (3.147) Prec@1 69.53 (71.10) Prec@5 85.94 (88.78) + train[2018-10-17-13:35:54] Epoch: [112][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.164 (3.147) Prec@1 67.19 (71.09) Prec@5 89.06 (88.78) + train[2018-10-17-13:37:39] Epoch: [112][9400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.032 (3.147) Prec@1 77.34 (71.09) Prec@5 90.62 (88.78) + train[2018-10-17-13:39:24] Epoch: [112][9600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.189 (3.147) Prec@1 67.19 (71.09) Prec@5 89.84 (88.78) + train[2018-10-17-13:41:08] Epoch: [112][9800/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.089 (3.147) Prec@1 69.53 (71.09) Prec@5 88.28 (88.78) + train[2018-10-17-13:42:52] Epoch: [112][10000/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.065 (3.148) Prec@1 73.44 (71.09) Prec@5 89.84 (88.78) + train[2018-10-17-13:42:57] Epoch: [112][10009/10010] Time 0.14 (0.53) Data 0.00 (0.00) Loss 4.500 (3.148) Prec@1 46.67 (71.09) Prec@5 73.33 (88.78) +[2018-10-17-13:42:57] **train** Prec@1 71.09 Prec@5 88.78 Error@1 28.91 Error@5 11.22 Loss:3.148 + test [2018-10-17-13:43:01] Epoch: [112][000/391] Time 4.01 (4.01) Data 3.87 (3.87) Loss 0.650 (0.650) Prec@1 85.16 (85.16) Prec@5 96.09 (96.09) + test [2018-10-17-13:43:28] Epoch: [112][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.379 (1.062) Prec@1 66.41 (75.67) Prec@5 89.84 (92.91) + test [2018-10-17-13:43:52] Epoch: [112][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.346 (1.227) Prec@1 37.50 (72.10) Prec@5 78.75 (90.55) +[2018-10-17-13:43:52] **test** Prec@1 72.10 Prec@5 90.55 Error@1 27.90 Error@5 9.45 Loss:1.227 +----> Best Accuracy : Acc@1=72.10, Acc@5=90.55, Error@1=27.90, Error@5=9.45 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-17-13:43:52] [Epoch=113/250] [Need: 204:22:42] LR=0.0032 ~ 0.0032, Batch=128 + train[2018-10-17-13:43:57] Epoch: [113][000/10010] Time 5.04 (5.04) Data 4.40 (4.40) Loss 3.530 (3.530) Prec@1 59.38 (59.38) Prec@5 85.94 (85.94) + train[2018-10-17-13:45:42] Epoch: [113][200/10010] Time 0.55 (0.55) Data 0.00 (0.02) Loss 3.353 (3.126) Prec@1 68.75 (71.49) Prec@5 87.50 (89.16) + train[2018-10-17-13:47:27] Epoch: [113][400/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 3.099 (3.116) Prec@1 71.88 (71.62) Prec@5 89.06 (89.21) + train[2018-10-17-13:49:10] Epoch: [113][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.084 (3.113) Prec@1 67.19 (71.64) Prec@5 92.19 (89.22) + train[2018-10-17-13:50:55] Epoch: [113][800/10010] Time 0.49 (0.53) Data 0.00 (0.01) Loss 3.040 (3.116) Prec@1 73.44 (71.71) Prec@5 89.06 (89.16) + train[2018-10-17-13:52:39] Epoch: [113][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.960 (3.112) Prec@1 77.34 (71.76) Prec@5 89.06 (89.21) + train[2018-10-17-13:54:24] Epoch: [113][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.078 (3.118) Prec@1 71.09 (71.63) Prec@5 89.06 (89.13) + train[2018-10-17-13:56:09] Epoch: [113][1400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.344 (3.117) Prec@1 67.19 (71.61) Prec@5 85.94 (89.13) + train[2018-10-17-13:57:53] Epoch: [113][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.287 (3.118) Prec@1 67.97 (71.62) Prec@5 87.50 (89.11) + train[2018-10-17-13:59:37] Epoch: [113][1800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.973 (3.123) Prec@1 75.00 (71.57) Prec@5 89.06 (89.06) + train[2018-10-17-14:01:22] Epoch: [113][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.368 (3.124) Prec@1 65.62 (71.57) Prec@5 85.94 (89.05) + train[2018-10-17-14:03:06] Epoch: [113][2200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.528 (3.126) Prec@1 64.84 (71.50) Prec@5 82.81 (89.05) + train[2018-10-17-14:04:51] Epoch: [113][2400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.040 (3.127) Prec@1 71.88 (71.46) Prec@5 92.19 (89.03) + train[2018-10-17-14:06:36] Epoch: [113][2600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.259 (3.129) Prec@1 67.97 (71.44) Prec@5 89.06 (89.01) + train[2018-10-17-14:08:20] Epoch: [113][2800/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.197 (3.130) Prec@1 76.56 (71.44) Prec@5 86.72 (89.01) + train[2018-10-17-14:10:04] Epoch: [113][3000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.156 (3.129) Prec@1 72.66 (71.45) Prec@5 87.50 (89.01) + train[2018-10-17-14:11:49] Epoch: [113][3200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.140 (3.129) Prec@1 70.31 (71.43) Prec@5 89.06 (89.03) + train[2018-10-17-14:13:37] Epoch: [113][3400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.951 (3.130) Prec@1 75.00 (71.40) Prec@5 92.19 (89.01) + train[2018-10-17-14:15:24] Epoch: [113][3600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.195 (3.130) Prec@1 67.19 (71.41) Prec@5 89.06 (89.02) + train[2018-10-17-14:17:10] Epoch: [113][3800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.248 (3.130) Prec@1 70.31 (71.42) Prec@5 85.94 (89.02) + train[2018-10-17-14:18:56] Epoch: [113][4000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.256 (3.132) Prec@1 70.31 (71.38) Prec@5 87.50 (89.00) + train[2018-10-17-14:20:39] Epoch: [113][4200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.574 (3.133) Prec@1 60.94 (71.36) Prec@5 83.59 (88.97) + train[2018-10-17-14:22:24] Epoch: [113][4400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.238 (3.131) Prec@1 66.41 (71.38) Prec@5 90.62 (88.99) + train[2018-10-17-14:24:09] Epoch: [113][4600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.275 (3.132) Prec@1 70.31 (71.36) Prec@5 87.50 (88.98) + train[2018-10-17-14:25:53] Epoch: [113][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.101 (3.132) Prec@1 72.66 (71.36) Prec@5 90.62 (88.98) + train[2018-10-17-14:27:38] Epoch: [113][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.319 (3.132) Prec@1 70.31 (71.37) Prec@5 84.38 (88.99) + train[2018-10-17-14:29:23] Epoch: [113][5200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.027 (3.132) Prec@1 71.88 (71.38) Prec@5 89.84 (88.99) + train[2018-10-17-14:31:08] Epoch: [113][5400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.767 (3.133) Prec@1 78.12 (71.37) Prec@5 91.41 (88.99) + train[2018-10-17-14:32:53] Epoch: [113][5600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.536 (3.133) Prec@1 67.19 (71.37) Prec@5 85.94 (88.99) + train[2018-10-17-14:34:37] Epoch: [113][5800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.501 (3.133) Prec@1 61.72 (71.36) Prec@5 85.16 (88.99) + train[2018-10-17-14:36:21] Epoch: [113][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.935 (3.133) Prec@1 74.22 (71.35) Prec@5 92.97 (88.99) + train[2018-10-17-14:38:07] Epoch: [113][6200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.857 (3.133) Prec@1 78.12 (71.35) Prec@5 92.19 (88.99) + train[2018-10-17-14:39:50] Epoch: [113][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.112 (3.134) Prec@1 67.19 (71.34) Prec@5 91.41 (88.99) + train[2018-10-17-14:41:34] Epoch: [113][6600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.230 (3.134) Prec@1 67.97 (71.34) Prec@5 91.41 (88.98) + train[2018-10-17-14:43:19] Epoch: [113][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.263 (3.134) Prec@1 73.44 (71.33) Prec@5 88.28 (88.97) + train[2018-10-17-14:45:04] Epoch: [113][7000/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.103 (3.134) Prec@1 69.53 (71.33) Prec@5 91.41 (88.97) + train[2018-10-17-14:46:49] Epoch: [113][7200/10010] Time 0.59 (0.52) Data 0.00 (0.00) Loss 3.271 (3.135) Prec@1 67.19 (71.33) Prec@5 85.94 (88.95) + train[2018-10-17-14:48:33] Epoch: [113][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.997 (3.135) Prec@1 71.09 (71.32) Prec@5 92.19 (88.95) + train[2018-10-17-14:50:18] Epoch: [113][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.173 (3.135) Prec@1 72.66 (71.32) Prec@5 89.06 (88.95) + train[2018-10-17-14:52:02] Epoch: [113][7800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.083 (3.136) Prec@1 71.09 (71.31) Prec@5 90.62 (88.94) + train[2018-10-17-14:53:47] Epoch: [113][8000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.250 (3.136) Prec@1 71.09 (71.29) Prec@5 86.72 (88.93) + train[2018-10-17-14:55:32] Epoch: [113][8200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.374 (3.137) Prec@1 72.66 (71.29) Prec@5 86.72 (88.92) + train[2018-10-17-14:57:16] Epoch: [113][8400/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.192 (3.138) Prec@1 71.88 (71.27) Prec@5 89.06 (88.91) + train[2018-10-17-14:59:01] Epoch: [113][8600/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.006 (3.138) Prec@1 71.09 (71.26) Prec@5 92.19 (88.90) + train[2018-10-17-15:00:47] Epoch: [113][8800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.252 (3.139) Prec@1 69.53 (71.24) Prec@5 89.84 (88.89) + train[2018-10-17-15:02:33] Epoch: [113][9000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.236 (3.139) Prec@1 67.97 (71.23) Prec@5 88.28 (88.89) + train[2018-10-17-15:04:18] Epoch: [113][9200/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.160 (3.140) Prec@1 68.75 (71.22) Prec@5 89.06 (88.89) + train[2018-10-17-15:06:03] Epoch: [113][9400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.073 (3.140) Prec@1 71.88 (71.22) Prec@5 89.84 (88.88) + train[2018-10-17-15:07:48] Epoch: [113][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.115 (3.140) Prec@1 75.78 (71.22) Prec@5 87.50 (88.87) + train[2018-10-17-15:09:33] Epoch: [113][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.516 (3.139) Prec@1 82.81 (71.23) Prec@5 96.88 (88.87) + train[2018-10-17-15:11:17] Epoch: [113][10000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.110 (3.140) Prec@1 73.44 (71.22) Prec@5 89.06 (88.87) + train[2018-10-17-15:11:22] Epoch: [113][10009/10010] Time 0.14 (0.52) Data 0.00 (0.00) Loss 3.157 (3.140) Prec@1 73.33 (71.22) Prec@5 86.67 (88.87) +[2018-10-17-15:11:22] **train** Prec@1 71.22 Prec@5 88.87 Error@1 28.78 Error@5 11.13 Loss:3.140 + test [2018-10-17-15:11:26] Epoch: [113][000/391] Time 3.92 (3.92) Data 3.78 (3.78) Loss 0.758 (0.758) Prec@1 83.59 (83.59) Prec@5 96.88 (96.88) + test [2018-10-17-15:11:52] Epoch: [113][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.311 (1.053) Prec@1 65.62 (75.52) Prec@5 89.84 (93.00) + test [2018-10-17-15:12:16] Epoch: [113][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.155 (1.223) Prec@1 46.25 (72.02) Prec@5 81.25 (90.67) +[2018-10-17-15:12:16] **test** Prec@1 72.02 Prec@5 90.67 Error@1 27.98 Error@5 9.33 Loss:1.223 +----> Best Accuracy : Acc@1=72.10, Acc@5=90.55, Error@1=27.90, Error@5=9.45 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-17-15:12:16] [Epoch=114/250] [Need: 200:22:52] LR=0.0031 ~ 0.0031, Batch=128 + train[2018-10-17-15:12:21] Epoch: [114][000/10010] Time 4.82 (4.82) Data 4.20 (4.20) Loss 2.987 (2.987) Prec@1 76.56 (76.56) Prec@5 93.75 (93.75) + train[2018-10-17-15:14:05] Epoch: [114][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 3.153 (3.121) Prec@1 74.22 (71.53) Prec@5 89.84 (89.24) + train[2018-10-17-15:15:49] Epoch: [114][400/10010] Time 0.56 (0.53) Data 0.00 (0.01) Loss 2.973 (3.106) Prec@1 76.56 (71.89) Prec@5 91.41 (89.34) + train[2018-10-17-15:17:34] Epoch: [114][600/10010] Time 0.56 (0.53) Data 0.00 (0.01) Loss 2.794 (3.117) Prec@1 78.12 (71.66) Prec@5 92.19 (89.23) + train[2018-10-17-15:19:18] Epoch: [114][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.429 (3.126) Prec@1 71.88 (71.61) Prec@5 83.59 (89.13) + train[2018-10-17-15:21:03] Epoch: [114][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.057 (3.125) Prec@1 72.66 (71.62) Prec@5 89.06 (89.11) + train[2018-10-17-15:22:48] Epoch: [114][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.543 (3.127) Prec@1 69.53 (71.64) Prec@5 84.38 (89.06) + train[2018-10-17-15:24:33] Epoch: [114][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.918 (3.129) Prec@1 77.34 (71.63) Prec@5 92.19 (89.03) + train[2018-10-17-15:26:18] Epoch: [114][1600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.217 (3.129) Prec@1 71.09 (71.62) Prec@5 88.28 (89.01) + train[2018-10-17-15:28:02] Epoch: [114][1800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.087 (3.127) Prec@1 71.88 (71.62) Prec@5 90.62 (89.03) + train[2018-10-17-15:29:47] Epoch: [114][2000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.257 (3.127) Prec@1 73.44 (71.61) Prec@5 85.94 (89.04) + train[2018-10-17-15:31:32] Epoch: [114][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.300 (3.127) Prec@1 71.88 (71.62) Prec@5 84.38 (89.06) + train[2018-10-17-15:33:17] Epoch: [114][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.183 (3.127) Prec@1 69.53 (71.63) Prec@5 87.50 (89.05) + train[2018-10-17-15:35:02] Epoch: [114][2600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.262 (3.126) Prec@1 68.75 (71.62) Prec@5 87.50 (89.05) + train[2018-10-17-15:36:47] Epoch: [114][2800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.425 (3.126) Prec@1 65.62 (71.60) Prec@5 86.72 (89.06) + train[2018-10-17-15:38:31] Epoch: [114][3000/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 3.038 (3.126) Prec@1 71.88 (71.59) Prec@5 90.62 (89.06) + train[2018-10-17-15:40:16] Epoch: [114][3200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.284 (3.127) Prec@1 71.88 (71.55) Prec@5 89.84 (89.05) + train[2018-10-17-15:42:02] Epoch: [114][3400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.212 (3.128) Prec@1 67.19 (71.55) Prec@5 86.72 (89.05) + train[2018-10-17-15:43:47] Epoch: [114][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.485 (3.128) Prec@1 58.59 (71.55) Prec@5 85.94 (89.05) + train[2018-10-17-15:45:32] Epoch: [114][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.627 (3.130) Prec@1 78.12 (71.50) Prec@5 93.75 (89.03) + train[2018-10-17-15:47:17] Epoch: [114][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.152 (3.130) Prec@1 71.88 (71.50) Prec@5 89.06 (89.02) + train[2018-10-17-15:49:01] Epoch: [114][4200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.942 (3.130) Prec@1 74.22 (71.49) Prec@5 92.97 (89.02) + train[2018-10-17-15:50:46] Epoch: [114][4400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.792 (3.130) Prec@1 78.12 (71.48) Prec@5 92.19 (89.03) + train[2018-10-17-15:52:30] Epoch: [114][4600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.262 (3.131) Prec@1 73.44 (71.46) Prec@5 88.28 (89.01) + train[2018-10-17-15:54:16] Epoch: [114][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.788 (3.132) Prec@1 79.69 (71.43) Prec@5 93.75 (89.01) + train[2018-10-17-15:56:00] Epoch: [114][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.452 (3.132) Prec@1 67.97 (71.43) Prec@5 85.16 (89.01) + train[2018-10-17-15:57:45] Epoch: [114][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.172 (3.132) Prec@1 69.53 (71.42) Prec@5 89.06 (89.00) + train[2018-10-17-15:59:29] Epoch: [114][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.036 (3.133) Prec@1 71.88 (71.42) Prec@5 89.06 (89.00) + train[2018-10-17-16:01:13] Epoch: [114][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.210 (3.133) Prec@1 69.53 (71.42) Prec@5 85.94 (88.99) + train[2018-10-17-16:02:58] Epoch: [114][5800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.230 (3.132) Prec@1 75.78 (71.42) Prec@5 88.28 (88.99) + train[2018-10-17-16:04:43] Epoch: [114][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.134 (3.132) Prec@1 65.62 (71.41) Prec@5 89.84 (88.99) + train[2018-10-17-16:06:28] Epoch: [114][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.901 (3.132) Prec@1 71.88 (71.42) Prec@5 91.41 (88.98) + train[2018-10-17-16:08:12] Epoch: [114][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.240 (3.132) Prec@1 70.31 (71.42) Prec@5 89.06 (88.98) + train[2018-10-17-16:09:57] Epoch: [114][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.028 (3.132) Prec@1 67.97 (71.42) Prec@5 92.97 (88.98) + train[2018-10-17-16:11:44] Epoch: [114][6800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.969 (3.132) Prec@1 72.66 (71.41) Prec@5 94.53 (88.97) + train[2018-10-17-16:13:29] Epoch: [114][7000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.066 (3.132) Prec@1 71.09 (71.41) Prec@5 92.19 (88.98) + train[2018-10-17-16:15:15] Epoch: [114][7200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.130 (3.132) Prec@1 71.88 (71.40) Prec@5 86.72 (88.98) + train[2018-10-17-16:17:00] Epoch: [114][7400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.328 (3.132) Prec@1 64.84 (71.39) Prec@5 89.06 (88.97) + train[2018-10-17-16:18:45] Epoch: [114][7600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.040 (3.133) Prec@1 71.88 (71.38) Prec@5 92.19 (88.96) + train[2018-10-17-16:20:30] Epoch: [114][7800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.091 (3.133) Prec@1 74.22 (71.37) Prec@5 89.84 (88.95) + train[2018-10-17-16:22:15] Epoch: [114][8000/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.155 (3.133) Prec@1 67.97 (71.36) Prec@5 89.06 (88.95) + train[2018-10-17-16:24:00] Epoch: [114][8200/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 2.976 (3.133) Prec@1 76.56 (71.36) Prec@5 89.84 (88.95) + train[2018-10-17-16:25:46] Epoch: [114][8400/10010] Time 0.60 (0.52) Data 0.00 (0.00) Loss 3.276 (3.134) Prec@1 67.19 (71.35) Prec@5 85.16 (88.95) + train[2018-10-17-16:27:31] Epoch: [114][8600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.128 (3.134) Prec@1 71.88 (71.34) Prec@5 89.84 (88.95) + train[2018-10-17-16:29:16] Epoch: [114][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.224 (3.134) Prec@1 67.97 (71.33) Prec@5 89.84 (88.95) + train[2018-10-17-16:31:01] Epoch: [114][9000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.368 (3.135) Prec@1 68.75 (71.33) Prec@5 85.16 (88.94) + train[2018-10-17-16:32:46] Epoch: [114][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.861 (3.135) Prec@1 75.00 (71.32) Prec@5 94.53 (88.93) + train[2018-10-17-16:34:31] Epoch: [114][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.917 (3.135) Prec@1 75.78 (71.33) Prec@5 90.62 (88.93) + train[2018-10-17-16:36:15] Epoch: [114][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.956 (3.135) Prec@1 71.88 (71.32) Prec@5 91.41 (88.93) + train[2018-10-17-16:38:00] Epoch: [114][9800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.353 (3.136) Prec@1 70.31 (71.32) Prec@5 83.59 (88.93) + train[2018-10-17-16:39:45] Epoch: [114][10000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.982 (3.136) Prec@1 74.22 (71.31) Prec@5 92.97 (88.93) + train[2018-10-17-16:39:50] Epoch: [114][10009/10010] Time 0.18 (0.52) Data 0.00 (0.00) Loss 2.893 (3.136) Prec@1 80.00 (71.31) Prec@5 93.33 (88.92) +[2018-10-17-16:39:50] **train** Prec@1 71.31 Prec@5 88.92 Error@1 28.69 Error@5 11.08 Loss:3.136 + test [2018-10-17-16:39:54] Epoch: [114][000/391] Time 3.60 (3.60) Data 3.45 (3.45) Loss 0.588 (0.588) Prec@1 89.06 (89.06) Prec@5 97.66 (97.66) + test [2018-10-17-16:40:22] Epoch: [114][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.385 (1.045) Prec@1 67.19 (75.89) Prec@5 89.84 (93.03) + test [2018-10-17-16:40:47] Epoch: [114][390/391] Time 0.08 (0.15) Data 0.00 (0.02) Loss 2.251 (1.219) Prec@1 38.75 (72.32) Prec@5 78.75 (90.73) +[2018-10-17-16:40:47] **test** Prec@1 72.32 Prec@5 90.73 Error@1 27.68 Error@5 9.27 Loss:1.219 +----> Best Accuracy : Acc@1=72.32, Acc@5=90.73, Error@1=27.68, Error@5=9.27 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-17-16:40:48] [Epoch=115/250] [Need: 199:10:21] LR=0.0030 ~ 0.0030, Batch=128 + train[2018-10-17-16:40:53] Epoch: [115][000/10010] Time 5.52 (5.52) Data 4.92 (4.92) Loss 3.003 (3.003) Prec@1 78.12 (78.12) Prec@5 89.06 (89.06) + train[2018-10-17-16:42:39] Epoch: [115][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.062 (3.113) Prec@1 75.78 (71.80) Prec@5 87.50 (89.26) + train[2018-10-17-16:44:24] Epoch: [115][400/10010] Time 0.53 (0.54) Data 0.00 (0.01) Loss 2.800 (3.109) Prec@1 78.12 (72.00) Prec@5 94.53 (89.21) + train[2018-10-17-16:46:09] Epoch: [115][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.793 (3.108) Prec@1 78.91 (72.00) Prec@5 95.31 (89.27) + train[2018-10-17-16:47:55] Epoch: [115][800/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.234 (3.106) Prec@1 69.53 (72.05) Prec@5 88.28 (89.25) + train[2018-10-17-16:49:40] Epoch: [115][1000/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.489 (3.108) Prec@1 64.06 (72.02) Prec@5 83.59 (89.19) + train[2018-10-17-16:51:26] Epoch: [115][1200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.031 (3.112) Prec@1 71.88 (71.95) Prec@5 90.62 (89.14) + train[2018-10-17-16:53:12] Epoch: [115][1400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.094 (3.112) Prec@1 71.09 (71.89) Prec@5 89.06 (89.14) + train[2018-10-17-16:54:57] Epoch: [115][1600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.825 (3.114) Prec@1 80.47 (71.87) Prec@5 89.06 (89.13) + train[2018-10-17-16:56:43] Epoch: [115][1800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.742 (3.112) Prec@1 77.34 (71.87) Prec@5 93.75 (89.15) + train[2018-10-17-16:58:29] Epoch: [115][2000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.105 (3.111) Prec@1 71.88 (71.86) Prec@5 89.06 (89.20) + train[2018-10-17-17:00:15] Epoch: [115][2200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.086 (3.111) Prec@1 70.31 (71.87) Prec@5 86.72 (89.19) + train[2018-10-17-17:02:01] Epoch: [115][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.089 (3.110) Prec@1 67.97 (71.89) Prec@5 87.50 (89.19) + train[2018-10-17-17:03:46] Epoch: [115][2600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.963 (3.112) Prec@1 73.44 (71.84) Prec@5 92.19 (89.19) + train[2018-10-17-17:05:32] Epoch: [115][2800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.068 (3.112) Prec@1 69.53 (71.86) Prec@5 92.19 (89.18) + train[2018-10-17-17:07:18] Epoch: [115][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.111 (3.111) Prec@1 71.88 (71.87) Prec@5 86.72 (89.20) + train[2018-10-17-17:09:04] Epoch: [115][3200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.239 (3.110) Prec@1 67.19 (71.88) Prec@5 88.28 (89.22) + train[2018-10-17-17:10:49] Epoch: [115][3400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.314 (3.110) Prec@1 67.97 (71.88) Prec@5 86.72 (89.21) + train[2018-10-17-17:12:34] Epoch: [115][3600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.148 (3.113) Prec@1 72.66 (71.82) Prec@5 88.28 (89.17) + train[2018-10-17-17:14:20] Epoch: [115][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.980 (3.113) Prec@1 75.00 (71.81) Prec@5 90.62 (89.16) + train[2018-10-17-17:16:06] Epoch: [115][4000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.474 (3.113) Prec@1 63.28 (71.81) Prec@5 87.50 (89.16) + train[2018-10-17-17:17:52] Epoch: [115][4200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.479 (3.113) Prec@1 67.97 (71.81) Prec@5 85.94 (89.15) + train[2018-10-17-17:19:37] Epoch: [115][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.222 (3.114) Prec@1 70.31 (71.78) Prec@5 87.50 (89.14) + train[2018-10-17-17:21:23] Epoch: [115][4600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.219 (3.115) Prec@1 74.22 (71.77) Prec@5 87.50 (89.13) + train[2018-10-17-17:23:09] Epoch: [115][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.052 (3.116) Prec@1 76.56 (71.75) Prec@5 86.72 (89.12) + train[2018-10-17-17:24:54] Epoch: [115][5000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.127 (3.117) Prec@1 73.44 (71.74) Prec@5 87.50 (89.11) + train[2018-10-17-17:26:39] Epoch: [115][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.985 (3.118) Prec@1 74.22 (71.72) Prec@5 91.41 (89.11) + train[2018-10-17-17:28:25] Epoch: [115][5400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.251 (3.118) Prec@1 69.53 (71.72) Prec@5 89.06 (89.11) + train[2018-10-17-17:30:10] Epoch: [115][5600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.186 (3.118) Prec@1 67.97 (71.71) Prec@5 89.06 (89.10) + train[2018-10-17-17:31:56] Epoch: [115][5800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.884 (3.119) Prec@1 76.56 (71.69) Prec@5 91.41 (89.09) + train[2018-10-17-17:33:42] Epoch: [115][6000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.111 (3.119) Prec@1 67.97 (71.67) Prec@5 89.06 (89.09) + train[2018-10-17-17:35:28] Epoch: [115][6200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.101 (3.120) Prec@1 70.31 (71.65) Prec@5 89.06 (89.08) + train[2018-10-17-17:37:13] Epoch: [115][6400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.126 (3.121) Prec@1 71.88 (71.62) Prec@5 89.06 (89.06) + train[2018-10-17-17:38:58] Epoch: [115][6600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.136 (3.121) Prec@1 72.66 (71.62) Prec@5 86.72 (89.06) + train[2018-10-17-17:40:43] Epoch: [115][6800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.293 (3.122) Prec@1 65.62 (71.60) Prec@5 87.50 (89.05) + train[2018-10-17-17:42:29] Epoch: [115][7000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.951 (3.122) Prec@1 72.66 (71.59) Prec@5 90.62 (89.04) + train[2018-10-17-17:44:14] Epoch: [115][7200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.073 (3.123) Prec@1 74.22 (71.59) Prec@5 87.50 (89.04) + train[2018-10-17-17:45:59] Epoch: [115][7400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.356 (3.123) Prec@1 68.75 (71.57) Prec@5 89.84 (89.03) + train[2018-10-17-17:47:45] Epoch: [115][7600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.022 (3.124) Prec@1 71.88 (71.57) Prec@5 92.97 (89.03) + train[2018-10-17-17:49:31] Epoch: [115][7800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.344 (3.124) Prec@1 69.53 (71.56) Prec@5 85.16 (89.02) + train[2018-10-17-17:51:18] Epoch: [115][8000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.433 (3.124) Prec@1 67.19 (71.55) Prec@5 83.59 (89.02) + train[2018-10-17-17:53:03] Epoch: [115][8200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.314 (3.124) Prec@1 68.75 (71.55) Prec@5 88.28 (89.02) + train[2018-10-17-17:54:48] Epoch: [115][8400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.304 (3.125) Prec@1 74.22 (71.53) Prec@5 85.16 (89.01) + train[2018-10-17-17:56:34] Epoch: [115][8600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.903 (3.125) Prec@1 74.22 (71.53) Prec@5 88.28 (89.00) + train[2018-10-17-17:58:20] Epoch: [115][8800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.232 (3.125) Prec@1 72.66 (71.52) Prec@5 89.06 (89.00) + train[2018-10-17-18:00:06] Epoch: [115][9000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.055 (3.126) Prec@1 70.31 (71.52) Prec@5 92.19 (89.00) + train[2018-10-17-18:01:51] Epoch: [115][9200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.095 (3.126) Prec@1 70.31 (71.52) Prec@5 92.97 (89.00) + train[2018-10-17-18:03:37] Epoch: [115][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.950 (3.125) Prec@1 75.00 (71.51) Prec@5 91.41 (89.00) + train[2018-10-17-18:05:22] Epoch: [115][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.014 (3.126) Prec@1 76.56 (71.51) Prec@5 90.62 (89.00) + train[2018-10-17-18:07:08] Epoch: [115][9800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.935 (3.126) Prec@1 75.78 (71.51) Prec@5 91.41 (89.00) + train[2018-10-17-18:08:52] Epoch: [115][10000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.991 (3.126) Prec@1 68.75 (71.50) Prec@5 91.41 (88.99) + train[2018-10-17-18:08:56] Epoch: [115][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 4.497 (3.126) Prec@1 46.67 (71.50) Prec@5 66.67 (88.99) +[2018-10-17-18:08:56] **train** Prec@1 71.50 Prec@5 88.99 Error@1 28.50 Error@5 11.01 Loss:3.126 + test [2018-10-17-18:09:01] Epoch: [115][000/391] Time 4.26 (4.26) Data 4.12 (4.12) Loss 0.660 (0.660) Prec@1 87.50 (87.50) Prec@5 96.88 (96.88) + test [2018-10-17-18:09:29] Epoch: [115][200/391] Time 0.16 (0.16) Data 0.00 (0.03) Loss 1.380 (1.059) Prec@1 61.72 (75.80) Prec@5 92.19 (92.89) + test [2018-10-17-18:09:54] Epoch: [115][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.091 (1.223) Prec@1 48.75 (72.22) Prec@5 80.00 (90.67) +[2018-10-17-18:09:54] **test** Prec@1 72.22 Prec@5 90.67 Error@1 27.78 Error@5 9.33 Loss:1.223 +----> Best Accuracy : Acc@1=72.32, Acc@5=90.73, Error@1=27.68, Error@5=9.27 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-17-18:09:54] [Epoch=116/250] [Need: 199:00:43] LR=0.0029 ~ 0.0029, Batch=128 + train[2018-10-17-18:10:00] Epoch: [116][000/10010] Time 5.51 (5.51) Data 4.96 (4.96) Loss 2.993 (2.993) Prec@1 70.31 (70.31) Prec@5 92.97 (92.97) + train[2018-10-17-18:11:44] Epoch: [116][200/10010] Time 0.51 (0.55) Data 0.00 (0.02) Loss 3.071 (3.086) Prec@1 73.44 (72.24) Prec@5 90.62 (89.51) + train[2018-10-17-18:13:30] Epoch: [116][400/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 2.777 (3.092) Prec@1 77.34 (71.99) Prec@5 93.75 (89.43) + train[2018-10-17-18:15:15] Epoch: [116][600/10010] Time 0.58 (0.53) Data 0.00 (0.01) Loss 3.093 (3.095) Prec@1 71.09 (72.08) Prec@5 88.28 (89.30) + train[2018-10-17-18:17:01] Epoch: [116][800/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.082 (3.102) Prec@1 72.66 (71.96) Prec@5 89.84 (89.30) + train[2018-10-17-18:18:46] Epoch: [116][1000/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.973 (3.106) Prec@1 76.56 (71.92) Prec@5 91.41 (89.25) + train[2018-10-17-18:20:31] Epoch: [116][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.904 (3.104) Prec@1 75.00 (72.01) Prec@5 92.97 (89.32) + train[2018-10-17-18:22:17] Epoch: [116][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.135 (3.105) Prec@1 75.00 (71.99) Prec@5 90.62 (89.30) + train[2018-10-17-18:24:03] Epoch: [116][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.378 (3.106) Prec@1 63.28 (71.94) Prec@5 86.72 (89.29) + train[2018-10-17-18:25:49] Epoch: [116][1800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.897 (3.105) Prec@1 79.69 (71.96) Prec@5 93.75 (89.30) + train[2018-10-17-18:27:34] Epoch: [116][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.107 (3.106) Prec@1 67.97 (71.93) Prec@5 92.97 (89.27) + train[2018-10-17-18:29:19] Epoch: [116][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.934 (3.108) Prec@1 75.00 (71.87) Prec@5 88.28 (89.26) + train[2018-10-17-18:31:05] Epoch: [116][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.844 (3.108) Prec@1 75.78 (71.88) Prec@5 93.75 (89.27) + train[2018-10-17-18:32:50] Epoch: [116][2600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.061 (3.108) Prec@1 69.53 (71.86) Prec@5 89.84 (89.26) + train[2018-10-17-18:34:36] Epoch: [116][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.235 (3.109) Prec@1 68.75 (71.84) Prec@5 89.84 (89.24) + train[2018-10-17-18:36:20] Epoch: [116][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.762 (3.109) Prec@1 78.91 (71.83) Prec@5 92.19 (89.23) + train[2018-10-17-18:38:06] Epoch: [116][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.150 (3.109) Prec@1 66.41 (71.83) Prec@5 89.84 (89.22) + train[2018-10-17-18:39:51] Epoch: [116][3400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.217 (3.110) Prec@1 72.66 (71.80) Prec@5 88.28 (89.21) + train[2018-10-17-18:41:37] Epoch: [116][3600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.915 (3.110) Prec@1 71.88 (71.79) Prec@5 92.97 (89.20) + train[2018-10-17-18:43:23] Epoch: [116][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.827 (3.111) Prec@1 77.34 (71.78) Prec@5 92.19 (89.20) + train[2018-10-17-18:45:08] Epoch: [116][4000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.077 (3.112) Prec@1 71.09 (71.76) Prec@5 92.19 (89.19) + train[2018-10-17-18:46:53] Epoch: [116][4200/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.043 (3.112) Prec@1 77.34 (71.75) Prec@5 89.06 (89.18) + train[2018-10-17-18:48:39] Epoch: [116][4400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.299 (3.112) Prec@1 64.84 (71.76) Prec@5 87.50 (89.18) + train[2018-10-17-18:50:24] Epoch: [116][4600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.241 (3.113) Prec@1 71.09 (71.74) Prec@5 88.28 (89.16) + train[2018-10-17-18:52:10] Epoch: [116][4800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.329 (3.114) Prec@1 62.50 (71.74) Prec@5 86.72 (89.15) + train[2018-10-17-18:53:55] Epoch: [116][5000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.939 (3.114) Prec@1 71.09 (71.73) Prec@5 93.75 (89.15) + train[2018-10-17-18:55:41] Epoch: [116][5200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.189 (3.114) Prec@1 67.97 (71.71) Prec@5 85.94 (89.14) + train[2018-10-17-18:57:27] Epoch: [116][5400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.891 (3.115) Prec@1 74.22 (71.69) Prec@5 91.41 (89.13) + train[2018-10-17-18:59:12] Epoch: [116][5600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.968 (3.116) Prec@1 76.56 (71.68) Prec@5 89.06 (89.11) + train[2018-10-17-19:00:57] Epoch: [116][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.217 (3.116) Prec@1 67.97 (71.67) Prec@5 85.16 (89.11) + train[2018-10-17-19:02:42] Epoch: [116][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.000 (3.117) Prec@1 70.31 (71.67) Prec@5 88.28 (89.09) + train[2018-10-17-19:04:28] Epoch: [116][6200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.927 (3.118) Prec@1 74.22 (71.66) Prec@5 91.41 (89.09) + train[2018-10-17-19:06:13] Epoch: [116][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.177 (3.119) Prec@1 67.19 (71.65) Prec@5 89.06 (89.09) + train[2018-10-17-19:07:58] Epoch: [116][6600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.188 (3.118) Prec@1 69.53 (71.65) Prec@5 88.28 (89.09) + train[2018-10-17-19:09:43] Epoch: [116][6800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.871 (3.119) Prec@1 73.44 (71.65) Prec@5 90.62 (89.09) + train[2018-10-17-19:11:29] Epoch: [116][7000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.079 (3.119) Prec@1 70.31 (71.64) Prec@5 89.84 (89.09) + train[2018-10-17-19:13:15] Epoch: [116][7200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.702 (3.119) Prec@1 64.84 (71.63) Prec@5 82.81 (89.08) + train[2018-10-17-19:15:00] Epoch: [116][7400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.778 (3.120) Prec@1 76.56 (71.62) Prec@5 92.97 (89.07) + train[2018-10-17-19:16:46] Epoch: [116][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.157 (3.119) Prec@1 70.31 (71.62) Prec@5 87.50 (89.08) + train[2018-10-17-19:18:31] Epoch: [116][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.138 (3.119) Prec@1 70.31 (71.62) Prec@5 85.16 (89.08) + train[2018-10-17-19:20:16] Epoch: [116][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.184 (3.119) Prec@1 73.44 (71.61) Prec@5 88.28 (89.08) + train[2018-10-17-19:22:00] Epoch: [116][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.816 (3.120) Prec@1 77.34 (71.61) Prec@5 92.97 (89.08) + train[2018-10-17-19:23:45] Epoch: [116][8400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.105 (3.120) Prec@1 71.09 (71.61) Prec@5 92.19 (89.07) + train[2018-10-17-19:25:31] Epoch: [116][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.546 (3.120) Prec@1 58.59 (71.60) Prec@5 84.38 (89.07) + train[2018-10-17-19:27:16] Epoch: [116][8800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.078 (3.120) Prec@1 74.22 (71.60) Prec@5 87.50 (89.07) + train[2018-10-17-19:29:00] Epoch: [116][9000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.716 (3.120) Prec@1 77.34 (71.59) Prec@5 93.75 (89.07) + train[2018-10-17-19:30:46] Epoch: [116][9200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.004 (3.120) Prec@1 71.88 (71.59) Prec@5 91.41 (89.08) + train[2018-10-17-19:32:31] Epoch: [116][9400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.127 (3.121) Prec@1 75.00 (71.58) Prec@5 87.50 (89.07) + train[2018-10-17-19:34:16] Epoch: [116][9600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.889 (3.121) Prec@1 75.00 (71.58) Prec@5 92.97 (89.07) + train[2018-10-17-19:36:02] Epoch: [116][9800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.379 (3.122) Prec@1 68.75 (71.58) Prec@5 83.59 (89.06) + train[2018-10-17-19:37:46] Epoch: [116][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.274 (3.122) Prec@1 71.09 (71.58) Prec@5 89.06 (89.06) + train[2018-10-17-19:37:50] Epoch: [116][10009/10010] Time 0.14 (0.53) Data 0.00 (0.00) Loss 3.508 (3.122) Prec@1 73.33 (71.58) Prec@5 86.67 (89.06) +[2018-10-17-19:37:50] **train** Prec@1 71.58 Prec@5 89.06 Error@1 28.42 Error@5 10.94 Loss:3.122 + test [2018-10-17-19:37:54] Epoch: [116][000/391] Time 3.62 (3.62) Data 3.48 (3.48) Loss 0.603 (0.603) Prec@1 91.41 (91.41) Prec@5 96.88 (96.88) + test [2018-10-17-19:38:23] Epoch: [116][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.266 (1.058) Prec@1 68.75 (75.69) Prec@5 92.97 (92.82) + test [2018-10-17-19:38:49] Epoch: [116][390/391] Time 0.09 (0.15) Data 0.00 (0.02) Loss 2.160 (1.228) Prec@1 42.50 (71.99) Prec@5 81.25 (90.61) +[2018-10-17-19:38:49] **test** Prec@1 71.99 Prec@5 90.61 Error@1 28.01 Error@5 9.39 Loss:1.228 +----> Best Accuracy : Acc@1=72.32, Acc@5=90.73, Error@1=27.68, Error@5=9.27 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-17-19:38:49] [Epoch=117/250] [Need: 197:04:48] LR=0.0028 ~ 0.0028, Batch=128 + train[2018-10-17-19:38:53] Epoch: [117][000/10010] Time 4.74 (4.74) Data 4.08 (4.08) Loss 3.417 (3.417) Prec@1 64.84 (64.84) Prec@5 85.16 (85.16) + train[2018-10-17-19:40:39] Epoch: [117][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.280 (3.116) Prec@1 68.75 (71.81) Prec@5 89.06 (89.10) + train[2018-10-17-19:42:24] Epoch: [117][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 3.276 (3.110) Prec@1 67.97 (71.95) Prec@5 87.50 (89.18) + train[2018-10-17-19:44:10] Epoch: [117][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.339 (3.108) Prec@1 64.06 (71.95) Prec@5 87.50 (89.25) + train[2018-10-17-19:45:55] Epoch: [117][800/10010] Time 0.49 (0.53) Data 0.00 (0.01) Loss 3.060 (3.104) Prec@1 69.53 (71.96) Prec@5 91.41 (89.33) + train[2018-10-17-19:47:41] Epoch: [117][1000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.120 (3.100) Prec@1 71.09 (72.10) Prec@5 89.06 (89.35) + train[2018-10-17-19:49:26] Epoch: [117][1200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.233 (3.102) Prec@1 75.78 (72.08) Prec@5 87.50 (89.31) + train[2018-10-17-19:51:12] Epoch: [117][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.796 (3.103) Prec@1 77.34 (72.00) Prec@5 95.31 (89.33) + train[2018-10-17-19:52:57] Epoch: [117][1600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.177 (3.103) Prec@1 67.97 (72.02) Prec@5 92.19 (89.31) + train[2018-10-17-19:54:43] Epoch: [117][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.548 (3.106) Prec@1 82.81 (71.99) Prec@5 95.31 (89.27) + train[2018-10-17-19:56:28] Epoch: [117][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.240 (3.108) Prec@1 70.31 (72.01) Prec@5 89.84 (89.23) + train[2018-10-17-19:58:14] Epoch: [117][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.787 (3.108) Prec@1 82.03 (72.02) Prec@5 92.19 (89.25) + train[2018-10-17-20:00:00] Epoch: [117][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.904 (3.106) Prec@1 74.22 (72.05) Prec@5 92.97 (89.27) + train[2018-10-17-20:01:45] Epoch: [117][2600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.001 (3.105) Prec@1 77.34 (72.06) Prec@5 91.41 (89.28) + train[2018-10-17-20:03:30] Epoch: [117][2800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.103 (3.106) Prec@1 73.44 (72.03) Prec@5 90.62 (89.26) + train[2018-10-17-20:05:15] Epoch: [117][3000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.461 (3.107) Prec@1 63.28 (72.00) Prec@5 84.38 (89.25) + train[2018-10-17-20:07:01] Epoch: [117][3200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.320 (3.107) Prec@1 68.75 (71.99) Prec@5 87.50 (89.24) + train[2018-10-17-20:08:46] Epoch: [117][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.989 (3.106) Prec@1 71.09 (71.98) Prec@5 90.62 (89.25) + train[2018-10-17-20:10:31] Epoch: [117][3600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.981 (3.106) Prec@1 72.66 (71.99) Prec@5 89.84 (89.25) + train[2018-10-17-20:12:17] Epoch: [117][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.146 (3.107) Prec@1 67.97 (71.97) Prec@5 89.06 (89.24) + train[2018-10-17-20:14:03] Epoch: [117][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.063 (3.107) Prec@1 72.66 (71.98) Prec@5 89.84 (89.25) + train[2018-10-17-20:15:49] Epoch: [117][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.022 (3.107) Prec@1 76.56 (71.98) Prec@5 89.84 (89.25) + train[2018-10-17-20:17:35] Epoch: [117][4400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.944 (3.107) Prec@1 75.00 (71.98) Prec@5 92.97 (89.25) + train[2018-10-17-20:19:19] Epoch: [117][4600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.200 (3.108) Prec@1 72.66 (71.96) Prec@5 86.72 (89.24) + train[2018-10-17-20:21:05] Epoch: [117][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.858 (3.109) Prec@1 78.12 (71.94) Prec@5 91.41 (89.21) + train[2018-10-17-20:22:51] Epoch: [117][5000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.954 (3.108) Prec@1 73.44 (71.95) Prec@5 93.75 (89.22) + train[2018-10-17-20:24:36] Epoch: [117][5200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.245 (3.109) Prec@1 69.53 (71.94) Prec@5 86.72 (89.21) + train[2018-10-17-20:26:22] Epoch: [117][5400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.129 (3.110) Prec@1 71.09 (71.92) Prec@5 89.06 (89.20) + train[2018-10-17-20:28:07] Epoch: [117][5600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.971 (3.110) Prec@1 71.09 (71.93) Prec@5 89.06 (89.20) + train[2018-10-17-20:29:52] Epoch: [117][5800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.321 (3.111) Prec@1 69.53 (71.88) Prec@5 84.38 (89.18) + train[2018-10-17-20:31:38] Epoch: [117][6000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.933 (3.112) Prec@1 71.88 (71.87) Prec@5 92.97 (89.17) + train[2018-10-17-20:33:23] Epoch: [117][6200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.892 (3.111) Prec@1 78.12 (71.88) Prec@5 89.84 (89.18) + train[2018-10-17-20:35:09] Epoch: [117][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.186 (3.111) Prec@1 72.66 (71.88) Prec@5 86.72 (89.17) + train[2018-10-17-20:36:54] Epoch: [117][6600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.773 (3.111) Prec@1 77.34 (71.87) Prec@5 93.75 (89.17) + train[2018-10-17-20:38:39] Epoch: [117][6800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.119 (3.112) Prec@1 67.97 (71.87) Prec@5 88.28 (89.16) + train[2018-10-17-20:40:24] Epoch: [117][7000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.168 (3.112) Prec@1 71.09 (71.86) Prec@5 89.06 (89.16) + train[2018-10-17-20:42:10] Epoch: [117][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.032 (3.112) Prec@1 75.78 (71.85) Prec@5 91.41 (89.16) + train[2018-10-17-20:43:56] Epoch: [117][7400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.112 (3.112) Prec@1 69.53 (71.84) Prec@5 87.50 (89.15) + train[2018-10-17-20:45:40] Epoch: [117][7600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.977 (3.112) Prec@1 79.69 (71.83) Prec@5 90.62 (89.16) + train[2018-10-17-20:47:26] Epoch: [117][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.122 (3.112) Prec@1 70.31 (71.83) Prec@5 89.84 (89.16) + train[2018-10-17-20:49:12] Epoch: [117][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.201 (3.112) Prec@1 70.31 (71.82) Prec@5 90.62 (89.16) + train[2018-10-17-20:50:58] Epoch: [117][8200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.257 (3.113) Prec@1 65.62 (71.81) Prec@5 87.50 (89.15) + train[2018-10-17-20:52:43] Epoch: [117][8400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.904 (3.113) Prec@1 75.78 (71.80) Prec@5 92.19 (89.15) + train[2018-10-17-20:54:29] Epoch: [117][8600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.521 (3.114) Prec@1 68.75 (71.78) Prec@5 82.81 (89.14) + train[2018-10-17-20:56:15] Epoch: [117][8800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.356 (3.114) Prec@1 70.31 (71.77) Prec@5 84.38 (89.14) + train[2018-10-17-20:58:01] Epoch: [117][9000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.181 (3.114) Prec@1 71.09 (71.77) Prec@5 89.06 (89.14) + train[2018-10-17-20:59:47] Epoch: [117][9200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.937 (3.115) Prec@1 74.22 (71.75) Prec@5 89.06 (89.13) + train[2018-10-17-21:01:32] Epoch: [117][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.210 (3.116) Prec@1 71.09 (71.74) Prec@5 86.72 (89.12) + train[2018-10-17-21:03:18] Epoch: [117][9600/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.128 (3.116) Prec@1 75.78 (71.73) Prec@5 87.50 (89.11) + train[2018-10-17-21:05:04] Epoch: [117][9800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.136 (3.116) Prec@1 75.00 (71.73) Prec@5 86.72 (89.11) + train[2018-10-17-21:06:49] Epoch: [117][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.079 (3.116) Prec@1 72.66 (71.72) Prec@5 90.62 (89.11) + train[2018-10-17-21:06:54] Epoch: [117][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.336 (3.117) Prec@1 80.00 (71.72) Prec@5 93.33 (89.11) +[2018-10-17-21:06:54] **train** Prec@1 71.72 Prec@5 89.11 Error@1 28.28 Error@5 10.89 Loss:3.117 + test [2018-10-17-21:06:58] Epoch: [117][000/391] Time 4.35 (4.35) Data 4.22 (4.22) Loss 0.597 (0.597) Prec@1 88.28 (88.28) Prec@5 96.09 (96.09) + test [2018-10-17-21:07:26] Epoch: [117][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.234 (1.045) Prec@1 65.62 (75.78) Prec@5 91.41 (93.09) + test [2018-10-17-21:07:51] Epoch: [117][390/391] Time 0.09 (0.15) Data 0.00 (0.02) Loss 2.239 (1.212) Prec@1 42.50 (72.25) Prec@5 81.25 (90.80) +[2018-10-17-21:07:51] **test** Prec@1 72.25 Prec@5 90.80 Error@1 27.75 Error@5 9.20 Loss:1.212 +----> Best Accuracy : Acc@1=72.32, Acc@5=90.73, Error@1=27.68, Error@5=9.27 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-17-21:07:52] [Epoch=118/250] [Need: 195:54:29] LR=0.0027 ~ 0.0027, Batch=128 + train[2018-10-17-21:07:56] Epoch: [118][000/10010] Time 4.32 (4.32) Data 3.66 (3.66) Loss 3.204 (3.204) Prec@1 65.62 (65.62) Prec@5 86.72 (86.72) + train[2018-10-17-21:09:42] Epoch: [118][200/10010] Time 0.52 (0.55) Data 0.00 (0.02) Loss 3.043 (3.109) Prec@1 74.22 (71.81) Prec@5 88.28 (89.33) + train[2018-10-17-21:11:27] Epoch: [118][400/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 3.013 (3.094) Prec@1 72.66 (72.20) Prec@5 88.28 (89.39) + train[2018-10-17-21:13:12] Epoch: [118][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.932 (3.099) Prec@1 74.22 (72.13) Prec@5 90.62 (89.34) + train[2018-10-17-21:14:57] Epoch: [118][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.993 (3.096) Prec@1 69.53 (72.15) Prec@5 91.41 (89.37) + train[2018-10-17-21:16:42] Epoch: [118][1000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.469 (3.096) Prec@1 64.06 (72.13) Prec@5 85.94 (89.35) + train[2018-10-17-21:18:27] Epoch: [118][1200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.884 (3.097) Prec@1 81.25 (72.15) Prec@5 92.97 (89.35) + train[2018-10-17-21:20:13] Epoch: [118][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.324 (3.096) Prec@1 66.41 (72.14) Prec@5 87.50 (89.36) + train[2018-10-17-21:21:58] Epoch: [118][1600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.385 (3.098) Prec@1 67.97 (72.13) Prec@5 85.16 (89.35) + train[2018-10-17-21:23:44] Epoch: [118][1800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.931 (3.098) Prec@1 69.53 (72.11) Prec@5 90.62 (89.34) + train[2018-10-17-21:25:29] Epoch: [118][2000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.090 (3.098) Prec@1 71.09 (72.10) Prec@5 89.06 (89.35) + train[2018-10-17-21:27:14] Epoch: [118][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.757 (3.097) Prec@1 83.59 (72.11) Prec@5 93.75 (89.36) + train[2018-10-17-21:28:59] Epoch: [118][2400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.955 (3.099) Prec@1 75.00 (72.06) Prec@5 89.84 (89.35) + train[2018-10-17-21:30:45] Epoch: [118][2600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.999 (3.100) Prec@1 71.88 (72.04) Prec@5 89.84 (89.33) + train[2018-10-17-21:32:31] Epoch: [118][2800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.011 (3.101) Prec@1 75.00 (72.02) Prec@5 92.19 (89.33) + train[2018-10-17-21:34:16] Epoch: [118][3000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.198 (3.100) Prec@1 70.31 (72.03) Prec@5 86.72 (89.34) + train[2018-10-17-21:36:02] Epoch: [118][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.124 (3.100) Prec@1 69.53 (72.02) Prec@5 90.62 (89.34) + train[2018-10-17-21:37:49] Epoch: [118][3400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.959 (3.100) Prec@1 75.78 (72.02) Prec@5 92.19 (89.33) + train[2018-10-17-21:39:34] Epoch: [118][3600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.245 (3.101) Prec@1 67.19 (72.01) Prec@5 89.06 (89.31) + train[2018-10-17-21:41:19] Epoch: [118][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.750 (3.100) Prec@1 80.47 (72.01) Prec@5 94.53 (89.34) + train[2018-10-17-21:43:05] Epoch: [118][4000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.006 (3.101) Prec@1 71.09 (72.02) Prec@5 90.62 (89.32) + train[2018-10-17-21:44:50] Epoch: [118][4200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.088 (3.102) Prec@1 68.75 (71.99) Prec@5 89.06 (89.31) + train[2018-10-17-21:46:36] Epoch: [118][4400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.130 (3.102) Prec@1 72.66 (71.97) Prec@5 86.72 (89.30) + train[2018-10-17-21:48:21] Epoch: [118][4600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.117 (3.102) Prec@1 72.66 (71.96) Prec@5 90.62 (89.30) + train[2018-10-17-21:50:07] Epoch: [118][4800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.196 (3.103) Prec@1 73.44 (71.96) Prec@5 87.50 (89.28) + train[2018-10-17-21:51:52] Epoch: [118][5000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.513 (3.104) Prec@1 64.06 (71.96) Prec@5 81.25 (89.28) + train[2018-10-17-21:53:37] Epoch: [118][5200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.002 (3.105) Prec@1 74.22 (71.95) Prec@5 92.19 (89.27) + train[2018-10-17-21:55:22] Epoch: [118][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.031 (3.105) Prec@1 68.75 (71.94) Prec@5 89.06 (89.26) + train[2018-10-17-21:57:08] Epoch: [118][5600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.233 (3.106) Prec@1 67.97 (71.92) Prec@5 87.50 (89.25) + train[2018-10-17-21:58:53] Epoch: [118][5800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.227 (3.106) Prec@1 71.09 (71.92) Prec@5 86.72 (89.24) + train[2018-10-17-22:00:38] Epoch: [118][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.902 (3.106) Prec@1 73.44 (71.92) Prec@5 92.19 (89.25) + train[2018-10-17-22:02:24] Epoch: [118][6200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.276 (3.107) Prec@1 64.84 (71.91) Prec@5 89.84 (89.25) + train[2018-10-17-22:04:10] Epoch: [118][6400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.054 (3.108) Prec@1 76.56 (71.89) Prec@5 91.41 (89.23) + train[2018-10-17-22:05:56] Epoch: [118][6600/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 3.255 (3.108) Prec@1 68.75 (71.87) Prec@5 90.62 (89.22) + train[2018-10-17-22:07:42] Epoch: [118][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.009 (3.109) Prec@1 74.22 (71.86) Prec@5 87.50 (89.21) + train[2018-10-17-22:09:29] Epoch: [118][7000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.374 (3.109) Prec@1 67.97 (71.86) Prec@5 85.16 (89.21) + train[2018-10-17-22:11:16] Epoch: [118][7200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.306 (3.109) Prec@1 68.75 (71.87) Prec@5 85.16 (89.22) + train[2018-10-17-22:13:01] Epoch: [118][7400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.005 (3.108) Prec@1 71.09 (71.87) Prec@5 90.62 (89.22) + train[2018-10-17-22:14:46] Epoch: [118][7600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.064 (3.108) Prec@1 71.09 (71.87) Prec@5 87.50 (89.22) + train[2018-10-17-22:16:32] Epoch: [118][7800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.290 (3.108) Prec@1 69.53 (71.87) Prec@5 87.50 (89.22) + train[2018-10-17-22:18:16] Epoch: [118][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.086 (3.109) Prec@1 75.78 (71.87) Prec@5 90.62 (89.21) + train[2018-10-17-22:20:02] Epoch: [118][8200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.975 (3.109) Prec@1 75.00 (71.86) Prec@5 88.28 (89.21) + train[2018-10-17-22:21:47] Epoch: [118][8400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.979 (3.109) Prec@1 73.44 (71.84) Prec@5 92.19 (89.20) + train[2018-10-17-22:23:32] Epoch: [118][8600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.303 (3.110) Prec@1 71.09 (71.83) Prec@5 87.50 (89.20) + train[2018-10-17-22:25:17] Epoch: [118][8800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.254 (3.110) Prec@1 71.09 (71.82) Prec@5 82.03 (89.20) + train[2018-10-17-22:27:02] Epoch: [118][9000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.236 (3.110) Prec@1 68.75 (71.82) Prec@5 90.62 (89.20) + train[2018-10-17-22:28:47] Epoch: [118][9200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.695 (3.110) Prec@1 68.75 (71.83) Prec@5 81.25 (89.19) + train[2018-10-17-22:30:32] Epoch: [118][9400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.526 (3.110) Prec@1 66.41 (71.83) Prec@5 83.59 (89.19) + train[2018-10-17-22:32:18] Epoch: [118][9600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.221 (3.110) Prec@1 63.28 (71.82) Prec@5 92.19 (89.18) + train[2018-10-17-22:34:03] Epoch: [118][9800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.138 (3.110) Prec@1 70.31 (71.81) Prec@5 90.62 (89.18) + train[2018-10-17-22:35:48] Epoch: [118][10000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.934 (3.111) Prec@1 75.78 (71.81) Prec@5 94.53 (89.18) + train[2018-10-17-22:35:52] Epoch: [118][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 4.466 (3.111) Prec@1 60.00 (71.81) Prec@5 66.67 (89.18) +[2018-10-17-22:35:52] **train** Prec@1 71.81 Prec@5 89.18 Error@1 28.19 Error@5 10.82 Loss:3.111 + test [2018-10-17-22:35:56] Epoch: [118][000/391] Time 3.93 (3.93) Data 3.79 (3.79) Loss 0.534 (0.534) Prec@1 90.62 (90.62) Prec@5 98.44 (98.44) + test [2018-10-17-22:36:24] Epoch: [118][200/391] Time 0.12 (0.16) Data 0.00 (0.03) Loss 1.218 (1.045) Prec@1 67.19 (75.76) Prec@5 92.19 (92.85) + test [2018-10-17-22:36:49] Epoch: [118][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.218 (1.217) Prec@1 43.75 (72.17) Prec@5 80.00 (90.50) +[2018-10-17-22:36:49] **test** Prec@1 72.17 Prec@5 90.50 Error@1 27.83 Error@5 9.50 Loss:1.217 +----> Best Accuracy : Acc@1=72.32, Acc@5=90.73, Error@1=27.68, Error@5=9.27 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-17-22:36:50] [Epoch=119/250] [Need: 194:14:32] LR=0.0027 ~ 0.0027, Batch=128 + train[2018-10-17-22:36:55] Epoch: [119][000/10010] Time 4.97 (4.97) Data 4.36 (4.36) Loss 2.905 (2.905) Prec@1 78.12 (78.12) Prec@5 92.19 (92.19) + train[2018-10-17-22:38:40] Epoch: [119][200/10010] Time 0.51 (0.55) Data 0.00 (0.02) Loss 3.202 (3.076) Prec@1 65.62 (72.61) Prec@5 89.84 (89.71) + train[2018-10-17-22:40:25] Epoch: [119][400/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 3.393 (3.077) Prec@1 67.19 (72.48) Prec@5 85.16 (89.70) + train[2018-10-17-22:42:10] Epoch: [119][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.089 (3.075) Prec@1 73.44 (72.50) Prec@5 89.06 (89.65) + train[2018-10-17-22:43:56] Epoch: [119][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 2.975 (3.075) Prec@1 77.34 (72.44) Prec@5 90.62 (89.63) + train[2018-10-17-22:45:42] Epoch: [119][1000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.235 (3.080) Prec@1 71.09 (72.42) Prec@5 86.72 (89.55) + train[2018-10-17-22:47:27] Epoch: [119][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.495 (3.083) Prec@1 71.09 (72.43) Prec@5 85.94 (89.51) + train[2018-10-17-22:49:13] Epoch: [119][1400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.156 (3.084) Prec@1 68.75 (72.35) Prec@5 89.84 (89.49) + train[2018-10-17-22:50:59] Epoch: [119][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.911 (3.086) Prec@1 74.22 (72.27) Prec@5 89.06 (89.50) + train[2018-10-17-22:52:45] Epoch: [119][1800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.975 (3.087) Prec@1 74.22 (72.25) Prec@5 92.19 (89.48) + train[2018-10-17-22:54:31] Epoch: [119][2000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.211 (3.086) Prec@1 66.41 (72.28) Prec@5 92.19 (89.50) + train[2018-10-17-22:56:16] Epoch: [119][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.947 (3.086) Prec@1 72.66 (72.26) Prec@5 89.06 (89.50) + train[2018-10-17-22:58:02] Epoch: [119][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.939 (3.087) Prec@1 75.00 (72.24) Prec@5 93.75 (89.49) + train[2018-10-17-22:59:47] Epoch: [119][2600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.903 (3.087) Prec@1 73.44 (72.24) Prec@5 91.41 (89.49) + train[2018-10-17-23:01:33] Epoch: [119][2800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.076 (3.087) Prec@1 70.31 (72.26) Prec@5 87.50 (89.48) + train[2018-10-17-23:03:18] Epoch: [119][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.853 (3.087) Prec@1 77.34 (72.25) Prec@5 94.53 (89.46) + train[2018-10-17-23:05:03] Epoch: [119][3200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.097 (3.085) Prec@1 71.88 (72.27) Prec@5 89.84 (89.48) + train[2018-10-17-23:06:49] Epoch: [119][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.244 (3.085) Prec@1 66.41 (72.29) Prec@5 88.28 (89.48) + train[2018-10-17-23:08:35] Epoch: [119][3600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.270 (3.087) Prec@1 65.62 (72.26) Prec@5 89.84 (89.47) + train[2018-10-17-23:10:21] Epoch: [119][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.061 (3.089) Prec@1 71.09 (72.23) Prec@5 89.06 (89.44) + train[2018-10-17-23:12:07] Epoch: [119][4000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.826 (3.089) Prec@1 78.12 (72.22) Prec@5 94.53 (89.42) + train[2018-10-17-23:13:52] Epoch: [119][4200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.148 (3.089) Prec@1 71.88 (72.22) Prec@5 89.06 (89.41) + train[2018-10-17-23:15:38] Epoch: [119][4400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.878 (3.090) Prec@1 75.00 (72.22) Prec@5 94.53 (89.41) + train[2018-10-17-23:17:24] Epoch: [119][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.002 (3.091) Prec@1 73.44 (72.20) Prec@5 89.84 (89.40) + train[2018-10-17-23:19:10] Epoch: [119][4800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.892 (3.091) Prec@1 78.91 (72.20) Prec@5 93.75 (89.39) + train[2018-10-17-23:20:55] Epoch: [119][5000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.890 (3.091) Prec@1 76.56 (72.21) Prec@5 90.62 (89.39) + train[2018-10-17-23:22:41] Epoch: [119][5200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.149 (3.092) Prec@1 77.34 (72.19) Prec@5 87.50 (89.38) + train[2018-10-17-23:24:26] Epoch: [119][5400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.172 (3.092) Prec@1 67.19 (72.18) Prec@5 86.72 (89.36) + train[2018-10-17-23:26:12] Epoch: [119][5600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.130 (3.092) Prec@1 73.44 (72.17) Prec@5 87.50 (89.36) + train[2018-10-17-23:27:57] Epoch: [119][5800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.289 (3.093) Prec@1 68.75 (72.16) Prec@5 85.94 (89.36) + train[2018-10-17-23:29:43] Epoch: [119][6000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.930 (3.094) Prec@1 69.53 (72.15) Prec@5 92.97 (89.35) + train[2018-10-17-23:31:29] Epoch: [119][6200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.373 (3.094) Prec@1 70.31 (72.13) Prec@5 85.16 (89.34) + train[2018-10-17-23:33:15] Epoch: [119][6400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.039 (3.095) Prec@1 73.44 (72.10) Prec@5 88.28 (89.33) + train[2018-10-17-23:35:01] Epoch: [119][6600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.248 (3.096) Prec@1 75.00 (72.10) Prec@5 88.28 (89.33) + train[2018-10-17-23:36:47] Epoch: [119][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.077 (3.096) Prec@1 73.44 (72.10) Prec@5 89.06 (89.33) + train[2018-10-17-23:38:32] Epoch: [119][7000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.035 (3.097) Prec@1 71.88 (72.09) Prec@5 89.84 (89.32) + train[2018-10-17-23:40:18] Epoch: [119][7200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.376 (3.097) Prec@1 67.19 (72.09) Prec@5 86.72 (89.32) + train[2018-10-17-23:42:03] Epoch: [119][7400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.806 (3.097) Prec@1 75.00 (72.08) Prec@5 93.75 (89.32) + train[2018-10-17-23:43:48] Epoch: [119][7600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.274 (3.097) Prec@1 71.09 (72.07) Prec@5 85.16 (89.32) + train[2018-10-17-23:45:34] Epoch: [119][7800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.661 (3.097) Prec@1 65.62 (72.07) Prec@5 83.59 (89.32) + train[2018-10-17-23:47:19] Epoch: [119][8000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.306 (3.098) Prec@1 71.88 (72.06) Prec@5 85.94 (89.32) + train[2018-10-17-23:49:04] Epoch: [119][8200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.177 (3.099) Prec@1 75.00 (72.06) Prec@5 88.28 (89.31) + train[2018-10-17-23:50:50] Epoch: [119][8400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.966 (3.098) Prec@1 71.88 (72.06) Prec@5 90.62 (89.31) + train[2018-10-17-23:52:35] Epoch: [119][8600/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.051 (3.099) Prec@1 74.22 (72.05) Prec@5 87.50 (89.31) + train[2018-10-17-23:54:21] Epoch: [119][8800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.034 (3.099) Prec@1 71.88 (72.04) Prec@5 89.06 (89.30) + train[2018-10-17-23:56:06] Epoch: [119][9000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.088 (3.100) Prec@1 73.44 (72.03) Prec@5 86.72 (89.29) + train[2018-10-17-23:57:51] Epoch: [119][9200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.031 (3.100) Prec@1 77.34 (72.03) Prec@5 90.62 (89.29) + train[2018-10-17-23:59:36] Epoch: [119][9400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.305 (3.101) Prec@1 67.97 (72.02) Prec@5 85.94 (89.28) + train[2018-10-18-00:01:21] Epoch: [119][9600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.173 (3.101) Prec@1 67.19 (72.00) Prec@5 87.50 (89.27) + train[2018-10-18-00:03:07] Epoch: [119][9800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.925 (3.102) Prec@1 75.78 (72.00) Prec@5 93.75 (89.27) + train[2018-10-18-00:04:52] Epoch: [119][10000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.025 (3.102) Prec@1 70.31 (72.00) Prec@5 89.06 (89.27) + train[2018-10-18-00:04:56] Epoch: [119][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 4.187 (3.102) Prec@1 46.67 (71.99) Prec@5 73.33 (89.27) +[2018-10-18-00:04:56] **train** Prec@1 71.99 Prec@5 89.27 Error@1 28.01 Error@5 10.73 Loss:3.102 + test [2018-10-18-00:05:01] Epoch: [119][000/391] Time 4.78 (4.78) Data 4.64 (4.64) Loss 0.671 (0.671) Prec@1 88.28 (88.28) Prec@5 96.09 (96.09) + test [2018-10-18-00:05:28] Epoch: [119][200/391] Time 0.15 (0.16) Data 0.00 (0.03) Loss 1.346 (1.057) Prec@1 66.41 (75.60) Prec@5 91.41 (93.10) + test [2018-10-18-00:05:53] Epoch: [119][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.311 (1.220) Prec@1 38.75 (72.22) Prec@5 83.75 (90.73) +[2018-10-18-00:05:53] **test** Prec@1 72.22 Prec@5 90.73 Error@1 27.78 Error@5 9.27 Loss:1.220 +----> Best Accuracy : Acc@1=72.32, Acc@5=90.73, Error@1=27.68, Error@5=9.27 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-18-00:05:53] [Epoch=120/250] [Need: 192:57:55] LR=0.0026 ~ 0.0026, Batch=128 + train[2018-10-18-00:05:58] Epoch: [120][000/10010] Time 5.17 (5.17) Data 4.55 (4.55) Loss 2.948 (2.948) Prec@1 76.56 (76.56) Prec@5 91.41 (91.41) + train[2018-10-18-00:07:44] Epoch: [120][200/10010] Time 0.51 (0.55) Data 0.00 (0.02) Loss 3.386 (3.087) Prec@1 70.31 (72.12) Prec@5 86.72 (89.53) + train[2018-10-18-00:09:29] Epoch: [120][400/10010] Time 0.53 (0.54) Data 0.00 (0.01) Loss 3.119 (3.092) Prec@1 72.66 (72.16) Prec@5 90.62 (89.42) + train[2018-10-18-00:11:14] Epoch: [120][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.147 (3.090) Prec@1 71.88 (72.19) Prec@5 87.50 (89.42) + train[2018-10-18-00:13:00] Epoch: [120][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 2.735 (3.090) Prec@1 79.69 (72.25) Prec@5 90.62 (89.45) + train[2018-10-18-00:14:45] Epoch: [120][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.015 (3.087) Prec@1 75.00 (72.26) Prec@5 89.84 (89.53) + train[2018-10-18-00:16:30] Epoch: [120][1200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.688 (3.086) Prec@1 78.12 (72.28) Prec@5 93.75 (89.53) + train[2018-10-18-00:18:15] Epoch: [120][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.226 (3.088) Prec@1 75.78 (72.25) Prec@5 89.06 (89.49) + train[2018-10-18-00:20:00] Epoch: [120][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.953 (3.088) Prec@1 71.88 (72.21) Prec@5 90.62 (89.50) + train[2018-10-18-00:21:45] Epoch: [120][1800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.120 (3.088) Prec@1 74.22 (72.25) Prec@5 87.50 (89.50) + train[2018-10-18-00:23:30] Epoch: [120][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.957 (3.087) Prec@1 75.78 (72.27) Prec@5 91.41 (89.51) + train[2018-10-18-00:25:15] Epoch: [120][2200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.983 (3.088) Prec@1 75.00 (72.26) Prec@5 92.19 (89.51) + train[2018-10-18-00:27:00] Epoch: [120][2400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.913 (3.088) Prec@1 71.88 (72.22) Prec@5 92.19 (89.50) + train[2018-10-18-00:28:45] Epoch: [120][2600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.906 (3.088) Prec@1 75.00 (72.24) Prec@5 92.19 (89.51) + train[2018-10-18-00:30:31] Epoch: [120][2800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.344 (3.089) Prec@1 71.09 (72.22) Prec@5 85.94 (89.49) + train[2018-10-18-00:32:17] Epoch: [120][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.062 (3.090) Prec@1 67.97 (72.21) Prec@5 91.41 (89.50) + train[2018-10-18-00:34:02] Epoch: [120][3200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.306 (3.089) Prec@1 67.97 (72.21) Prec@5 86.72 (89.50) + train[2018-10-18-00:35:48] Epoch: [120][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.879 (3.090) Prec@1 71.88 (72.20) Prec@5 91.41 (89.49) + train[2018-10-18-00:37:33] Epoch: [120][3600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.927 (3.091) Prec@1 72.66 (72.19) Prec@5 91.41 (89.47) + train[2018-10-18-00:39:18] Epoch: [120][3800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.668 (3.092) Prec@1 79.69 (72.18) Prec@5 90.62 (89.45) + train[2018-10-18-00:41:04] Epoch: [120][4000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.179 (3.091) Prec@1 68.75 (72.20) Prec@5 88.28 (89.46) + train[2018-10-18-00:42:49] Epoch: [120][4200/10010] Time 0.62 (0.53) Data 0.00 (0.00) Loss 2.936 (3.090) Prec@1 77.34 (72.20) Prec@5 89.84 (89.47) + train[2018-10-18-00:44:35] Epoch: [120][4400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.041 (3.090) Prec@1 75.78 (72.20) Prec@5 90.62 (89.47) + train[2018-10-18-00:46:20] Epoch: [120][4600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.308 (3.090) Prec@1 64.06 (72.20) Prec@5 86.72 (89.47) + train[2018-10-18-00:48:06] Epoch: [120][4800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.289 (3.090) Prec@1 71.09 (72.22) Prec@5 85.94 (89.47) + train[2018-10-18-00:49:51] Epoch: [120][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.082 (3.090) Prec@1 71.88 (72.19) Prec@5 87.50 (89.46) + train[2018-10-18-00:51:36] Epoch: [120][5200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.194 (3.092) Prec@1 69.53 (72.16) Prec@5 86.72 (89.44) + train[2018-10-18-00:53:21] Epoch: [120][5400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.265 (3.092) Prec@1 68.75 (72.16) Prec@5 86.72 (89.44) + train[2018-10-18-00:55:06] Epoch: [120][5600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.424 (3.093) Prec@1 64.06 (72.15) Prec@5 85.94 (89.43) + train[2018-10-18-00:56:51] Epoch: [120][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.737 (3.093) Prec@1 79.69 (72.14) Prec@5 91.41 (89.42) + train[2018-10-18-00:58:37] Epoch: [120][6000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.026 (3.094) Prec@1 74.22 (72.14) Prec@5 90.62 (89.41) + train[2018-10-18-01:00:22] Epoch: [120][6200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.916 (3.094) Prec@1 75.78 (72.14) Prec@5 91.41 (89.40) + train[2018-10-18-01:02:07] Epoch: [120][6400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.642 (3.095) Prec@1 65.62 (72.11) Prec@5 82.81 (89.39) + train[2018-10-18-01:03:54] Epoch: [120][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.792 (3.095) Prec@1 76.56 (72.10) Prec@5 92.19 (89.38) + train[2018-10-18-01:05:39] Epoch: [120][6800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.638 (3.096) Prec@1 66.41 (72.08) Prec@5 85.16 (89.37) + train[2018-10-18-01:07:24] Epoch: [120][7000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.677 (3.096) Prec@1 80.47 (72.08) Prec@5 96.09 (89.37) + train[2018-10-18-01:09:09] Epoch: [120][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.060 (3.096) Prec@1 69.53 (72.08) Prec@5 89.84 (89.37) + train[2018-10-18-01:10:54] Epoch: [120][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.218 (3.097) Prec@1 74.22 (72.06) Prec@5 86.72 (89.36) + train[2018-10-18-01:12:40] Epoch: [120][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.978 (3.097) Prec@1 75.00 (72.07) Prec@5 90.62 (89.36) + train[2018-10-18-01:14:25] Epoch: [120][7800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.095 (3.097) Prec@1 68.75 (72.07) Prec@5 92.19 (89.36) + train[2018-10-18-01:16:10] Epoch: [120][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.140 (3.096) Prec@1 69.53 (72.08) Prec@5 85.94 (89.36) + train[2018-10-18-01:17:56] Epoch: [120][8200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.045 (3.096) Prec@1 76.56 (72.07) Prec@5 89.84 (89.36) + train[2018-10-18-01:19:42] Epoch: [120][8400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.957 (3.097) Prec@1 77.34 (72.06) Prec@5 90.62 (89.36) + train[2018-10-18-01:21:27] Epoch: [120][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.879 (3.097) Prec@1 73.44 (72.06) Prec@5 91.41 (89.35) + train[2018-10-18-01:23:12] Epoch: [120][8800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.094 (3.097) Prec@1 71.09 (72.07) Prec@5 92.19 (89.35) + train[2018-10-18-01:24:58] Epoch: [120][9000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.327 (3.097) Prec@1 68.75 (72.07) Prec@5 85.16 (89.35) + train[2018-10-18-01:26:43] Epoch: [120][9200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.831 (3.097) Prec@1 80.47 (72.06) Prec@5 93.75 (89.34) + train[2018-10-18-01:28:28] Epoch: [120][9400/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.083 (3.098) Prec@1 75.00 (72.04) Prec@5 89.06 (89.33) + train[2018-10-18-01:30:14] Epoch: [120][9600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.345 (3.098) Prec@1 68.75 (72.04) Prec@5 88.28 (89.33) + train[2018-10-18-01:32:00] Epoch: [120][9800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.442 (3.099) Prec@1 61.72 (72.03) Prec@5 86.72 (89.33) + train[2018-10-18-01:33:44] Epoch: [120][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.953 (3.099) Prec@1 74.22 (72.02) Prec@5 89.84 (89.32) + train[2018-10-18-01:33:49] Epoch: [120][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 3.153 (3.099) Prec@1 86.67 (72.02) Prec@5 93.33 (89.32) +[2018-10-18-01:33:49] **train** Prec@1 72.02 Prec@5 89.32 Error@1 27.98 Error@5 10.68 Loss:3.099 + test [2018-10-18-01:33:53] Epoch: [120][000/391] Time 4.62 (4.62) Data 4.48 (4.48) Loss 0.583 (0.583) Prec@1 89.84 (89.84) Prec@5 99.22 (99.22) + test [2018-10-18-01:34:20] Epoch: [120][200/391] Time 0.15 (0.16) Data 0.00 (0.03) Loss 1.243 (1.040) Prec@1 68.75 (76.01) Prec@5 89.84 (93.02) + test [2018-10-18-01:34:46] Epoch: [120][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.202 (1.201) Prec@1 42.50 (72.50) Prec@5 80.00 (90.85) +[2018-10-18-01:34:46] **test** Prec@1 72.50 Prec@5 90.85 Error@1 27.50 Error@5 9.15 Loss:1.201 +----> Best Accuracy : Acc@1=72.50, Acc@5=90.85, Error@1=27.50, Error@5=9.15 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-18-01:34:46] [Epoch=121/250] [Need: 191:04:45] LR=0.0025 ~ 0.0025, Batch=128 + train[2018-10-18-01:34:51] Epoch: [121][000/10010] Time 5.04 (5.04) Data 4.27 (4.27) Loss 3.097 (3.097) Prec@1 71.88 (71.88) Prec@5 91.41 (91.41) + train[2018-10-18-01:36:36] Epoch: [121][200/10010] Time 0.51 (0.55) Data 0.00 (0.02) Loss 3.037 (3.079) Prec@1 71.09 (72.32) Prec@5 89.84 (89.56) + train[2018-10-18-01:38:21] Epoch: [121][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.927 (3.076) Prec@1 75.00 (72.53) Prec@5 92.19 (89.45) + train[2018-10-18-01:40:06] Epoch: [121][600/10010] Time 0.58 (0.53) Data 0.00 (0.01) Loss 3.165 (3.074) Prec@1 68.75 (72.55) Prec@5 86.72 (89.52) + train[2018-10-18-01:41:51] Epoch: [121][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.245 (3.074) Prec@1 63.28 (72.56) Prec@5 89.06 (89.54) + train[2018-10-18-01:43:36] Epoch: [121][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.065 (3.073) Prec@1 71.88 (72.56) Prec@5 89.84 (89.59) + train[2018-10-18-01:45:22] Epoch: [121][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.172 (3.079) Prec@1 70.31 (72.45) Prec@5 85.94 (89.52) + train[2018-10-18-01:47:07] Epoch: [121][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.964 (3.080) Prec@1 74.22 (72.42) Prec@5 92.97 (89.51) + train[2018-10-18-01:48:52] Epoch: [121][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.090 (3.081) Prec@1 68.75 (72.38) Prec@5 92.19 (89.48) + train[2018-10-18-01:50:37] Epoch: [121][1800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.792 (3.083) Prec@1 79.69 (72.34) Prec@5 90.62 (89.45) + train[2018-10-18-01:52:22] Epoch: [121][2000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.187 (3.086) Prec@1 71.09 (72.28) Prec@5 89.84 (89.39) + train[2018-10-18-01:54:07] Epoch: [121][2200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.041 (3.088) Prec@1 73.44 (72.24) Prec@5 90.62 (89.40) + train[2018-10-18-01:55:53] Epoch: [121][2400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.485 (3.087) Prec@1 63.28 (72.30) Prec@5 84.38 (89.41) + train[2018-10-18-01:57:39] Epoch: [121][2600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.978 (3.085) Prec@1 75.00 (72.33) Prec@5 89.84 (89.43) + train[2018-10-18-01:59:25] Epoch: [121][2800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.316 (3.084) Prec@1 65.62 (72.38) Prec@5 88.28 (89.45) + train[2018-10-18-02:01:10] Epoch: [121][3000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.931 (3.084) Prec@1 71.88 (72.37) Prec@5 93.75 (89.46) + train[2018-10-18-02:02:56] Epoch: [121][3200/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 2.899 (3.085) Prec@1 76.56 (72.34) Prec@5 90.62 (89.45) + train[2018-10-18-02:04:42] Epoch: [121][3400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.981 (3.085) Prec@1 74.22 (72.34) Prec@5 86.72 (89.46) + train[2018-10-18-02:06:27] Epoch: [121][3600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.130 (3.084) Prec@1 75.00 (72.35) Prec@5 87.50 (89.47) + train[2018-10-18-02:08:13] Epoch: [121][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.142 (3.084) Prec@1 75.78 (72.33) Prec@5 86.72 (89.47) + train[2018-10-18-02:09:58] Epoch: [121][4000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.117 (3.085) Prec@1 67.97 (72.32) Prec@5 89.06 (89.47) + train[2018-10-18-02:11:44] Epoch: [121][4200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.137 (3.086) Prec@1 71.88 (72.29) Prec@5 90.62 (89.46) + train[2018-10-18-02:13:29] Epoch: [121][4400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.056 (3.086) Prec@1 75.00 (72.28) Prec@5 89.06 (89.46) + train[2018-10-18-02:15:15] Epoch: [121][4600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.202 (3.087) Prec@1 64.84 (72.28) Prec@5 89.06 (89.45) + train[2018-10-18-02:17:00] Epoch: [121][4800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.208 (3.087) Prec@1 70.31 (72.26) Prec@5 87.50 (89.44) + train[2018-10-18-02:18:46] Epoch: [121][5000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.870 (3.088) Prec@1 76.56 (72.25) Prec@5 93.75 (89.45) + train[2018-10-18-02:20:32] Epoch: [121][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.074 (3.088) Prec@1 73.44 (72.24) Prec@5 87.50 (89.44) + train[2018-10-18-02:22:17] Epoch: [121][5400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.899 (3.089) Prec@1 74.22 (72.22) Prec@5 91.41 (89.43) + train[2018-10-18-02:24:03] Epoch: [121][5600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.098 (3.089) Prec@1 71.09 (72.22) Prec@5 88.28 (89.43) + train[2018-10-18-02:25:48] Epoch: [121][5800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.101 (3.089) Prec@1 72.66 (72.22) Prec@5 89.84 (89.43) + train[2018-10-18-02:27:33] Epoch: [121][6000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.165 (3.090) Prec@1 70.31 (72.19) Prec@5 87.50 (89.41) + train[2018-10-18-02:29:19] Epoch: [121][6200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.019 (3.090) Prec@1 70.31 (72.19) Prec@5 89.84 (89.41) + train[2018-10-18-02:31:04] Epoch: [121][6400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.179 (3.090) Prec@1 74.22 (72.20) Prec@5 89.06 (89.41) + train[2018-10-18-02:32:50] Epoch: [121][6600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.013 (3.090) Prec@1 72.66 (72.20) Prec@5 89.06 (89.42) + train[2018-10-18-02:34:35] Epoch: [121][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.910 (3.090) Prec@1 76.56 (72.20) Prec@5 92.97 (89.42) + train[2018-10-18-02:36:20] Epoch: [121][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.244 (3.090) Prec@1 64.84 (72.21) Prec@5 82.81 (89.42) + train[2018-10-18-02:38:06] Epoch: [121][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.099 (3.090) Prec@1 73.44 (72.21) Prec@5 90.62 (89.41) + train[2018-10-18-02:39:52] Epoch: [121][7400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.039 (3.090) Prec@1 71.09 (72.20) Prec@5 92.19 (89.42) + train[2018-10-18-02:41:37] Epoch: [121][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.833 (3.090) Prec@1 74.22 (72.20) Prec@5 93.75 (89.42) + train[2018-10-18-02:43:22] Epoch: [121][7800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.025 (3.091) Prec@1 74.22 (72.19) Prec@5 88.28 (89.40) + train[2018-10-18-02:45:08] Epoch: [121][8000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.185 (3.092) Prec@1 71.09 (72.18) Prec@5 87.50 (89.40) + train[2018-10-18-02:46:53] Epoch: [121][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.141 (3.092) Prec@1 73.44 (72.17) Prec@5 88.28 (89.39) + train[2018-10-18-02:48:39] Epoch: [121][8400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.047 (3.092) Prec@1 71.09 (72.16) Prec@5 89.84 (89.40) + train[2018-10-18-02:50:24] Epoch: [121][8600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.142 (3.092) Prec@1 75.78 (72.16) Prec@5 87.50 (89.39) + train[2018-10-18-02:52:09] Epoch: [121][8800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.206 (3.093) Prec@1 75.00 (72.16) Prec@5 87.50 (89.39) + train[2018-10-18-02:53:56] Epoch: [121][9000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.940 (3.093) Prec@1 77.34 (72.15) Prec@5 92.19 (89.38) + train[2018-10-18-02:55:43] Epoch: [121][9200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.150 (3.092) Prec@1 67.97 (72.16) Prec@5 92.19 (89.39) + train[2018-10-18-02:57:30] Epoch: [121][9400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.931 (3.092) Prec@1 75.00 (72.16) Prec@5 91.41 (89.38) + train[2018-10-18-02:59:16] Epoch: [121][9600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.716 (3.093) Prec@1 79.69 (72.15) Prec@5 91.41 (89.38) + train[2018-10-18-03:01:02] Epoch: [121][9800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.894 (3.092) Prec@1 75.78 (72.15) Prec@5 94.53 (89.38) + train[2018-10-18-03:02:47] Epoch: [121][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.856 (3.093) Prec@1 76.56 (72.15) Prec@5 89.84 (89.37) + train[2018-10-18-03:02:51] Epoch: [121][10009/10010] Time 0.14 (0.53) Data 0.00 (0.00) Loss 3.704 (3.093) Prec@1 60.00 (72.15) Prec@5 80.00 (89.37) +[2018-10-18-03:02:51] **train** Prec@1 72.15 Prec@5 89.37 Error@1 27.85 Error@5 10.63 Loss:3.093 + test [2018-10-18-03:02:55] Epoch: [121][000/391] Time 4.17 (4.17) Data 4.03 (4.03) Loss 0.586 (0.586) Prec@1 90.62 (90.62) Prec@5 98.44 (98.44) + test [2018-10-18-03:03:23] Epoch: [121][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.363 (1.057) Prec@1 67.19 (75.76) Prec@5 90.62 (93.02) + test [2018-10-18-03:03:49] Epoch: [121][390/391] Time 0.09 (0.15) Data 0.00 (0.02) Loss 2.226 (1.226) Prec@1 38.75 (72.23) Prec@5 81.25 (90.74) +[2018-10-18-03:03:49] **test** Prec@1 72.23 Prec@5 90.74 Error@1 27.77 Error@5 9.26 Loss:1.226 +----> Best Accuracy : Acc@1=72.50, Acc@5=90.85, Error@1=27.50, Error@5=9.15 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-18-03:03:49] [Epoch=122/250] [Need: 189:58:44] LR=0.0024 ~ 0.0024, Batch=128 + train[2018-10-18-03:03:54] Epoch: [122][000/10010] Time 4.91 (4.91) Data 4.27 (4.27) Loss 2.875 (2.875) Prec@1 76.56 (76.56) Prec@5 93.75 (93.75) + train[2018-10-18-03:05:38] Epoch: [122][200/10010] Time 0.51 (0.54) Data 0.00 (0.02) Loss 3.376 (3.043) Prec@1 67.97 (72.93) Prec@5 84.38 (89.97) + train[2018-10-18-03:07:23] Epoch: [122][400/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 2.990 (3.054) Prec@1 75.78 (72.80) Prec@5 90.62 (89.87) + train[2018-10-18-03:09:08] Epoch: [122][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.115 (3.062) Prec@1 68.75 (72.63) Prec@5 88.28 (89.82) + train[2018-10-18-03:10:53] Epoch: [122][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.471 (3.057) Prec@1 65.62 (72.74) Prec@5 88.28 (89.84) + train[2018-10-18-03:12:38] Epoch: [122][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.903 (3.060) Prec@1 71.88 (72.71) Prec@5 92.97 (89.80) + train[2018-10-18-03:14:22] Epoch: [122][1200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.068 (3.061) Prec@1 71.09 (72.72) Prec@5 89.06 (89.76) + train[2018-10-18-03:16:08] Epoch: [122][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.043 (3.064) Prec@1 73.44 (72.68) Prec@5 90.62 (89.73) + train[2018-10-18-03:17:52] Epoch: [122][1600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.891 (3.066) Prec@1 75.00 (72.64) Prec@5 91.41 (89.72) + train[2018-10-18-03:19:37] Epoch: [122][1800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.368 (3.068) Prec@1 64.06 (72.59) Prec@5 87.50 (89.70) + train[2018-10-18-03:21:21] Epoch: [122][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.999 (3.067) Prec@1 74.22 (72.60) Prec@5 89.84 (89.70) + train[2018-10-18-03:23:06] Epoch: [122][2200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.753 (3.067) Prec@1 79.69 (72.55) Prec@5 94.53 (89.71) + train[2018-10-18-03:24:52] Epoch: [122][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.083 (3.070) Prec@1 75.00 (72.52) Prec@5 89.84 (89.69) + train[2018-10-18-03:26:36] Epoch: [122][2600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.034 (3.070) Prec@1 71.09 (72.54) Prec@5 91.41 (89.68) + train[2018-10-18-03:28:21] Epoch: [122][2800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.991 (3.072) Prec@1 77.34 (72.49) Prec@5 90.62 (89.66) + train[2018-10-18-03:30:05] Epoch: [122][3000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.113 (3.073) Prec@1 72.66 (72.50) Prec@5 88.28 (89.64) + train[2018-10-18-03:31:50] Epoch: [122][3200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.108 (3.074) Prec@1 73.44 (72.46) Prec@5 90.62 (89.61) + train[2018-10-18-03:33:35] Epoch: [122][3400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.456 (3.074) Prec@1 67.97 (72.50) Prec@5 85.94 (89.62) + train[2018-10-18-03:35:19] Epoch: [122][3600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.579 (3.074) Prec@1 63.28 (72.50) Prec@5 83.59 (89.61) + train[2018-10-18-03:37:05] Epoch: [122][3800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.936 (3.074) Prec@1 69.53 (72.51) Prec@5 94.53 (89.61) + train[2018-10-18-03:38:49] Epoch: [122][4000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.556 (3.075) Prec@1 82.81 (72.49) Prec@5 96.09 (89.59) + train[2018-10-18-03:40:34] Epoch: [122][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.947 (3.077) Prec@1 71.88 (72.44) Prec@5 91.41 (89.56) + train[2018-10-18-03:42:18] Epoch: [122][4400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.732 (3.078) Prec@1 83.59 (72.42) Prec@5 93.75 (89.55) + train[2018-10-18-03:44:03] Epoch: [122][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.086 (3.078) Prec@1 73.44 (72.43) Prec@5 89.06 (89.56) + train[2018-10-18-03:45:48] Epoch: [122][4800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.111 (3.077) Prec@1 67.97 (72.43) Prec@5 89.84 (89.57) + train[2018-10-18-03:47:33] Epoch: [122][5000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.062 (3.077) Prec@1 74.22 (72.45) Prec@5 89.84 (89.56) + train[2018-10-18-03:49:18] Epoch: [122][5200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.060 (3.077) Prec@1 69.53 (72.45) Prec@5 91.41 (89.57) + train[2018-10-18-03:51:03] Epoch: [122][5400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.050 (3.077) Prec@1 75.00 (72.43) Prec@5 91.41 (89.56) + train[2018-10-18-03:52:48] Epoch: [122][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.958 (3.077) Prec@1 71.09 (72.42) Prec@5 91.41 (89.57) + train[2018-10-18-03:54:33] Epoch: [122][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.112 (3.077) Prec@1 69.53 (72.43) Prec@5 87.50 (89.57) + train[2018-10-18-03:56:18] Epoch: [122][6000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 2.972 (3.078) Prec@1 76.56 (72.43) Prec@5 91.41 (89.56) + train[2018-10-18-03:58:03] Epoch: [122][6200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.139 (3.078) Prec@1 69.53 (72.42) Prec@5 87.50 (89.56) + train[2018-10-18-03:59:48] Epoch: [122][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.881 (3.079) Prec@1 78.12 (72.42) Prec@5 91.41 (89.55) + train[2018-10-18-04:01:33] Epoch: [122][6600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.438 (3.079) Prec@1 64.84 (72.41) Prec@5 86.72 (89.54) + train[2018-10-18-04:03:18] Epoch: [122][6800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.135 (3.079) Prec@1 71.09 (72.40) Prec@5 89.84 (89.54) + train[2018-10-18-04:05:03] Epoch: [122][7000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.575 (3.080) Prec@1 64.06 (72.39) Prec@5 85.94 (89.53) + train[2018-10-18-04:06:47] Epoch: [122][7200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.030 (3.080) Prec@1 77.34 (72.37) Prec@5 91.41 (89.52) + train[2018-10-18-04:08:32] Epoch: [122][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.241 (3.081) Prec@1 64.84 (72.37) Prec@5 89.06 (89.51) + train[2018-10-18-04:10:17] Epoch: [122][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.087 (3.081) Prec@1 67.97 (72.35) Prec@5 90.62 (89.51) + train[2018-10-18-04:12:02] Epoch: [122][7800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 2.905 (3.081) Prec@1 74.22 (72.35) Prec@5 89.06 (89.51) + train[2018-10-18-04:13:47] Epoch: [122][8000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.009 (3.081) Prec@1 73.44 (72.35) Prec@5 89.84 (89.51) + train[2018-10-18-04:15:32] Epoch: [122][8200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.296 (3.082) Prec@1 70.31 (72.34) Prec@5 86.72 (89.51) + train[2018-10-18-04:17:16] Epoch: [122][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.114 (3.082) Prec@1 71.88 (72.33) Prec@5 89.84 (89.50) + train[2018-10-18-04:19:01] Epoch: [122][8600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.237 (3.083) Prec@1 72.66 (72.31) Prec@5 88.28 (89.50) + train[2018-10-18-04:20:46] Epoch: [122][8800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.086 (3.083) Prec@1 71.09 (72.30) Prec@5 89.84 (89.49) + train[2018-10-18-04:22:32] Epoch: [122][9000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.286 (3.084) Prec@1 69.53 (72.29) Prec@5 85.94 (89.48) + train[2018-10-18-04:24:17] Epoch: [122][9200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.348 (3.084) Prec@1 67.97 (72.28) Prec@5 85.94 (89.47) + train[2018-10-18-04:26:02] Epoch: [122][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.297 (3.084) Prec@1 71.09 (72.28) Prec@5 85.16 (89.47) + train[2018-10-18-04:27:47] Epoch: [122][9600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.025 (3.084) Prec@1 76.56 (72.27) Prec@5 89.84 (89.47) + train[2018-10-18-04:29:32] Epoch: [122][9800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 2.926 (3.085) Prec@1 75.78 (72.26) Prec@5 91.41 (89.47) + train[2018-10-18-04:31:17] Epoch: [122][10000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.081 (3.085) Prec@1 71.88 (72.26) Prec@5 89.06 (89.46) + train[2018-10-18-04:31:21] Epoch: [122][10009/10010] Time 0.14 (0.52) Data 0.00 (0.00) Loss 3.406 (3.085) Prec@1 60.00 (72.26) Prec@5 86.67 (89.46) +[2018-10-18-04:31:21] **train** Prec@1 72.26 Prec@5 89.46 Error@1 27.74 Error@5 10.54 Loss:3.085 + test [2018-10-18-04:31:25] Epoch: [122][000/391] Time 4.06 (4.06) Data 3.92 (3.92) Loss 0.560 (0.560) Prec@1 87.50 (87.50) Prec@5 97.66 (97.66) + test [2018-10-18-04:31:53] Epoch: [122][200/391] Time 0.14 (0.16) Data 0.00 (0.03) Loss 1.239 (1.029) Prec@1 64.84 (76.26) Prec@5 92.19 (92.96) + test [2018-10-18-04:32:18] Epoch: [122][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.131 (1.195) Prec@1 46.25 (72.53) Prec@5 82.50 (90.81) +[2018-10-18-04:32:18] **test** Prec@1 72.53 Prec@5 90.81 Error@1 27.47 Error@5 9.19 Loss:1.195 +----> Best Accuracy : Acc@1=72.53, Acc@5=90.81, Error@1=27.47, Error@5=9.19 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-18-04:32:18] [Epoch=123/250] [Need: 187:18:08] LR=0.0024 ~ 0.0024, Batch=128 + train[2018-10-18-04:32:23] Epoch: [123][000/10010] Time 4.81 (4.81) Data 4.16 (4.16) Loss 3.067 (3.067) Prec@1 73.44 (73.44) Prec@5 91.41 (91.41) + train[2018-10-18-04:34:09] Epoch: [123][200/10010] Time 0.53 (0.55) Data 0.00 (0.02) Loss 3.078 (3.085) Prec@1 71.88 (72.45) Prec@5 89.84 (89.54) + train[2018-10-18-04:35:56] Epoch: [123][400/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.917 (3.074) Prec@1 73.44 (72.65) Prec@5 89.06 (89.65) + train[2018-10-18-04:37:41] Epoch: [123][600/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.879 (3.065) Prec@1 72.66 (72.85) Prec@5 89.84 (89.75) + train[2018-10-18-04:39:26] Epoch: [123][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.050 (3.067) Prec@1 78.12 (72.80) Prec@5 92.97 (89.71) + train[2018-10-18-04:41:12] Epoch: [123][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.746 (3.067) Prec@1 78.91 (72.72) Prec@5 92.19 (89.77) + train[2018-10-18-04:42:57] Epoch: [123][1200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.199 (3.070) Prec@1 67.97 (72.67) Prec@5 85.16 (89.69) + train[2018-10-18-04:44:42] Epoch: [123][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.262 (3.067) Prec@1 64.84 (72.69) Prec@5 90.62 (89.74) + train[2018-10-18-04:46:27] Epoch: [123][1600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.048 (3.068) Prec@1 71.88 (72.65) Prec@5 90.62 (89.74) + train[2018-10-18-04:48:13] Epoch: [123][1800/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 2.831 (3.071) Prec@1 74.22 (72.58) Prec@5 89.84 (89.71) + train[2018-10-18-04:49:58] Epoch: [123][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.063 (3.069) Prec@1 74.22 (72.58) Prec@5 89.84 (89.72) + train[2018-10-18-04:51:44] Epoch: [123][2200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.329 (3.070) Prec@1 71.09 (72.57) Prec@5 83.59 (89.71) + train[2018-10-18-04:53:31] Epoch: [123][2400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.598 (3.069) Prec@1 64.84 (72.61) Prec@5 81.25 (89.71) + train[2018-10-18-04:55:16] Epoch: [123][2600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.926 (3.069) Prec@1 81.25 (72.61) Prec@5 89.84 (89.70) + train[2018-10-18-04:57:02] Epoch: [123][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.161 (3.069) Prec@1 72.66 (72.62) Prec@5 89.06 (89.69) + train[2018-10-18-04:58:47] Epoch: [123][3000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.842 (3.069) Prec@1 71.88 (72.63) Prec@5 93.75 (89.70) + train[2018-10-18-05:00:32] Epoch: [123][3200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.073 (3.071) Prec@1 73.44 (72.60) Prec@5 89.06 (89.67) + train[2018-10-18-05:02:18] Epoch: [123][3400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.197 (3.071) Prec@1 72.66 (72.62) Prec@5 84.38 (89.66) + train[2018-10-18-05:04:04] Epoch: [123][3600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.959 (3.071) Prec@1 69.53 (72.61) Prec@5 94.53 (89.66) + train[2018-10-18-05:05:50] Epoch: [123][3800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.100 (3.071) Prec@1 74.22 (72.62) Prec@5 92.19 (89.65) + train[2018-10-18-05:07:35] Epoch: [123][4000/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 2.920 (3.070) Prec@1 75.00 (72.64) Prec@5 90.62 (89.65) + train[2018-10-18-05:09:19] Epoch: [123][4200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.917 (3.070) Prec@1 75.00 (72.64) Prec@5 91.41 (89.66) + train[2018-10-18-05:11:05] Epoch: [123][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.043 (3.070) Prec@1 75.78 (72.63) Prec@5 89.06 (89.66) + train[2018-10-18-05:12:50] Epoch: [123][4600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.084 (3.071) Prec@1 72.66 (72.62) Prec@5 88.28 (89.64) + train[2018-10-18-05:14:37] Epoch: [123][4800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.991 (3.072) Prec@1 72.66 (72.59) Prec@5 92.19 (89.63) + train[2018-10-18-05:16:22] Epoch: [123][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.931 (3.074) Prec@1 73.44 (72.56) Prec@5 90.62 (89.62) + train[2018-10-18-05:18:08] Epoch: [123][5200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.371 (3.074) Prec@1 68.75 (72.56) Prec@5 85.94 (89.61) + train[2018-10-18-05:19:53] Epoch: [123][5400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.124 (3.074) Prec@1 77.34 (72.56) Prec@5 88.28 (89.61) + train[2018-10-18-05:21:38] Epoch: [123][5600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.094 (3.075) Prec@1 67.97 (72.55) Prec@5 88.28 (89.60) + train[2018-10-18-05:23:23] Epoch: [123][5800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.899 (3.075) Prec@1 75.00 (72.54) Prec@5 92.19 (89.58) + train[2018-10-18-05:25:09] Epoch: [123][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.120 (3.075) Prec@1 74.22 (72.53) Prec@5 88.28 (89.59) + train[2018-10-18-05:26:54] Epoch: [123][6200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.902 (3.076) Prec@1 76.56 (72.51) Prec@5 91.41 (89.58) + train[2018-10-18-05:28:39] Epoch: [123][6400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.997 (3.077) Prec@1 73.44 (72.51) Prec@5 93.75 (89.56) + train[2018-10-18-05:30:25] Epoch: [123][6600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.323 (3.076) Prec@1 71.88 (72.50) Prec@5 85.94 (89.57) + train[2018-10-18-05:32:11] Epoch: [123][6800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.162 (3.077) Prec@1 71.88 (72.50) Prec@5 87.50 (89.55) + train[2018-10-18-05:33:56] Epoch: [123][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.858 (3.077) Prec@1 78.12 (72.49) Prec@5 92.19 (89.55) + train[2018-10-18-05:35:43] Epoch: [123][7200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.759 (3.077) Prec@1 75.78 (72.48) Prec@5 96.09 (89.55) + train[2018-10-18-05:37:28] Epoch: [123][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.154 (3.077) Prec@1 70.31 (72.46) Prec@5 87.50 (89.54) + train[2018-10-18-05:39:14] Epoch: [123][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.550 (3.078) Prec@1 64.06 (72.45) Prec@5 82.81 (89.53) + train[2018-10-18-05:40:59] Epoch: [123][7800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.423 (3.078) Prec@1 64.06 (72.44) Prec@5 85.94 (89.53) + train[2018-10-18-05:42:44] Epoch: [123][8000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.140 (3.078) Prec@1 73.44 (72.43) Prec@5 89.06 (89.53) + train[2018-10-18-05:44:29] Epoch: [123][8200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.920 (3.079) Prec@1 78.91 (72.42) Prec@5 90.62 (89.52) + train[2018-10-18-05:46:15] Epoch: [123][8400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.016 (3.079) Prec@1 74.22 (72.42) Prec@5 92.19 (89.53) + train[2018-10-18-05:48:00] Epoch: [123][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.011 (3.079) Prec@1 73.44 (72.41) Prec@5 89.06 (89.53) + train[2018-10-18-05:49:45] Epoch: [123][8800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.140 (3.079) Prec@1 66.41 (72.41) Prec@5 90.62 (89.52) + train[2018-10-18-05:51:30] Epoch: [123][9000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.801 (3.080) Prec@1 76.56 (72.40) Prec@5 95.31 (89.52) + train[2018-10-18-05:53:16] Epoch: [123][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.791 (3.080) Prec@1 79.69 (72.38) Prec@5 92.97 (89.51) + train[2018-10-18-05:55:01] Epoch: [123][9400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.281 (3.081) Prec@1 68.75 (72.38) Prec@5 84.38 (89.50) + train[2018-10-18-05:56:46] Epoch: [123][9600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.067 (3.081) Prec@1 70.31 (72.37) Prec@5 87.50 (89.51) + train[2018-10-18-05:58:31] Epoch: [123][9800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.917 (3.081) Prec@1 75.00 (72.37) Prec@5 92.19 (89.50) + train[2018-10-18-06:00:17] Epoch: [123][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.825 (3.081) Prec@1 75.00 (72.37) Prec@5 93.75 (89.50) + train[2018-10-18-06:00:21] Epoch: [123][10009/10010] Time 0.17 (0.53) Data 0.00 (0.00) Loss 4.118 (3.081) Prec@1 53.33 (72.37) Prec@5 86.67 (89.50) +[2018-10-18-06:00:21] **train** Prec@1 72.37 Prec@5 89.50 Error@1 27.63 Error@5 10.50 Loss:3.081 + test [2018-10-18-06:00:25] Epoch: [123][000/391] Time 3.55 (3.55) Data 3.42 (3.42) Loss 0.568 (0.568) Prec@1 91.41 (91.41) Prec@5 99.22 (99.22) + test [2018-10-18-06:00:53] Epoch: [123][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.273 (1.037) Prec@1 67.19 (75.97) Prec@5 92.97 (93.04) + test [2018-10-18-06:01:19] Epoch: [123][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.157 (1.205) Prec@1 47.50 (72.41) Prec@5 81.25 (90.84) +[2018-10-18-06:01:19] **test** Prec@1 72.41 Prec@5 90.84 Error@1 27.59 Error@5 9.16 Loss:1.205 +----> Best Accuracy : Acc@1=72.53, Acc@5=90.81, Error@1=27.47, Error@5=9.19 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-18-06:01:19] [Epoch=124/250] [Need: 186:55:02] LR=0.0023 ~ 0.0023, Batch=128 + train[2018-10-18-06:01:24] Epoch: [124][000/10010] Time 4.88 (4.88) Data 4.21 (4.21) Loss 2.872 (2.872) Prec@1 76.56 (76.56) Prec@5 92.19 (92.19) + train[2018-10-18-06:03:09] Epoch: [124][200/10010] Time 0.52 (0.55) Data 0.00 (0.02) Loss 3.453 (3.048) Prec@1 62.50 (73.07) Prec@5 85.94 (89.97) + train[2018-10-18-06:04:54] Epoch: [124][400/10010] Time 0.56 (0.54) Data 0.00 (0.01) Loss 3.162 (3.063) Prec@1 70.31 (72.78) Prec@5 84.38 (89.72) + train[2018-10-18-06:06:38] Epoch: [124][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.982 (3.060) Prec@1 69.53 (72.80) Prec@5 89.84 (89.74) + train[2018-10-18-06:08:25] Epoch: [124][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.045 (3.063) Prec@1 72.66 (72.75) Prec@5 90.62 (89.69) + train[2018-10-18-06:10:10] Epoch: [124][1000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.078 (3.062) Prec@1 73.44 (72.83) Prec@5 90.62 (89.74) + train[2018-10-18-06:11:56] Epoch: [124][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.322 (3.059) Prec@1 62.50 (72.88) Prec@5 87.50 (89.78) + train[2018-10-18-06:13:42] Epoch: [124][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.030 (3.059) Prec@1 76.56 (72.91) Prec@5 89.06 (89.76) + train[2018-10-18-06:15:27] Epoch: [124][1600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.272 (3.061) Prec@1 64.84 (72.87) Prec@5 89.84 (89.75) + train[2018-10-18-06:17:13] Epoch: [124][1800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.882 (3.063) Prec@1 75.78 (72.81) Prec@5 93.75 (89.72) + train[2018-10-18-06:18:58] Epoch: [124][2000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.953 (3.063) Prec@1 77.34 (72.80) Prec@5 91.41 (89.71) + train[2018-10-18-06:20:44] Epoch: [124][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.160 (3.063) Prec@1 70.31 (72.79) Prec@5 85.94 (89.71) + train[2018-10-18-06:22:30] Epoch: [124][2400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.321 (3.064) Prec@1 66.41 (72.79) Prec@5 85.94 (89.69) + train[2018-10-18-06:24:15] Epoch: [124][2600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.455 (3.063) Prec@1 69.53 (72.81) Prec@5 85.16 (89.70) + train[2018-10-18-06:26:00] Epoch: [124][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.100 (3.065) Prec@1 69.53 (72.76) Prec@5 90.62 (89.69) + train[2018-10-18-06:27:46] Epoch: [124][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.101 (3.064) Prec@1 68.75 (72.77) Prec@5 92.97 (89.69) + train[2018-10-18-06:29:31] Epoch: [124][3200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.923 (3.064) Prec@1 76.56 (72.79) Prec@5 93.75 (89.69) + train[2018-10-18-06:31:16] Epoch: [124][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.374 (3.066) Prec@1 70.31 (72.76) Prec@5 84.38 (89.67) + train[2018-10-18-06:33:01] Epoch: [124][3600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.046 (3.066) Prec@1 72.66 (72.75) Prec@5 92.19 (89.66) + train[2018-10-18-06:34:47] Epoch: [124][3800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.154 (3.066) Prec@1 70.31 (72.75) Prec@5 87.50 (89.65) + train[2018-10-18-06:36:32] Epoch: [124][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.209 (3.066) Prec@1 69.53 (72.73) Prec@5 91.41 (89.65) + train[2018-10-18-06:38:17] Epoch: [124][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.011 (3.067) Prec@1 77.34 (72.71) Prec@5 91.41 (89.64) + train[2018-10-18-06:40:03] Epoch: [124][4400/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.858 (3.066) Prec@1 75.78 (72.71) Prec@5 90.62 (89.65) + train[2018-10-18-06:41:48] Epoch: [124][4600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.427 (3.067) Prec@1 63.28 (72.69) Prec@5 86.72 (89.65) + train[2018-10-18-06:43:34] Epoch: [124][4800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.631 (3.067) Prec@1 84.38 (72.69) Prec@5 93.75 (89.65) + train[2018-10-18-06:45:20] Epoch: [124][5000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.193 (3.068) Prec@1 71.88 (72.69) Prec@5 90.62 (89.64) + train[2018-10-18-06:47:05] Epoch: [124][5200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.186 (3.068) Prec@1 66.41 (72.68) Prec@5 90.62 (89.63) + train[2018-10-18-06:48:51] Epoch: [124][5400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.089 (3.067) Prec@1 70.31 (72.69) Prec@5 88.28 (89.64) + train[2018-10-18-06:50:37] Epoch: [124][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.107 (3.068) Prec@1 72.66 (72.67) Prec@5 87.50 (89.63) + train[2018-10-18-06:52:22] Epoch: [124][5800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.239 (3.068) Prec@1 70.31 (72.66) Prec@5 88.28 (89.63) + train[2018-10-18-06:54:08] Epoch: [124][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.210 (3.068) Prec@1 73.44 (72.66) Prec@5 89.06 (89.63) + train[2018-10-18-06:55:54] Epoch: [124][6200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.091 (3.069) Prec@1 75.00 (72.66) Prec@5 88.28 (89.63) + train[2018-10-18-06:57:39] Epoch: [124][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.790 (3.069) Prec@1 75.78 (72.63) Prec@5 92.19 (89.62) + train[2018-10-18-06:59:24] Epoch: [124][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.689 (3.070) Prec@1 82.03 (72.63) Prec@5 93.75 (89.62) + train[2018-10-18-07:01:10] Epoch: [124][6800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.306 (3.070) Prec@1 69.53 (72.61) Prec@5 85.94 (89.61) + train[2018-10-18-07:02:55] Epoch: [124][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.071 (3.070) Prec@1 72.66 (72.62) Prec@5 89.06 (89.61) + train[2018-10-18-07:04:40] Epoch: [124][7200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.115 (3.071) Prec@1 71.09 (72.59) Prec@5 87.50 (89.60) + train[2018-10-18-07:06:25] Epoch: [124][7400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.097 (3.072) Prec@1 71.88 (72.58) Prec@5 87.50 (89.59) + train[2018-10-18-07:08:10] Epoch: [124][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.960 (3.072) Prec@1 72.66 (72.57) Prec@5 90.62 (89.59) + train[2018-10-18-07:09:56] Epoch: [124][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.409 (3.073) Prec@1 63.28 (72.56) Prec@5 86.72 (89.59) + train[2018-10-18-07:11:41] Epoch: [124][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.617 (3.073) Prec@1 61.72 (72.54) Prec@5 83.59 (89.58) + train[2018-10-18-07:13:26] Epoch: [124][8200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.100 (3.074) Prec@1 68.75 (72.53) Prec@5 91.41 (89.58) + train[2018-10-18-07:15:12] Epoch: [124][8400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.106 (3.074) Prec@1 71.88 (72.53) Prec@5 89.06 (89.57) + train[2018-10-18-07:16:57] Epoch: [124][8600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.127 (3.074) Prec@1 73.44 (72.52) Prec@5 87.50 (89.57) + train[2018-10-18-07:18:43] Epoch: [124][8800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.428 (3.074) Prec@1 67.19 (72.52) Prec@5 84.38 (89.57) + train[2018-10-18-07:20:28] Epoch: [124][9000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.272 (3.074) Prec@1 69.53 (72.52) Prec@5 87.50 (89.57) + train[2018-10-18-07:22:13] Epoch: [124][9200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.204 (3.075) Prec@1 68.75 (72.52) Prec@5 84.38 (89.57) + train[2018-10-18-07:23:59] Epoch: [124][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.402 (3.075) Prec@1 69.53 (72.51) Prec@5 83.59 (89.56) + train[2018-10-18-07:25:44] Epoch: [124][9600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.291 (3.075) Prec@1 66.41 (72.50) Prec@5 91.41 (89.55) + train[2018-10-18-07:27:29] Epoch: [124][9800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.342 (3.076) Prec@1 64.06 (72.49) Prec@5 85.16 (89.55) + train[2018-10-18-07:29:14] Epoch: [124][10000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.035 (3.076) Prec@1 73.44 (72.50) Prec@5 92.19 (89.56) + train[2018-10-18-07:29:18] Epoch: [124][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.045 (3.076) Prec@1 66.67 (72.49) Prec@5 93.33 (89.56) +[2018-10-18-07:29:19] **train** Prec@1 72.49 Prec@5 89.56 Error@1 27.51 Error@5 10.44 Loss:3.076 + test [2018-10-18-07:29:23] Epoch: [124][000/391] Time 4.54 (4.54) Data 4.40 (4.40) Loss 0.630 (0.630) Prec@1 87.50 (87.50) Prec@5 96.88 (96.88) + test [2018-10-18-07:29:50] Epoch: [124][200/391] Time 0.14 (0.16) Data 0.00 (0.02) Loss 1.355 (1.032) Prec@1 66.41 (76.06) Prec@5 92.19 (93.28) + test [2018-10-18-07:30:16] Epoch: [124][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.346 (1.202) Prec@1 40.00 (72.38) Prec@5 78.75 (90.99) +[2018-10-18-07:30:16] **test** Prec@1 72.38 Prec@5 90.99 Error@1 27.62 Error@5 9.01 Loss:1.202 +----> Best Accuracy : Acc@1=72.53, Acc@5=90.81, Error@1=27.47, Error@5=9.19 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-18-07:30:16] [Epoch=125/250] [Need: 185:18:40] LR=0.0022 ~ 0.0022, Batch=128 + train[2018-10-18-07:30:20] Epoch: [125][000/10010] Time 4.77 (4.77) Data 4.11 (4.11) Loss 2.734 (2.734) Prec@1 83.59 (83.59) Prec@5 92.97 (92.97) + train[2018-10-18-07:32:06] Epoch: [125][200/10010] Time 0.54 (0.55) Data 0.00 (0.02) Loss 2.970 (3.062) Prec@1 73.44 (72.55) Prec@5 90.62 (89.57) + train[2018-10-18-07:33:52] Epoch: [125][400/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 3.127 (3.053) Prec@1 72.66 (72.82) Prec@5 85.94 (89.75) + train[2018-10-18-07:35:37] Epoch: [125][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.220 (3.055) Prec@1 73.44 (72.72) Prec@5 86.72 (89.75) + train[2018-10-18-07:37:22] Epoch: [125][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.945 (3.050) Prec@1 69.53 (72.94) Prec@5 92.19 (89.83) + train[2018-10-18-07:39:06] Epoch: [125][1000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.016 (3.051) Prec@1 69.53 (72.91) Prec@5 91.41 (89.84) + train[2018-10-18-07:40:52] Epoch: [125][1200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.858 (3.051) Prec@1 74.22 (72.97) Prec@5 92.19 (89.81) + train[2018-10-18-07:42:38] Epoch: [125][1400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.004 (3.052) Prec@1 73.44 (72.92) Prec@5 91.41 (89.80) + train[2018-10-18-07:44:23] Epoch: [125][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.831 (3.053) Prec@1 72.66 (72.90) Prec@5 92.97 (89.79) + train[2018-10-18-07:46:09] Epoch: [125][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.703 (3.055) Prec@1 80.47 (72.90) Prec@5 91.41 (89.78) + train[2018-10-18-07:47:55] Epoch: [125][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.261 (3.056) Prec@1 71.88 (72.87) Prec@5 84.38 (89.77) + train[2018-10-18-07:49:40] Epoch: [125][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.201 (3.057) Prec@1 68.75 (72.88) Prec@5 92.19 (89.74) + train[2018-10-18-07:51:25] Epoch: [125][2400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.227 (3.057) Prec@1 71.09 (72.86) Prec@5 87.50 (89.74) + train[2018-10-18-07:53:10] Epoch: [125][2600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.183 (3.058) Prec@1 72.66 (72.84) Prec@5 87.50 (89.75) + train[2018-10-18-07:54:56] Epoch: [125][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.883 (3.058) Prec@1 74.22 (72.82) Prec@5 89.84 (89.75) + train[2018-10-18-07:56:41] Epoch: [125][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.109 (3.059) Prec@1 75.78 (72.83) Prec@5 85.94 (89.73) + train[2018-10-18-07:58:26] Epoch: [125][3200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.143 (3.060) Prec@1 67.97 (72.82) Prec@5 86.72 (89.72) + train[2018-10-18-08:00:12] Epoch: [125][3400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.088 (3.061) Prec@1 78.12 (72.79) Prec@5 87.50 (89.71) + train[2018-10-18-08:01:57] Epoch: [125][3600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.758 (3.061) Prec@1 76.56 (72.78) Prec@5 89.06 (89.72) + train[2018-10-18-08:03:42] Epoch: [125][3800/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 3.249 (3.062) Prec@1 71.88 (72.76) Prec@5 86.72 (89.70) + train[2018-10-18-08:05:27] Epoch: [125][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.010 (3.063) Prec@1 73.44 (72.72) Prec@5 90.62 (89.70) + train[2018-10-18-08:07:13] Epoch: [125][4200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.124 (3.063) Prec@1 67.97 (72.73) Prec@5 89.84 (89.69) + train[2018-10-18-08:09:00] Epoch: [125][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.039 (3.063) Prec@1 78.91 (72.73) Prec@5 89.84 (89.70) + train[2018-10-18-08:10:45] Epoch: [125][4600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.789 (3.062) Prec@1 77.34 (72.74) Prec@5 93.75 (89.71) + train[2018-10-18-08:12:31] Epoch: [125][4800/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.033 (3.063) Prec@1 71.09 (72.73) Prec@5 91.41 (89.70) + train[2018-10-18-08:14:17] Epoch: [125][5000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.868 (3.063) Prec@1 76.56 (72.74) Prec@5 91.41 (89.69) + train[2018-10-18-08:16:03] Epoch: [125][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.956 (3.063) Prec@1 78.91 (72.73) Prec@5 90.62 (89.68) + train[2018-10-18-08:17:48] Epoch: [125][5400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.711 (3.064) Prec@1 77.34 (72.71) Prec@5 94.53 (89.68) + train[2018-10-18-08:19:33] Epoch: [125][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.917 (3.064) Prec@1 77.34 (72.71) Prec@5 88.28 (89.68) + train[2018-10-18-08:21:19] Epoch: [125][5800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.390 (3.064) Prec@1 65.62 (72.69) Prec@5 85.16 (89.68) + train[2018-10-18-08:23:04] Epoch: [125][6000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.150 (3.065) Prec@1 68.75 (72.68) Prec@5 88.28 (89.67) + train[2018-10-18-08:24:50] Epoch: [125][6200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.264 (3.066) Prec@1 67.97 (72.67) Prec@5 89.06 (89.67) + train[2018-10-18-08:26:37] Epoch: [125][6400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.914 (3.067) Prec@1 75.78 (72.65) Prec@5 89.06 (89.66) + train[2018-10-18-08:28:22] Epoch: [125][6600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.154 (3.067) Prec@1 71.88 (72.66) Prec@5 88.28 (89.66) + train[2018-10-18-08:30:07] Epoch: [125][6800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.789 (3.067) Prec@1 77.34 (72.66) Prec@5 92.19 (89.65) + train[2018-10-18-08:31:53] Epoch: [125][7000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.176 (3.067) Prec@1 67.19 (72.65) Prec@5 89.84 (89.64) + train[2018-10-18-08:33:39] Epoch: [125][7200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.340 (3.068) Prec@1 61.72 (72.64) Prec@5 85.94 (89.64) + train[2018-10-18-08:35:24] Epoch: [125][7400/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 3.003 (3.069) Prec@1 72.66 (72.63) Prec@5 92.97 (89.63) + train[2018-10-18-08:37:09] Epoch: [125][7600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.132 (3.069) Prec@1 72.66 (72.63) Prec@5 90.62 (89.62) + train[2018-10-18-08:38:54] Epoch: [125][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.959 (3.070) Prec@1 73.44 (72.62) Prec@5 89.84 (89.62) + train[2018-10-18-08:40:39] Epoch: [125][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.248 (3.070) Prec@1 74.22 (72.61) Prec@5 89.06 (89.61) + train[2018-10-18-08:42:24] Epoch: [125][8200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.083 (3.070) Prec@1 69.53 (72.61) Prec@5 89.06 (89.61) + train[2018-10-18-08:44:09] Epoch: [125][8400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.219 (3.070) Prec@1 71.88 (72.61) Prec@5 85.94 (89.60) + train[2018-10-18-08:45:54] Epoch: [125][8600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.845 (3.071) Prec@1 77.34 (72.60) Prec@5 89.84 (89.60) + train[2018-10-18-08:47:41] Epoch: [125][8800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.151 (3.071) Prec@1 70.31 (72.59) Prec@5 90.62 (89.60) + train[2018-10-18-08:49:26] Epoch: [125][9000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.867 (3.071) Prec@1 74.22 (72.59) Prec@5 91.41 (89.60) + train[2018-10-18-08:51:11] Epoch: [125][9200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.949 (3.071) Prec@1 74.22 (72.58) Prec@5 89.06 (89.60) + train[2018-10-18-08:52:56] Epoch: [125][9400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.101 (3.071) Prec@1 71.88 (72.58) Prec@5 89.84 (89.59) + train[2018-10-18-08:54:42] Epoch: [125][9600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.316 (3.071) Prec@1 67.97 (72.58) Prec@5 87.50 (89.60) + train[2018-10-18-08:56:28] Epoch: [125][9800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.930 (3.071) Prec@1 73.44 (72.59) Prec@5 90.62 (89.60) + train[2018-10-18-08:58:13] Epoch: [125][10000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.219 (3.071) Prec@1 66.41 (72.59) Prec@5 89.06 (89.59) + train[2018-10-18-08:58:18] Epoch: [125][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 4.232 (3.071) Prec@1 53.33 (72.59) Prec@5 86.67 (89.59) +[2018-10-18-08:58:18] **train** Prec@1 72.59 Prec@5 89.59 Error@1 27.41 Error@5 10.41 Loss:3.071 + test [2018-10-18-08:58:22] Epoch: [125][000/391] Time 3.66 (3.66) Data 3.52 (3.52) Loss 0.649 (0.649) Prec@1 86.72 (86.72) Prec@5 98.44 (98.44) + test [2018-10-18-08:58:50] Epoch: [125][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.264 (1.047) Prec@1 62.50 (75.96) Prec@5 90.62 (93.23) + test [2018-10-18-08:59:15] Epoch: [125][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.250 (1.211) Prec@1 41.25 (72.47) Prec@5 81.25 (90.93) +[2018-10-18-08:59:15] **test** Prec@1 72.47 Prec@5 90.93 Error@1 27.53 Error@5 9.07 Loss:1.211 +----> Best Accuracy : Acc@1=72.53, Acc@5=90.81, Error@1=27.47, Error@5=9.19 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-18-08:59:15] [Epoch=126/250] [Need: 183:55:30] LR=0.0022 ~ 0.0022, Batch=128 + train[2018-10-18-08:59:21] Epoch: [126][000/10010] Time 5.26 (5.26) Data 4.59 (4.59) Loss 3.028 (3.028) Prec@1 78.12 (78.12) Prec@5 89.84 (89.84) + train[2018-10-18-09:01:06] Epoch: [126][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.206 (3.065) Prec@1 71.88 (72.71) Prec@5 86.72 (89.77) + train[2018-10-18-09:02:53] Epoch: [126][400/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 3.068 (3.053) Prec@1 71.88 (72.87) Prec@5 88.28 (89.77) + train[2018-10-18-09:04:39] Epoch: [126][600/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.858 (3.057) Prec@1 75.00 (72.91) Prec@5 92.97 (89.77) + train[2018-10-18-09:06:25] Epoch: [126][800/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 3.008 (3.058) Prec@1 75.00 (72.86) Prec@5 87.50 (89.75) + train[2018-10-18-09:08:10] Epoch: [126][1000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.943 (3.056) Prec@1 76.56 (72.89) Prec@5 92.97 (89.77) + train[2018-10-18-09:09:56] Epoch: [126][1200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.849 (3.050) Prec@1 77.34 (73.04) Prec@5 93.75 (89.87) + train[2018-10-18-09:11:42] Epoch: [126][1400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.985 (3.049) Prec@1 74.22 (73.06) Prec@5 91.41 (89.91) + train[2018-10-18-09:13:28] Epoch: [126][1600/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 3.302 (3.046) Prec@1 74.22 (73.14) Prec@5 85.94 (89.94) + train[2018-10-18-09:15:14] Epoch: [126][1800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.983 (3.048) Prec@1 71.09 (73.12) Prec@5 89.06 (89.92) + train[2018-10-18-09:16:58] Epoch: [126][2000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.156 (3.049) Prec@1 71.88 (73.06) Prec@5 89.06 (89.90) + train[2018-10-18-09:18:44] Epoch: [126][2200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.084 (3.049) Prec@1 71.88 (73.06) Prec@5 88.28 (89.91) + train[2018-10-18-09:20:28] Epoch: [126][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.993 (3.050) Prec@1 73.44 (73.01) Prec@5 90.62 (89.90) + train[2018-10-18-09:22:13] Epoch: [126][2600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.839 (3.051) Prec@1 76.56 (73.00) Prec@5 92.19 (89.87) + train[2018-10-18-09:23:59] Epoch: [126][2800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.917 (3.052) Prec@1 72.66 (72.96) Prec@5 92.19 (89.87) + train[2018-10-18-09:25:45] Epoch: [126][3000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.986 (3.053) Prec@1 74.22 (72.95) Prec@5 91.41 (89.86) + train[2018-10-18-09:27:29] Epoch: [126][3200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.369 (3.052) Prec@1 67.97 (72.96) Prec@5 89.06 (89.86) + train[2018-10-18-09:29:14] Epoch: [126][3400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.028 (3.052) Prec@1 69.53 (72.96) Prec@5 91.41 (89.85) + train[2018-10-18-09:31:01] Epoch: [126][3600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.209 (3.052) Prec@1 69.53 (72.96) Prec@5 85.16 (89.84) + train[2018-10-18-09:32:46] Epoch: [126][3800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.327 (3.053) Prec@1 71.09 (72.95) Prec@5 86.72 (89.83) + train[2018-10-18-09:34:31] Epoch: [126][4000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.935 (3.054) Prec@1 75.00 (72.93) Prec@5 90.62 (89.82) + train[2018-10-18-09:36:17] Epoch: [126][4200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.158 (3.053) Prec@1 72.66 (72.93) Prec@5 88.28 (89.82) + train[2018-10-18-09:38:02] Epoch: [126][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.971 (3.054) Prec@1 74.22 (72.90) Prec@5 92.97 (89.81) + train[2018-10-18-09:39:47] Epoch: [126][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.137 (3.055) Prec@1 71.88 (72.88) Prec@5 86.72 (89.81) + train[2018-10-18-09:41:33] Epoch: [126][4800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.007 (3.055) Prec@1 72.66 (72.89) Prec@5 87.50 (89.79) + train[2018-10-18-09:43:18] Epoch: [126][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.719 (3.056) Prec@1 75.78 (72.87) Prec@5 93.75 (89.78) + train[2018-10-18-09:45:04] Epoch: [126][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.902 (3.056) Prec@1 80.47 (72.87) Prec@5 90.62 (89.78) + train[2018-10-18-09:46:49] Epoch: [126][5400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.160 (3.057) Prec@1 71.09 (72.87) Prec@5 88.28 (89.77) + train[2018-10-18-09:48:34] Epoch: [126][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.757 (3.058) Prec@1 75.78 (72.85) Prec@5 92.19 (89.76) + train[2018-10-18-09:50:21] Epoch: [126][5800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.296 (3.059) Prec@1 71.09 (72.83) Prec@5 89.84 (89.75) + train[2018-10-18-09:52:06] Epoch: [126][6000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.138 (3.059) Prec@1 69.53 (72.82) Prec@5 87.50 (89.75) + train[2018-10-18-09:53:51] Epoch: [126][6200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.047 (3.059) Prec@1 75.78 (72.81) Prec@5 88.28 (89.74) + train[2018-10-18-09:55:37] Epoch: [126][6400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.806 (3.060) Prec@1 76.56 (72.79) Prec@5 92.19 (89.73) + train[2018-10-18-09:57:22] Epoch: [126][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.230 (3.060) Prec@1 67.97 (72.78) Prec@5 89.06 (89.73) + train[2018-10-18-09:59:07] Epoch: [126][6800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.031 (3.061) Prec@1 77.34 (72.78) Prec@5 91.41 (89.73) + train[2018-10-18-10:00:53] Epoch: [126][7000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.254 (3.061) Prec@1 71.09 (72.78) Prec@5 86.72 (89.73) + train[2018-10-18-10:02:39] Epoch: [126][7200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.846 (3.061) Prec@1 75.78 (72.78) Prec@5 93.75 (89.73) + train[2018-10-18-10:04:23] Epoch: [126][7400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.178 (3.061) Prec@1 72.66 (72.77) Prec@5 85.94 (89.73) + train[2018-10-18-10:06:09] Epoch: [126][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.468 (3.061) Prec@1 64.06 (72.76) Prec@5 82.03 (89.72) + train[2018-10-18-10:07:56] Epoch: [126][7800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.162 (3.062) Prec@1 72.66 (72.75) Prec@5 87.50 (89.72) + train[2018-10-18-10:09:41] Epoch: [126][8000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.202 (3.062) Prec@1 68.75 (72.74) Prec@5 86.72 (89.71) + train[2018-10-18-10:11:27] Epoch: [126][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.079 (3.062) Prec@1 73.44 (72.74) Prec@5 87.50 (89.72) + train[2018-10-18-10:13:13] Epoch: [126][8400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.077 (3.062) Prec@1 70.31 (72.73) Prec@5 88.28 (89.71) + train[2018-10-18-10:15:00] Epoch: [126][8600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.082 (3.062) Prec@1 71.09 (72.73) Prec@5 91.41 (89.71) + train[2018-10-18-10:16:46] Epoch: [126][8800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.851 (3.062) Prec@1 75.00 (72.73) Prec@5 91.41 (89.71) + train[2018-10-18-10:18:31] Epoch: [126][9000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.128 (3.062) Prec@1 68.75 (72.74) Prec@5 90.62 (89.71) + train[2018-10-18-10:20:18] Epoch: [126][9200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.253 (3.062) Prec@1 68.75 (72.74) Prec@5 88.28 (89.71) + train[2018-10-18-10:22:04] Epoch: [126][9400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.113 (3.062) Prec@1 74.22 (72.74) Prec@5 88.28 (89.70) + train[2018-10-18-10:23:50] Epoch: [126][9600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.248 (3.063) Prec@1 71.88 (72.73) Prec@5 90.62 (89.70) + train[2018-10-18-10:25:36] Epoch: [126][9800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.246 (3.063) Prec@1 69.53 (72.73) Prec@5 85.94 (89.71) + train[2018-10-18-10:27:21] Epoch: [126][10000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.133 (3.063) Prec@1 72.66 (72.73) Prec@5 87.50 (89.71) + train[2018-10-18-10:27:25] Epoch: [126][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.840 (3.063) Prec@1 66.67 (72.73) Prec@5 73.33 (89.71) +[2018-10-18-10:27:25] **train** Prec@1 72.73 Prec@5 89.71 Error@1 27.27 Error@5 10.29 Loss:3.063 + test [2018-10-18-10:27:29] Epoch: [126][000/391] Time 3.71 (3.71) Data 3.57 (3.57) Loss 0.639 (0.639) Prec@1 88.28 (88.28) Prec@5 96.09 (96.09) + test [2018-10-18-10:27:58] Epoch: [126][200/391] Time 0.14 (0.16) Data 0.00 (0.03) Loss 1.293 (1.050) Prec@1 64.84 (76.06) Prec@5 93.75 (93.05) + test [2018-10-18-10:28:23] Epoch: [126][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.139 (1.209) Prec@1 45.00 (72.52) Prec@5 81.25 (90.94) +[2018-10-18-10:28:23] **test** Prec@1 72.52 Prec@5 90.94 Error@1 27.48 Error@5 9.06 Loss:1.209 +----> Best Accuracy : Acc@1=72.53, Acc@5=90.81, Error@1=27.47, Error@5=9.19 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-18-10:28:23] [Epoch=127/250] [Need: 182:41:48] LR=0.0021 ~ 0.0021, Batch=128 + train[2018-10-18-10:28:28] Epoch: [127][000/10010] Time 5.09 (5.09) Data 4.47 (4.47) Loss 3.442 (3.442) Prec@1 62.50 (62.50) Prec@5 89.06 (89.06) + train[2018-10-18-10:30:15] Epoch: [127][200/10010] Time 0.55 (0.56) Data 0.00 (0.02) Loss 3.093 (3.039) Prec@1 71.09 (73.41) Prec@5 88.28 (89.85) + train[2018-10-18-10:32:00] Epoch: [127][400/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 2.878 (3.055) Prec@1 77.34 (73.15) Prec@5 92.97 (89.67) + train[2018-10-18-10:33:45] Epoch: [127][600/10010] Time 0.53 (0.54) Data 0.00 (0.01) Loss 3.296 (3.054) Prec@1 67.19 (73.06) Prec@5 86.72 (89.73) + train[2018-10-18-10:35:30] Epoch: [127][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.995 (3.050) Prec@1 76.56 (73.06) Prec@5 88.28 (89.79) + train[2018-10-18-10:37:16] Epoch: [127][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.848 (3.047) Prec@1 76.56 (73.12) Prec@5 92.19 (89.86) + train[2018-10-18-10:39:02] Epoch: [127][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.289 (3.050) Prec@1 71.88 (73.09) Prec@5 83.59 (89.82) + train[2018-10-18-10:40:47] Epoch: [127][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.103 (3.052) Prec@1 70.31 (73.01) Prec@5 89.84 (89.83) + train[2018-10-18-10:42:32] Epoch: [127][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.999 (3.053) Prec@1 70.31 (72.95) Prec@5 92.97 (89.83) + train[2018-10-18-10:44:17] Epoch: [127][1800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.931 (3.052) Prec@1 76.56 (72.97) Prec@5 92.19 (89.85) + train[2018-10-18-10:46:03] Epoch: [127][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.338 (3.052) Prec@1 69.53 (72.98) Prec@5 86.72 (89.85) + train[2018-10-18-10:47:49] Epoch: [127][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.973 (3.052) Prec@1 71.88 (72.98) Prec@5 92.97 (89.86) + train[2018-10-18-10:49:34] Epoch: [127][2400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.237 (3.054) Prec@1 68.75 (72.97) Prec@5 85.94 (89.84) + train[2018-10-18-10:51:19] Epoch: [127][2600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.021 (3.055) Prec@1 71.09 (72.96) Prec@5 91.41 (89.82) + train[2018-10-18-10:53:05] Epoch: [127][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.089 (3.054) Prec@1 71.09 (72.97) Prec@5 89.06 (89.84) + train[2018-10-18-10:54:50] Epoch: [127][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.033 (3.053) Prec@1 75.00 (72.98) Prec@5 90.62 (89.85) + train[2018-10-18-10:56:36] Epoch: [127][3200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.947 (3.054) Prec@1 73.44 (72.97) Prec@5 91.41 (89.82) + train[2018-10-18-10:58:22] Epoch: [127][3400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.168 (3.056) Prec@1 73.44 (72.96) Prec@5 91.41 (89.79) + train[2018-10-18-11:00:09] Epoch: [127][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.989 (3.055) Prec@1 72.66 (72.95) Prec@5 91.41 (89.80) + train[2018-10-18-11:01:54] Epoch: [127][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.730 (3.055) Prec@1 78.12 (72.96) Prec@5 94.53 (89.80) + train[2018-10-18-11:03:40] Epoch: [127][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.946 (3.054) Prec@1 79.69 (72.97) Prec@5 91.41 (89.80) + train[2018-10-18-11:05:25] Epoch: [127][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.056 (3.054) Prec@1 77.34 (72.95) Prec@5 90.62 (89.80) + train[2018-10-18-11:07:10] Epoch: [127][4400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.981 (3.054) Prec@1 71.88 (72.96) Prec@5 92.97 (89.81) + train[2018-10-18-11:08:56] Epoch: [127][4600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.370 (3.054) Prec@1 67.97 (72.95) Prec@5 89.06 (89.81) + train[2018-10-18-11:10:41] Epoch: [127][4800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.973 (3.055) Prec@1 73.44 (72.94) Prec@5 91.41 (89.80) + train[2018-10-18-11:12:27] Epoch: [127][5000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.156 (3.056) Prec@1 69.53 (72.92) Prec@5 89.84 (89.79) + train[2018-10-18-11:14:12] Epoch: [127][5200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.997 (3.056) Prec@1 71.09 (72.91) Prec@5 89.06 (89.79) + train[2018-10-18-11:15:57] Epoch: [127][5400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.299 (3.056) Prec@1 70.31 (72.91) Prec@5 85.94 (89.78) + train[2018-10-18-11:17:42] Epoch: [127][5600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.062 (3.057) Prec@1 69.53 (72.90) Prec@5 88.28 (89.79) + train[2018-10-18-11:19:28] Epoch: [127][5800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.947 (3.057) Prec@1 73.44 (72.89) Prec@5 92.97 (89.78) + train[2018-10-18-11:21:13] Epoch: [127][6000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.959 (3.057) Prec@1 78.91 (72.88) Prec@5 89.06 (89.78) + train[2018-10-18-11:22:59] Epoch: [127][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.177 (3.057) Prec@1 68.75 (72.88) Prec@5 87.50 (89.78) + train[2018-10-18-11:24:44] Epoch: [127][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.649 (3.057) Prec@1 80.47 (72.88) Prec@5 92.97 (89.78) + train[2018-10-18-11:26:30] Epoch: [127][6600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.994 (3.058) Prec@1 75.00 (72.86) Prec@5 92.19 (89.78) + train[2018-10-18-11:28:16] Epoch: [127][6800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.127 (3.058) Prec@1 70.31 (72.85) Prec@5 89.06 (89.78) + train[2018-10-18-11:30:01] Epoch: [127][7000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.300 (3.058) Prec@1 67.19 (72.85) Prec@5 89.06 (89.77) + train[2018-10-18-11:31:47] Epoch: [127][7200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.880 (3.058) Prec@1 75.78 (72.84) Prec@5 93.75 (89.77) + train[2018-10-18-11:33:32] Epoch: [127][7400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.214 (3.058) Prec@1 71.88 (72.83) Prec@5 86.72 (89.77) + train[2018-10-18-11:35:18] Epoch: [127][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.175 (3.058) Prec@1 67.19 (72.84) Prec@5 89.84 (89.77) + train[2018-10-18-11:37:04] Epoch: [127][7800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.910 (3.059) Prec@1 76.56 (72.82) Prec@5 92.19 (89.77) + train[2018-10-18-11:38:50] Epoch: [127][8000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.234 (3.059) Prec@1 68.75 (72.83) Prec@5 86.72 (89.77) + train[2018-10-18-11:40:36] Epoch: [127][8200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.246 (3.059) Prec@1 71.09 (72.82) Prec@5 87.50 (89.76) + train[2018-10-18-11:42:22] Epoch: [127][8400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.306 (3.059) Prec@1 70.31 (72.82) Prec@5 85.94 (89.76) + train[2018-10-18-11:44:09] Epoch: [127][8600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.050 (3.059) Prec@1 73.44 (72.81) Prec@5 92.97 (89.76) + train[2018-10-18-11:45:56] Epoch: [127][8800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.797 (3.059) Prec@1 80.47 (72.81) Prec@5 92.97 (89.76) + train[2018-10-18-11:47:41] Epoch: [127][9000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.062 (3.060) Prec@1 71.88 (72.80) Prec@5 91.41 (89.75) + train[2018-10-18-11:49:27] Epoch: [127][9200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.141 (3.060) Prec@1 73.44 (72.80) Prec@5 89.06 (89.76) + train[2018-10-18-11:51:12] Epoch: [127][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.233 (3.060) Prec@1 67.19 (72.80) Prec@5 85.94 (89.75) + train[2018-10-18-11:52:57] Epoch: [127][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.780 (3.060) Prec@1 71.88 (72.80) Prec@5 95.31 (89.75) + train[2018-10-18-11:54:42] Epoch: [127][9800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.174 (3.060) Prec@1 74.22 (72.80) Prec@5 88.28 (89.75) + train[2018-10-18-11:56:28] Epoch: [127][10000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.033 (3.060) Prec@1 75.78 (72.80) Prec@5 90.62 (89.74) + train[2018-10-18-11:56:32] Epoch: [127][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.673 (3.060) Prec@1 66.67 (72.80) Prec@5 80.00 (89.74) +[2018-10-18-11:56:32] **train** Prec@1 72.80 Prec@5 89.74 Error@1 27.20 Error@5 10.26 Loss:3.060 + test [2018-10-18-11:56:36] Epoch: [127][000/391] Time 4.11 (4.11) Data 3.97 (3.97) Loss 0.629 (0.629) Prec@1 85.16 (85.16) Prec@5 96.09 (96.09) + test [2018-10-18-11:57:04] Epoch: [127][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.217 (1.030) Prec@1 63.28 (76.22) Prec@5 93.75 (93.09) + test [2018-10-18-11:57:29] Epoch: [127][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.181 (1.196) Prec@1 46.25 (72.60) Prec@5 77.50 (90.84) +[2018-10-18-11:57:29] **test** Prec@1 72.60 Prec@5 90.84 Error@1 27.40 Error@5 9.16 Loss:1.196 +----> Best Accuracy : Acc@1=72.60, Acc@5=90.84, Error@1=27.40, Error@5=9.16 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-18-11:57:29] [Epoch=128/250] [Need: 181:11:19] LR=0.0020 ~ 0.0020, Batch=128 + train[2018-10-18-11:57:34] Epoch: [128][000/10010] Time 5.14 (5.14) Data 4.43 (4.43) Loss 2.880 (2.880) Prec@1 74.22 (74.22) Prec@5 92.97 (92.97) + train[2018-10-18-11:59:20] Epoch: [128][200/10010] Time 0.49 (0.55) Data 0.00 (0.02) Loss 2.895 (3.032) Prec@1 76.56 (73.47) Prec@5 90.62 (90.07) + train[2018-10-18-12:01:06] Epoch: [128][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.943 (3.029) Prec@1 70.31 (73.48) Prec@5 92.19 (90.09) + train[2018-10-18-12:02:52] Epoch: [128][600/10010] Time 0.54 (0.54) Data 0.00 (0.01) Loss 3.014 (3.035) Prec@1 76.56 (73.39) Prec@5 89.06 (89.98) + train[2018-10-18-12:04:37] Epoch: [128][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.060 (3.037) Prec@1 71.88 (73.33) Prec@5 89.06 (89.94) + train[2018-10-18-12:06:23] Epoch: [128][1000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.993 (3.036) Prec@1 73.44 (73.27) Prec@5 92.19 (89.96) + train[2018-10-18-12:08:08] Epoch: [128][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.184 (3.035) Prec@1 74.22 (73.22) Prec@5 86.72 (89.97) + train[2018-10-18-12:09:54] Epoch: [128][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.137 (3.038) Prec@1 75.00 (73.24) Prec@5 89.06 (89.95) + train[2018-10-18-12:11:39] Epoch: [128][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.996 (3.036) Prec@1 69.53 (73.29) Prec@5 90.62 (89.98) + train[2018-10-18-12:13:24] Epoch: [128][1800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.554 (3.037) Prec@1 65.62 (73.28) Prec@5 84.38 (89.99) + train[2018-10-18-12:15:11] Epoch: [128][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.847 (3.036) Prec@1 78.12 (73.30) Prec@5 92.19 (90.00) + train[2018-10-18-12:16:56] Epoch: [128][2200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.159 (3.036) Prec@1 72.66 (73.27) Prec@5 89.06 (90.00) + train[2018-10-18-12:18:41] Epoch: [128][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.877 (3.037) Prec@1 74.22 (73.27) Prec@5 92.19 (89.97) + train[2018-10-18-12:20:27] Epoch: [128][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.907 (3.038) Prec@1 73.44 (73.27) Prec@5 92.19 (89.96) + train[2018-10-18-12:22:13] Epoch: [128][2800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.199 (3.041) Prec@1 69.53 (73.25) Prec@5 89.06 (89.92) + train[2018-10-18-12:23:59] Epoch: [128][3000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.823 (3.039) Prec@1 78.12 (73.27) Prec@5 92.19 (89.95) + train[2018-10-18-12:25:46] Epoch: [128][3200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.109 (3.040) Prec@1 69.53 (73.25) Prec@5 90.62 (89.95) + train[2018-10-18-12:27:31] Epoch: [128][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.078 (3.041) Prec@1 75.00 (73.21) Prec@5 88.28 (89.92) + train[2018-10-18-12:29:16] Epoch: [128][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.116 (3.042) Prec@1 70.31 (73.20) Prec@5 89.84 (89.94) + train[2018-10-18-12:31:01] Epoch: [128][3800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.784 (3.043) Prec@1 77.34 (73.17) Prec@5 92.97 (89.93) + train[2018-10-18-12:32:47] Epoch: [128][4000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.989 (3.044) Prec@1 75.00 (73.14) Prec@5 86.72 (89.93) + train[2018-10-18-12:34:32] Epoch: [128][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.076 (3.044) Prec@1 71.09 (73.14) Prec@5 90.62 (89.91) + train[2018-10-18-12:36:18] Epoch: [128][4400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.002 (3.045) Prec@1 75.78 (73.12) Prec@5 89.06 (89.90) + train[2018-10-18-12:38:04] Epoch: [128][4600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.742 (3.045) Prec@1 77.34 (73.13) Prec@5 92.97 (89.91) + train[2018-10-18-12:39:49] Epoch: [128][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.953 (3.045) Prec@1 74.22 (73.12) Prec@5 91.41 (89.91) + train[2018-10-18-12:41:35] Epoch: [128][5000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.101 (3.046) Prec@1 69.53 (73.10) Prec@5 89.84 (89.90) + train[2018-10-18-12:43:21] Epoch: [128][5200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.086 (3.046) Prec@1 72.66 (73.09) Prec@5 91.41 (89.89) + train[2018-10-18-12:45:07] Epoch: [128][5400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.112 (3.047) Prec@1 71.09 (73.08) Prec@5 89.06 (89.89) + train[2018-10-18-12:46:53] Epoch: [128][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.076 (3.048) Prec@1 73.44 (73.05) Prec@5 89.84 (89.88) + train[2018-10-18-12:48:39] Epoch: [128][5800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.031 (3.047) Prec@1 68.75 (73.06) Prec@5 90.62 (89.88) + train[2018-10-18-12:50:24] Epoch: [128][6000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.297 (3.047) Prec@1 73.44 (73.06) Prec@5 85.16 (89.88) + train[2018-10-18-12:52:11] Epoch: [128][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.923 (3.048) Prec@1 76.56 (73.05) Prec@5 92.19 (89.87) + train[2018-10-18-12:53:56] Epoch: [128][6400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.346 (3.049) Prec@1 64.84 (73.04) Prec@5 87.50 (89.87) + train[2018-10-18-12:55:42] Epoch: [128][6600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.080 (3.049) Prec@1 69.53 (73.04) Prec@5 89.84 (89.86) + train[2018-10-18-12:57:28] Epoch: [128][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.133 (3.050) Prec@1 73.44 (73.03) Prec@5 87.50 (89.86) + train[2018-10-18-12:59:12] Epoch: [128][7000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.079 (3.050) Prec@1 71.88 (73.01) Prec@5 89.84 (89.85) + train[2018-10-18-13:00:58] Epoch: [128][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.018 (3.051) Prec@1 74.22 (73.01) Prec@5 91.41 (89.85) + train[2018-10-18-13:02:43] Epoch: [128][7400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.018 (3.051) Prec@1 76.56 (73.00) Prec@5 91.41 (89.84) + train[2018-10-18-13:04:29] Epoch: [128][7600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.060 (3.051) Prec@1 72.66 (72.99) Prec@5 90.62 (89.84) + train[2018-10-18-13:06:15] Epoch: [128][7800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.167 (3.052) Prec@1 70.31 (72.99) Prec@5 87.50 (89.83) + train[2018-10-18-13:08:03] Epoch: [128][8000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.925 (3.052) Prec@1 71.09 (72.98) Prec@5 93.75 (89.82) + train[2018-10-18-13:09:49] Epoch: [128][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.972 (3.053) Prec@1 75.78 (72.97) Prec@5 90.62 (89.82) + train[2018-10-18-13:11:34] Epoch: [128][8400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.918 (3.054) Prec@1 75.00 (72.95) Prec@5 92.19 (89.81) + train[2018-10-18-13:13:20] Epoch: [128][8600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.067 (3.055) Prec@1 71.88 (72.93) Prec@5 89.06 (89.80) + train[2018-10-18-13:15:06] Epoch: [128][8800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.103 (3.054) Prec@1 71.09 (72.93) Prec@5 88.28 (89.80) + train[2018-10-18-13:16:51] Epoch: [128][9000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.078 (3.055) Prec@1 71.09 (72.91) Prec@5 89.06 (89.78) + train[2018-10-18-13:18:37] Epoch: [128][9200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.402 (3.056) Prec@1 67.97 (72.91) Prec@5 85.16 (89.78) + train[2018-10-18-13:20:22] Epoch: [128][9400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.257 (3.056) Prec@1 70.31 (72.90) Prec@5 88.28 (89.78) + train[2018-10-18-13:22:09] Epoch: [128][9600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.689 (3.056) Prec@1 76.56 (72.89) Prec@5 92.97 (89.78) + train[2018-10-18-13:23:54] Epoch: [128][9800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.774 (3.056) Prec@1 72.66 (72.89) Prec@5 92.97 (89.78) + train[2018-10-18-13:25:39] Epoch: [128][10000/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 2.682 (3.056) Prec@1 80.47 (72.89) Prec@5 92.97 (89.78) + train[2018-10-18-13:25:43] Epoch: [128][10009/10010] Time 0.14 (0.53) Data 0.00 (0.00) Loss 3.708 (3.056) Prec@1 73.33 (72.89) Prec@5 86.67 (89.78) +[2018-10-18-13:25:43] **train** Prec@1 72.89 Prec@5 89.78 Error@1 27.11 Error@5 10.22 Loss:3.056 + test [2018-10-18-13:25:48] Epoch: [128][000/391] Time 4.37 (4.37) Data 4.21 (4.21) Loss 0.540 (0.540) Prec@1 89.84 (89.84) Prec@5 96.88 (96.88) + test [2018-10-18-13:26:16] Epoch: [128][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.186 (1.021) Prec@1 69.53 (76.24) Prec@5 92.19 (93.21) + test [2018-10-18-13:26:41] Epoch: [128][390/391] Time 0.08 (0.15) Data 0.00 (0.02) Loss 2.151 (1.192) Prec@1 46.25 (72.60) Prec@5 81.25 (90.93) +[2018-10-18-13:26:41] **test** Prec@1 72.60 Prec@5 90.93 Error@1 27.40 Error@5 9.07 Loss:1.192 +----> Best Accuracy : Acc@1=72.60, Acc@5=90.93, Error@1=27.40, Error@5=9.07 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-18-13:26:41] [Epoch=129/250] [Need: 179:53:25] LR=0.0020 ~ 0.0020, Batch=128 + train[2018-10-18-13:26:46] Epoch: [129][000/10010] Time 4.58 (4.58) Data 3.95 (3.95) Loss 3.163 (3.163) Prec@1 70.31 (70.31) Prec@5 89.06 (89.06) + train[2018-10-18-13:28:32] Epoch: [129][200/10010] Time 0.53 (0.55) Data 0.00 (0.02) Loss 2.974 (3.030) Prec@1 73.44 (73.36) Prec@5 92.19 (90.14) + train[2018-10-18-13:30:17] Epoch: [129][400/10010] Time 0.53 (0.54) Data 0.00 (0.01) Loss 3.052 (3.033) Prec@1 71.09 (73.32) Prec@5 89.06 (90.04) + train[2018-10-18-13:32:03] Epoch: [129][600/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.132 (3.033) Prec@1 75.00 (73.30) Prec@5 89.06 (90.10) + train[2018-10-18-13:33:49] Epoch: [129][800/10010] Time 0.59 (0.53) Data 0.00 (0.01) Loss 3.218 (3.034) Prec@1 66.41 (73.32) Prec@5 87.50 (90.10) + train[2018-10-18-13:35:35] Epoch: [129][1000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.039 (3.030) Prec@1 71.88 (73.39) Prec@5 89.06 (90.12) + train[2018-10-18-13:37:21] Epoch: [129][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.064 (3.031) Prec@1 67.97 (73.35) Prec@5 89.06 (90.10) + train[2018-10-18-13:39:07] Epoch: [129][1400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.540 (3.033) Prec@1 62.50 (73.28) Prec@5 82.81 (90.07) + train[2018-10-18-13:40:52] Epoch: [129][1600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.373 (3.034) Prec@1 61.72 (73.28) Prec@5 89.06 (90.05) + train[2018-10-18-13:42:38] Epoch: [129][1800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.119 (3.033) Prec@1 68.75 (73.30) Prec@5 92.19 (90.07) + train[2018-10-18-13:44:23] Epoch: [129][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.911 (3.036) Prec@1 75.78 (73.31) Prec@5 90.62 (90.02) + train[2018-10-18-13:46:09] Epoch: [129][2200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.128 (3.035) Prec@1 77.34 (73.33) Prec@5 88.28 (90.01) + train[2018-10-18-13:47:55] Epoch: [129][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.921 (3.036) Prec@1 80.47 (73.30) Prec@5 91.41 (90.00) + train[2018-10-18-13:49:41] Epoch: [129][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.941 (3.038) Prec@1 71.88 (73.23) Prec@5 92.19 (89.97) + train[2018-10-18-13:51:27] Epoch: [129][2800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.050 (3.038) Prec@1 73.44 (73.22) Prec@5 89.06 (89.97) + train[2018-10-18-13:53:14] Epoch: [129][3000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.283 (3.039) Prec@1 71.09 (73.21) Prec@5 89.06 (89.96) + train[2018-10-18-13:55:00] Epoch: [129][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.865 (3.040) Prec@1 79.69 (73.19) Prec@5 92.19 (89.95) + train[2018-10-18-13:56:46] Epoch: [129][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.067 (3.040) Prec@1 75.00 (73.20) Prec@5 89.06 (89.95) + train[2018-10-18-13:58:32] Epoch: [129][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.998 (3.041) Prec@1 71.09 (73.18) Prec@5 90.62 (89.95) + train[2018-10-18-14:00:19] Epoch: [129][3800/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.020 (3.042) Prec@1 73.44 (73.16) Prec@5 91.41 (89.95) + train[2018-10-18-14:02:06] Epoch: [129][4000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.948 (3.041) Prec@1 67.97 (73.18) Prec@5 92.97 (89.96) + train[2018-10-18-14:03:53] Epoch: [129][4200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.897 (3.040) Prec@1 76.56 (73.19) Prec@5 92.19 (89.96) + train[2018-10-18-14:05:39] Epoch: [129][4400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.126 (3.041) Prec@1 75.00 (73.18) Prec@5 88.28 (89.96) + train[2018-10-18-14:07:25] Epoch: [129][4600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.231 (3.041) Prec@1 69.53 (73.18) Prec@5 89.84 (89.96) + train[2018-10-18-14:09:10] Epoch: [129][4800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.250 (3.042) Prec@1 67.97 (73.19) Prec@5 89.06 (89.96) + train[2018-10-18-14:10:56] Epoch: [129][5000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.210 (3.042) Prec@1 71.09 (73.19) Prec@5 87.50 (89.96) + train[2018-10-18-14:12:41] Epoch: [129][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.390 (3.043) Prec@1 68.75 (73.15) Prec@5 87.50 (89.95) + train[2018-10-18-14:14:27] Epoch: [129][5400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.303 (3.043) Prec@1 68.75 (73.15) Prec@5 85.16 (89.93) + train[2018-10-18-14:16:12] Epoch: [129][5600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.905 (3.043) Prec@1 80.47 (73.14) Prec@5 92.19 (89.94) + train[2018-10-18-14:17:58] Epoch: [129][5800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.073 (3.043) Prec@1 71.88 (73.13) Prec@5 89.06 (89.94) + train[2018-10-18-14:19:43] Epoch: [129][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.297 (3.044) Prec@1 69.53 (73.11) Prec@5 87.50 (89.93) + train[2018-10-18-14:21:28] Epoch: [129][6200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.811 (3.044) Prec@1 72.66 (73.11) Prec@5 92.97 (89.93) + train[2018-10-18-14:23:14] Epoch: [129][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.068 (3.045) Prec@1 70.31 (73.11) Prec@5 89.06 (89.92) + train[2018-10-18-14:24:59] Epoch: [129][6600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.007 (3.045) Prec@1 79.69 (73.11) Prec@5 89.84 (89.92) + train[2018-10-18-14:26:45] Epoch: [129][6800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.143 (3.045) Prec@1 73.44 (73.10) Prec@5 88.28 (89.91) + train[2018-10-18-14:28:31] Epoch: [129][7000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.126 (3.046) Prec@1 71.88 (73.09) Prec@5 87.50 (89.90) + train[2018-10-18-14:30:16] Epoch: [129][7200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.145 (3.046) Prec@1 71.88 (73.07) Prec@5 87.50 (89.90) + train[2018-10-18-14:32:02] Epoch: [129][7400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.925 (3.047) Prec@1 76.56 (73.07) Prec@5 92.19 (89.89) + train[2018-10-18-14:33:47] Epoch: [129][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.123 (3.047) Prec@1 74.22 (73.07) Prec@5 92.19 (89.89) + train[2018-10-18-14:35:32] Epoch: [129][7800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.033 (3.047) Prec@1 71.88 (73.07) Prec@5 88.28 (89.88) + train[2018-10-18-14:37:17] Epoch: [129][8000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.923 (3.048) Prec@1 74.22 (73.06) Prec@5 90.62 (89.87) + train[2018-10-18-14:39:04] Epoch: [129][8200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.985 (3.048) Prec@1 68.75 (73.06) Prec@5 95.31 (89.87) + train[2018-10-18-14:40:50] Epoch: [129][8400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.265 (3.048) Prec@1 73.44 (73.06) Prec@5 85.94 (89.86) + train[2018-10-18-14:42:36] Epoch: [129][8600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.215 (3.048) Prec@1 69.53 (73.05) Prec@5 89.06 (89.86) + train[2018-10-18-14:44:22] Epoch: [129][8800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.898 (3.049) Prec@1 70.31 (73.04) Prec@5 91.41 (89.85) + train[2018-10-18-14:46:08] Epoch: [129][9000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.036 (3.049) Prec@1 71.88 (73.04) Prec@5 89.84 (89.84) + train[2018-10-18-14:47:53] Epoch: [129][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.740 (3.050) Prec@1 75.78 (73.02) Prec@5 92.97 (89.84) + train[2018-10-18-14:49:39] Epoch: [129][9400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.853 (3.050) Prec@1 78.12 (73.02) Prec@5 90.62 (89.84) + train[2018-10-18-14:51:25] Epoch: [129][9600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.998 (3.050) Prec@1 74.22 (73.02) Prec@5 92.19 (89.84) + train[2018-10-18-14:53:10] Epoch: [129][9800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.212 (3.050) Prec@1 71.88 (73.01) Prec@5 85.16 (89.83) + train[2018-10-18-14:54:56] Epoch: [129][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.855 (3.050) Prec@1 79.69 (73.01) Prec@5 91.41 (89.84) + train[2018-10-18-14:55:00] Epoch: [129][10009/10010] Time 0.14 (0.53) Data 0.00 (0.00) Loss 3.287 (3.050) Prec@1 73.33 (73.01) Prec@5 93.33 (89.84) +[2018-10-18-14:55:00] **train** Prec@1 73.01 Prec@5 89.84 Error@1 26.99 Error@5 10.16 Loss:3.050 + test [2018-10-18-14:55:04] Epoch: [129][000/391] Time 4.14 (4.14) Data 4.00 (4.00) Loss 0.553 (0.553) Prec@1 91.41 (91.41) Prec@5 98.44 (98.44) + test [2018-10-18-14:55:33] Epoch: [129][200/391] Time 0.12 (0.16) Data 0.00 (0.03) Loss 1.237 (1.029) Prec@1 70.31 (76.53) Prec@5 91.41 (93.27) + test [2018-10-18-14:55:58] Epoch: [129][390/391] Time 0.08 (0.15) Data 0.00 (0.02) Loss 2.082 (1.201) Prec@1 48.75 (72.92) Prec@5 82.50 (90.90) +[2018-10-18-14:55:58] **test** Prec@1 72.92 Prec@5 90.90 Error@1 27.08 Error@5 9.10 Loss:1.201 +----> Best Accuracy : Acc@1=72.92, Acc@5=90.90, Error@1=27.08, Error@5=9.10 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-18-14:55:58] [Epoch=130/250] [Need: 178:32:48] LR=0.0019 ~ 0.0019, Batch=128 + train[2018-10-18-14:56:02] Epoch: [130][000/10010] Time 4.51 (4.51) Data 3.87 (3.87) Loss 2.898 (2.898) Prec@1 76.56 (76.56) Prec@5 96.09 (96.09) + train[2018-10-18-14:57:49] Epoch: [130][200/10010] Time 0.55 (0.55) Data 0.00 (0.02) Loss 3.155 (3.041) Prec@1 70.31 (73.15) Prec@5 89.06 (89.87) + train[2018-10-18-14:59:35] Epoch: [130][400/10010] Time 0.53 (0.54) Data 0.00 (0.01) Loss 2.893 (3.036) Prec@1 75.00 (73.24) Prec@5 91.41 (90.02) + train[2018-10-18-15:01:20] Epoch: [130][600/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.817 (3.037) Prec@1 80.47 (73.34) Prec@5 92.97 (89.99) + train[2018-10-18-15:03:06] Epoch: [130][800/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 3.192 (3.035) Prec@1 72.66 (73.43) Prec@5 88.28 (90.01) + train[2018-10-18-15:04:52] Epoch: [130][1000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.989 (3.039) Prec@1 71.88 (73.37) Prec@5 92.19 (89.99) + train[2018-10-18-15:06:39] Epoch: [130][1200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.119 (3.037) Prec@1 69.53 (73.41) Prec@5 89.84 (90.03) + train[2018-10-18-15:08:25] Epoch: [130][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.991 (3.038) Prec@1 82.03 (73.40) Prec@5 89.06 (90.02) + train[2018-10-18-15:10:11] Epoch: [130][1600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.868 (3.039) Prec@1 78.12 (73.39) Prec@5 91.41 (90.03) + train[2018-10-18-15:11:56] Epoch: [130][1800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.014 (3.038) Prec@1 73.44 (73.39) Prec@5 88.28 (89.99) + train[2018-10-18-15:13:42] Epoch: [130][2000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.941 (3.037) Prec@1 78.12 (73.38) Prec@5 92.19 (90.01) + train[2018-10-18-15:15:28] Epoch: [130][2200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.021 (3.038) Prec@1 73.44 (73.38) Prec@5 89.84 (89.99) + train[2018-10-18-15:17:13] Epoch: [130][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.363 (3.036) Prec@1 68.75 (73.40) Prec@5 87.50 (89.98) + train[2018-10-18-15:18:59] Epoch: [130][2600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.348 (3.038) Prec@1 65.62 (73.36) Prec@5 84.38 (89.97) + train[2018-10-18-15:20:45] Epoch: [130][2800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.925 (3.038) Prec@1 72.66 (73.34) Prec@5 92.19 (89.96) + train[2018-10-18-15:22:30] Epoch: [130][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.209 (3.038) Prec@1 70.31 (73.33) Prec@5 86.72 (89.96) + train[2018-10-18-15:24:16] Epoch: [130][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.030 (3.037) Prec@1 70.31 (73.34) Prec@5 92.19 (89.98) + train[2018-10-18-15:26:01] Epoch: [130][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.244 (3.038) Prec@1 67.97 (73.33) Prec@5 87.50 (89.97) + train[2018-10-18-15:27:47] Epoch: [130][3600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.210 (3.040) Prec@1 64.84 (73.29) Prec@5 88.28 (89.95) + train[2018-10-18-15:29:32] Epoch: [130][3800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.254 (3.039) Prec@1 69.53 (73.30) Prec@5 87.50 (89.95) + train[2018-10-18-15:31:17] Epoch: [130][4000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.136 (3.040) Prec@1 71.09 (73.28) Prec@5 89.84 (89.93) + train[2018-10-18-15:33:03] Epoch: [130][4200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.954 (3.041) Prec@1 75.00 (73.27) Prec@5 88.28 (89.93) + train[2018-10-18-15:34:50] Epoch: [130][4400/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.064 (3.040) Prec@1 72.66 (73.26) Prec@5 89.06 (89.93) + train[2018-10-18-15:36:37] Epoch: [130][4600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.986 (3.041) Prec@1 74.22 (73.26) Prec@5 91.41 (89.93) + train[2018-10-18-15:38:24] Epoch: [130][4800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.869 (3.041) Prec@1 75.78 (73.25) Prec@5 92.19 (89.94) + train[2018-10-18-15:40:11] Epoch: [130][5000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.945 (3.041) Prec@1 72.66 (73.25) Prec@5 91.41 (89.94) + train[2018-10-18-15:41:59] Epoch: [130][5200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.152 (3.041) Prec@1 67.19 (73.26) Prec@5 87.50 (89.94) + train[2018-10-18-15:43:44] Epoch: [130][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.147 (3.041) Prec@1 72.66 (73.25) Prec@5 87.50 (89.94) + train[2018-10-18-15:45:30] Epoch: [130][5600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.305 (3.041) Prec@1 64.84 (73.23) Prec@5 88.28 (89.93) + train[2018-10-18-15:47:16] Epoch: [130][5800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.387 (3.042) Prec@1 67.19 (73.22) Prec@5 85.94 (89.92) + train[2018-10-18-15:49:02] Epoch: [130][6000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.177 (3.042) Prec@1 75.00 (73.21) Prec@5 86.72 (89.91) + train[2018-10-18-15:50:47] Epoch: [130][6200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.049 (3.043) Prec@1 75.78 (73.19) Prec@5 89.84 (89.92) + train[2018-10-18-15:52:32] Epoch: [130][6400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.375 (3.042) Prec@1 67.97 (73.21) Prec@5 86.72 (89.92) + train[2018-10-18-15:54:18] Epoch: [130][6600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.921 (3.042) Prec@1 75.00 (73.20) Prec@5 90.62 (89.92) + train[2018-10-18-15:56:04] Epoch: [130][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.627 (3.043) Prec@1 82.03 (73.19) Prec@5 93.75 (89.91) + train[2018-10-18-15:57:48] Epoch: [130][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.536 (3.043) Prec@1 67.97 (73.19) Prec@5 84.38 (89.91) + train[2018-10-18-15:59:34] Epoch: [130][7200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.888 (3.043) Prec@1 77.34 (73.19) Prec@5 92.19 (89.92) + train[2018-10-18-16:01:20] Epoch: [130][7400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.096 (3.043) Prec@1 75.78 (73.18) Prec@5 86.72 (89.91) + train[2018-10-18-16:03:05] Epoch: [130][7600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.208 (3.043) Prec@1 72.66 (73.18) Prec@5 85.16 (89.91) + train[2018-10-18-16:04:50] Epoch: [130][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.017 (3.043) Prec@1 71.88 (73.17) Prec@5 90.62 (89.91) + train[2018-10-18-16:06:36] Epoch: [130][8000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.412 (3.043) Prec@1 66.41 (73.16) Prec@5 87.50 (89.91) + train[2018-10-18-16:08:22] Epoch: [130][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.055 (3.043) Prec@1 73.44 (73.16) Prec@5 89.84 (89.92) + train[2018-10-18-16:10:07] Epoch: [130][8400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.072 (3.043) Prec@1 65.62 (73.16) Prec@5 92.97 (89.92) + train[2018-10-18-16:11:53] Epoch: [130][8600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.351 (3.044) Prec@1 70.31 (73.15) Prec@5 85.94 (89.91) + train[2018-10-18-16:13:39] Epoch: [130][8800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.029 (3.044) Prec@1 72.66 (73.13) Prec@5 89.06 (89.91) + train[2018-10-18-16:15:24] Epoch: [130][9000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.174 (3.044) Prec@1 75.78 (73.13) Prec@5 87.50 (89.90) + train[2018-10-18-16:17:10] Epoch: [130][9200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.914 (3.045) Prec@1 73.44 (73.12) Prec@5 90.62 (89.89) + train[2018-10-18-16:18:56] Epoch: [130][9400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.823 (3.045) Prec@1 74.22 (73.13) Prec@5 94.53 (89.89) + train[2018-10-18-16:20:41] Epoch: [130][9600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.865 (3.045) Prec@1 77.34 (73.12) Prec@5 92.97 (89.89) + train[2018-10-18-16:22:27] Epoch: [130][9800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.113 (3.045) Prec@1 64.06 (73.12) Prec@5 89.06 (89.89) + train[2018-10-18-16:24:13] Epoch: [130][10000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.204 (3.045) Prec@1 71.09 (73.11) Prec@5 89.06 (89.89) + train[2018-10-18-16:24:17] Epoch: [130][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 4.024 (3.045) Prec@1 53.33 (73.11) Prec@5 86.67 (89.89) +[2018-10-18-16:24:17] **train** Prec@1 73.11 Prec@5 89.89 Error@1 26.89 Error@5 10.11 Loss:3.045 + test [2018-10-18-16:24:21] Epoch: [130][000/391] Time 3.91 (3.91) Data 3.76 (3.76) Loss 0.508 (0.508) Prec@1 92.19 (92.19) Prec@5 97.66 (97.66) + test [2018-10-18-16:24:49] Epoch: [130][200/391] Time 0.12 (0.16) Data 0.00 (0.02) Loss 1.174 (1.024) Prec@1 71.88 (76.45) Prec@5 92.97 (93.31) + test [2018-10-18-16:25:16] Epoch: [130][390/391] Time 0.09 (0.15) Data 0.00 (0.02) Loss 2.339 (1.197) Prec@1 41.25 (72.79) Prec@5 78.75 (91.02) +[2018-10-18-16:25:16] **test** Prec@1 72.79 Prec@5 91.02 Error@1 27.21 Error@5 8.98 Loss:1.197 +----> Best Accuracy : Acc@1=72.92, Acc@5=90.90, Error@1=27.08, Error@5=9.10 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-18-16:25:16] [Epoch=131/250] [Need: 177:06:39] LR=0.0018 ~ 0.0018, Batch=128 + train[2018-10-18-16:25:21] Epoch: [131][000/10010] Time 4.82 (4.82) Data 4.24 (4.24) Loss 3.002 (3.002) Prec@1 76.56 (76.56) Prec@5 90.62 (90.62) + train[2018-10-18-16:27:06] Epoch: [131][200/10010] Time 0.51 (0.55) Data 0.00 (0.02) Loss 3.115 (3.031) Prec@1 71.09 (73.60) Prec@5 87.50 (90.02) + train[2018-10-18-16:28:52] Epoch: [131][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 3.167 (3.033) Prec@1 70.31 (73.62) Prec@5 85.94 (89.95) + train[2018-10-18-16:30:37] Epoch: [131][600/10010] Time 0.56 (0.54) Data 0.00 (0.01) Loss 3.251 (3.033) Prec@1 70.31 (73.54) Prec@5 89.06 (90.01) + train[2018-10-18-16:32:23] Epoch: [131][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.220 (3.030) Prec@1 71.09 (73.56) Prec@5 84.38 (90.05) + train[2018-10-18-16:34:09] Epoch: [131][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.842 (3.030) Prec@1 77.34 (73.60) Prec@5 92.97 (90.06) + train[2018-10-18-16:35:54] Epoch: [131][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.149 (3.025) Prec@1 70.31 (73.67) Prec@5 86.72 (90.10) + train[2018-10-18-16:37:40] Epoch: [131][1400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.394 (3.026) Prec@1 71.09 (73.60) Prec@5 85.16 (90.08) + train[2018-10-18-16:39:25] Epoch: [131][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.878 (3.026) Prec@1 77.34 (73.60) Prec@5 88.28 (90.09) + train[2018-10-18-16:41:10] Epoch: [131][1800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.052 (3.028) Prec@1 66.41 (73.54) Prec@5 90.62 (90.06) + train[2018-10-18-16:42:56] Epoch: [131][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.799 (3.027) Prec@1 77.34 (73.56) Prec@5 90.62 (90.06) + train[2018-10-18-16:44:41] Epoch: [131][2200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.176 (3.030) Prec@1 71.88 (73.52) Prec@5 87.50 (90.02) + train[2018-10-18-16:46:27] Epoch: [131][2400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.701 (3.027) Prec@1 78.91 (73.54) Prec@5 92.97 (90.06) + train[2018-10-18-16:48:12] Epoch: [131][2600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.996 (3.028) Prec@1 76.56 (73.51) Prec@5 89.06 (90.05) + train[2018-10-18-16:49:58] Epoch: [131][2800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.089 (3.028) Prec@1 67.19 (73.50) Prec@5 91.41 (90.05) + train[2018-10-18-16:51:43] Epoch: [131][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.098 (3.029) Prec@1 71.88 (73.50) Prec@5 86.72 (90.04) + train[2018-10-18-16:53:28] Epoch: [131][3200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.712 (3.029) Prec@1 73.44 (73.50) Prec@5 93.75 (90.02) + train[2018-10-18-16:55:14] Epoch: [131][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.750 (3.030) Prec@1 82.81 (73.48) Prec@5 93.75 (90.01) + train[2018-10-18-16:57:00] Epoch: [131][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.973 (3.031) Prec@1 72.66 (73.44) Prec@5 90.62 (90.01) + train[2018-10-18-16:58:45] Epoch: [131][3800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.113 (3.031) Prec@1 73.44 (73.43) Prec@5 90.62 (90.01) + train[2018-10-18-17:00:30] Epoch: [131][4000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.783 (3.031) Prec@1 74.22 (73.42) Prec@5 91.41 (90.01) + train[2018-10-18-17:02:16] Epoch: [131][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.106 (3.032) Prec@1 75.00 (73.39) Prec@5 89.84 (90.01) + train[2018-10-18-17:04:01] Epoch: [131][4400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.096 (3.032) Prec@1 71.09 (73.37) Prec@5 90.62 (90.00) + train[2018-10-18-17:05:46] Epoch: [131][4600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.763 (3.032) Prec@1 79.69 (73.39) Prec@5 92.97 (90.00) + train[2018-10-18-17:07:32] Epoch: [131][4800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.857 (3.032) Prec@1 81.25 (73.38) Prec@5 93.75 (90.00) + train[2018-10-18-17:09:17] Epoch: [131][5000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.074 (3.032) Prec@1 71.09 (73.38) Prec@5 90.62 (90.00) + train[2018-10-18-17:11:03] Epoch: [131][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.092 (3.032) Prec@1 71.09 (73.37) Prec@5 93.75 (90.02) + train[2018-10-18-17:12:49] Epoch: [131][5400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.980 (3.032) Prec@1 73.44 (73.36) Prec@5 91.41 (90.01) + train[2018-10-18-17:14:34] Epoch: [131][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.968 (3.033) Prec@1 77.34 (73.35) Prec@5 91.41 (90.01) + train[2018-10-18-17:16:20] Epoch: [131][5800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.991 (3.033) Prec@1 75.00 (73.34) Prec@5 90.62 (90.02) + train[2018-10-18-17:18:05] Epoch: [131][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.896 (3.034) Prec@1 77.34 (73.33) Prec@5 92.97 (90.01) + train[2018-10-18-17:19:50] Epoch: [131][6200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.790 (3.033) Prec@1 78.12 (73.35) Prec@5 92.19 (90.01) + train[2018-10-18-17:21:35] Epoch: [131][6400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.943 (3.033) Prec@1 71.88 (73.34) Prec@5 90.62 (90.01) + train[2018-10-18-17:23:21] Epoch: [131][6600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.942 (3.034) Prec@1 74.22 (73.34) Prec@5 92.19 (90.01) + train[2018-10-18-17:25:07] Epoch: [131][6800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.086 (3.035) Prec@1 74.22 (73.33) Prec@5 90.62 (90.00) + train[2018-10-18-17:26:53] Epoch: [131][7000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.047 (3.035) Prec@1 74.22 (73.31) Prec@5 91.41 (89.99) + train[2018-10-18-17:28:38] Epoch: [131][7200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.974 (3.035) Prec@1 72.66 (73.31) Prec@5 92.19 (89.98) + train[2018-10-18-17:30:23] Epoch: [131][7400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.018 (3.036) Prec@1 69.53 (73.29) Prec@5 89.84 (89.98) + train[2018-10-18-17:32:08] Epoch: [131][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.295 (3.036) Prec@1 69.53 (73.29) Prec@5 84.38 (89.97) + train[2018-10-18-17:33:53] Epoch: [131][7800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.208 (3.036) Prec@1 69.53 (73.29) Prec@5 88.28 (89.97) + train[2018-10-18-17:35:39] Epoch: [131][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.921 (3.037) Prec@1 71.88 (73.27) Prec@5 92.19 (89.97) + train[2018-10-18-17:37:25] Epoch: [131][8200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.939 (3.037) Prec@1 72.66 (73.27) Prec@5 92.19 (89.97) + train[2018-10-18-17:39:11] Epoch: [131][8400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.863 (3.038) Prec@1 77.34 (73.25) Prec@5 92.19 (89.96) + train[2018-10-18-17:40:56] Epoch: [131][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.404 (3.038) Prec@1 66.41 (73.24) Prec@5 86.72 (89.95) + train[2018-10-18-17:42:42] Epoch: [131][8800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.201 (3.038) Prec@1 71.88 (73.23) Prec@5 88.28 (89.95) + train[2018-10-18-17:44:26] Epoch: [131][9000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.068 (3.038) Prec@1 71.09 (73.23) Prec@5 87.50 (89.95) + train[2018-10-18-17:46:13] Epoch: [131][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.969 (3.039) Prec@1 72.66 (73.22) Prec@5 89.84 (89.95) + train[2018-10-18-17:47:58] Epoch: [131][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.291 (3.039) Prec@1 61.72 (73.21) Prec@5 89.06 (89.95) + train[2018-10-18-17:49:44] Epoch: [131][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.940 (3.039) Prec@1 71.88 (73.21) Prec@5 93.75 (89.94) + train[2018-10-18-17:51:29] Epoch: [131][9800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.956 (3.039) Prec@1 74.22 (73.20) Prec@5 91.41 (89.94) + train[2018-10-18-17:53:15] Epoch: [131][10000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.114 (3.039) Prec@1 71.88 (73.20) Prec@5 88.28 (89.93) + train[2018-10-18-17:53:20] Epoch: [131][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 2.824 (3.039) Prec@1 86.67 (73.20) Prec@5 86.67 (89.93) +[2018-10-18-17:53:20] **train** Prec@1 73.20 Prec@5 89.93 Error@1 26.80 Error@5 10.07 Loss:3.039 + test [2018-10-18-17:53:24] Epoch: [131][000/391] Time 4.50 (4.50) Data 4.35 (4.35) Loss 0.520 (0.520) Prec@1 92.97 (92.97) Prec@5 98.44 (98.44) + test [2018-10-18-17:53:51] Epoch: [131][200/391] Time 0.17 (0.16) Data 0.00 (0.03) Loss 1.223 (1.029) Prec@1 71.09 (76.40) Prec@5 92.19 (93.20) + test [2018-10-18-17:54:17] Epoch: [131][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.156 (1.195) Prec@1 43.75 (72.72) Prec@5 81.25 (90.94) +[2018-10-18-17:54:17] **test** Prec@1 72.72 Prec@5 90.94 Error@1 27.28 Error@5 9.06 Loss:1.195 +----> Best Accuracy : Acc@1=72.92, Acc@5=90.90, Error@1=27.08, Error@5=9.10 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-18-17:54:17] [Epoch=132/250] [Need: 175:04:08] LR=0.0018 ~ 0.0018, Batch=128 + train[2018-10-18-17:54:21] Epoch: [132][000/10010] Time 4.61 (4.61) Data 4.02 (4.02) Loss 2.915 (2.915) Prec@1 77.34 (77.34) Prec@5 90.62 (90.62) + train[2018-10-18-17:56:07] Epoch: [132][200/10010] Time 0.56 (0.55) Data 0.00 (0.02) Loss 2.962 (3.018) Prec@1 74.22 (73.47) Prec@5 89.84 (90.17) + train[2018-10-18-17:57:53] Epoch: [132][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 3.181 (3.011) Prec@1 68.75 (73.62) Prec@5 88.28 (90.23) + train[2018-10-18-17:59:38] Epoch: [132][600/10010] Time 0.57 (0.53) Data 0.00 (0.01) Loss 2.975 (3.013) Prec@1 74.22 (73.75) Prec@5 88.28 (90.21) + train[2018-10-18-18:01:23] Epoch: [132][800/10010] Time 0.57 (0.53) Data 0.00 (0.01) Loss 3.092 (3.015) Prec@1 71.09 (73.74) Prec@5 90.62 (90.20) + train[2018-10-18-18:03:09] Epoch: [132][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.922 (3.015) Prec@1 74.22 (73.76) Prec@5 87.50 (90.21) + train[2018-10-18-18:04:54] Epoch: [132][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.549 (3.014) Prec@1 64.06 (73.76) Prec@5 82.81 (90.22) + train[2018-10-18-18:06:40] Epoch: [132][1400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.095 (3.016) Prec@1 73.44 (73.72) Prec@5 87.50 (90.19) + train[2018-10-18-18:08:25] Epoch: [132][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.168 (3.016) Prec@1 70.31 (73.73) Prec@5 87.50 (90.17) + train[2018-10-18-18:10:10] Epoch: [132][1800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.967 (3.017) Prec@1 81.25 (73.73) Prec@5 90.62 (90.17) + train[2018-10-18-18:11:55] Epoch: [132][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.076 (3.017) Prec@1 71.09 (73.72) Prec@5 92.19 (90.16) + train[2018-10-18-18:13:41] Epoch: [132][2200/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.875 (3.017) Prec@1 78.12 (73.72) Prec@5 92.97 (90.17) + train[2018-10-18-18:15:27] Epoch: [132][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.963 (3.019) Prec@1 75.78 (73.68) Prec@5 90.62 (90.16) + train[2018-10-18-18:17:13] Epoch: [132][2600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.756 (3.023) Prec@1 75.78 (73.62) Prec@5 89.06 (90.12) + train[2018-10-18-18:18:58] Epoch: [132][2800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.969 (3.022) Prec@1 72.66 (73.65) Prec@5 91.41 (90.13) + train[2018-10-18-18:20:43] Epoch: [132][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.811 (3.022) Prec@1 73.44 (73.63) Prec@5 92.97 (90.14) + train[2018-10-18-18:22:28] Epoch: [132][3200/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 2.636 (3.022) Prec@1 78.91 (73.61) Prec@5 93.75 (90.13) + train[2018-10-18-18:24:13] Epoch: [132][3400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.608 (3.023) Prec@1 59.38 (73.60) Prec@5 84.38 (90.12) + train[2018-10-18-18:25:58] Epoch: [132][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.097 (3.024) Prec@1 73.44 (73.57) Prec@5 88.28 (90.11) + train[2018-10-18-18:27:43] Epoch: [132][3800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.323 (3.024) Prec@1 70.31 (73.58) Prec@5 87.50 (90.13) + train[2018-10-18-18:29:29] Epoch: [132][4000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.857 (3.024) Prec@1 74.22 (73.55) Prec@5 91.41 (90.11) + train[2018-10-18-18:31:15] Epoch: [132][4200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.193 (3.025) Prec@1 71.09 (73.55) Prec@5 87.50 (90.12) + train[2018-10-18-18:33:00] Epoch: [132][4400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.274 (3.025) Prec@1 69.53 (73.54) Prec@5 86.72 (90.11) + train[2018-10-18-18:34:44] Epoch: [132][4600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.040 (3.025) Prec@1 70.31 (73.52) Prec@5 87.50 (90.10) + train[2018-10-18-18:36:28] Epoch: [132][4800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.384 (3.026) Prec@1 67.19 (73.51) Prec@5 86.72 (90.09) + train[2018-10-18-18:38:14] Epoch: [132][5000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.260 (3.026) Prec@1 71.09 (73.50) Prec@5 89.84 (90.09) + train[2018-10-18-18:39:59] Epoch: [132][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.830 (3.027) Prec@1 74.22 (73.50) Prec@5 92.19 (90.08) + train[2018-10-18-18:41:45] Epoch: [132][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.295 (3.026) Prec@1 68.75 (73.50) Prec@5 84.38 (90.09) + train[2018-10-18-18:43:29] Epoch: [132][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.906 (3.027) Prec@1 75.78 (73.48) Prec@5 88.28 (90.08) + train[2018-10-18-18:45:15] Epoch: [132][5800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.971 (3.027) Prec@1 76.56 (73.47) Prec@5 92.19 (90.08) + train[2018-10-18-18:47:00] Epoch: [132][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.112 (3.028) Prec@1 74.22 (73.47) Prec@5 89.06 (90.06) + train[2018-10-18-18:48:46] Epoch: [132][6200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.932 (3.028) Prec@1 75.00 (73.46) Prec@5 90.62 (90.06) + train[2018-10-18-18:50:32] Epoch: [132][6400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.390 (3.029) Prec@1 69.53 (73.46) Prec@5 83.59 (90.06) + train[2018-10-18-18:52:16] Epoch: [132][6600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.135 (3.029) Prec@1 68.75 (73.46) Prec@5 89.06 (90.06) + train[2018-10-18-18:54:02] Epoch: [132][6800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.047 (3.030) Prec@1 75.00 (73.44) Prec@5 86.72 (90.05) + train[2018-10-18-18:55:48] Epoch: [132][7000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.066 (3.030) Prec@1 74.22 (73.44) Prec@5 90.62 (90.05) + train[2018-10-18-18:57:33] Epoch: [132][7200/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.894 (3.030) Prec@1 72.66 (73.43) Prec@5 90.62 (90.04) + train[2018-10-18-18:59:18] Epoch: [132][7400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.249 (3.031) Prec@1 71.09 (73.41) Prec@5 85.94 (90.03) + train[2018-10-18-19:01:04] Epoch: [132][7600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.772 (3.031) Prec@1 74.22 (73.40) Prec@5 91.41 (90.02) + train[2018-10-18-19:02:51] Epoch: [132][7800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.998 (3.032) Prec@1 72.66 (73.40) Prec@5 91.41 (90.02) + train[2018-10-18-19:04:38] Epoch: [132][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.388 (3.032) Prec@1 67.19 (73.39) Prec@5 83.59 (90.02) + train[2018-10-18-19:06:24] Epoch: [132][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.127 (3.032) Prec@1 69.53 (73.38) Prec@5 86.72 (90.01) + train[2018-10-18-19:08:12] Epoch: [132][8400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.188 (3.032) Prec@1 67.97 (73.37) Prec@5 85.94 (90.01) + train[2018-10-18-19:10:00] Epoch: [132][8600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.044 (3.032) Prec@1 72.66 (73.36) Prec@5 90.62 (90.01) + train[2018-10-18-19:11:47] Epoch: [132][8800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.956 (3.033) Prec@1 73.44 (73.36) Prec@5 91.41 (90.01) + train[2018-10-18-19:13:34] Epoch: [132][9000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.787 (3.032) Prec@1 79.69 (73.36) Prec@5 94.53 (90.01) + train[2018-10-18-19:15:21] Epoch: [132][9200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.903 (3.033) Prec@1 72.66 (73.36) Prec@5 90.62 (90.01) + train[2018-10-18-19:17:09] Epoch: [132][9400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.945 (3.033) Prec@1 81.25 (73.35) Prec@5 90.62 (90.01) + train[2018-10-18-19:18:57] Epoch: [132][9600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.032 (3.033) Prec@1 73.44 (73.35) Prec@5 91.41 (90.01) + train[2018-10-18-19:20:45] Epoch: [132][9800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.236 (3.033) Prec@1 66.41 (73.35) Prec@5 87.50 (90.01) + train[2018-10-18-19:22:32] Epoch: [132][10000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.706 (3.034) Prec@1 78.91 (73.33) Prec@5 94.53 (90.00) + train[2018-10-18-19:22:36] Epoch: [132][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.663 (3.033) Prec@1 53.33 (73.33) Prec@5 86.67 (90.00) +[2018-10-18-19:22:36] **train** Prec@1 73.33 Prec@5 90.00 Error@1 26.67 Error@5 10.00 Loss:3.033 + test [2018-10-18-19:22:40] Epoch: [132][000/391] Time 3.89 (3.89) Data 3.74 (3.74) Loss 0.622 (0.622) Prec@1 89.84 (89.84) Prec@5 95.31 (95.31) + test [2018-10-18-19:23:06] Epoch: [132][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.248 (1.035) Prec@1 68.75 (76.43) Prec@5 92.97 (93.19) + test [2018-10-18-19:23:31] Epoch: [132][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.199 (1.197) Prec@1 42.50 (72.83) Prec@5 80.00 (91.01) +[2018-10-18-19:23:31] **test** Prec@1 72.83 Prec@5 91.01 Error@1 27.17 Error@5 8.99 Loss:1.197 +----> Best Accuracy : Acc@1=72.92, Acc@5=90.90, Error@1=27.08, Error@5=9.10 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-18-19:23:32] [Epoch=133/250] [Need: 174:01:49] LR=0.0017 ~ 0.0017, Batch=128 + train[2018-10-18-19:23:37] Epoch: [133][000/10010] Time 5.19 (5.19) Data 4.56 (4.56) Loss 2.648 (2.648) Prec@1 78.91 (78.91) Prec@5 91.41 (91.41) + train[2018-10-18-19:25:22] Epoch: [133][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.054 (3.011) Prec@1 74.22 (73.87) Prec@5 86.72 (90.19) + train[2018-10-18-19:27:07] Epoch: [133][400/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.753 (3.014) Prec@1 78.12 (73.83) Prec@5 91.41 (90.17) + train[2018-10-18-19:28:51] Epoch: [133][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 2.958 (3.022) Prec@1 68.75 (73.66) Prec@5 94.53 (90.04) + train[2018-10-18-19:30:36] Epoch: [133][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.407 (3.023) Prec@1 65.62 (73.65) Prec@5 86.72 (90.08) + train[2018-10-18-19:32:20] Epoch: [133][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.051 (3.029) Prec@1 70.31 (73.51) Prec@5 90.62 (90.00) + train[2018-10-18-19:34:05] Epoch: [133][1200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.954 (3.030) Prec@1 79.69 (73.55) Prec@5 92.19 (90.02) + train[2018-10-18-19:35:50] Epoch: [133][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.033 (3.030) Prec@1 73.44 (73.54) Prec@5 88.28 (90.02) + train[2018-10-18-19:37:34] Epoch: [133][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.112 (3.033) Prec@1 72.66 (73.49) Prec@5 88.28 (89.97) + train[2018-10-18-19:39:19] Epoch: [133][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.024 (3.031) Prec@1 76.56 (73.50) Prec@5 89.84 (90.01) + train[2018-10-18-19:41:05] Epoch: [133][2000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.965 (3.029) Prec@1 71.88 (73.50) Prec@5 92.19 (90.06) + train[2018-10-18-19:42:49] Epoch: [133][2200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.206 (3.029) Prec@1 71.88 (73.49) Prec@5 87.50 (90.06) + train[2018-10-18-19:44:36] Epoch: [133][2400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.151 (3.031) Prec@1 77.34 (73.43) Prec@5 85.16 (90.03) + train[2018-10-18-19:46:22] Epoch: [133][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.141 (3.030) Prec@1 75.00 (73.44) Prec@5 89.84 (90.04) + train[2018-10-18-19:48:07] Epoch: [133][2800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.918 (3.030) Prec@1 77.34 (73.46) Prec@5 90.62 (90.03) + train[2018-10-18-19:49:53] Epoch: [133][3000/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 2.923 (3.030) Prec@1 74.22 (73.45) Prec@5 92.97 (90.04) + train[2018-10-18-19:51:39] Epoch: [133][3200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.844 (3.029) Prec@1 79.69 (73.47) Prec@5 90.62 (90.06) + train[2018-10-18-19:53:26] Epoch: [133][3400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.531 (3.029) Prec@1 62.50 (73.46) Prec@5 82.81 (90.06) + train[2018-10-18-19:55:11] Epoch: [133][3600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.217 (3.028) Prec@1 71.88 (73.47) Prec@5 88.28 (90.06) + train[2018-10-18-19:56:56] Epoch: [133][3800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.870 (3.028) Prec@1 71.88 (73.46) Prec@5 92.19 (90.06) + train[2018-10-18-19:58:41] Epoch: [133][4000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.955 (3.027) Prec@1 78.12 (73.49) Prec@5 90.62 (90.06) + train[2018-10-18-20:00:26] Epoch: [133][4200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.133 (3.026) Prec@1 71.88 (73.49) Prec@5 89.06 (90.07) + train[2018-10-18-20:02:12] Epoch: [133][4400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.866 (3.026) Prec@1 75.78 (73.49) Prec@5 90.62 (90.06) + train[2018-10-18-20:03:58] Epoch: [133][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.891 (3.026) Prec@1 74.22 (73.49) Prec@5 92.97 (90.06) + train[2018-10-18-20:05:43] Epoch: [133][4800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.347 (3.027) Prec@1 67.97 (73.48) Prec@5 87.50 (90.06) + train[2018-10-18-20:07:28] Epoch: [133][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.061 (3.028) Prec@1 72.66 (73.46) Prec@5 90.62 (90.05) + train[2018-10-18-20:09:13] Epoch: [133][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.892 (3.027) Prec@1 75.78 (73.47) Prec@5 90.62 (90.05) + train[2018-10-18-20:10:58] Epoch: [133][5400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.930 (3.028) Prec@1 71.09 (73.46) Prec@5 92.19 (90.05) + train[2018-10-18-20:12:42] Epoch: [133][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.920 (3.027) Prec@1 75.78 (73.46) Prec@5 90.62 (90.06) + train[2018-10-18-20:14:28] Epoch: [133][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.197 (3.027) Prec@1 72.66 (73.46) Prec@5 92.19 (90.07) + train[2018-10-18-20:16:13] Epoch: [133][6000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.188 (3.027) Prec@1 68.75 (73.46) Prec@5 86.72 (90.08) + train[2018-10-18-20:17:57] Epoch: [133][6200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.922 (3.027) Prec@1 73.44 (73.45) Prec@5 94.53 (90.07) + train[2018-10-18-20:19:42] Epoch: [133][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.262 (3.028) Prec@1 69.53 (73.43) Prec@5 88.28 (90.07) + train[2018-10-18-20:21:27] Epoch: [133][6600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.936 (3.028) Prec@1 72.66 (73.43) Prec@5 90.62 (90.06) + train[2018-10-18-20:23:12] Epoch: [133][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.975 (3.029) Prec@1 75.00 (73.41) Prec@5 92.19 (90.05) + train[2018-10-18-20:24:57] Epoch: [133][7000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.648 (3.029) Prec@1 80.47 (73.39) Prec@5 94.53 (90.04) + train[2018-10-18-20:26:42] Epoch: [133][7200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.963 (3.030) Prec@1 74.22 (73.39) Prec@5 90.62 (90.03) + train[2018-10-18-20:28:27] Epoch: [133][7400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.894 (3.030) Prec@1 76.56 (73.39) Prec@5 92.97 (90.03) + train[2018-10-18-20:30:11] Epoch: [133][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.801 (3.030) Prec@1 77.34 (73.38) Prec@5 90.62 (90.03) + train[2018-10-18-20:31:58] Epoch: [133][7800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.107 (3.030) Prec@1 71.88 (73.38) Prec@5 92.97 (90.04) + train[2018-10-18-20:33:44] Epoch: [133][8000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.820 (3.030) Prec@1 77.34 (73.39) Prec@5 91.41 (90.04) + train[2018-10-18-20:35:29] Epoch: [133][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.056 (3.031) Prec@1 71.88 (73.38) Prec@5 92.19 (90.03) + train[2018-10-18-20:37:13] Epoch: [133][8400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.793 (3.031) Prec@1 75.00 (73.37) Prec@5 94.53 (90.03) + train[2018-10-18-20:38:58] Epoch: [133][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.163 (3.031) Prec@1 68.75 (73.37) Prec@5 89.84 (90.03) + train[2018-10-18-20:40:43] Epoch: [133][8800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.364 (3.032) Prec@1 68.75 (73.37) Prec@5 82.81 (90.02) + train[2018-10-18-20:42:28] Epoch: [133][9000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.183 (3.033) Prec@1 67.19 (73.34) Prec@5 89.06 (90.02) + train[2018-10-18-20:44:14] Epoch: [133][9200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.147 (3.033) Prec@1 67.97 (73.33) Prec@5 89.06 (90.01) + train[2018-10-18-20:46:00] Epoch: [133][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.092 (3.033) Prec@1 70.31 (73.32) Prec@5 88.28 (90.01) + train[2018-10-18-20:47:45] Epoch: [133][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.995 (3.033) Prec@1 72.66 (73.33) Prec@5 90.62 (90.02) + train[2018-10-18-20:49:32] Epoch: [133][9800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.864 (3.032) Prec@1 77.34 (73.34) Prec@5 92.19 (90.02) + train[2018-10-18-20:51:18] Epoch: [133][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.919 (3.033) Prec@1 74.22 (73.33) Prec@5 92.19 (90.02) + train[2018-10-18-20:51:22] Epoch: [133][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.554 (3.033) Prec@1 80.00 (73.33) Prec@5 93.33 (90.01) +[2018-10-18-20:51:22] **train** Prec@1 73.33 Prec@5 90.01 Error@1 26.67 Error@5 9.99 Loss:3.033 + test [2018-10-18-20:51:27] Epoch: [133][000/391] Time 4.06 (4.06) Data 3.93 (3.93) Loss 0.598 (0.598) Prec@1 90.62 (90.62) Prec@5 97.66 (97.66) + test [2018-10-18-20:51:53] Epoch: [133][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.363 (1.050) Prec@1 65.62 (76.54) Prec@5 88.28 (93.32) + test [2018-10-18-20:52:17] Epoch: [133][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.125 (1.216) Prec@1 46.25 (72.77) Prec@5 82.50 (91.01) +[2018-10-18-20:52:17] **test** Prec@1 72.77 Prec@5 91.01 Error@1 27.23 Error@5 8.99 Loss:1.216 +----> Best Accuracy : Acc@1=72.92, Acc@5=90.90, Error@1=27.08, Error@5=9.10 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-18-20:52:17] [Epoch=134/250] [Need: 171:36:29] LR=0.0017 ~ 0.0017, Batch=128 + train[2018-10-18-20:52:22] Epoch: [134][000/10010] Time 4.92 (4.92) Data 4.31 (4.31) Loss 2.792 (2.792) Prec@1 77.34 (77.34) Prec@5 94.53 (94.53) + train[2018-10-18-20:54:07] Epoch: [134][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 3.120 (3.004) Prec@1 71.09 (73.74) Prec@5 87.50 (90.34) + train[2018-10-18-20:55:52] Epoch: [134][400/10010] Time 0.56 (0.53) Data 0.00 (0.01) Loss 3.141 (2.999) Prec@1 70.31 (73.99) Prec@5 89.06 (90.36) + train[2018-10-18-20:57:37] Epoch: [134][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.167 (3.001) Prec@1 70.31 (74.05) Prec@5 86.72 (90.34) + train[2018-10-18-20:59:22] Epoch: [134][800/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 2.974 (3.005) Prec@1 75.78 (74.00) Prec@5 92.97 (90.25) + train[2018-10-18-21:01:07] Epoch: [134][1000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.192 (3.009) Prec@1 68.75 (73.92) Prec@5 90.62 (90.22) + train[2018-10-18-21:02:52] Epoch: [134][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.940 (3.008) Prec@1 78.91 (73.92) Prec@5 92.97 (90.28) + train[2018-10-18-21:04:36] Epoch: [134][1400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.170 (3.010) Prec@1 68.75 (73.90) Prec@5 89.06 (90.26) + train[2018-10-18-21:06:21] Epoch: [134][1600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.466 (3.010) Prec@1 63.28 (73.88) Prec@5 87.50 (90.26) + train[2018-10-18-21:08:07] Epoch: [134][1800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.888 (3.011) Prec@1 73.44 (73.88) Prec@5 90.62 (90.23) + train[2018-10-18-21:09:52] Epoch: [134][2000/10010] Time 0.69 (0.53) Data 0.00 (0.00) Loss 3.127 (3.009) Prec@1 74.22 (73.91) Prec@5 90.62 (90.25) + train[2018-10-18-21:11:37] Epoch: [134][2200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.417 (3.009) Prec@1 67.19 (73.91) Prec@5 87.50 (90.25) + train[2018-10-18-21:13:23] Epoch: [134][2400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.304 (3.011) Prec@1 68.75 (73.87) Prec@5 85.16 (90.24) + train[2018-10-18-21:15:08] Epoch: [134][2600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.235 (3.013) Prec@1 70.31 (73.83) Prec@5 87.50 (90.21) + train[2018-10-18-21:16:53] Epoch: [134][2800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.018 (3.014) Prec@1 74.22 (73.81) Prec@5 91.41 (90.19) + train[2018-10-18-21:18:37] Epoch: [134][3000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.111 (3.014) Prec@1 71.09 (73.79) Prec@5 88.28 (90.18) + train[2018-10-18-21:20:23] Epoch: [134][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.696 (3.014) Prec@1 75.78 (73.78) Prec@5 96.09 (90.18) + train[2018-10-18-21:22:08] Epoch: [134][3400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.057 (3.015) Prec@1 74.22 (73.76) Prec@5 91.41 (90.18) + train[2018-10-18-21:23:54] Epoch: [134][3600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.064 (3.014) Prec@1 74.22 (73.75) Prec@5 89.84 (90.18) + train[2018-10-18-21:25:39] Epoch: [134][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.098 (3.016) Prec@1 71.88 (73.73) Prec@5 88.28 (90.16) + train[2018-10-18-21:27:25] Epoch: [134][4000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.752 (3.015) Prec@1 75.78 (73.75) Prec@5 94.53 (90.17) + train[2018-10-18-21:29:10] Epoch: [134][4200/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.570 (3.015) Prec@1 83.59 (73.74) Prec@5 93.75 (90.18) + train[2018-10-18-21:30:56] Epoch: [134][4400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.069 (3.016) Prec@1 77.34 (73.73) Prec@5 89.84 (90.18) + train[2018-10-18-21:32:41] Epoch: [134][4600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.342 (3.017) Prec@1 70.31 (73.71) Prec@5 86.72 (90.16) + train[2018-10-18-21:34:27] Epoch: [134][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.228 (3.018) Prec@1 72.66 (73.69) Prec@5 89.06 (90.15) + train[2018-10-18-21:36:12] Epoch: [134][5000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.085 (3.018) Prec@1 71.88 (73.68) Prec@5 91.41 (90.14) + train[2018-10-18-21:37:57] Epoch: [134][5200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.076 (3.018) Prec@1 72.66 (73.68) Prec@5 89.06 (90.14) + train[2018-10-18-21:39:43] Epoch: [134][5400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.708 (3.018) Prec@1 75.78 (73.68) Prec@5 94.53 (90.14) + train[2018-10-18-21:41:28] Epoch: [134][5600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.113 (3.019) Prec@1 71.09 (73.67) Prec@5 89.84 (90.13) + train[2018-10-18-21:43:13] Epoch: [134][5800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.186 (3.020) Prec@1 71.09 (73.66) Prec@5 89.06 (90.11) + train[2018-10-18-21:44:58] Epoch: [134][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.826 (3.020) Prec@1 78.12 (73.66) Prec@5 92.19 (90.11) + train[2018-10-18-21:46:43] Epoch: [134][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.199 (3.021) Prec@1 70.31 (73.64) Prec@5 85.94 (90.10) + train[2018-10-18-21:48:28] Epoch: [134][6400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.422 (3.020) Prec@1 64.84 (73.65) Prec@5 86.72 (90.11) + train[2018-10-18-21:50:13] Epoch: [134][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.023 (3.020) Prec@1 70.31 (73.63) Prec@5 91.41 (90.11) + train[2018-10-18-21:51:57] Epoch: [134][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.970 (3.020) Prec@1 70.31 (73.63) Prec@5 93.75 (90.11) + train[2018-10-18-21:53:42] Epoch: [134][7000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.141 (3.020) Prec@1 72.66 (73.63) Prec@5 88.28 (90.12) + train[2018-10-18-21:55:26] Epoch: [134][7200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.246 (3.020) Prec@1 72.66 (73.63) Prec@5 89.06 (90.12) + train[2018-10-18-21:57:11] Epoch: [134][7400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.139 (3.021) Prec@1 72.66 (73.62) Prec@5 87.50 (90.11) + train[2018-10-18-21:58:57] Epoch: [134][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.330 (3.021) Prec@1 67.97 (73.62) Prec@5 85.94 (90.11) + train[2018-10-18-22:00:42] Epoch: [134][7800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.762 (3.021) Prec@1 79.69 (73.61) Prec@5 90.62 (90.10) + train[2018-10-18-22:02:27] Epoch: [134][8000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.289 (3.022) Prec@1 72.66 (73.61) Prec@5 85.16 (90.10) + train[2018-10-18-22:04:13] Epoch: [134][8200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.806 (3.022) Prec@1 75.78 (73.60) Prec@5 95.31 (90.10) + train[2018-10-18-22:05:58] Epoch: [134][8400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.963 (3.022) Prec@1 72.66 (73.58) Prec@5 90.62 (90.09) + train[2018-10-18-22:07:43] Epoch: [134][8600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.044 (3.022) Prec@1 72.66 (73.58) Prec@5 90.62 (90.09) + train[2018-10-18-22:09:27] Epoch: [134][8800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.166 (3.023) Prec@1 71.88 (73.56) Prec@5 87.50 (90.08) + train[2018-10-18-22:11:12] Epoch: [134][9000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.025 (3.023) Prec@1 77.34 (73.56) Prec@5 85.94 (90.08) + train[2018-10-18-22:12:57] Epoch: [134][9200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.271 (3.024) Prec@1 65.62 (73.55) Prec@5 89.06 (90.08) + train[2018-10-18-22:14:42] Epoch: [134][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.277 (3.024) Prec@1 63.28 (73.56) Prec@5 87.50 (90.08) + train[2018-10-18-22:16:26] Epoch: [134][9600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.996 (3.024) Prec@1 67.19 (73.55) Prec@5 91.41 (90.07) + train[2018-10-18-22:18:11] Epoch: [134][9800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.991 (3.024) Prec@1 71.09 (73.54) Prec@5 89.84 (90.08) + train[2018-10-18-22:19:56] Epoch: [134][10000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.119 (3.025) Prec@1 68.75 (73.53) Prec@5 88.28 (90.07) + train[2018-10-18-22:20:01] Epoch: [134][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 2.581 (3.025) Prec@1 86.67 (73.53) Prec@5 100.00 (90.07) +[2018-10-18-22:20:01] **train** Prec@1 73.53 Prec@5 90.07 Error@1 26.47 Error@5 9.93 Loss:3.025 + test [2018-10-18-22:20:05] Epoch: [134][000/391] Time 3.78 (3.78) Data 3.65 (3.65) Loss 0.702 (0.702) Prec@1 86.72 (86.72) Prec@5 94.53 (94.53) + test [2018-10-18-22:20:31] Epoch: [134][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.309 (1.030) Prec@1 63.28 (76.54) Prec@5 91.41 (93.20) + test [2018-10-18-22:20:56] Epoch: [134][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.165 (1.194) Prec@1 42.50 (72.81) Prec@5 82.50 (90.95) +[2018-10-18-22:20:56] **test** Prec@1 72.81 Prec@5 90.95 Error@1 27.19 Error@5 9.05 Loss:1.194 +----> Best Accuracy : Acc@1=72.92, Acc@5=90.90, Error@1=27.08, Error@5=9.10 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-18-22:20:56] [Epoch=135/250] [Need: 169:54:18] LR=0.0016 ~ 0.0016, Batch=128 + train[2018-10-18-22:21:01] Epoch: [135][000/10010] Time 5.02 (5.02) Data 4.41 (4.41) Loss 3.258 (3.258) Prec@1 67.97 (67.97) Prec@5 87.50 (87.50) + train[2018-10-18-22:22:46] Epoch: [135][200/10010] Time 0.51 (0.55) Data 0.00 (0.02) Loss 2.915 (3.000) Prec@1 79.69 (73.93) Prec@5 88.28 (90.43) + train[2018-10-18-22:24:31] Epoch: [135][400/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 3.270 (3.005) Prec@1 67.97 (73.68) Prec@5 88.28 (90.43) + train[2018-10-18-22:26:16] Epoch: [135][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 2.841 (3.014) Prec@1 81.25 (73.68) Prec@5 93.75 (90.35) + train[2018-10-18-22:28:01] Epoch: [135][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.856 (3.011) Prec@1 72.66 (73.72) Prec@5 90.62 (90.40) + train[2018-10-18-22:29:46] Epoch: [135][1000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.877 (3.014) Prec@1 76.56 (73.75) Prec@5 91.41 (90.29) + train[2018-10-18-22:31:32] Epoch: [135][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.824 (3.011) Prec@1 78.91 (73.78) Prec@5 89.06 (90.32) + train[2018-10-18-22:33:16] Epoch: [135][1400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.138 (3.011) Prec@1 70.31 (73.78) Prec@5 90.62 (90.29) + train[2018-10-18-22:35:00] Epoch: [135][1600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.907 (3.010) Prec@1 68.75 (73.77) Prec@5 89.84 (90.28) + train[2018-10-18-22:36:45] Epoch: [135][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.235 (3.011) Prec@1 72.66 (73.75) Prec@5 88.28 (90.27) + train[2018-10-18-22:38:29] Epoch: [135][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.049 (3.011) Prec@1 75.78 (73.76) Prec@5 88.28 (90.25) + train[2018-10-18-22:40:14] Epoch: [135][2200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.506 (3.013) Prec@1 80.47 (73.75) Prec@5 95.31 (90.22) + train[2018-10-18-22:41:59] Epoch: [135][2400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.812 (3.012) Prec@1 73.44 (73.75) Prec@5 92.19 (90.23) + train[2018-10-18-22:43:45] Epoch: [135][2600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.141 (3.013) Prec@1 71.09 (73.73) Prec@5 89.06 (90.22) + train[2018-10-18-22:45:29] Epoch: [135][2800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.818 (3.012) Prec@1 75.78 (73.75) Prec@5 93.75 (90.23) + train[2018-10-18-22:47:14] Epoch: [135][3000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.203 (3.013) Prec@1 69.53 (73.74) Prec@5 87.50 (90.22) + train[2018-10-18-22:48:59] Epoch: [135][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.651 (3.011) Prec@1 82.81 (73.78) Prec@5 95.31 (90.25) + train[2018-10-18-22:50:44] Epoch: [135][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.235 (3.011) Prec@1 69.53 (73.78) Prec@5 89.84 (90.25) + train[2018-10-18-22:52:29] Epoch: [135][3600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.246 (3.012) Prec@1 68.75 (73.77) Prec@5 87.50 (90.25) + train[2018-10-18-22:54:14] Epoch: [135][3800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.010 (3.012) Prec@1 71.09 (73.78) Prec@5 93.75 (90.24) + train[2018-10-18-22:56:00] Epoch: [135][4000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.719 (3.013) Prec@1 82.03 (73.76) Prec@5 90.62 (90.22) + train[2018-10-18-22:57:45] Epoch: [135][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.911 (3.014) Prec@1 72.66 (73.75) Prec@5 92.97 (90.21) + train[2018-10-18-22:59:30] Epoch: [135][4400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.045 (3.013) Prec@1 71.88 (73.77) Prec@5 87.50 (90.20) + train[2018-10-18-23:01:15] Epoch: [135][4600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.145 (3.013) Prec@1 71.09 (73.77) Prec@5 89.06 (90.21) + train[2018-10-18-23:03:00] Epoch: [135][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.123 (3.013) Prec@1 75.78 (73.77) Prec@5 87.50 (90.21) + train[2018-10-18-23:04:46] Epoch: [135][5000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.123 (3.014) Prec@1 67.97 (73.74) Prec@5 88.28 (90.20) + train[2018-10-18-23:06:31] Epoch: [135][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.795 (3.014) Prec@1 80.47 (73.74) Prec@5 92.19 (90.19) + train[2018-10-18-23:08:17] Epoch: [135][5400/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.840 (3.015) Prec@1 75.00 (73.73) Prec@5 92.19 (90.19) + train[2018-10-18-23:10:02] Epoch: [135][5600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.646 (3.015) Prec@1 80.47 (73.72) Prec@5 93.75 (90.19) + train[2018-10-18-23:11:47] Epoch: [135][5800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.007 (3.016) Prec@1 78.12 (73.71) Prec@5 89.06 (90.18) + train[2018-10-18-23:13:32] Epoch: [135][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.636 (3.016) Prec@1 81.25 (73.71) Prec@5 92.19 (90.18) + train[2018-10-18-23:15:18] Epoch: [135][6200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.223 (3.016) Prec@1 71.88 (73.70) Prec@5 86.72 (90.17) + train[2018-10-18-23:17:03] Epoch: [135][6400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.939 (3.016) Prec@1 75.78 (73.70) Prec@5 91.41 (90.17) + train[2018-10-18-23:18:48] Epoch: [135][6600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.985 (3.016) Prec@1 72.66 (73.70) Prec@5 89.84 (90.17) + train[2018-10-18-23:20:33] Epoch: [135][6800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.043 (3.017) Prec@1 75.00 (73.68) Prec@5 89.84 (90.16) + train[2018-10-18-23:22:18] Epoch: [135][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.959 (3.017) Prec@1 77.34 (73.68) Prec@5 89.84 (90.16) + train[2018-10-18-23:24:03] Epoch: [135][7200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.925 (3.017) Prec@1 73.44 (73.67) Prec@5 92.97 (90.17) + train[2018-10-18-23:25:48] Epoch: [135][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.036 (3.017) Prec@1 73.44 (73.67) Prec@5 90.62 (90.17) + train[2018-10-18-23:27:33] Epoch: [135][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.901 (3.017) Prec@1 77.34 (73.67) Prec@5 90.62 (90.17) + train[2018-10-18-23:29:19] Epoch: [135][7800/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.798 (3.018) Prec@1 77.34 (73.65) Prec@5 91.41 (90.16) + train[2018-10-18-23:31:04] Epoch: [135][8000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.952 (3.019) Prec@1 75.78 (73.64) Prec@5 89.84 (90.15) + train[2018-10-18-23:32:49] Epoch: [135][8200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.383 (3.019) Prec@1 72.66 (73.63) Prec@5 83.59 (90.14) + train[2018-10-18-23:34:34] Epoch: [135][8400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.741 (3.019) Prec@1 75.00 (73.62) Prec@5 93.75 (90.14) + train[2018-10-18-23:36:19] Epoch: [135][8600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.870 (3.019) Prec@1 79.69 (73.63) Prec@5 90.62 (90.14) + train[2018-10-18-23:38:04] Epoch: [135][8800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.896 (3.019) Prec@1 75.78 (73.62) Prec@5 92.19 (90.14) + train[2018-10-18-23:39:50] Epoch: [135][9000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.062 (3.020) Prec@1 74.22 (73.62) Prec@5 90.62 (90.13) + train[2018-10-18-23:41:35] Epoch: [135][9200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.068 (3.020) Prec@1 72.66 (73.63) Prec@5 89.84 (90.14) + train[2018-10-18-23:43:20] Epoch: [135][9400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.268 (3.020) Prec@1 71.09 (73.63) Prec@5 84.38 (90.14) + train[2018-10-18-23:45:05] Epoch: [135][9600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.641 (3.020) Prec@1 83.59 (73.62) Prec@5 92.97 (90.14) + train[2018-10-18-23:46:49] Epoch: [135][9800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.132 (3.020) Prec@1 72.66 (73.62) Prec@5 87.50 (90.13) + train[2018-10-18-23:48:34] Epoch: [135][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.113 (3.020) Prec@1 71.88 (73.62) Prec@5 87.50 (90.13) + train[2018-10-18-23:48:38] Epoch: [135][10009/10010] Time 0.18 (0.53) Data 0.00 (0.00) Loss 4.267 (3.020) Prec@1 60.00 (73.62) Prec@5 86.67 (90.13) +[2018-10-18-23:48:38] **train** Prec@1 73.62 Prec@5 90.13 Error@1 26.38 Error@5 9.87 Loss:3.020 + test [2018-10-18-23:48:42] Epoch: [135][000/391] Time 4.36 (4.36) Data 4.23 (4.23) Loss 0.602 (0.602) Prec@1 85.94 (85.94) Prec@5 96.88 (96.88) + test [2018-10-18-23:49:09] Epoch: [135][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.282 (1.018) Prec@1 66.41 (76.62) Prec@5 91.41 (93.44) + test [2018-10-18-23:49:33] Epoch: [135][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.175 (1.184) Prec@1 48.75 (73.10) Prec@5 81.25 (91.17) +[2018-10-18-23:49:33] **test** Prec@1 73.10 Prec@5 91.17 Error@1 26.90 Error@5 8.83 Loss:1.184 +----> Best Accuracy : Acc@1=73.10, Acc@5=91.17, Error@1=26.90, Error@5=8.83 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-18-23:49:34] [Epoch=136/250] [Need: 168:23:06] LR=0.0016 ~ 0.0016, Batch=128 + train[2018-10-18-23:49:38] Epoch: [136][000/10010] Time 4.88 (4.88) Data 4.32 (4.32) Loss 2.978 (2.978) Prec@1 73.44 (73.44) Prec@5 91.41 (91.41) + train[2018-10-18-23:51:24] Epoch: [136][200/10010] Time 0.51 (0.55) Data 0.00 (0.02) Loss 2.885 (3.041) Prec@1 71.88 (73.32) Prec@5 93.75 (89.95) + train[2018-10-18-23:53:10] Epoch: [136][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.844 (3.020) Prec@1 75.78 (73.73) Prec@5 89.84 (90.22) + train[2018-10-18-23:54:54] Epoch: [136][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.944 (3.013) Prec@1 71.88 (73.93) Prec@5 89.84 (90.24) + train[2018-10-18-23:56:38] Epoch: [136][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.776 (3.013) Prec@1 79.69 (73.84) Prec@5 92.97 (90.23) + train[2018-10-18-23:58:23] Epoch: [136][1000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.002 (3.015) Prec@1 72.66 (73.87) Prec@5 92.19 (90.26) + train[2018-10-19-00:00:09] Epoch: [136][1200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.959 (3.019) Prec@1 71.88 (73.78) Prec@5 90.62 (90.19) + train[2018-10-19-00:01:53] Epoch: [136][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.968 (3.017) Prec@1 77.34 (73.77) Prec@5 89.06 (90.21) + train[2018-10-19-00:03:39] Epoch: [136][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.039 (3.014) Prec@1 67.97 (73.84) Prec@5 92.19 (90.23) + train[2018-10-19-00:05:24] Epoch: [136][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.913 (3.012) Prec@1 77.34 (73.83) Prec@5 92.97 (90.28) + train[2018-10-19-00:07:09] Epoch: [136][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.135 (3.015) Prec@1 70.31 (73.77) Prec@5 87.50 (90.24) + train[2018-10-19-00:08:55] Epoch: [136][2200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.251 (3.017) Prec@1 64.84 (73.75) Prec@5 87.50 (90.22) + train[2018-10-19-00:10:41] Epoch: [136][2400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.041 (3.016) Prec@1 73.44 (73.78) Prec@5 92.19 (90.22) + train[2018-10-19-00:12:26] Epoch: [136][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.952 (3.015) Prec@1 75.00 (73.79) Prec@5 87.50 (90.21) + train[2018-10-19-00:14:11] Epoch: [136][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.964 (3.016) Prec@1 74.22 (73.76) Prec@5 89.06 (90.21) + train[2018-10-19-00:15:57] Epoch: [136][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.542 (3.016) Prec@1 67.19 (73.76) Prec@5 83.59 (90.21) + train[2018-10-19-00:17:42] Epoch: [136][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.381 (3.016) Prec@1 67.19 (73.77) Prec@5 85.94 (90.21) + train[2018-10-19-00:19:27] Epoch: [136][3400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.714 (3.015) Prec@1 77.34 (73.77) Prec@5 94.53 (90.22) + train[2018-10-19-00:21:12] Epoch: [136][3600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.910 (3.015) Prec@1 74.22 (73.76) Prec@5 93.75 (90.22) + train[2018-10-19-00:22:58] Epoch: [136][3800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.392 (3.015) Prec@1 65.62 (73.77) Prec@5 84.38 (90.23) + train[2018-10-19-00:24:43] Epoch: [136][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.752 (3.014) Prec@1 81.25 (73.76) Prec@5 90.62 (90.24) + train[2018-10-19-00:26:30] Epoch: [136][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.031 (3.013) Prec@1 75.00 (73.78) Prec@5 90.62 (90.25) + train[2018-10-19-00:28:15] Epoch: [136][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.879 (3.013) Prec@1 71.88 (73.78) Prec@5 90.62 (90.25) + train[2018-10-19-00:30:00] Epoch: [136][4600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.798 (3.013) Prec@1 81.25 (73.77) Prec@5 91.41 (90.23) + train[2018-10-19-00:31:45] Epoch: [136][4800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.137 (3.014) Prec@1 72.66 (73.76) Prec@5 89.06 (90.22) + train[2018-10-19-00:33:30] Epoch: [136][5000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.861 (3.014) Prec@1 75.78 (73.74) Prec@5 92.97 (90.22) + train[2018-10-19-00:35:15] Epoch: [136][5200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.866 (3.015) Prec@1 74.22 (73.74) Prec@5 91.41 (90.21) + train[2018-10-19-00:37:00] Epoch: [136][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.000 (3.015) Prec@1 69.53 (73.73) Prec@5 91.41 (90.20) + train[2018-10-19-00:38:45] Epoch: [136][5600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.826 (3.016) Prec@1 76.56 (73.72) Prec@5 94.53 (90.20) + train[2018-10-19-00:40:30] Epoch: [136][5800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.840 (3.016) Prec@1 76.56 (73.71) Prec@5 92.19 (90.20) + train[2018-10-19-00:42:15] Epoch: [136][6000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.946 (3.016) Prec@1 77.34 (73.71) Prec@5 90.62 (90.19) + train[2018-10-19-00:43:59] Epoch: [136][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.994 (3.016) Prec@1 75.78 (73.69) Prec@5 87.50 (90.19) + train[2018-10-19-00:45:45] Epoch: [136][6400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.945 (3.016) Prec@1 78.91 (73.69) Prec@5 89.06 (90.19) + train[2018-10-19-00:47:30] Epoch: [136][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.171 (3.017) Prec@1 67.97 (73.67) Prec@5 89.06 (90.18) + train[2018-10-19-00:49:14] Epoch: [136][6800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.942 (3.017) Prec@1 73.44 (73.67) Prec@5 92.97 (90.17) + train[2018-10-19-00:50:59] Epoch: [136][7000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.088 (3.017) Prec@1 74.22 (73.68) Prec@5 90.62 (90.18) + train[2018-10-19-00:52:44] Epoch: [136][7200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.011 (3.017) Prec@1 74.22 (73.66) Prec@5 92.97 (90.17) + train[2018-10-19-00:54:29] Epoch: [136][7400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.814 (3.017) Prec@1 75.78 (73.65) Prec@5 93.75 (90.17) + train[2018-10-19-00:56:14] Epoch: [136][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.246 (3.017) Prec@1 72.66 (73.65) Prec@5 85.94 (90.18) + train[2018-10-19-00:57:59] Epoch: [136][7800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.033 (3.017) Prec@1 74.22 (73.66) Prec@5 90.62 (90.19) + train[2018-10-19-00:59:44] Epoch: [136][8000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.875 (3.017) Prec@1 78.12 (73.67) Prec@5 92.19 (90.19) + train[2018-10-19-01:01:28] Epoch: [136][8200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.936 (3.017) Prec@1 75.00 (73.66) Prec@5 92.19 (90.19) + train[2018-10-19-01:03:13] Epoch: [136][8400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.032 (3.017) Prec@1 72.66 (73.65) Prec@5 91.41 (90.19) + train[2018-10-19-01:04:57] Epoch: [136][8600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.057 (3.017) Prec@1 72.66 (73.65) Prec@5 89.06 (90.19) + train[2018-10-19-01:06:42] Epoch: [136][8800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.092 (3.017) Prec@1 65.62 (73.64) Prec@5 92.19 (90.18) + train[2018-10-19-01:08:29] Epoch: [136][9000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.035 (3.017) Prec@1 72.66 (73.64) Prec@5 89.84 (90.17) + train[2018-10-19-01:10:15] Epoch: [136][9200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.011 (3.018) Prec@1 76.56 (73.63) Prec@5 90.62 (90.17) + train[2018-10-19-01:12:00] Epoch: [136][9400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.213 (3.018) Prec@1 68.75 (73.63) Prec@5 86.72 (90.16) + train[2018-10-19-01:13:45] Epoch: [136][9600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.062 (3.018) Prec@1 69.53 (73.63) Prec@5 92.19 (90.16) + train[2018-10-19-01:15:31] Epoch: [136][9800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.147 (3.018) Prec@1 71.09 (73.63) Prec@5 89.84 (90.16) + train[2018-10-19-01:17:17] Epoch: [136][10000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.091 (3.018) Prec@1 72.66 (73.63) Prec@5 88.28 (90.17) + train[2018-10-19-01:17:21] Epoch: [136][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 3.504 (3.018) Prec@1 66.67 (73.63) Prec@5 86.67 (90.17) +[2018-10-19-01:17:21] **train** Prec@1 73.63 Prec@5 90.17 Error@1 26.37 Error@5 9.83 Loss:3.018 + test [2018-10-19-01:17:24] Epoch: [136][000/391] Time 3.43 (3.43) Data 3.29 (3.29) Loss 0.546 (0.546) Prec@1 92.19 (92.19) Prec@5 97.66 (97.66) + test [2018-10-19-01:17:52] Epoch: [136][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.338 (1.014) Prec@1 64.06 (76.58) Prec@5 91.41 (93.33) + test [2018-10-19-01:18:16] Epoch: [136][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 1.965 (1.177) Prec@1 48.75 (73.13) Prec@5 82.50 (91.18) +[2018-10-19-01:18:16] **test** Prec@1 73.13 Prec@5 91.18 Error@1 26.87 Error@5 8.82 Loss:1.177 +----> Best Accuracy : Acc@1=73.13, Acc@5=91.18, Error@1=26.87, Error@5=8.82 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-19-01:18:16] [Epoch=137/250] [Need: 167:04:22] LR=0.0015 ~ 0.0015, Batch=128 + train[2018-10-19-01:18:21] Epoch: [137][000/10010] Time 4.41 (4.41) Data 3.84 (3.84) Loss 2.658 (2.658) Prec@1 76.56 (76.56) Prec@5 96.09 (96.09) + train[2018-10-19-01:20:05] Epoch: [137][200/10010] Time 0.56 (0.54) Data 0.00 (0.02) Loss 3.134 (2.989) Prec@1 73.44 (74.36) Prec@5 89.84 (90.50) + train[2018-10-19-01:21:50] Epoch: [137][400/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.799 (2.993) Prec@1 77.34 (74.23) Prec@5 93.75 (90.47) + train[2018-10-19-01:23:34] Epoch: [137][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.177 (2.994) Prec@1 73.44 (74.20) Prec@5 89.06 (90.44) + train[2018-10-19-01:25:19] Epoch: [137][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.069 (2.998) Prec@1 71.88 (74.14) Prec@5 90.62 (90.39) + train[2018-10-19-01:27:04] Epoch: [137][1000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.715 (2.998) Prec@1 78.12 (74.10) Prec@5 93.75 (90.39) + train[2018-10-19-01:28:48] Epoch: [137][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.049 (2.998) Prec@1 71.88 (74.05) Prec@5 88.28 (90.41) + train[2018-10-19-01:30:32] Epoch: [137][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.134 (2.997) Prec@1 71.09 (74.06) Prec@5 87.50 (90.43) + train[2018-10-19-01:32:17] Epoch: [137][1600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.205 (2.999) Prec@1 69.53 (74.02) Prec@5 89.06 (90.39) + train[2018-10-19-01:34:02] Epoch: [137][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.174 (2.998) Prec@1 74.22 (74.03) Prec@5 86.72 (90.40) + train[2018-10-19-01:35:48] Epoch: [137][2000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.906 (3.000) Prec@1 78.12 (73.99) Prec@5 92.19 (90.38) + train[2018-10-19-01:37:33] Epoch: [137][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.606 (3.000) Prec@1 65.62 (74.01) Prec@5 83.59 (90.38) + train[2018-10-19-01:39:20] Epoch: [137][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.030 (2.999) Prec@1 73.44 (74.01) Prec@5 90.62 (90.38) + train[2018-10-19-01:41:07] Epoch: [137][2600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.070 (3.000) Prec@1 74.22 (73.99) Prec@5 91.41 (90.38) + train[2018-10-19-01:42:53] Epoch: [137][2800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.005 (3.001) Prec@1 71.09 (73.98) Prec@5 92.19 (90.38) + train[2018-10-19-01:44:39] Epoch: [137][3000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.970 (3.000) Prec@1 76.56 (73.99) Prec@5 91.41 (90.39) + train[2018-10-19-01:46:27] Epoch: [137][3200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.245 (3.001) Prec@1 74.22 (73.96) Prec@5 86.72 (90.38) + train[2018-10-19-01:48:13] Epoch: [137][3400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.900 (3.003) Prec@1 77.34 (73.94) Prec@5 91.41 (90.37) + train[2018-10-19-01:49:59] Epoch: [137][3600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.696 (3.003) Prec@1 78.12 (73.92) Prec@5 96.88 (90.37) + train[2018-10-19-01:51:46] Epoch: [137][3800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.077 (3.004) Prec@1 71.88 (73.91) Prec@5 89.06 (90.36) + train[2018-10-19-01:53:32] Epoch: [137][4000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.908 (3.004) Prec@1 81.25 (73.90) Prec@5 93.75 (90.34) + train[2018-10-19-01:55:17] Epoch: [137][4200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.193 (3.005) Prec@1 68.75 (73.89) Prec@5 87.50 (90.33) + train[2018-10-19-01:57:03] Epoch: [137][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.119 (3.005) Prec@1 70.31 (73.89) Prec@5 89.84 (90.34) + train[2018-10-19-01:58:47] Epoch: [137][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.342 (3.006) Prec@1 69.53 (73.88) Prec@5 85.16 (90.33) + train[2018-10-19-02:00:33] Epoch: [137][4800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.906 (3.008) Prec@1 78.12 (73.85) Prec@5 93.75 (90.30) + train[2018-10-19-02:02:18] Epoch: [137][5000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.061 (3.009) Prec@1 76.56 (73.83) Prec@5 86.72 (90.29) + train[2018-10-19-02:04:02] Epoch: [137][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.162 (3.009) Prec@1 64.84 (73.84) Prec@5 92.19 (90.30) + train[2018-10-19-02:05:47] Epoch: [137][5400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.673 (3.009) Prec@1 78.12 (73.81) Prec@5 94.53 (90.29) + train[2018-10-19-02:07:33] Epoch: [137][5600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.024 (3.010) Prec@1 77.34 (73.80) Prec@5 86.72 (90.29) + train[2018-10-19-02:09:19] Epoch: [137][5800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.242 (3.011) Prec@1 70.31 (73.79) Prec@5 90.62 (90.27) + train[2018-10-19-02:11:04] Epoch: [137][6000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.898 (3.010) Prec@1 72.66 (73.80) Prec@5 95.31 (90.28) + train[2018-10-19-02:12:50] Epoch: [137][6200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.257 (3.011) Prec@1 68.75 (73.78) Prec@5 86.72 (90.27) + train[2018-10-19-02:14:35] Epoch: [137][6400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.141 (3.012) Prec@1 70.31 (73.76) Prec@5 89.06 (90.25) + train[2018-10-19-02:16:20] Epoch: [137][6600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.998 (3.011) Prec@1 75.00 (73.77) Prec@5 91.41 (90.26) + train[2018-10-19-02:18:06] Epoch: [137][6800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.930 (3.012) Prec@1 73.44 (73.77) Prec@5 92.19 (90.25) + train[2018-10-19-02:19:51] Epoch: [137][7000/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.633 (3.012) Prec@1 76.56 (73.76) Prec@5 96.88 (90.25) + train[2018-10-19-02:21:36] Epoch: [137][7200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.041 (3.012) Prec@1 70.31 (73.76) Prec@5 92.19 (90.24) + train[2018-10-19-02:23:21] Epoch: [137][7400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.427 (3.012) Prec@1 67.19 (73.77) Prec@5 85.94 (90.23) + train[2018-10-19-02:25:07] Epoch: [137][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.901 (3.013) Prec@1 75.78 (73.75) Prec@5 92.19 (90.23) + train[2018-10-19-02:26:52] Epoch: [137][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.790 (3.013) Prec@1 75.00 (73.74) Prec@5 94.53 (90.22) + train[2018-10-19-02:28:36] Epoch: [137][8000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.355 (3.014) Prec@1 72.66 (73.73) Prec@5 86.72 (90.22) + train[2018-10-19-02:30:20] Epoch: [137][8200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.078 (3.014) Prec@1 72.66 (73.72) Prec@5 87.50 (90.22) + train[2018-10-19-02:32:05] Epoch: [137][8400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.047 (3.014) Prec@1 69.53 (73.70) Prec@5 89.84 (90.21) + train[2018-10-19-02:33:49] Epoch: [137][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.791 (3.014) Prec@1 77.34 (73.70) Prec@5 93.75 (90.21) + train[2018-10-19-02:35:33] Epoch: [137][8800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.009 (3.014) Prec@1 69.53 (73.70) Prec@5 91.41 (90.21) + train[2018-10-19-02:37:17] Epoch: [137][9000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.767 (3.014) Prec@1 76.56 (73.69) Prec@5 92.97 (90.21) + train[2018-10-19-02:39:04] Epoch: [137][9200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.163 (3.015) Prec@1 73.44 (73.69) Prec@5 87.50 (90.21) + train[2018-10-19-02:40:51] Epoch: [137][9400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.083 (3.014) Prec@1 69.53 (73.69) Prec@5 92.19 (90.22) + train[2018-10-19-02:42:38] Epoch: [137][9600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.902 (3.014) Prec@1 78.12 (73.70) Prec@5 91.41 (90.22) + train[2018-10-19-02:44:26] Epoch: [137][9800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.024 (3.015) Prec@1 73.44 (73.69) Prec@5 91.41 (90.22) + train[2018-10-19-02:46:12] Epoch: [137][10000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.855 (3.015) Prec@1 75.78 (73.69) Prec@5 90.62 (90.22) + train[2018-10-19-02:46:17] Epoch: [137][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 4.223 (3.015) Prec@1 60.00 (73.69) Prec@5 73.33 (90.22) +[2018-10-19-02:46:17] **train** Prec@1 73.69 Prec@5 90.22 Error@1 26.31 Error@5 9.78 Loss:3.015 + test [2018-10-19-02:46:21] Epoch: [137][000/391] Time 3.97 (3.97) Data 3.84 (3.84) Loss 0.493 (0.493) Prec@1 92.19 (92.19) Prec@5 99.22 (99.22) + test [2018-10-19-02:46:47] Epoch: [137][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.250 (1.019) Prec@1 67.97 (76.59) Prec@5 94.53 (93.39) + test [2018-10-19-02:47:12] Epoch: [137][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.125 (1.185) Prec@1 46.25 (73.01) Prec@5 83.75 (91.15) +[2018-10-19-02:47:12] **test** Prec@1 73.01 Prec@5 91.15 Error@1 26.99 Error@5 8.85 Loss:1.185 +----> Best Accuracy : Acc@1=73.13, Acc@5=91.18, Error@1=26.87, Error@5=8.82 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-19-02:47:12] [Epoch=138/250] [Need: 165:59:45] LR=0.0015 ~ 0.0015, Batch=128 + train[2018-10-19-02:47:17] Epoch: [138][000/10010] Time 5.34 (5.34) Data 4.74 (4.74) Loss 3.062 (3.062) Prec@1 75.00 (75.00) Prec@5 88.28 (88.28) + train[2018-10-19-02:49:01] Epoch: [138][200/10010] Time 0.52 (0.54) Data 0.00 (0.02) Loss 2.835 (3.003) Prec@1 78.12 (74.27) Prec@5 91.41 (90.12) + train[2018-10-19-02:50:46] Epoch: [138][400/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.150 (3.008) Prec@1 68.75 (74.01) Prec@5 88.28 (90.15) + train[2018-10-19-02:52:31] Epoch: [138][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.103 (3.003) Prec@1 68.75 (73.99) Prec@5 88.28 (90.21) + train[2018-10-19-02:54:16] Epoch: [138][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.833 (2.996) Prec@1 74.22 (74.17) Prec@5 94.53 (90.30) + train[2018-10-19-02:56:00] Epoch: [138][1000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.086 (2.996) Prec@1 76.56 (74.17) Prec@5 90.62 (90.33) + train[2018-10-19-02:57:45] Epoch: [138][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.087 (2.992) Prec@1 70.31 (74.24) Prec@5 89.84 (90.41) + train[2018-10-19-02:59:30] Epoch: [138][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.659 (2.995) Prec@1 80.47 (74.17) Prec@5 94.53 (90.35) + train[2018-10-19-03:01:14] Epoch: [138][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.309 (2.994) Prec@1 70.31 (74.18) Prec@5 89.06 (90.40) + train[2018-10-19-03:02:58] Epoch: [138][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.931 (2.998) Prec@1 77.34 (74.15) Prec@5 91.41 (90.36) + train[2018-10-19-03:04:42] Epoch: [138][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.641 (2.997) Prec@1 80.47 (74.11) Prec@5 92.97 (90.38) + train[2018-10-19-03:06:28] Epoch: [138][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.136 (2.997) Prec@1 68.75 (74.11) Prec@5 89.84 (90.39) + train[2018-10-19-03:08:13] Epoch: [138][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.108 (2.999) Prec@1 75.00 (74.10) Prec@5 88.28 (90.37) + train[2018-10-19-03:09:57] Epoch: [138][2600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.159 (2.998) Prec@1 70.31 (74.07) Prec@5 89.06 (90.36) + train[2018-10-19-03:11:43] Epoch: [138][2800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.020 (2.999) Prec@1 71.09 (74.05) Prec@5 89.84 (90.36) + train[2018-10-19-03:13:28] Epoch: [138][3000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.973 (2.999) Prec@1 72.66 (74.05) Prec@5 91.41 (90.36) + train[2018-10-19-03:15:12] Epoch: [138][3200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.801 (3.000) Prec@1 80.47 (74.05) Prec@5 93.75 (90.36) + train[2018-10-19-03:16:57] Epoch: [138][3400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.199 (3.000) Prec@1 71.09 (74.05) Prec@5 86.72 (90.36) + train[2018-10-19-03:18:44] Epoch: [138][3600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.856 (3.000) Prec@1 76.56 (74.06) Prec@5 92.19 (90.37) + train[2018-10-19-03:20:29] Epoch: [138][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.148 (3.000) Prec@1 76.56 (74.05) Prec@5 90.62 (90.37) + train[2018-10-19-03:22:14] Epoch: [138][4000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.020 (3.000) Prec@1 72.66 (74.06) Prec@5 89.06 (90.38) + train[2018-10-19-03:23:59] Epoch: [138][4200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.183 (3.000) Prec@1 71.09 (74.04) Prec@5 86.72 (90.37) + train[2018-10-19-03:25:45] Epoch: [138][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.100 (3.000) Prec@1 74.22 (74.03) Prec@5 86.72 (90.38) + train[2018-10-19-03:27:32] Epoch: [138][4600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.802 (3.001) Prec@1 76.56 (74.00) Prec@5 89.84 (90.37) + train[2018-10-19-03:29:19] Epoch: [138][4800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.872 (3.001) Prec@1 76.56 (73.99) Prec@5 92.19 (90.37) + train[2018-10-19-03:31:06] Epoch: [138][5000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.990 (3.000) Prec@1 75.78 (74.00) Prec@5 88.28 (90.38) + train[2018-10-19-03:32:53] Epoch: [138][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.946 (3.001) Prec@1 73.44 (74.00) Prec@5 92.97 (90.37) + train[2018-10-19-03:34:40] Epoch: [138][5400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.879 (3.001) Prec@1 75.00 (73.99) Prec@5 92.19 (90.37) + train[2018-10-19-03:36:27] Epoch: [138][5600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.082 (3.001) Prec@1 72.66 (73.99) Prec@5 88.28 (90.36) + train[2018-10-19-03:38:13] Epoch: [138][5800/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.934 (3.001) Prec@1 75.00 (73.99) Prec@5 92.19 (90.36) + train[2018-10-19-03:40:00] Epoch: [138][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.779 (3.002) Prec@1 79.69 (73.98) Prec@5 92.19 (90.35) + train[2018-10-19-03:41:46] Epoch: [138][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.424 (3.002) Prec@1 64.06 (73.97) Prec@5 85.94 (90.34) + train[2018-10-19-03:43:33] Epoch: [138][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.052 (3.003) Prec@1 72.66 (73.96) Prec@5 89.06 (90.33) + train[2018-10-19-03:45:19] Epoch: [138][6600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.971 (3.003) Prec@1 76.56 (73.95) Prec@5 89.84 (90.33) + train[2018-10-19-03:47:06] Epoch: [138][6800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.976 (3.003) Prec@1 74.22 (73.95) Prec@5 89.84 (90.33) + train[2018-10-19-03:48:52] Epoch: [138][7000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.019 (3.003) Prec@1 70.31 (73.94) Prec@5 92.19 (90.32) + train[2018-10-19-03:50:39] Epoch: [138][7200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.979 (3.004) Prec@1 74.22 (73.94) Prec@5 91.41 (90.32) + train[2018-10-19-03:52:25] Epoch: [138][7400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.732 (3.004) Prec@1 83.59 (73.93) Prec@5 91.41 (90.32) + train[2018-10-19-03:54:10] Epoch: [138][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.278 (3.004) Prec@1 67.19 (73.92) Prec@5 88.28 (90.32) + train[2018-10-19-03:55:56] Epoch: [138][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.663 (3.004) Prec@1 81.25 (73.92) Prec@5 96.09 (90.32) + train[2018-10-19-03:57:42] Epoch: [138][8000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.851 (3.005) Prec@1 78.12 (73.91) Prec@5 91.41 (90.32) + train[2018-10-19-03:59:28] Epoch: [138][8200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.067 (3.006) Prec@1 72.66 (73.89) Prec@5 91.41 (90.31) + train[2018-10-19-04:01:12] Epoch: [138][8400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.102 (3.006) Prec@1 72.66 (73.88) Prec@5 86.72 (90.31) + train[2018-10-19-04:02:57] Epoch: [138][8600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.697 (3.006) Prec@1 79.69 (73.88) Prec@5 94.53 (90.31) + train[2018-10-19-04:04:43] Epoch: [138][8800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.780 (3.006) Prec@1 75.78 (73.89) Prec@5 93.75 (90.31) + train[2018-10-19-04:06:28] Epoch: [138][9000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.204 (3.006) Prec@1 70.31 (73.87) Prec@5 88.28 (90.30) + train[2018-10-19-04:08:12] Epoch: [138][9200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.359 (3.006) Prec@1 68.75 (73.87) Prec@5 84.38 (90.30) + train[2018-10-19-04:09:58] Epoch: [138][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.176 (3.007) Prec@1 65.62 (73.86) Prec@5 89.06 (90.29) + train[2018-10-19-04:11:42] Epoch: [138][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.972 (3.007) Prec@1 75.78 (73.86) Prec@5 90.62 (90.30) + train[2018-10-19-04:13:28] Epoch: [138][9800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.796 (3.007) Prec@1 75.78 (73.85) Prec@5 92.19 (90.29) + train[2018-10-19-04:15:13] Epoch: [138][10000/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 2.738 (3.007) Prec@1 78.91 (73.84) Prec@5 92.19 (90.29) + train[2018-10-19-04:15:18] Epoch: [138][10009/10010] Time 0.18 (0.53) Data 0.00 (0.00) Loss 3.124 (3.007) Prec@1 86.67 (73.84) Prec@5 93.33 (90.29) +[2018-10-19-04:15:18] **train** Prec@1 73.84 Prec@5 90.29 Error@1 26.16 Error@5 9.71 Loss:3.007 + test [2018-10-19-04:15:22] Epoch: [138][000/391] Time 3.93 (3.93) Data 3.80 (3.80) Loss 0.585 (0.585) Prec@1 88.28 (88.28) Prec@5 98.44 (98.44) + test [2018-10-19-04:15:48] Epoch: [138][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.171 (1.004) Prec@1 68.75 (77.17) Prec@5 93.75 (93.41) + test [2018-10-19-04:16:13] Epoch: [138][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.122 (1.176) Prec@1 41.25 (73.38) Prec@5 81.25 (91.19) +[2018-10-19-04:16:13] **test** Prec@1 73.38 Prec@5 91.19 Error@1 26.62 Error@5 8.81 Loss:1.176 +----> Best Accuracy : Acc@1=73.38, Acc@5=91.19, Error@1=26.62, Error@5=8.81 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-19-04:16:13] [Epoch=139/250] [Need: 164:40:37] LR=0.0014 ~ 0.0014, Batch=128 + train[2018-10-19-04:16:18] Epoch: [139][000/10010] Time 5.08 (5.08) Data 4.48 (4.48) Loss 3.280 (3.280) Prec@1 71.88 (71.88) Prec@5 87.50 (87.50) + train[2018-10-19-04:18:03] Epoch: [139][200/10010] Time 0.55 (0.55) Data 0.00 (0.02) Loss 2.876 (2.991) Prec@1 77.34 (74.38) Prec@5 89.84 (90.54) + train[2018-10-19-04:19:48] Epoch: [139][400/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 3.098 (2.993) Prec@1 71.09 (74.18) Prec@5 89.84 (90.52) + train[2018-10-19-04:21:33] Epoch: [139][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 2.859 (2.990) Prec@1 72.66 (74.17) Prec@5 90.62 (90.52) + train[2018-10-19-04:23:18] Epoch: [139][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.818 (2.994) Prec@1 76.56 (74.07) Prec@5 92.19 (90.47) + train[2018-10-19-04:25:03] Epoch: [139][1000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.602 (2.993) Prec@1 83.59 (74.16) Prec@5 96.88 (90.49) + train[2018-10-19-04:26:50] Epoch: [139][1200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.066 (2.992) Prec@1 72.66 (74.20) Prec@5 89.84 (90.49) + train[2018-10-19-04:28:36] Epoch: [139][1400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.946 (2.992) Prec@1 73.44 (74.21) Prec@5 92.19 (90.47) + train[2018-10-19-04:30:21] Epoch: [139][1600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.883 (2.990) Prec@1 75.78 (74.28) Prec@5 91.41 (90.47) + train[2018-10-19-04:32:05] Epoch: [139][1800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.806 (2.990) Prec@1 79.69 (74.27) Prec@5 95.31 (90.48) + train[2018-10-19-04:33:50] Epoch: [139][2000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.115 (2.990) Prec@1 71.88 (74.25) Prec@5 89.84 (90.48) + train[2018-10-19-04:35:36] Epoch: [139][2200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.061 (2.990) Prec@1 74.22 (74.25) Prec@5 88.28 (90.49) + train[2018-10-19-04:37:21] Epoch: [139][2400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.052 (2.992) Prec@1 69.53 (74.20) Prec@5 90.62 (90.46) + train[2018-10-19-04:39:07] Epoch: [139][2600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.926 (2.991) Prec@1 78.91 (74.23) Prec@5 88.28 (90.48) + train[2018-10-19-04:40:54] Epoch: [139][2800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.032 (2.993) Prec@1 75.00 (74.19) Prec@5 89.84 (90.45) + train[2018-10-19-04:42:39] Epoch: [139][3000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.042 (2.994) Prec@1 73.44 (74.16) Prec@5 87.50 (90.42) + train[2018-10-19-04:44:24] Epoch: [139][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.132 (2.995) Prec@1 71.09 (74.13) Prec@5 88.28 (90.42) + train[2018-10-19-04:46:09] Epoch: [139][3400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.045 (2.995) Prec@1 76.56 (74.12) Prec@5 91.41 (90.43) + train[2018-10-19-04:47:54] Epoch: [139][3600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.175 (2.996) Prec@1 70.31 (74.09) Prec@5 87.50 (90.42) + train[2018-10-19-04:49:39] Epoch: [139][3800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.981 (2.996) Prec@1 77.34 (74.08) Prec@5 90.62 (90.40) + train[2018-10-19-04:51:24] Epoch: [139][4000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.925 (2.997) Prec@1 72.66 (74.06) Prec@5 93.75 (90.39) + train[2018-10-19-04:53:08] Epoch: [139][4200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.149 (2.997) Prec@1 72.66 (74.06) Prec@5 87.50 (90.40) + train[2018-10-19-04:54:53] Epoch: [139][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.830 (2.996) Prec@1 77.34 (74.07) Prec@5 94.53 (90.40) + train[2018-10-19-04:56:39] Epoch: [139][4600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.970 (2.997) Prec@1 74.22 (74.08) Prec@5 93.75 (90.40) + train[2018-10-19-04:58:26] Epoch: [139][4800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.130 (2.997) Prec@1 70.31 (74.07) Prec@5 89.06 (90.40) + train[2018-10-19-05:00:12] Epoch: [139][5000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.877 (2.997) Prec@1 75.78 (74.05) Prec@5 92.19 (90.40) + train[2018-10-19-05:01:58] Epoch: [139][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.705 (2.998) Prec@1 77.34 (74.04) Prec@5 95.31 (90.40) + train[2018-10-19-05:03:43] Epoch: [139][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.013 (2.998) Prec@1 71.88 (74.03) Prec@5 89.06 (90.39) + train[2018-10-19-05:05:28] Epoch: [139][5600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.133 (2.998) Prec@1 71.88 (74.02) Prec@5 87.50 (90.38) + train[2018-10-19-05:07:13] Epoch: [139][5800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.868 (2.998) Prec@1 75.78 (74.05) Prec@5 91.41 (90.40) + train[2018-10-19-05:08:58] Epoch: [139][6000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.880 (2.998) Prec@1 75.00 (74.04) Prec@5 91.41 (90.39) + train[2018-10-19-05:10:43] Epoch: [139][6200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.171 (2.999) Prec@1 72.66 (74.02) Prec@5 87.50 (90.38) + train[2018-10-19-05:12:29] Epoch: [139][6400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.082 (2.999) Prec@1 71.09 (74.01) Prec@5 89.84 (90.38) + train[2018-10-19-05:14:14] Epoch: [139][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.147 (2.999) Prec@1 72.66 (73.99) Prec@5 90.62 (90.38) + train[2018-10-19-05:15:58] Epoch: [139][6800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.120 (2.999) Prec@1 71.88 (73.98) Prec@5 87.50 (90.38) + train[2018-10-19-05:17:43] Epoch: [139][7000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.083 (3.000) Prec@1 72.66 (73.97) Prec@5 87.50 (90.37) + train[2018-10-19-05:19:27] Epoch: [139][7200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.881 (3.000) Prec@1 77.34 (73.97) Prec@5 90.62 (90.36) + train[2018-10-19-05:21:12] Epoch: [139][7400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.137 (3.000) Prec@1 71.88 (73.97) Prec@5 91.41 (90.37) + train[2018-10-19-05:22:57] Epoch: [139][7600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.144 (3.001) Prec@1 75.78 (73.96) Prec@5 89.84 (90.36) + train[2018-10-19-05:24:44] Epoch: [139][7800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.918 (3.001) Prec@1 78.91 (73.94) Prec@5 91.41 (90.35) + train[2018-10-19-05:26:32] Epoch: [139][8000/10010] Time 0.64 (0.53) Data 0.00 (0.00) Loss 3.010 (3.001) Prec@1 75.78 (73.94) Prec@5 87.50 (90.35) + train[2018-10-19-05:28:19] Epoch: [139][8200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.881 (3.001) Prec@1 73.44 (73.95) Prec@5 90.62 (90.36) + train[2018-10-19-05:30:07] Epoch: [139][8400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.941 (3.001) Prec@1 72.66 (73.95) Prec@5 92.19 (90.36) + train[2018-10-19-05:31:55] Epoch: [139][8600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.123 (3.001) Prec@1 77.34 (73.95) Prec@5 89.84 (90.35) + train[2018-10-19-05:33:42] Epoch: [139][8800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.815 (3.002) Prec@1 75.00 (73.94) Prec@5 94.53 (90.35) + train[2018-10-19-05:35:29] Epoch: [139][9000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.163 (3.002) Prec@1 69.53 (73.93) Prec@5 94.53 (90.35) + train[2018-10-19-05:37:16] Epoch: [139][9200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.097 (3.002) Prec@1 69.53 (73.92) Prec@5 91.41 (90.35) + train[2018-10-19-05:39:05] Epoch: [139][9400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.975 (3.003) Prec@1 73.44 (73.90) Prec@5 90.62 (90.34) + train[2018-10-19-05:40:52] Epoch: [139][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.832 (3.003) Prec@1 76.56 (73.90) Prec@5 90.62 (90.34) + train[2018-10-19-05:42:40] Epoch: [139][9800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.995 (3.004) Prec@1 72.66 (73.88) Prec@5 89.06 (90.33) + train[2018-10-19-05:44:29] Epoch: [139][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.153 (3.004) Prec@1 75.00 (73.88) Prec@5 89.84 (90.33) + train[2018-10-19-05:44:33] Epoch: [139][10009/10010] Time 0.21 (0.53) Data 0.00 (0.00) Loss 4.709 (3.004) Prec@1 46.67 (73.88) Prec@5 80.00 (90.33) +[2018-10-19-05:44:33] **train** Prec@1 73.88 Prec@5 90.33 Error@1 26.12 Error@5 9.67 Loss:3.004 + test [2018-10-19-05:44:37] Epoch: [139][000/391] Time 4.08 (4.08) Data 3.94 (3.94) Loss 0.553 (0.553) Prec@1 90.62 (90.62) Prec@5 98.44 (98.44) + test [2018-10-19-05:45:03] Epoch: [139][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.261 (1.015) Prec@1 67.97 (76.80) Prec@5 92.19 (93.47) + test [2018-10-19-05:45:28] Epoch: [139][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.057 (1.180) Prec@1 46.25 (73.18) Prec@5 83.75 (91.21) +[2018-10-19-05:45:28] **test** Prec@1 73.18 Prec@5 91.21 Error@1 26.82 Error@5 8.79 Loss:1.180 +----> Best Accuracy : Acc@1=73.38, Acc@5=91.19, Error@1=26.62, Error@5=8.81 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-19-05:45:28] [Epoch=140/250] [Need: 163:38:31] LR=0.0014 ~ 0.0014, Batch=128 + train[2018-10-19-05:45:34] Epoch: [140][000/10010] Time 5.25 (5.25) Data 4.62 (4.62) Loss 2.848 (2.848) Prec@1 74.22 (74.22) Prec@5 95.31 (95.31) + train[2018-10-19-05:47:18] Epoch: [140][200/10010] Time 0.54 (0.55) Data 0.00 (0.02) Loss 2.858 (3.012) Prec@1 72.66 (73.95) Prec@5 94.53 (90.26) + train[2018-10-19-05:49:03] Epoch: [140][400/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 2.744 (2.993) Prec@1 76.56 (74.06) Prec@5 95.31 (90.46) + train[2018-10-19-05:50:47] Epoch: [140][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 2.987 (2.990) Prec@1 72.66 (74.11) Prec@5 92.19 (90.50) + train[2018-10-19-05:52:32] Epoch: [140][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.913 (2.987) Prec@1 67.97 (74.22) Prec@5 95.31 (90.55) + train[2018-10-19-05:54:18] Epoch: [140][1000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.747 (2.985) Prec@1 75.78 (74.22) Prec@5 93.75 (90.57) + train[2018-10-19-05:56:03] Epoch: [140][1200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.037 (2.985) Prec@1 73.44 (74.27) Prec@5 90.62 (90.57) + train[2018-10-19-05:57:48] Epoch: [140][1400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.756 (2.987) Prec@1 75.78 (74.21) Prec@5 95.31 (90.55) + train[2018-10-19-05:59:33] Epoch: [140][1600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.195 (2.986) Prec@1 67.97 (74.23) Prec@5 89.06 (90.57) + train[2018-10-19-06:01:18] Epoch: [140][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.879 (2.988) Prec@1 75.00 (74.21) Prec@5 90.62 (90.54) + train[2018-10-19-06:03:03] Epoch: [140][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.157 (2.988) Prec@1 71.09 (74.21) Prec@5 89.84 (90.54) + train[2018-10-19-06:04:48] Epoch: [140][2200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.083 (2.988) Prec@1 70.31 (74.21) Prec@5 89.84 (90.53) + train[2018-10-19-06:06:33] Epoch: [140][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.047 (2.989) Prec@1 75.78 (74.20) Prec@5 89.84 (90.53) + train[2018-10-19-06:08:18] Epoch: [140][2600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.708 (2.989) Prec@1 79.69 (74.22) Prec@5 92.97 (90.52) + train[2018-10-19-06:10:03] Epoch: [140][2800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.824 (2.989) Prec@1 71.09 (74.20) Prec@5 92.19 (90.51) + train[2018-10-19-06:11:48] Epoch: [140][3000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.007 (2.990) Prec@1 77.34 (74.18) Prec@5 89.06 (90.51) + train[2018-10-19-06:13:34] Epoch: [140][3200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.235 (2.991) Prec@1 73.44 (74.16) Prec@5 86.72 (90.50) + train[2018-10-19-06:15:18] Epoch: [140][3400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.208 (2.991) Prec@1 72.66 (74.15) Prec@5 86.72 (90.48) + train[2018-10-19-06:17:03] Epoch: [140][3600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.954 (2.991) Prec@1 71.09 (74.15) Prec@5 91.41 (90.49) + train[2018-10-19-06:18:48] Epoch: [140][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.170 (2.991) Prec@1 71.09 (74.16) Prec@5 89.06 (90.50) + train[2018-10-19-06:20:33] Epoch: [140][4000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.286 (2.991) Prec@1 71.88 (74.14) Prec@5 87.50 (90.50) + train[2018-10-19-06:22:18] Epoch: [140][4200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.012 (2.991) Prec@1 74.22 (74.15) Prec@5 92.19 (90.50) + train[2018-10-19-06:24:03] Epoch: [140][4400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.150 (2.991) Prec@1 70.31 (74.16) Prec@5 89.06 (90.50) + train[2018-10-19-06:25:49] Epoch: [140][4600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.728 (2.992) Prec@1 77.34 (74.15) Prec@5 95.31 (90.49) + train[2018-10-19-06:27:33] Epoch: [140][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.101 (2.993) Prec@1 71.09 (74.12) Prec@5 89.06 (90.46) + train[2018-10-19-06:29:18] Epoch: [140][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.146 (2.994) Prec@1 74.22 (74.11) Prec@5 87.50 (90.46) + train[2018-10-19-06:31:03] Epoch: [140][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.811 (2.994) Prec@1 72.66 (74.11) Prec@5 93.75 (90.46) + train[2018-10-19-06:32:48] Epoch: [140][5400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.994 (2.994) Prec@1 68.75 (74.11) Prec@5 91.41 (90.44) + train[2018-10-19-06:34:32] Epoch: [140][5600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.078 (2.995) Prec@1 75.00 (74.10) Prec@5 85.94 (90.43) + train[2018-10-19-06:36:18] Epoch: [140][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.810 (2.996) Prec@1 75.78 (74.08) Prec@5 92.19 (90.43) + train[2018-10-19-06:38:03] Epoch: [140][6000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.218 (2.996) Prec@1 66.41 (74.07) Prec@5 88.28 (90.42) + train[2018-10-19-06:39:47] Epoch: [140][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.116 (2.996) Prec@1 72.66 (74.08) Prec@5 89.84 (90.42) + train[2018-10-19-06:41:31] Epoch: [140][6400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.285 (2.997) Prec@1 71.09 (74.07) Prec@5 85.94 (90.41) + train[2018-10-19-06:43:17] Epoch: [140][6600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.022 (2.997) Prec@1 71.88 (74.05) Prec@5 89.06 (90.41) + train[2018-10-19-06:45:02] Epoch: [140][6800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.377 (2.997) Prec@1 64.06 (74.05) Prec@5 83.59 (90.40) + train[2018-10-19-06:46:47] Epoch: [140][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.831 (2.997) Prec@1 76.56 (74.05) Prec@5 92.19 (90.41) + train[2018-10-19-06:48:32] Epoch: [140][7200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.166 (2.996) Prec@1 71.09 (74.06) Prec@5 89.06 (90.41) + train[2018-10-19-06:50:18] Epoch: [140][7400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.815 (2.996) Prec@1 75.78 (74.06) Prec@5 92.97 (90.41) + train[2018-10-19-06:52:03] Epoch: [140][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.151 (2.997) Prec@1 74.22 (74.06) Prec@5 86.72 (90.40) + train[2018-10-19-06:53:49] Epoch: [140][7800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.790 (2.997) Prec@1 76.56 (74.06) Prec@5 92.19 (90.40) + train[2018-10-19-06:55:34] Epoch: [140][8000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.578 (2.996) Prec@1 82.81 (74.06) Prec@5 95.31 (90.41) + train[2018-10-19-06:57:20] Epoch: [140][8200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.005 (2.997) Prec@1 75.00 (74.06) Prec@5 87.50 (90.41) + train[2018-10-19-06:59:05] Epoch: [140][8400/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.193 (2.997) Prec@1 69.53 (74.05) Prec@5 86.72 (90.41) + train[2018-10-19-07:00:52] Epoch: [140][8600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.032 (2.998) Prec@1 74.22 (74.04) Prec@5 89.84 (90.40) + train[2018-10-19-07:02:37] Epoch: [140][8800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.158 (2.998) Prec@1 67.19 (74.03) Prec@5 85.16 (90.40) + train[2018-10-19-07:04:23] Epoch: [140][9000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.584 (2.999) Prec@1 82.03 (74.02) Prec@5 96.09 (90.39) + train[2018-10-19-07:06:11] Epoch: [140][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.662 (2.999) Prec@1 80.47 (74.01) Prec@5 93.75 (90.39) + train[2018-10-19-07:07:58] Epoch: [140][9400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.008 (2.999) Prec@1 72.66 (74.01) Prec@5 89.84 (90.39) + train[2018-10-19-07:09:45] Epoch: [140][9600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.150 (2.999) Prec@1 74.22 (74.01) Prec@5 86.72 (90.38) + train[2018-10-19-07:11:32] Epoch: [140][9800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.758 (2.999) Prec@1 74.22 (74.00) Prec@5 95.31 (90.38) + train[2018-10-19-07:13:19] Epoch: [140][10000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.908 (3.000) Prec@1 75.78 (74.00) Prec@5 92.97 (90.38) + train[2018-10-19-07:13:23] Epoch: [140][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 2.364 (3.000) Prec@1 93.33 (74.00) Prec@5 100.00 (90.38) +[2018-10-19-07:13:23] **train** Prec@1 74.00 Prec@5 90.38 Error@1 26.00 Error@5 9.62 Loss:3.000 + test [2018-10-19-07:13:27] Epoch: [140][000/391] Time 3.72 (3.72) Data 3.58 (3.58) Loss 0.529 (0.529) Prec@1 91.41 (91.41) Prec@5 99.22 (99.22) + test [2018-10-19-07:13:53] Epoch: [140][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.238 (1.004) Prec@1 65.62 (76.76) Prec@5 91.41 (93.39) + test [2018-10-19-07:14:18] Epoch: [140][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.067 (1.168) Prec@1 46.25 (73.21) Prec@5 81.25 (91.23) +[2018-10-19-07:14:18] **test** Prec@1 73.21 Prec@5 91.23 Error@1 26.79 Error@5 8.77 Loss:1.168 +----> Best Accuracy : Acc@1=73.38, Acc@5=91.19, Error@1=26.62, Error@5=8.81 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-19-07:14:18] [Epoch=141/250] [Need: 161:22:09] LR=0.0014 ~ 0.0014, Batch=128 + train[2018-10-19-07:14:23] Epoch: [141][000/10010] Time 5.48 (5.48) Data 4.88 (4.88) Loss 2.829 (2.829) Prec@1 76.56 (76.56) Prec@5 93.75 (93.75) + train[2018-10-19-07:16:09] Epoch: [141][200/10010] Time 0.53 (0.55) Data 0.00 (0.02) Loss 2.951 (2.990) Prec@1 71.88 (74.14) Prec@5 89.06 (90.46) + train[2018-10-19-07:17:55] Epoch: [141][400/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.921 (2.991) Prec@1 75.78 (74.37) Prec@5 90.62 (90.48) + train[2018-10-19-07:19:40] Epoch: [141][600/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.739 (2.993) Prec@1 78.91 (74.36) Prec@5 92.97 (90.48) + train[2018-10-19-07:21:25] Epoch: [141][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.984 (2.993) Prec@1 75.78 (74.34) Prec@5 89.06 (90.45) + train[2018-10-19-07:23:10] Epoch: [141][1000/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.191 (2.996) Prec@1 70.31 (74.28) Prec@5 89.06 (90.43) + train[2018-10-19-07:24:55] Epoch: [141][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.782 (2.993) Prec@1 75.78 (74.31) Prec@5 92.97 (90.41) + train[2018-10-19-07:26:39] Epoch: [141][1400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.138 (2.991) Prec@1 71.88 (74.35) Prec@5 88.28 (90.45) + train[2018-10-19-07:28:24] Epoch: [141][1600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.034 (2.988) Prec@1 75.00 (74.39) Prec@5 89.84 (90.49) + train[2018-10-19-07:30:09] Epoch: [141][1800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.283 (2.988) Prec@1 70.31 (74.38) Prec@5 85.94 (90.50) + train[2018-10-19-07:31:54] Epoch: [141][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.983 (2.988) Prec@1 73.44 (74.36) Prec@5 91.41 (90.48) + train[2018-10-19-07:33:40] Epoch: [141][2200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.943 (2.989) Prec@1 75.78 (74.30) Prec@5 93.75 (90.49) + train[2018-10-19-07:35:25] Epoch: [141][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.985 (2.988) Prec@1 74.22 (74.30) Prec@5 92.97 (90.49) + train[2018-10-19-07:37:10] Epoch: [141][2600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.950 (2.988) Prec@1 72.66 (74.29) Prec@5 92.97 (90.48) + train[2018-10-19-07:38:57] Epoch: [141][2800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.972 (2.988) Prec@1 70.31 (74.29) Prec@5 91.41 (90.48) + train[2018-10-19-07:40:44] Epoch: [141][3000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.716 (2.990) Prec@1 79.69 (74.23) Prec@5 94.53 (90.45) + train[2018-10-19-07:42:30] Epoch: [141][3200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.196 (2.991) Prec@1 72.66 (74.23) Prec@5 85.16 (90.43) + train[2018-10-19-07:44:15] Epoch: [141][3400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.895 (2.992) Prec@1 74.22 (74.22) Prec@5 92.97 (90.43) + train[2018-10-19-07:46:00] Epoch: [141][3600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.826 (2.992) Prec@1 78.12 (74.20) Prec@5 92.19 (90.43) + train[2018-10-19-07:47:45] Epoch: [141][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.726 (2.991) Prec@1 80.47 (74.23) Prec@5 92.97 (90.43) + train[2018-10-19-07:49:29] Epoch: [141][4000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.047 (2.991) Prec@1 75.00 (74.21) Prec@5 88.28 (90.42) + train[2018-10-19-07:51:15] Epoch: [141][4200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.898 (2.992) Prec@1 78.91 (74.19) Prec@5 91.41 (90.41) + train[2018-10-19-07:53:02] Epoch: [141][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.815 (2.992) Prec@1 78.12 (74.19) Prec@5 93.75 (90.41) + train[2018-10-19-07:54:48] Epoch: [141][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.767 (2.994) Prec@1 80.47 (74.17) Prec@5 92.19 (90.39) + train[2018-10-19-07:56:35] Epoch: [141][4800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.271 (2.993) Prec@1 67.97 (74.16) Prec@5 85.94 (90.39) + train[2018-10-19-07:58:23] Epoch: [141][5000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.243 (2.993) Prec@1 71.88 (74.16) Prec@5 86.72 (90.39) + train[2018-10-19-08:00:10] Epoch: [141][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.928 (2.994) Prec@1 73.44 (74.15) Prec@5 91.41 (90.39) + train[2018-10-19-08:01:57] Epoch: [141][5400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.775 (2.994) Prec@1 78.12 (74.14) Prec@5 91.41 (90.39) + train[2018-10-19-08:03:42] Epoch: [141][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.915 (2.994) Prec@1 75.78 (74.13) Prec@5 89.84 (90.39) + train[2018-10-19-08:05:26] Epoch: [141][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.902 (2.994) Prec@1 76.56 (74.13) Prec@5 90.62 (90.38) + train[2018-10-19-08:07:12] Epoch: [141][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.012 (2.995) Prec@1 74.22 (74.12) Prec@5 89.06 (90.37) + train[2018-10-19-08:08:57] Epoch: [141][6200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.170 (2.995) Prec@1 73.44 (74.11) Prec@5 87.50 (90.37) + train[2018-10-19-08:10:41] Epoch: [141][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.223 (2.995) Prec@1 75.00 (74.11) Prec@5 86.72 (90.37) + train[2018-10-19-08:12:26] Epoch: [141][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.901 (2.996) Prec@1 67.19 (74.11) Prec@5 95.31 (90.36) + train[2018-10-19-08:14:11] Epoch: [141][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.025 (2.996) Prec@1 73.44 (74.11) Prec@5 91.41 (90.36) + train[2018-10-19-08:15:56] Epoch: [141][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.929 (2.996) Prec@1 75.78 (74.10) Prec@5 92.97 (90.35) + train[2018-10-19-08:17:40] Epoch: [141][7200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.954 (2.996) Prec@1 75.78 (74.10) Prec@5 92.19 (90.36) + train[2018-10-19-08:19:26] Epoch: [141][7400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.900 (2.996) Prec@1 75.78 (74.09) Prec@5 91.41 (90.36) + train[2018-10-19-08:21:11] Epoch: [141][7600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.400 (2.996) Prec@1 85.16 (74.09) Prec@5 99.22 (90.35) + train[2018-10-19-08:22:55] Epoch: [141][7800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.954 (2.996) Prec@1 72.66 (74.07) Prec@5 89.06 (90.35) + train[2018-10-19-08:24:41] Epoch: [141][8000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.874 (2.996) Prec@1 77.34 (74.08) Prec@5 89.84 (90.35) + train[2018-10-19-08:26:28] Epoch: [141][8200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.962 (2.996) Prec@1 77.34 (74.08) Prec@5 91.41 (90.35) + train[2018-10-19-08:28:15] Epoch: [141][8400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.973 (2.996) Prec@1 72.66 (74.07) Prec@5 92.97 (90.35) + train[2018-10-19-08:30:01] Epoch: [141][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.851 (2.996) Prec@1 75.00 (74.08) Prec@5 92.97 (90.34) + train[2018-10-19-08:31:47] Epoch: [141][8800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.137 (2.996) Prec@1 71.88 (74.07) Prec@5 90.62 (90.34) + train[2018-10-19-08:33:34] Epoch: [141][9000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.155 (2.996) Prec@1 71.09 (74.07) Prec@5 89.84 (90.35) + train[2018-10-19-08:35:20] Epoch: [141][9200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.839 (2.996) Prec@1 78.12 (74.07) Prec@5 91.41 (90.34) + train[2018-10-19-08:37:05] Epoch: [141][9400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.046 (2.996) Prec@1 67.97 (74.07) Prec@5 92.97 (90.35) + train[2018-10-19-08:38:51] Epoch: [141][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.993 (2.996) Prec@1 76.56 (74.06) Prec@5 89.06 (90.35) + train[2018-10-19-08:40:38] Epoch: [141][9800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.808 (2.996) Prec@1 78.12 (74.06) Prec@5 92.19 (90.35) + train[2018-10-19-08:42:24] Epoch: [141][10000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.036 (2.996) Prec@1 70.31 (74.05) Prec@5 91.41 (90.35) + train[2018-10-19-08:42:28] Epoch: [141][10009/10010] Time 0.21 (0.53) Data 0.00 (0.00) Loss 3.123 (2.996) Prec@1 73.33 (74.06) Prec@5 86.67 (90.35) +[2018-10-19-08:42:29] **train** Prec@1 74.06 Prec@5 90.35 Error@1 25.94 Error@5 9.65 Loss:2.996 + test [2018-10-19-08:42:32] Epoch: [141][000/391] Time 3.88 (3.88) Data 3.74 (3.74) Loss 0.611 (0.611) Prec@1 89.06 (89.06) Prec@5 98.44 (98.44) + test [2018-10-19-08:42:59] Epoch: [141][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.157 (1.027) Prec@1 66.41 (76.73) Prec@5 93.75 (93.32) + test [2018-10-19-08:43:24] Epoch: [141][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.044 (1.192) Prec@1 50.00 (73.03) Prec@5 82.50 (91.12) +[2018-10-19-08:43:24] **test** Prec@1 73.03 Prec@5 91.12 Error@1 26.97 Error@5 8.88 Loss:1.192 +----> Best Accuracy : Acc@1=73.38, Acc@5=91.19, Error@1=26.62, Error@5=8.81 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-19-08:43:24] [Epoch=142/250] [Need: 160:22:23] LR=0.0013 ~ 0.0013, Batch=128 + train[2018-10-19-08:43:29] Epoch: [142][000/10010] Time 4.92 (4.92) Data 4.37 (4.37) Loss 2.987 (2.987) Prec@1 75.00 (75.00) Prec@5 89.84 (89.84) + train[2018-10-19-08:45:14] Epoch: [142][200/10010] Time 0.55 (0.55) Data 0.00 (0.02) Loss 3.386 (2.999) Prec@1 68.75 (74.05) Prec@5 85.16 (90.37) + train[2018-10-19-08:46:58] Epoch: [142][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.951 (2.999) Prec@1 72.66 (74.21) Prec@5 92.19 (90.40) + train[2018-10-19-08:48:43] Epoch: [142][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.890 (2.986) Prec@1 75.00 (74.44) Prec@5 92.19 (90.59) + train[2018-10-19-08:50:28] Epoch: [142][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.163 (2.983) Prec@1 71.88 (74.47) Prec@5 86.72 (90.58) + train[2018-10-19-08:52:13] Epoch: [142][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.108 (2.983) Prec@1 75.00 (74.43) Prec@5 86.72 (90.55) + train[2018-10-19-08:53:58] Epoch: [142][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.819 (2.980) Prec@1 77.34 (74.49) Prec@5 92.97 (90.57) + train[2018-10-19-08:55:42] Epoch: [142][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.163 (2.983) Prec@1 71.09 (74.41) Prec@5 88.28 (90.55) + train[2018-10-19-08:57:27] Epoch: [142][1600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.062 (2.984) Prec@1 70.31 (74.39) Prec@5 87.50 (90.54) + train[2018-10-19-08:59:12] Epoch: [142][1800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.981 (2.984) Prec@1 71.88 (74.40) Prec@5 90.62 (90.53) + train[2018-10-19-09:00:58] Epoch: [142][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.705 (2.982) Prec@1 78.12 (74.44) Prec@5 96.09 (90.55) + train[2018-10-19-09:02:43] Epoch: [142][2200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.730 (2.983) Prec@1 78.91 (74.43) Prec@5 94.53 (90.53) + train[2018-10-19-09:04:29] Epoch: [142][2400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.036 (2.985) Prec@1 69.53 (74.38) Prec@5 88.28 (90.49) + train[2018-10-19-09:06:15] Epoch: [142][2600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.010 (2.985) Prec@1 77.34 (74.38) Prec@5 90.62 (90.49) + train[2018-10-19-09:07:59] Epoch: [142][2800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.796 (2.983) Prec@1 76.56 (74.41) Prec@5 91.41 (90.51) + train[2018-10-19-09:09:44] Epoch: [142][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.087 (2.984) Prec@1 75.00 (74.38) Prec@5 89.06 (90.52) + train[2018-10-19-09:11:29] Epoch: [142][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.248 (2.984) Prec@1 69.53 (74.38) Prec@5 86.72 (90.52) + train[2018-10-19-09:13:13] Epoch: [142][3400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.207 (2.985) Prec@1 77.34 (74.37) Prec@5 84.38 (90.51) + train[2018-10-19-09:14:59] Epoch: [142][3600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.454 (2.986) Prec@1 68.75 (74.34) Prec@5 82.81 (90.50) + train[2018-10-19-09:16:44] Epoch: [142][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.784 (2.986) Prec@1 79.69 (74.33) Prec@5 93.75 (90.49) + train[2018-10-19-09:18:30] Epoch: [142][4000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.995 (2.985) Prec@1 73.44 (74.35) Prec@5 90.62 (90.51) + train[2018-10-19-09:20:15] Epoch: [142][4200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.202 (2.986) Prec@1 70.31 (74.32) Prec@5 87.50 (90.50) + train[2018-10-19-09:21:59] Epoch: [142][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.834 (2.984) Prec@1 75.00 (74.34) Prec@5 94.53 (90.52) + train[2018-10-19-09:23:44] Epoch: [142][4600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.035 (2.985) Prec@1 75.00 (74.33) Prec@5 90.62 (90.51) + train[2018-10-19-09:25:29] Epoch: [142][4800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.423 (2.985) Prec@1 64.06 (74.32) Prec@5 86.72 (90.50) + train[2018-10-19-09:27:14] Epoch: [142][5000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.970 (2.985) Prec@1 71.09 (74.32) Prec@5 88.28 (90.51) + train[2018-10-19-09:28:59] Epoch: [142][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.930 (2.985) Prec@1 76.56 (74.32) Prec@5 91.41 (90.50) + train[2018-10-19-09:30:43] Epoch: [142][5400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.613 (2.985) Prec@1 82.81 (74.31) Prec@5 94.53 (90.50) + train[2018-10-19-09:32:28] Epoch: [142][5600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.055 (2.986) Prec@1 78.91 (74.30) Prec@5 87.50 (90.48) + train[2018-10-19-09:34:13] Epoch: [142][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.974 (2.987) Prec@1 75.78 (74.29) Prec@5 91.41 (90.48) + train[2018-10-19-09:35:59] Epoch: [142][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.298 (2.987) Prec@1 69.53 (74.28) Prec@5 83.59 (90.48) + train[2018-10-19-09:37:43] Epoch: [142][6200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.042 (2.989) Prec@1 75.00 (74.26) Prec@5 88.28 (90.47) + train[2018-10-19-09:39:29] Epoch: [142][6400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.034 (2.989) Prec@1 76.56 (74.26) Prec@5 89.84 (90.47) + train[2018-10-19-09:41:15] Epoch: [142][6600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.197 (2.989) Prec@1 68.75 (74.24) Prec@5 91.41 (90.46) + train[2018-10-19-09:42:59] Epoch: [142][6800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.963 (2.990) Prec@1 76.56 (74.23) Prec@5 88.28 (90.46) + train[2018-10-19-09:44:44] Epoch: [142][7000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.409 (2.990) Prec@1 66.41 (74.22) Prec@5 85.16 (90.45) + train[2018-10-19-09:46:29] Epoch: [142][7200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.116 (2.989) Prec@1 68.75 (74.24) Prec@5 89.06 (90.46) + train[2018-10-19-09:48:15] Epoch: [142][7400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.024 (2.989) Prec@1 69.53 (74.24) Prec@5 91.41 (90.47) + train[2018-10-19-09:50:00] Epoch: [142][7600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.068 (2.989) Prec@1 68.75 (74.24) Prec@5 89.84 (90.46) + train[2018-10-19-09:51:45] Epoch: [142][7800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.991 (2.990) Prec@1 73.44 (74.24) Prec@5 90.62 (90.46) + train[2018-10-19-09:53:30] Epoch: [142][8000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.027 (2.990) Prec@1 75.78 (74.23) Prec@5 89.84 (90.46) + train[2018-10-19-09:55:15] Epoch: [142][8200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.137 (2.990) Prec@1 71.88 (74.23) Prec@5 91.41 (90.46) + train[2018-10-19-09:57:00] Epoch: [142][8400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.399 (2.990) Prec@1 72.66 (74.22) Prec@5 84.38 (90.45) + train[2018-10-19-09:58:45] Epoch: [142][8600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.362 (2.990) Prec@1 63.28 (74.21) Prec@5 87.50 (90.45) + train[2018-10-19-10:00:29] Epoch: [142][8800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.559 (2.990) Prec@1 64.84 (74.21) Prec@5 84.38 (90.46) + train[2018-10-19-10:02:15] Epoch: [142][9000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.758 (2.990) Prec@1 77.34 (74.21) Prec@5 92.19 (90.46) + train[2018-10-19-10:04:00] Epoch: [142][9200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.842 (2.991) Prec@1 75.00 (74.21) Prec@5 92.97 (90.45) + train[2018-10-19-10:05:45] Epoch: [142][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.795 (2.991) Prec@1 75.00 (74.20) Prec@5 90.62 (90.45) + train[2018-10-19-10:07:30] Epoch: [142][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.929 (2.991) Prec@1 77.34 (74.19) Prec@5 89.06 (90.45) + train[2018-10-19-10:09:15] Epoch: [142][9800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.973 (2.991) Prec@1 73.44 (74.18) Prec@5 89.84 (90.44) + train[2018-10-19-10:11:01] Epoch: [142][10000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.721 (2.991) Prec@1 78.91 (74.18) Prec@5 95.31 (90.44) + train[2018-10-19-10:11:05] Epoch: [142][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 3.894 (2.991) Prec@1 66.67 (74.18) Prec@5 80.00 (90.44) +[2018-10-19-10:11:05] **train** Prec@1 74.18 Prec@5 90.44 Error@1 25.82 Error@5 9.56 Loss:2.991 + test [2018-10-19-10:11:09] Epoch: [142][000/391] Time 4.00 (4.00) Data 3.87 (3.87) Loss 0.533 (0.533) Prec@1 91.41 (91.41) Prec@5 99.22 (99.22) + test [2018-10-19-10:11:35] Epoch: [142][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.211 (1.010) Prec@1 67.97 (76.90) Prec@5 93.75 (93.42) + test [2018-10-19-10:12:00] Epoch: [142][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 1.998 (1.177) Prec@1 45.00 (73.21) Prec@5 81.25 (91.21) +[2018-10-19-10:12:00] **test** Prec@1 73.21 Prec@5 91.21 Error@1 26.79 Error@5 8.79 Loss:1.177 +----> Best Accuracy : Acc@1=73.38, Acc@5=91.19, Error@1=26.62, Error@5=8.81 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-19-10:12:00] [Epoch=143/250] [Need: 158:01:28] LR=0.0013 ~ 0.0013, Batch=128 + train[2018-10-19-10:12:05] Epoch: [143][000/10010] Time 4.39 (4.39) Data 3.77 (3.77) Loss 3.106 (3.106) Prec@1 67.19 (67.19) Prec@5 91.41 (91.41) + train[2018-10-19-10:13:50] Epoch: [143][200/10010] Time 0.51 (0.55) Data 0.00 (0.02) Loss 3.002 (3.004) Prec@1 76.56 (74.23) Prec@5 93.75 (90.10) + train[2018-10-19-10:15:35] Epoch: [143][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.983 (2.988) Prec@1 72.66 (74.50) Prec@5 92.97 (90.42) + train[2018-10-19-10:17:19] Epoch: [143][600/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.034 (2.982) Prec@1 72.66 (74.50) Prec@5 91.41 (90.51) + train[2018-10-19-10:19:05] Epoch: [143][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.226 (2.983) Prec@1 72.66 (74.42) Prec@5 89.84 (90.51) + train[2018-10-19-10:20:50] Epoch: [143][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.045 (2.981) Prec@1 69.53 (74.48) Prec@5 89.06 (90.53) + train[2018-10-19-10:22:35] Epoch: [143][1200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.513 (2.981) Prec@1 64.06 (74.45) Prec@5 83.59 (90.57) + train[2018-10-19-10:24:21] Epoch: [143][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.208 (2.982) Prec@1 71.09 (74.43) Prec@5 84.38 (90.53) + train[2018-10-19-10:26:06] Epoch: [143][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.071 (2.981) Prec@1 75.00 (74.43) Prec@5 87.50 (90.56) + train[2018-10-19-10:27:50] Epoch: [143][1800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.873 (2.980) Prec@1 78.91 (74.42) Prec@5 91.41 (90.58) + train[2018-10-19-10:29:36] Epoch: [143][2000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.736 (2.980) Prec@1 78.12 (74.40) Prec@5 93.75 (90.59) + train[2018-10-19-10:31:22] Epoch: [143][2200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.274 (2.981) Prec@1 69.53 (74.39) Prec@5 87.50 (90.59) + train[2018-10-19-10:33:07] Epoch: [143][2400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.940 (2.981) Prec@1 74.22 (74.39) Prec@5 90.62 (90.57) + train[2018-10-19-10:34:51] Epoch: [143][2600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.912 (2.983) Prec@1 76.56 (74.36) Prec@5 91.41 (90.53) + train[2018-10-19-10:36:36] Epoch: [143][2800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.072 (2.982) Prec@1 68.75 (74.38) Prec@5 89.06 (90.55) + train[2018-10-19-10:38:21] Epoch: [143][3000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.857 (2.983) Prec@1 72.66 (74.35) Prec@5 92.97 (90.53) + train[2018-10-19-10:40:07] Epoch: [143][3200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.762 (2.984) Prec@1 80.47 (74.34) Prec@5 93.75 (90.52) + train[2018-10-19-10:41:52] Epoch: [143][3400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.897 (2.983) Prec@1 76.56 (74.35) Prec@5 90.62 (90.53) + train[2018-10-19-10:43:38] Epoch: [143][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.819 (2.984) Prec@1 75.00 (74.33) Prec@5 91.41 (90.51) + train[2018-10-19-10:45:23] Epoch: [143][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.818 (2.984) Prec@1 76.56 (74.34) Prec@5 92.19 (90.52) + train[2018-10-19-10:47:09] Epoch: [143][4000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.999 (2.983) Prec@1 70.31 (74.32) Prec@5 91.41 (90.52) + train[2018-10-19-10:48:54] Epoch: [143][4200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.882 (2.985) Prec@1 73.44 (74.30) Prec@5 92.19 (90.50) + train[2018-10-19-10:50:40] Epoch: [143][4400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.077 (2.985) Prec@1 70.31 (74.30) Prec@5 88.28 (90.50) + train[2018-10-19-10:52:25] Epoch: [143][4600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.864 (2.984) Prec@1 73.44 (74.30) Prec@5 89.84 (90.50) + train[2018-10-19-10:54:10] Epoch: [143][4800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.727 (2.985) Prec@1 78.91 (74.29) Prec@5 94.53 (90.49) + train[2018-10-19-10:55:55] Epoch: [143][5000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.951 (2.984) Prec@1 71.09 (74.31) Prec@5 90.62 (90.50) + train[2018-10-19-10:57:40] Epoch: [143][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.828 (2.985) Prec@1 75.00 (74.30) Prec@5 91.41 (90.49) + train[2018-10-19-10:59:26] Epoch: [143][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.837 (2.984) Prec@1 79.69 (74.30) Prec@5 90.62 (90.50) + train[2018-10-19-11:01:10] Epoch: [143][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.103 (2.985) Prec@1 76.56 (74.29) Prec@5 90.62 (90.49) + train[2018-10-19-11:02:55] Epoch: [143][5800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.178 (2.986) Prec@1 69.53 (74.28) Prec@5 87.50 (90.48) + train[2018-10-19-11:04:40] Epoch: [143][6000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.487 (2.986) Prec@1 62.50 (74.28) Prec@5 84.38 (90.47) + train[2018-10-19-11:06:25] Epoch: [143][6200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.203 (2.986) Prec@1 69.53 (74.29) Prec@5 89.06 (90.48) + train[2018-10-19-11:08:09] Epoch: [143][6400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.040 (2.987) Prec@1 71.09 (74.27) Prec@5 92.19 (90.48) + train[2018-10-19-11:09:53] Epoch: [143][6600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.962 (2.987) Prec@1 75.00 (74.26) Prec@5 92.19 (90.47) + train[2018-10-19-11:11:39] Epoch: [143][6800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.811 (2.987) Prec@1 74.22 (74.26) Prec@5 92.19 (90.47) + train[2018-10-19-11:13:24] Epoch: [143][7000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.949 (2.988) Prec@1 74.22 (74.25) Prec@5 92.97 (90.46) + train[2018-10-19-11:15:09] Epoch: [143][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.595 (2.988) Prec@1 82.03 (74.25) Prec@5 95.31 (90.46) + train[2018-10-19-11:16:54] Epoch: [143][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.949 (2.988) Prec@1 80.47 (74.25) Prec@5 91.41 (90.47) + train[2018-10-19-11:18:39] Epoch: [143][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.061 (2.988) Prec@1 72.66 (74.25) Prec@5 90.62 (90.46) + train[2018-10-19-11:20:24] Epoch: [143][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.063 (2.988) Prec@1 71.09 (74.25) Prec@5 90.62 (90.46) + train[2018-10-19-11:22:09] Epoch: [143][8000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.046 (2.988) Prec@1 72.66 (74.24) Prec@5 92.97 (90.46) + train[2018-10-19-11:23:54] Epoch: [143][8200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.682 (2.988) Prec@1 74.22 (74.23) Prec@5 94.53 (90.46) + train[2018-10-19-11:25:39] Epoch: [143][8400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.816 (2.988) Prec@1 78.12 (74.22) Prec@5 92.19 (90.46) + train[2018-10-19-11:27:24] Epoch: [143][8600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.867 (2.989) Prec@1 71.88 (74.22) Prec@5 94.53 (90.46) + train[2018-10-19-11:29:09] Epoch: [143][8800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.811 (2.989) Prec@1 75.78 (74.21) Prec@5 92.19 (90.46) + train[2018-10-19-11:30:54] Epoch: [143][9000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.237 (2.990) Prec@1 69.53 (74.20) Prec@5 86.72 (90.44) + train[2018-10-19-11:32:38] Epoch: [143][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.811 (2.990) Prec@1 79.69 (74.21) Prec@5 92.97 (90.44) + train[2018-10-19-11:34:23] Epoch: [143][9400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.843 (2.990) Prec@1 73.44 (74.19) Prec@5 93.75 (90.44) + train[2018-10-19-11:36:07] Epoch: [143][9600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.155 (2.990) Prec@1 73.44 (74.19) Prec@5 89.06 (90.44) + train[2018-10-19-11:37:53] Epoch: [143][9800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.048 (2.990) Prec@1 76.56 (74.19) Prec@5 85.16 (90.44) + train[2018-10-19-11:39:38] Epoch: [143][10000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.795 (2.991) Prec@1 77.34 (74.19) Prec@5 89.84 (90.44) + train[2018-10-19-11:39:42] Epoch: [143][10009/10010] Time 0.18 (0.53) Data 0.00 (0.00) Loss 2.833 (2.991) Prec@1 66.67 (74.19) Prec@5 100.00 (90.44) +[2018-10-19-11:39:42] **train** Prec@1 74.19 Prec@5 90.44 Error@1 25.81 Error@5 9.56 Loss:2.991 + test [2018-10-19-11:39:46] Epoch: [143][000/391] Time 3.74 (3.74) Data 3.61 (3.61) Loss 0.622 (0.622) Prec@1 89.84 (89.84) Prec@5 97.66 (97.66) + test [2018-10-19-11:40:13] Epoch: [143][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.289 (1.018) Prec@1 65.62 (76.75) Prec@5 90.62 (93.37) + test [2018-10-19-11:40:37] Epoch: [143][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.106 (1.181) Prec@1 46.25 (73.19) Prec@5 81.25 (91.22) +[2018-10-19-11:40:37] **test** Prec@1 73.19 Prec@5 91.22 Error@1 26.81 Error@5 8.78 Loss:1.181 +----> Best Accuracy : Acc@1=73.38, Acc@5=91.19, Error@1=26.62, Error@5=8.81 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-19-11:40:37] [Epoch=144/250] [Need: 156:33:03] LR=0.0012 ~ 0.0012, Batch=128 + train[2018-10-19-11:40:42] Epoch: [144][000/10010] Time 4.69 (4.69) Data 4.07 (4.07) Loss 2.833 (2.833) Prec@1 78.12 (78.12) Prec@5 92.97 (92.97) + train[2018-10-19-11:42:27] Epoch: [144][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 3.033 (2.964) Prec@1 71.88 (74.80) Prec@5 86.72 (90.73) + train[2018-10-19-11:44:11] Epoch: [144][400/10010] Time 0.56 (0.53) Data 0.00 (0.01) Loss 2.841 (2.962) Prec@1 77.34 (74.68) Prec@5 92.19 (90.69) + train[2018-10-19-11:45:56] Epoch: [144][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.177 (2.969) Prec@1 70.31 (74.56) Prec@5 89.84 (90.60) + train[2018-10-19-11:47:41] Epoch: [144][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.843 (2.965) Prec@1 77.34 (74.75) Prec@5 92.19 (90.67) + train[2018-10-19-11:49:27] Epoch: [144][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.973 (2.968) Prec@1 74.22 (74.64) Prec@5 89.84 (90.68) + train[2018-10-19-11:51:12] Epoch: [144][1200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.652 (2.970) Prec@1 82.03 (74.64) Prec@5 92.97 (90.61) + train[2018-10-19-11:52:57] Epoch: [144][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.061 (2.974) Prec@1 68.75 (74.54) Prec@5 88.28 (90.55) + train[2018-10-19-11:54:42] Epoch: [144][1600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.898 (2.976) Prec@1 71.09 (74.48) Prec@5 92.97 (90.54) + train[2018-10-19-11:56:26] Epoch: [144][1800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.224 (2.980) Prec@1 69.53 (74.43) Prec@5 89.06 (90.52) + train[2018-10-19-11:58:12] Epoch: [144][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.852 (2.980) Prec@1 75.78 (74.50) Prec@5 92.19 (90.52) + train[2018-10-19-11:59:57] Epoch: [144][2200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.015 (2.982) Prec@1 72.66 (74.44) Prec@5 94.53 (90.51) + train[2018-10-19-12:01:42] Epoch: [144][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.196 (2.980) Prec@1 71.88 (74.45) Prec@5 88.28 (90.54) + train[2018-10-19-12:03:28] Epoch: [144][2600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.887 (2.979) Prec@1 76.56 (74.47) Prec@5 91.41 (90.55) + train[2018-10-19-12:05:13] Epoch: [144][2800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.919 (2.981) Prec@1 75.78 (74.41) Prec@5 90.62 (90.52) + train[2018-10-19-12:06:58] Epoch: [144][3000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.994 (2.980) Prec@1 72.66 (74.42) Prec@5 89.84 (90.55) + train[2018-10-19-12:08:44] Epoch: [144][3200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.074 (2.980) Prec@1 71.88 (74.44) Prec@5 89.06 (90.55) + train[2018-10-19-12:10:29] Epoch: [144][3400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.012 (2.980) Prec@1 71.88 (74.42) Prec@5 89.84 (90.55) + train[2018-10-19-12:12:15] Epoch: [144][3600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.109 (2.980) Prec@1 68.75 (74.42) Prec@5 89.06 (90.55) + train[2018-10-19-12:14:00] Epoch: [144][3800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.938 (2.980) Prec@1 75.78 (74.43) Prec@5 89.84 (90.55) + train[2018-10-19-12:15:46] Epoch: [144][4000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.014 (2.980) Prec@1 71.88 (74.43) Prec@5 91.41 (90.55) + train[2018-10-19-12:17:31] Epoch: [144][4200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.993 (2.981) Prec@1 71.09 (74.41) Prec@5 92.97 (90.53) + train[2018-10-19-12:19:16] Epoch: [144][4400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.660 (2.982) Prec@1 77.34 (74.41) Prec@5 96.09 (90.52) + train[2018-10-19-12:21:02] Epoch: [144][4600/10010] Time 0.64 (0.53) Data 0.00 (0.00) Loss 3.410 (2.982) Prec@1 68.75 (74.41) Prec@5 86.72 (90.53) + train[2018-10-19-12:22:47] Epoch: [144][4800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.824 (2.982) Prec@1 78.91 (74.40) Prec@5 92.19 (90.53) + train[2018-10-19-12:24:32] Epoch: [144][5000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.140 (2.983) Prec@1 71.88 (74.38) Prec@5 88.28 (90.52) + train[2018-10-19-12:26:18] Epoch: [144][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.362 (2.983) Prec@1 68.75 (74.39) Prec@5 85.94 (90.52) + train[2018-10-19-12:28:03] Epoch: [144][5400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.375 (2.984) Prec@1 75.00 (74.37) Prec@5 89.84 (90.52) + train[2018-10-19-12:29:48] Epoch: [144][5600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.089 (2.984) Prec@1 68.75 (74.36) Prec@5 90.62 (90.52) + train[2018-10-19-12:31:34] Epoch: [144][5800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.275 (2.984) Prec@1 71.88 (74.35) Prec@5 86.72 (90.52) + train[2018-10-19-12:33:20] Epoch: [144][6000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.835 (2.984) Prec@1 78.91 (74.34) Prec@5 93.75 (90.51) + train[2018-10-19-12:35:05] Epoch: [144][6200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.729 (2.984) Prec@1 75.00 (74.33) Prec@5 92.97 (90.51) + train[2018-10-19-12:36:52] Epoch: [144][6400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.827 (2.984) Prec@1 77.34 (74.33) Prec@5 93.75 (90.52) + train[2018-10-19-12:38:37] Epoch: [144][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.786 (2.984) Prec@1 79.69 (74.33) Prec@5 92.97 (90.52) + train[2018-10-19-12:40:22] Epoch: [144][6800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.972 (2.984) Prec@1 71.09 (74.32) Prec@5 92.19 (90.52) + train[2018-10-19-12:42:09] Epoch: [144][7000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.847 (2.985) Prec@1 75.78 (74.31) Prec@5 92.19 (90.52) + train[2018-10-19-12:43:56] Epoch: [144][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.057 (2.985) Prec@1 74.22 (74.30) Prec@5 90.62 (90.51) + train[2018-10-19-12:45:43] Epoch: [144][7400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.116 (2.985) Prec@1 71.09 (74.30) Prec@5 89.06 (90.51) + train[2018-10-19-12:47:30] Epoch: [144][7600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.960 (2.985) Prec@1 76.56 (74.31) Prec@5 91.41 (90.51) + train[2018-10-19-12:49:18] Epoch: [144][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.663 (2.985) Prec@1 78.12 (74.30) Prec@5 94.53 (90.51) + train[2018-10-19-12:51:04] Epoch: [144][8000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.038 (2.985) Prec@1 73.44 (74.31) Prec@5 89.84 (90.52) + train[2018-10-19-12:52:50] Epoch: [144][8200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.854 (2.985) Prec@1 76.56 (74.31) Prec@5 92.19 (90.51) + train[2018-10-19-12:54:37] Epoch: [144][8400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.148 (2.985) Prec@1 72.66 (74.30) Prec@5 88.28 (90.51) + train[2018-10-19-12:56:25] Epoch: [144][8600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.058 (2.986) Prec@1 72.66 (74.28) Prec@5 87.50 (90.50) + train[2018-10-19-12:58:12] Epoch: [144][8800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.239 (2.986) Prec@1 67.97 (74.29) Prec@5 87.50 (90.50) + train[2018-10-19-12:59:59] Epoch: [144][9000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.989 (2.986) Prec@1 76.56 (74.30) Prec@5 89.06 (90.50) + train[2018-10-19-13:01:46] Epoch: [144][9200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.105 (2.986) Prec@1 69.53 (74.29) Prec@5 89.06 (90.50) + train[2018-10-19-13:03:33] Epoch: [144][9400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.852 (2.986) Prec@1 75.78 (74.28) Prec@5 92.19 (90.50) + train[2018-10-19-13:05:20] Epoch: [144][9600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.042 (2.986) Prec@1 72.66 (74.28) Prec@5 88.28 (90.50) + train[2018-10-19-13:07:07] Epoch: [144][9800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.872 (2.986) Prec@1 78.12 (74.28) Prec@5 90.62 (90.50) + train[2018-10-19-13:08:54] Epoch: [144][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.909 (2.986) Prec@1 78.12 (74.27) Prec@5 93.75 (90.50) + train[2018-10-19-13:08:58] Epoch: [144][10009/10010] Time 0.21 (0.53) Data 0.00 (0.00) Loss 2.732 (2.987) Prec@1 80.00 (74.27) Prec@5 100.00 (90.50) +[2018-10-19-13:08:58] **train** Prec@1 74.27 Prec@5 90.50 Error@1 25.73 Error@5 9.50 Loss:2.987 + test [2018-10-19-13:09:02] Epoch: [144][000/391] Time 3.70 (3.70) Data 3.56 (3.56) Loss 0.565 (0.565) Prec@1 89.06 (89.06) Prec@5 97.66 (97.66) + test [2018-10-19-13:09:29] Epoch: [144][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.213 (1.023) Prec@1 68.75 (76.83) Prec@5 93.75 (93.45) + test [2018-10-19-13:09:54] Epoch: [144][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.102 (1.189) Prec@1 42.50 (73.22) Prec@5 81.25 (91.24) +[2018-10-19-13:09:54] **test** Prec@1 73.22 Prec@5 91.24 Error@1 26.78 Error@5 8.76 Loss:1.189 +----> Best Accuracy : Acc@1=73.38, Acc@5=91.19, Error@1=26.62, Error@5=8.81 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-19-13:09:54] [Epoch=145/250] [Need: 156:15:11] LR=0.0012 ~ 0.0012, Batch=128 + train[2018-10-19-13:10:00] Epoch: [145][000/10010] Time 5.10 (5.10) Data 4.46 (4.46) Loss 3.014 (3.014) Prec@1 75.00 (75.00) Prec@5 92.19 (92.19) + train[2018-10-19-13:11:45] Epoch: [145][200/10010] Time 0.52 (0.55) Data 0.00 (0.02) Loss 3.355 (2.974) Prec@1 67.97 (74.55) Prec@5 84.38 (90.62) + train[2018-10-19-13:13:29] Epoch: [145][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.955 (2.977) Prec@1 74.22 (74.53) Prec@5 92.97 (90.62) + train[2018-10-19-13:15:15] Epoch: [145][600/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.271 (2.973) Prec@1 70.31 (74.64) Prec@5 85.16 (90.63) + train[2018-10-19-13:17:00] Epoch: [145][800/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 2.869 (2.971) Prec@1 78.12 (74.62) Prec@5 89.84 (90.70) + train[2018-10-19-13:18:45] Epoch: [145][1000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.817 (2.967) Prec@1 77.34 (74.63) Prec@5 93.75 (90.77) + train[2018-10-19-13:20:30] Epoch: [145][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.802 (2.967) Prec@1 74.22 (74.64) Prec@5 91.41 (90.75) + train[2018-10-19-13:22:15] Epoch: [145][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.610 (2.968) Prec@1 83.59 (74.68) Prec@5 96.09 (90.76) + train[2018-10-19-13:24:01] Epoch: [145][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.247 (2.969) Prec@1 67.19 (74.65) Prec@5 88.28 (90.77) + train[2018-10-19-13:25:46] Epoch: [145][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.901 (2.969) Prec@1 76.56 (74.65) Prec@5 92.97 (90.75) + train[2018-10-19-13:27:32] Epoch: [145][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.945 (2.968) Prec@1 77.34 (74.66) Prec@5 91.41 (90.76) + train[2018-10-19-13:29:17] Epoch: [145][2200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.770 (2.969) Prec@1 77.34 (74.66) Prec@5 90.62 (90.74) + train[2018-10-19-13:31:03] Epoch: [145][2400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.925 (2.970) Prec@1 72.66 (74.62) Prec@5 93.75 (90.74) + train[2018-10-19-13:32:48] Epoch: [145][2600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.617 (2.969) Prec@1 78.91 (74.62) Prec@5 95.31 (90.76) + train[2018-10-19-13:34:33] Epoch: [145][2800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.214 (2.970) Prec@1 69.53 (74.60) Prec@5 88.28 (90.74) + train[2018-10-19-13:36:20] Epoch: [145][3000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.859 (2.970) Prec@1 75.78 (74.59) Prec@5 92.19 (90.72) + train[2018-10-19-13:38:06] Epoch: [145][3200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.104 (2.971) Prec@1 78.12 (74.56) Prec@5 85.94 (90.70) + train[2018-10-19-13:39:52] Epoch: [145][3400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.007 (2.972) Prec@1 73.44 (74.54) Prec@5 89.06 (90.69) + train[2018-10-19-13:41:36] Epoch: [145][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.833 (2.972) Prec@1 75.00 (74.55) Prec@5 92.19 (90.69) + train[2018-10-19-13:43:22] Epoch: [145][3800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.128 (2.974) Prec@1 73.44 (74.54) Prec@5 88.28 (90.67) + train[2018-10-19-13:45:09] Epoch: [145][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.050 (2.973) Prec@1 69.53 (74.56) Prec@5 87.50 (90.66) + train[2018-10-19-13:46:57] Epoch: [145][4200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.107 (2.975) Prec@1 71.88 (74.53) Prec@5 91.41 (90.65) + train[2018-10-19-13:48:42] Epoch: [145][4400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.922 (2.974) Prec@1 75.00 (74.53) Prec@5 90.62 (90.65) + train[2018-10-19-13:50:29] Epoch: [145][4600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.936 (2.974) Prec@1 75.00 (74.55) Prec@5 90.62 (90.65) + train[2018-10-19-13:52:14] Epoch: [145][4800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.419 (2.974) Prec@1 70.31 (74.54) Prec@5 85.94 (90.65) + train[2018-10-19-13:53:59] Epoch: [145][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.039 (2.975) Prec@1 72.66 (74.51) Prec@5 87.50 (90.64) + train[2018-10-19-13:55:45] Epoch: [145][5200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.004 (2.976) Prec@1 73.44 (74.50) Prec@5 94.53 (90.64) + train[2018-10-19-13:57:31] Epoch: [145][5400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.970 (2.976) Prec@1 74.22 (74.50) Prec@5 91.41 (90.63) + train[2018-10-19-13:59:17] Epoch: [145][5600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.067 (2.976) Prec@1 74.22 (74.50) Prec@5 90.62 (90.62) + train[2018-10-19-14:01:02] Epoch: [145][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.705 (2.976) Prec@1 77.34 (74.49) Prec@5 92.97 (90.62) + train[2018-10-19-14:02:48] Epoch: [145][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.026 (2.977) Prec@1 76.56 (74.48) Prec@5 89.84 (90.61) + train[2018-10-19-14:04:33] Epoch: [145][6200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.121 (2.977) Prec@1 73.44 (74.47) Prec@5 88.28 (90.60) + train[2018-10-19-14:06:19] Epoch: [145][6400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.923 (2.977) Prec@1 75.78 (74.47) Prec@5 89.84 (90.60) + train[2018-10-19-14:08:04] Epoch: [145][6600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.721 (2.977) Prec@1 78.91 (74.47) Prec@5 96.09 (90.60) + train[2018-10-19-14:09:49] Epoch: [145][6800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.996 (2.977) Prec@1 71.09 (74.48) Prec@5 89.06 (90.61) + train[2018-10-19-14:11:34] Epoch: [145][7000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.925 (2.977) Prec@1 75.00 (74.47) Prec@5 92.19 (90.60) + train[2018-10-19-14:13:20] Epoch: [145][7200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.758 (2.978) Prec@1 78.12 (74.47) Prec@5 94.53 (90.60) + train[2018-10-19-14:15:07] Epoch: [145][7400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.800 (2.978) Prec@1 73.44 (74.46) Prec@5 93.75 (90.60) + train[2018-10-19-14:16:54] Epoch: [145][7600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.027 (2.978) Prec@1 76.56 (74.46) Prec@5 87.50 (90.60) + train[2018-10-19-14:18:40] Epoch: [145][7800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.834 (2.978) Prec@1 74.22 (74.46) Prec@5 91.41 (90.59) + train[2018-10-19-14:20:27] Epoch: [145][8000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.672 (2.978) Prec@1 59.38 (74.46) Prec@5 82.03 (90.60) + train[2018-10-19-14:22:13] Epoch: [145][8200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.297 (2.978) Prec@1 70.31 (74.45) Prec@5 89.06 (90.59) + train[2018-10-19-14:24:00] Epoch: [145][8400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.077 (2.978) Prec@1 72.66 (74.44) Prec@5 90.62 (90.58) + train[2018-10-19-14:25:46] Epoch: [145][8600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.916 (2.979) Prec@1 75.78 (74.44) Prec@5 92.19 (90.58) + train[2018-10-19-14:27:30] Epoch: [145][8800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.068 (2.979) Prec@1 75.78 (74.43) Prec@5 85.94 (90.57) + train[2018-10-19-14:29:15] Epoch: [145][9000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.984 (2.979) Prec@1 70.31 (74.42) Prec@5 89.06 (90.58) + train[2018-10-19-14:31:01] Epoch: [145][9200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.129 (2.980) Prec@1 74.22 (74.42) Prec@5 88.28 (90.57) + train[2018-10-19-14:32:47] Epoch: [145][9400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.618 (2.980) Prec@1 77.34 (74.41) Prec@5 94.53 (90.57) + train[2018-10-19-14:34:32] Epoch: [145][9600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.876 (2.980) Prec@1 75.78 (74.41) Prec@5 89.84 (90.56) + train[2018-10-19-14:36:17] Epoch: [145][9800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.318 (2.980) Prec@1 63.28 (74.42) Prec@5 89.06 (90.56) + train[2018-10-19-14:38:02] Epoch: [145][10000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.852 (2.980) Prec@1 75.00 (74.42) Prec@5 92.97 (90.56) + train[2018-10-19-14:38:07] Epoch: [145][10009/10010] Time 0.21 (0.53) Data 0.00 (0.00) Loss 3.935 (2.980) Prec@1 60.00 (74.42) Prec@5 73.33 (90.56) +[2018-10-19-14:38:07] **train** Prec@1 74.42 Prec@5 90.56 Error@1 25.58 Error@5 9.44 Loss:2.980 + test [2018-10-19-14:38:11] Epoch: [145][000/391] Time 4.28 (4.28) Data 4.15 (4.15) Loss 0.602 (0.602) Prec@1 89.06 (89.06) Prec@5 97.66 (97.66) + test [2018-10-19-14:38:38] Epoch: [145][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.250 (1.014) Prec@1 67.19 (76.89) Prec@5 92.19 (93.44) + test [2018-10-19-14:39:02] Epoch: [145][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.109 (1.176) Prec@1 46.25 (73.42) Prec@5 81.25 (91.21) +[2018-10-19-14:39:02] **test** Prec@1 73.42 Prec@5 91.21 Error@1 26.58 Error@5 8.79 Loss:1.176 +----> Best Accuracy : Acc@1=73.42, Acc@5=91.21, Error@1=26.58, Error@5=8.79 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-19-14:39:02] [Epoch=146/250] [Need: 154:29:41] LR=0.0012 ~ 0.0012, Batch=128 + train[2018-10-19-14:39:08] Epoch: [146][000/10010] Time 5.67 (5.67) Data 5.10 (5.10) Loss 3.145 (3.145) Prec@1 75.78 (75.78) Prec@5 89.06 (89.06) + train[2018-10-19-14:40:54] Epoch: [146][200/10010] Time 0.50 (0.55) Data 0.00 (0.03) Loss 2.904 (2.958) Prec@1 75.00 (75.05) Prec@5 92.97 (90.78) + train[2018-10-19-14:42:39] Epoch: [146][400/10010] Time 0.56 (0.54) Data 0.00 (0.01) Loss 3.084 (2.968) Prec@1 75.00 (74.60) Prec@5 89.84 (90.62) + train[2018-10-19-14:44:24] Epoch: [146][600/10010] Time 0.56 (0.53) Data 0.00 (0.01) Loss 2.765 (2.969) Prec@1 76.56 (74.58) Prec@5 92.19 (90.61) + train[2018-10-19-14:46:10] Epoch: [146][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.993 (2.973) Prec@1 74.22 (74.53) Prec@5 92.19 (90.60) + train[2018-10-19-14:47:55] Epoch: [146][1000/10010] Time 0.57 (0.53) Data 0.00 (0.01) Loss 2.820 (2.970) Prec@1 75.78 (74.60) Prec@5 92.19 (90.64) + train[2018-10-19-14:49:40] Epoch: [146][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.927 (2.972) Prec@1 75.78 (74.60) Prec@5 93.75 (90.63) + train[2018-10-19-14:51:25] Epoch: [146][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.980 (2.974) Prec@1 70.31 (74.56) Prec@5 88.28 (90.58) + train[2018-10-19-14:53:10] Epoch: [146][1600/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 3.149 (2.977) Prec@1 71.88 (74.51) Prec@5 87.50 (90.57) + train[2018-10-19-14:54:55] Epoch: [146][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.757 (2.979) Prec@1 76.56 (74.48) Prec@5 92.97 (90.55) + train[2018-10-19-14:56:41] Epoch: [146][2000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.809 (2.978) Prec@1 78.91 (74.50) Prec@5 92.19 (90.55) + train[2018-10-19-14:58:27] Epoch: [146][2200/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.766 (2.977) Prec@1 80.47 (74.50) Prec@5 92.97 (90.59) + train[2018-10-19-15:00:12] Epoch: [146][2400/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 3.093 (2.978) Prec@1 71.09 (74.46) Prec@5 91.41 (90.57) + train[2018-10-19-15:01:59] Epoch: [146][2600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.804 (2.978) Prec@1 78.12 (74.48) Prec@5 91.41 (90.56) + train[2018-10-19-15:03:44] Epoch: [146][2800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.048 (2.978) Prec@1 71.88 (74.48) Prec@5 92.19 (90.56) + train[2018-10-19-15:05:30] Epoch: [146][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.843 (2.978) Prec@1 77.34 (74.51) Prec@5 89.06 (90.56) + train[2018-10-19-15:07:14] Epoch: [146][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.976 (2.978) Prec@1 75.00 (74.50) Prec@5 90.62 (90.56) + train[2018-10-19-15:09:00] Epoch: [146][3400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.727 (2.978) Prec@1 75.00 (74.49) Prec@5 92.97 (90.56) + train[2018-10-19-15:10:45] Epoch: [146][3600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.738 (2.978) Prec@1 76.56 (74.48) Prec@5 92.19 (90.57) + train[2018-10-19-15:12:30] Epoch: [146][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.023 (2.978) Prec@1 74.22 (74.47) Prec@5 90.62 (90.57) + train[2018-10-19-15:14:15] Epoch: [146][4000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.947 (2.978) Prec@1 74.22 (74.47) Prec@5 91.41 (90.57) + train[2018-10-19-15:16:00] Epoch: [146][4200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.800 (2.978) Prec@1 78.91 (74.46) Prec@5 93.75 (90.58) + train[2018-10-19-15:17:46] Epoch: [146][4400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.696 (2.978) Prec@1 77.34 (74.47) Prec@5 92.97 (90.58) + train[2018-10-19-15:19:32] Epoch: [146][4600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.862 (2.979) Prec@1 73.44 (74.46) Prec@5 92.97 (90.57) + train[2018-10-19-15:21:18] Epoch: [146][4800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.046 (2.979) Prec@1 72.66 (74.45) Prec@5 90.62 (90.56) + train[2018-10-19-15:23:04] Epoch: [146][5000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.562 (2.979) Prec@1 82.03 (74.47) Prec@5 94.53 (90.57) + train[2018-10-19-15:24:49] Epoch: [146][5200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.993 (2.979) Prec@1 71.88 (74.45) Prec@5 89.06 (90.56) + train[2018-10-19-15:26:34] Epoch: [146][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.859 (2.979) Prec@1 77.34 (74.45) Prec@5 89.84 (90.57) + train[2018-10-19-15:28:19] Epoch: [146][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.055 (2.979) Prec@1 75.00 (74.46) Prec@5 88.28 (90.57) + train[2018-10-19-15:30:04] Epoch: [146][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.115 (2.979) Prec@1 71.09 (74.47) Prec@5 89.06 (90.56) + train[2018-10-19-15:31:48] Epoch: [146][6000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.024 (2.980) Prec@1 76.56 (74.45) Prec@5 92.97 (90.55) + train[2018-10-19-15:33:33] Epoch: [146][6200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.102 (2.980) Prec@1 74.22 (74.45) Prec@5 85.94 (90.56) + train[2018-10-19-15:35:18] Epoch: [146][6400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.096 (2.980) Prec@1 67.97 (74.44) Prec@5 89.84 (90.55) + train[2018-10-19-15:37:03] Epoch: [146][6600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.824 (2.980) Prec@1 78.91 (74.43) Prec@5 91.41 (90.55) + train[2018-10-19-15:38:48] Epoch: [146][6800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.109 (2.980) Prec@1 71.09 (74.43) Prec@5 90.62 (90.55) + train[2018-10-19-15:40:33] Epoch: [146][7000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.840 (2.980) Prec@1 78.12 (74.44) Prec@5 91.41 (90.55) + train[2018-10-19-15:42:18] Epoch: [146][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.845 (2.980) Prec@1 73.44 (74.44) Prec@5 92.97 (90.56) + train[2018-10-19-15:44:03] Epoch: [146][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.973 (2.980) Prec@1 69.53 (74.45) Prec@5 89.06 (90.56) + train[2018-10-19-15:45:48] Epoch: [146][7600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.315 (2.980) Prec@1 67.97 (74.45) Prec@5 87.50 (90.55) + train[2018-10-19-15:47:34] Epoch: [146][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.765 (2.980) Prec@1 76.56 (74.44) Prec@5 94.53 (90.55) + train[2018-10-19-15:49:18] Epoch: [146][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.699 (2.980) Prec@1 79.69 (74.44) Prec@5 94.53 (90.55) + train[2018-10-19-15:51:03] Epoch: [146][8200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.892 (2.980) Prec@1 74.22 (74.44) Prec@5 92.97 (90.55) + train[2018-10-19-15:52:49] Epoch: [146][8400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.795 (2.980) Prec@1 74.22 (74.43) Prec@5 92.97 (90.55) + train[2018-10-19-15:54:35] Epoch: [146][8600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.088 (2.981) Prec@1 75.78 (74.42) Prec@5 88.28 (90.54) + train[2018-10-19-15:56:22] Epoch: [146][8800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.364 (2.981) Prec@1 66.41 (74.43) Prec@5 85.16 (90.55) + train[2018-10-19-15:58:07] Epoch: [146][9000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.376 (2.980) Prec@1 68.75 (74.44) Prec@5 85.16 (90.55) + train[2018-10-19-15:59:53] Epoch: [146][9200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.919 (2.980) Prec@1 76.56 (74.44) Prec@5 89.06 (90.55) + train[2018-10-19-16:01:38] Epoch: [146][9400/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.855 (2.981) Prec@1 73.44 (74.44) Prec@5 90.62 (90.54) + train[2018-10-19-16:03:24] Epoch: [146][9600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.676 (2.981) Prec@1 80.47 (74.44) Prec@5 92.19 (90.54) + train[2018-10-19-16:05:10] Epoch: [146][9800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.487 (2.981) Prec@1 65.62 (74.43) Prec@5 83.59 (90.53) + train[2018-10-19-16:06:55] Epoch: [146][10000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.966 (2.981) Prec@1 71.09 (74.42) Prec@5 89.84 (90.53) + train[2018-10-19-16:07:00] Epoch: [146][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 4.068 (2.981) Prec@1 60.00 (74.42) Prec@5 73.33 (90.53) +[2018-10-19-16:07:00] **train** Prec@1 74.42 Prec@5 90.53 Error@1 25.58 Error@5 9.47 Loss:2.981 + test [2018-10-19-16:07:04] Epoch: [146][000/391] Time 4.08 (4.08) Data 3.94 (3.94) Loss 0.556 (0.556) Prec@1 91.41 (91.41) Prec@5 99.22 (99.22) + test [2018-10-19-16:07:31] Epoch: [146][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.147 (1.012) Prec@1 67.97 (76.82) Prec@5 92.97 (93.40) + test [2018-10-19-16:07:55] Epoch: [146][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.081 (1.180) Prec@1 47.50 (73.19) Prec@5 82.50 (91.14) +[2018-10-19-16:07:55] **test** Prec@1 73.19 Prec@5 91.14 Error@1 26.81 Error@5 8.86 Loss:1.180 +----> Best Accuracy : Acc@1=73.42, Acc@5=91.21, Error@1=26.58, Error@5=8.79 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-19-16:07:56] [Epoch=147/250] [Need: 152:35:17] LR=0.0011 ~ 0.0011, Batch=128 + train[2018-10-19-16:08:01] Epoch: [147][000/10010] Time 5.07 (5.07) Data 4.47 (4.47) Loss 2.813 (2.813) Prec@1 76.56 (76.56) Prec@5 92.19 (92.19) + train[2018-10-19-16:09:46] Epoch: [147][200/10010] Time 0.52 (0.55) Data 0.00 (0.02) Loss 3.381 (2.976) Prec@1 70.31 (74.60) Prec@5 82.81 (90.55) + train[2018-10-19-16:11:32] Epoch: [147][400/10010] Time 0.54 (0.54) Data 0.00 (0.01) Loss 3.019 (2.975) Prec@1 78.12 (74.60) Prec@5 88.28 (90.59) + train[2018-10-19-16:13:16] Epoch: [147][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 2.908 (2.967) Prec@1 71.09 (74.71) Prec@5 92.19 (90.72) + train[2018-10-19-16:15:02] Epoch: [147][800/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.041 (2.971) Prec@1 73.44 (74.58) Prec@5 91.41 (90.68) + train[2018-10-19-16:16:47] Epoch: [147][1000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.765 (2.970) Prec@1 80.47 (74.59) Prec@5 92.97 (90.71) + train[2018-10-19-16:18:32] Epoch: [147][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.949 (2.972) Prec@1 75.78 (74.56) Prec@5 89.84 (90.68) + train[2018-10-19-16:20:18] Epoch: [147][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.138 (2.972) Prec@1 77.34 (74.59) Prec@5 85.16 (90.67) + train[2018-10-19-16:22:03] Epoch: [147][1600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.694 (2.969) Prec@1 77.34 (74.62) Prec@5 94.53 (90.71) + train[2018-10-19-16:23:48] Epoch: [147][1800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.703 (2.972) Prec@1 78.12 (74.57) Prec@5 91.41 (90.66) + train[2018-10-19-16:25:33] Epoch: [147][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.685 (2.971) Prec@1 76.56 (74.60) Prec@5 94.53 (90.68) + train[2018-10-19-16:27:19] Epoch: [147][2200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.686 (2.970) Prec@1 78.12 (74.63) Prec@5 96.09 (90.69) + train[2018-10-19-16:29:06] Epoch: [147][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.813 (2.968) Prec@1 78.12 (74.65) Prec@5 92.19 (90.71) + train[2018-10-19-16:30:52] Epoch: [147][2600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.806 (2.969) Prec@1 77.34 (74.65) Prec@5 92.97 (90.73) + train[2018-10-19-16:32:38] Epoch: [147][2800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.038 (2.968) Prec@1 69.53 (74.66) Prec@5 90.62 (90.73) + train[2018-10-19-16:34:24] Epoch: [147][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.038 (2.968) Prec@1 74.22 (74.66) Prec@5 89.84 (90.73) + train[2018-10-19-16:36:11] Epoch: [147][3200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.004 (2.968) Prec@1 77.34 (74.64) Prec@5 89.84 (90.72) + train[2018-10-19-16:37:57] Epoch: [147][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.905 (2.968) Prec@1 72.66 (74.63) Prec@5 89.84 (90.72) + train[2018-10-19-16:39:44] Epoch: [147][3600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.843 (2.967) Prec@1 77.34 (74.63) Prec@5 92.97 (90.73) + train[2018-10-19-16:41:30] Epoch: [147][3800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.184 (2.967) Prec@1 71.09 (74.63) Prec@5 89.06 (90.73) + train[2018-10-19-16:43:17] Epoch: [147][4000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.685 (2.967) Prec@1 84.38 (74.63) Prec@5 92.19 (90.72) + train[2018-10-19-16:45:02] Epoch: [147][4200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.018 (2.968) Prec@1 75.78 (74.62) Prec@5 89.84 (90.71) + train[2018-10-19-16:46:50] Epoch: [147][4400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.978 (2.968) Prec@1 71.88 (74.62) Prec@5 95.31 (90.72) + train[2018-10-19-16:48:37] Epoch: [147][4600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.856 (2.968) Prec@1 78.91 (74.64) Prec@5 92.97 (90.71) + train[2018-10-19-16:50:23] Epoch: [147][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.949 (2.968) Prec@1 74.22 (74.65) Prec@5 89.84 (90.71) + train[2018-10-19-16:52:10] Epoch: [147][5000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.055 (2.968) Prec@1 70.31 (74.63) Prec@5 94.53 (90.71) + train[2018-10-19-16:53:57] Epoch: [147][5200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.929 (2.968) Prec@1 73.44 (74.63) Prec@5 92.19 (90.71) + train[2018-10-19-16:55:42] Epoch: [147][5400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.752 (2.969) Prec@1 77.34 (74.63) Prec@5 94.53 (90.70) + train[2018-10-19-16:57:28] Epoch: [147][5600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.691 (2.969) Prec@1 75.00 (74.62) Prec@5 93.75 (90.70) + train[2018-10-19-16:59:15] Epoch: [147][5800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.091 (2.969) Prec@1 70.31 (74.61) Prec@5 87.50 (90.70) + train[2018-10-19-17:01:03] Epoch: [147][6000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.948 (2.970) Prec@1 79.69 (74.60) Prec@5 89.84 (90.69) + train[2018-10-19-17:02:50] Epoch: [147][6200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.234 (2.970) Prec@1 72.66 (74.59) Prec@5 88.28 (90.69) + train[2018-10-19-17:04:37] Epoch: [147][6400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.021 (2.971) Prec@1 77.34 (74.59) Prec@5 89.06 (90.68) + train[2018-10-19-17:06:23] Epoch: [147][6600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.679 (2.971) Prec@1 80.47 (74.58) Prec@5 95.31 (90.67) + train[2018-10-19-17:08:11] Epoch: [147][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.056 (2.971) Prec@1 71.88 (74.58) Prec@5 89.06 (90.68) + train[2018-10-19-17:09:57] Epoch: [147][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.666 (2.971) Prec@1 78.12 (74.58) Prec@5 96.88 (90.68) + train[2018-10-19-17:11:43] Epoch: [147][7200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.942 (2.971) Prec@1 72.66 (74.56) Prec@5 95.31 (90.67) + train[2018-10-19-17:13:29] Epoch: [147][7400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.785 (2.971) Prec@1 72.66 (74.56) Prec@5 93.75 (90.68) + train[2018-10-19-17:15:16] Epoch: [147][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.759 (2.971) Prec@1 77.34 (74.57) Prec@5 96.09 (90.67) + train[2018-10-19-17:17:02] Epoch: [147][7800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.317 (2.971) Prec@1 70.31 (74.57) Prec@5 85.94 (90.67) + train[2018-10-19-17:18:49] Epoch: [147][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.897 (2.972) Prec@1 73.44 (74.56) Prec@5 93.75 (90.66) + train[2018-10-19-17:20:36] Epoch: [147][8200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.939 (2.972) Prec@1 75.78 (74.56) Prec@5 91.41 (90.66) + train[2018-10-19-17:22:22] Epoch: [147][8400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.926 (2.972) Prec@1 74.22 (74.55) Prec@5 92.97 (90.65) + train[2018-10-19-17:24:08] Epoch: [147][8600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.040 (2.973) Prec@1 73.44 (74.54) Prec@5 89.84 (90.65) + train[2018-10-19-17:25:54] Epoch: [147][8800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.735 (2.973) Prec@1 78.12 (74.54) Prec@5 92.19 (90.65) + train[2018-10-19-17:27:42] Epoch: [147][9000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.919 (2.974) Prec@1 77.34 (74.51) Prec@5 92.19 (90.63) + train[2018-10-19-17:29:28] Epoch: [147][9200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.192 (2.975) Prec@1 70.31 (74.51) Prec@5 89.06 (90.63) + train[2018-10-19-17:31:15] Epoch: [147][9400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.979 (2.975) Prec@1 75.78 (74.50) Prec@5 90.62 (90.63) + train[2018-10-19-17:33:01] Epoch: [147][9600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.600 (2.974) Prec@1 82.03 (74.51) Prec@5 93.75 (90.63) + train[2018-10-19-17:34:48] Epoch: [147][9800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.923 (2.974) Prec@1 76.56 (74.50) Prec@5 89.84 (90.63) + train[2018-10-19-17:36:35] Epoch: [147][10000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.870 (2.974) Prec@1 77.34 (74.51) Prec@5 89.84 (90.63) + train[2018-10-19-17:36:40] Epoch: [147][10009/10010] Time 0.28 (0.53) Data 0.00 (0.00) Loss 2.805 (2.974) Prec@1 86.67 (74.51) Prec@5 100.00 (90.63) +[2018-10-19-17:36:40] **train** Prec@1 74.51 Prec@5 90.63 Error@1 25.49 Error@5 9.37 Loss:2.974 + test [2018-10-19-17:36:43] Epoch: [147][000/391] Time 3.31 (3.31) Data 3.18 (3.18) Loss 0.624 (0.624) Prec@1 89.84 (89.84) Prec@5 98.44 (98.44) + test [2018-10-19-17:37:10] Epoch: [147][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.276 (1.023) Prec@1 67.19 (76.97) Prec@5 93.75 (93.41) + test [2018-10-19-17:37:35] Epoch: [147][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 1.910 (1.188) Prec@1 48.75 (73.31) Prec@5 85.00 (91.10) +[2018-10-19-17:37:35] **test** Prec@1 73.31 Prec@5 91.10 Error@1 26.69 Error@5 8.90 Loss:1.188 +----> Best Accuracy : Acc@1=73.42, Acc@5=91.21, Error@1=26.58, Error@5=8.79 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-19-17:37:35] [Epoch=148/250] [Need: 152:24:38] LR=0.0011 ~ 0.0011, Batch=128 + train[2018-10-19-17:37:39] Epoch: [148][000/10010] Time 4.20 (4.20) Data 3.60 (3.60) Loss 2.863 (2.863) Prec@1 75.00 (75.00) Prec@5 89.06 (89.06) + train[2018-10-19-17:39:25] Epoch: [148][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 2.956 (2.969) Prec@1 72.66 (74.56) Prec@5 92.97 (90.70) + train[2018-10-19-17:41:09] Epoch: [148][400/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.905 (2.972) Prec@1 75.00 (74.64) Prec@5 92.97 (90.66) + train[2018-10-19-17:42:55] Epoch: [148][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 2.777 (2.968) Prec@1 78.91 (74.54) Prec@5 92.19 (90.71) + train[2018-10-19-17:44:40] Epoch: [148][800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.904 (2.965) Prec@1 75.78 (74.64) Prec@5 92.19 (90.76) + train[2018-10-19-17:46:25] Epoch: [148][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.846 (2.970) Prec@1 74.22 (74.57) Prec@5 91.41 (90.70) + train[2018-10-19-17:48:09] Epoch: [148][1200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.879 (2.966) Prec@1 77.34 (74.65) Prec@5 92.19 (90.74) + train[2018-10-19-17:49:55] Epoch: [148][1400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.816 (2.965) Prec@1 76.56 (74.68) Prec@5 93.75 (90.77) + train[2018-10-19-17:51:41] Epoch: [148][1600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.819 (2.964) Prec@1 74.22 (74.66) Prec@5 92.97 (90.77) + train[2018-10-19-17:53:26] Epoch: [148][1800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.179 (2.967) Prec@1 70.31 (74.59) Prec@5 89.06 (90.74) + train[2018-10-19-17:55:11] Epoch: [148][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.597 (2.965) Prec@1 80.47 (74.60) Prec@5 97.66 (90.77) + train[2018-10-19-17:56:56] Epoch: [148][2200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.084 (2.966) Prec@1 74.22 (74.60) Prec@5 92.19 (90.78) + train[2018-10-19-17:58:43] Epoch: [148][2400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.969 (2.965) Prec@1 75.00 (74.63) Prec@5 88.28 (90.79) + train[2018-10-19-18:00:30] Epoch: [148][2600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.714 (2.965) Prec@1 83.59 (74.63) Prec@5 92.97 (90.78) + train[2018-10-19-18:02:17] Epoch: [148][2800/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 2.740 (2.964) Prec@1 77.34 (74.67) Prec@5 92.19 (90.79) + train[2018-10-19-18:04:04] Epoch: [148][3000/10010] Time 0.63 (0.53) Data 0.00 (0.00) Loss 3.228 (2.965) Prec@1 66.41 (74.66) Prec@5 83.59 (90.79) + train[2018-10-19-18:05:52] Epoch: [148][3200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.265 (2.966) Prec@1 69.53 (74.66) Prec@5 87.50 (90.77) + train[2018-10-19-18:07:40] Epoch: [148][3400/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.867 (2.966) Prec@1 79.69 (74.66) Prec@5 91.41 (90.77) + train[2018-10-19-18:09:28] Epoch: [148][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.043 (2.965) Prec@1 72.66 (74.68) Prec@5 91.41 (90.77) + train[2018-10-19-18:11:15] Epoch: [148][3800/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.816 (2.965) Prec@1 78.12 (74.69) Prec@5 92.97 (90.76) + train[2018-10-19-18:13:03] Epoch: [148][4000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.222 (2.966) Prec@1 69.53 (74.68) Prec@5 88.28 (90.75) + train[2018-10-19-18:14:52] Epoch: [148][4200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.082 (2.967) Prec@1 71.09 (74.67) Prec@5 89.84 (90.75) + train[2018-10-19-18:16:41] Epoch: [148][4400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.809 (2.967) Prec@1 75.78 (74.65) Prec@5 91.41 (90.73) + train[2018-10-19-18:18:29] Epoch: [148][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.090 (2.967) Prec@1 76.56 (74.66) Prec@5 86.72 (90.73) + train[2018-10-19-18:20:17] Epoch: [148][4800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.727 (2.967) Prec@1 78.91 (74.65) Prec@5 95.31 (90.71) + train[2018-10-19-18:22:05] Epoch: [148][5000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.932 (2.968) Prec@1 71.09 (74.65) Prec@5 92.19 (90.71) + train[2018-10-19-18:23:51] Epoch: [148][5200/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 2.924 (2.968) Prec@1 74.22 (74.65) Prec@5 90.62 (90.70) + train[2018-10-19-18:25:39] Epoch: [148][5400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.934 (2.968) Prec@1 75.78 (74.66) Prec@5 92.19 (90.70) + train[2018-10-19-18:27:27] Epoch: [148][5600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.000 (2.968) Prec@1 71.88 (74.65) Prec@5 92.19 (90.69) + train[2018-10-19-18:29:14] Epoch: [148][5800/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.996 (2.969) Prec@1 71.09 (74.63) Prec@5 89.84 (90.69) + train[2018-10-19-18:31:01] Epoch: [148][6000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.997 (2.969) Prec@1 70.31 (74.63) Prec@5 90.62 (90.69) + train[2018-10-19-18:32:48] Epoch: [148][6200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.856 (2.969) Prec@1 78.12 (74.63) Prec@5 93.75 (90.68) + train[2018-10-19-18:34:37] Epoch: [148][6400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.634 (2.969) Prec@1 84.38 (74.63) Prec@5 94.53 (90.68) + train[2018-10-19-18:36:25] Epoch: [148][6600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.423 (2.969) Prec@1 70.31 (74.63) Prec@5 84.38 (90.68) + train[2018-10-19-18:38:14] Epoch: [148][6800/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.738 (2.969) Prec@1 76.56 (74.61) Prec@5 94.53 (90.67) + train[2018-10-19-18:40:00] Epoch: [148][7000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.898 (2.969) Prec@1 76.56 (74.62) Prec@5 89.84 (90.67) + train[2018-10-19-18:41:48] Epoch: [148][7200/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.956 (2.968) Prec@1 73.44 (74.64) Prec@5 88.28 (90.68) + train[2018-10-19-18:43:36] Epoch: [148][7400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.876 (2.969) Prec@1 75.78 (74.63) Prec@5 92.97 (90.68) + train[2018-10-19-18:45:23] Epoch: [148][7600/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.947 (2.969) Prec@1 75.00 (74.62) Prec@5 89.06 (90.68) + train[2018-10-19-18:47:12] Epoch: [148][7800/10010] Time 0.62 (0.54) Data 0.00 (0.00) Loss 3.143 (2.969) Prec@1 70.31 (74.61) Prec@5 89.06 (90.66) + train[2018-10-19-18:49:00] Epoch: [148][8000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.892 (2.969) Prec@1 81.25 (74.62) Prec@5 91.41 (90.66) + train[2018-10-19-18:50:47] Epoch: [148][8200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.193 (2.970) Prec@1 69.53 (74.62) Prec@5 86.72 (90.66) + train[2018-10-19-18:52:35] Epoch: [148][8400/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.993 (2.969) Prec@1 75.78 (74.62) Prec@5 91.41 (90.67) + train[2018-10-19-18:54:24] Epoch: [148][8600/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 3.150 (2.969) Prec@1 75.00 (74.62) Prec@5 87.50 (90.67) + train[2018-10-19-18:56:12] Epoch: [148][8800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.757 (2.969) Prec@1 75.78 (74.61) Prec@5 95.31 (90.67) + train[2018-10-19-18:57:59] Epoch: [148][9000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.088 (2.970) Prec@1 73.44 (74.61) Prec@5 88.28 (90.66) + train[2018-10-19-18:59:47] Epoch: [148][9200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.782 (2.970) Prec@1 81.25 (74.61) Prec@5 92.97 (90.66) + train[2018-10-19-19:01:34] Epoch: [148][9400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.850 (2.970) Prec@1 76.56 (74.60) Prec@5 91.41 (90.66) + train[2018-10-19-19:03:21] Epoch: [148][9600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.792 (2.971) Prec@1 76.56 (74.59) Prec@5 92.97 (90.66) + train[2018-10-19-19:05:08] Epoch: [148][9800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 3.048 (2.971) Prec@1 68.75 (74.58) Prec@5 91.41 (90.66) + train[2018-10-19-19:06:54] Epoch: [148][10000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.032 (2.971) Prec@1 76.56 (74.58) Prec@5 88.28 (90.65) + train[2018-10-19-19:06:58] Epoch: [148][10009/10010] Time 0.19 (0.54) Data 0.00 (0.00) Loss 3.059 (2.971) Prec@1 73.33 (74.58) Prec@5 86.67 (90.65) +[2018-10-19-19:06:58] **train** Prec@1 74.58 Prec@5 90.65 Error@1 25.42 Error@5 9.35 Loss:2.971 + test [2018-10-19-19:07:02] Epoch: [148][000/391] Time 4.09 (4.09) Data 3.95 (3.95) Loss 0.592 (0.592) Prec@1 87.50 (87.50) Prec@5 98.44 (98.44) + test [2018-10-19-19:07:28] Epoch: [148][200/391] Time 0.13 (0.15) Data 0.01 (0.02) Loss 1.176 (1.013) Prec@1 69.53 (76.79) Prec@5 93.75 (93.55) + test [2018-10-19-19:07:54] Epoch: [148][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.064 (1.177) Prec@1 50.00 (73.34) Prec@5 82.50 (91.28) +[2018-10-19-19:07:54] **test** Prec@1 73.34 Prec@5 91.28 Error@1 26.66 Error@5 8.72 Loss:1.177 +----> Best Accuracy : Acc@1=73.42, Acc@5=91.21, Error@1=26.58, Error@5=8.79 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-19-19:07:54] [Epoch=149/250] [Need: 152:02:41] LR=0.0011 ~ 0.0011, Batch=128 + train[2018-10-19-19:07:59] Epoch: [149][000/10010] Time 4.63 (4.63) Data 4.00 (4.00) Loss 3.227 (3.227) Prec@1 71.09 (71.09) Prec@5 87.50 (87.50) + train[2018-10-19-19:09:44] Epoch: [149][200/10010] Time 0.56 (0.55) Data 0.00 (0.02) Loss 2.940 (2.973) Prec@1 76.56 (74.93) Prec@5 90.62 (90.60) + train[2018-10-19-19:11:29] Epoch: [149][400/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 3.151 (2.972) Prec@1 68.75 (74.61) Prec@5 89.84 (90.57) + train[2018-10-19-19:13:14] Epoch: [149][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.733 (2.964) Prec@1 82.03 (74.72) Prec@5 92.97 (90.71) + train[2018-10-19-19:15:00] Epoch: [149][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.495 (2.965) Prec@1 65.62 (74.73) Prec@5 84.38 (90.71) + train[2018-10-19-19:16:46] Epoch: [149][1000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.002 (2.966) Prec@1 76.56 (74.68) Prec@5 90.62 (90.66) + train[2018-10-19-19:18:31] Epoch: [149][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.767 (2.968) Prec@1 78.91 (74.64) Prec@5 92.19 (90.64) + train[2018-10-19-19:20:16] Epoch: [149][1400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.001 (2.967) Prec@1 73.44 (74.65) Prec@5 92.19 (90.64) + train[2018-10-19-19:22:01] Epoch: [149][1600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.974 (2.966) Prec@1 72.66 (74.66) Prec@5 91.41 (90.67) + train[2018-10-19-19:23:46] Epoch: [149][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.725 (2.964) Prec@1 79.69 (74.69) Prec@5 95.31 (90.70) + train[2018-10-19-19:25:32] Epoch: [149][2000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.735 (2.965) Prec@1 81.25 (74.67) Prec@5 92.19 (90.69) + train[2018-10-19-19:27:17] Epoch: [149][2200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.211 (2.964) Prec@1 71.09 (74.72) Prec@5 89.84 (90.71) + train[2018-10-19-19:29:03] Epoch: [149][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.893 (2.965) Prec@1 75.78 (74.69) Prec@5 92.19 (90.70) + train[2018-10-19-19:30:49] Epoch: [149][2600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.549 (2.965) Prec@1 82.81 (74.69) Prec@5 97.66 (90.69) + train[2018-10-19-19:32:33] Epoch: [149][2800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.025 (2.965) Prec@1 79.69 (74.69) Prec@5 88.28 (90.69) + train[2018-10-19-19:34:20] Epoch: [149][3000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.655 (2.965) Prec@1 81.25 (74.70) Prec@5 92.19 (90.69) + train[2018-10-19-19:36:05] Epoch: [149][3200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.776 (2.964) Prec@1 75.00 (74.71) Prec@5 92.97 (90.70) + train[2018-10-19-19:37:50] Epoch: [149][3400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.949 (2.965) Prec@1 74.22 (74.71) Prec@5 90.62 (90.71) + train[2018-10-19-19:39:37] Epoch: [149][3600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.836 (2.965) Prec@1 77.34 (74.71) Prec@5 91.41 (90.71) + train[2018-10-19-19:41:23] Epoch: [149][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.655 (2.965) Prec@1 79.69 (74.70) Prec@5 92.19 (90.71) + train[2018-10-19-19:43:08] Epoch: [149][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.046 (2.966) Prec@1 71.88 (74.70) Prec@5 92.19 (90.71) + train[2018-10-19-19:44:55] Epoch: [149][4200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.978 (2.966) Prec@1 72.66 (74.70) Prec@5 89.06 (90.72) + train[2018-10-19-19:46:40] Epoch: [149][4400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.889 (2.965) Prec@1 74.22 (74.70) Prec@5 92.97 (90.72) + train[2018-10-19-19:48:26] Epoch: [149][4600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.003 (2.965) Prec@1 75.00 (74.71) Prec@5 89.84 (90.73) + train[2018-10-19-19:50:12] Epoch: [149][4800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.013 (2.965) Prec@1 72.66 (74.71) Prec@5 89.06 (90.72) + train[2018-10-19-19:51:58] Epoch: [149][5000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.771 (2.965) Prec@1 78.91 (74.72) Prec@5 93.75 (90.72) + train[2018-10-19-19:53:44] Epoch: [149][5200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.090 (2.965) Prec@1 70.31 (74.72) Prec@5 86.72 (90.72) + train[2018-10-19-19:55:30] Epoch: [149][5400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.180 (2.966) Prec@1 75.78 (74.71) Prec@5 89.06 (90.71) + train[2018-10-19-19:57:16] Epoch: [149][5600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.931 (2.966) Prec@1 76.56 (74.70) Prec@5 89.84 (90.71) + train[2018-10-19-19:59:00] Epoch: [149][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.213 (2.966) Prec@1 69.53 (74.68) Prec@5 89.06 (90.71) + train[2018-10-19-20:00:45] Epoch: [149][6000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.446 (2.967) Prec@1 68.75 (74.67) Prec@5 85.16 (90.70) + train[2018-10-19-20:02:31] Epoch: [149][6200/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 3.362 (2.968) Prec@1 68.75 (74.67) Prec@5 85.16 (90.69) + train[2018-10-19-20:04:16] Epoch: [149][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.874 (2.968) Prec@1 78.91 (74.67) Prec@5 90.62 (90.69) + train[2018-10-19-20:06:01] Epoch: [149][6600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.970 (2.967) Prec@1 75.00 (74.68) Prec@5 89.84 (90.70) + train[2018-10-19-20:07:47] Epoch: [149][6800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.911 (2.968) Prec@1 78.12 (74.68) Prec@5 91.41 (90.69) + train[2018-10-19-20:09:32] Epoch: [149][7000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.104 (2.967) Prec@1 75.00 (74.69) Prec@5 89.06 (90.69) + train[2018-10-19-20:11:17] Epoch: [149][7200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.717 (2.967) Prec@1 80.47 (74.68) Prec@5 92.19 (90.69) + train[2018-10-19-20:13:02] Epoch: [149][7400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.194 (2.968) Prec@1 70.31 (74.68) Prec@5 90.62 (90.68) + train[2018-10-19-20:14:47] Epoch: [149][7600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.819 (2.968) Prec@1 78.91 (74.67) Prec@5 91.41 (90.68) + train[2018-10-19-20:16:32] Epoch: [149][7800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.856 (2.968) Prec@1 75.78 (74.68) Prec@5 90.62 (90.69) + train[2018-10-19-20:18:18] Epoch: [149][8000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.935 (2.968) Prec@1 75.78 (74.67) Prec@5 92.97 (90.68) + train[2018-10-19-20:20:03] Epoch: [149][8200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.028 (2.968) Prec@1 70.31 (74.67) Prec@5 87.50 (90.69) + train[2018-10-19-20:21:48] Epoch: [149][8400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.167 (2.968) Prec@1 72.66 (74.67) Prec@5 88.28 (90.69) + train[2018-10-19-20:23:32] Epoch: [149][8600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.324 (2.968) Prec@1 70.31 (74.67) Prec@5 84.38 (90.68) + train[2018-10-19-20:25:16] Epoch: [149][8800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.866 (2.968) Prec@1 74.22 (74.66) Prec@5 92.97 (90.69) + train[2018-10-19-20:27:01] Epoch: [149][9000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.819 (2.968) Prec@1 75.00 (74.66) Prec@5 92.97 (90.68) + train[2018-10-19-20:28:47] Epoch: [149][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.771 (2.969) Prec@1 76.56 (74.66) Prec@5 92.19 (90.68) + train[2018-10-19-20:30:32] Epoch: [149][9400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.815 (2.969) Prec@1 78.91 (74.65) Prec@5 92.19 (90.68) + train[2018-10-19-20:32:17] Epoch: [149][9600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.783 (2.969) Prec@1 78.91 (74.65) Prec@5 92.97 (90.67) + train[2018-10-19-20:34:03] Epoch: [149][9800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.794 (2.969) Prec@1 75.00 (74.65) Prec@5 90.62 (90.67) + train[2018-10-19-20:35:47] Epoch: [149][10000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.905 (2.969) Prec@1 72.66 (74.65) Prec@5 93.75 (90.68) + train[2018-10-19-20:35:52] Epoch: [149][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.601 (2.969) Prec@1 60.00 (74.65) Prec@5 93.33 (90.67) +[2018-10-19-20:35:52] **train** Prec@1 74.65 Prec@5 90.67 Error@1 25.35 Error@5 9.33 Loss:2.969 + test [2018-10-19-20:35:56] Epoch: [149][000/391] Time 3.79 (3.79) Data 3.65 (3.65) Loss 0.591 (0.591) Prec@1 90.62 (90.62) Prec@5 96.88 (96.88) + test [2018-10-19-20:36:22] Epoch: [149][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.204 (1.015) Prec@1 67.19 (76.73) Prec@5 92.19 (93.48) + test [2018-10-19-20:36:47] Epoch: [149][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.098 (1.181) Prec@1 48.75 (73.31) Prec@5 81.25 (91.25) +[2018-10-19-20:36:47] **test** Prec@1 73.31 Prec@5 91.25 Error@1 26.69 Error@5 8.75 Loss:1.181 +----> Best Accuracy : Acc@1=73.42, Acc@5=91.21, Error@1=26.58, Error@5=8.79 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-19-20:36:47] [Epoch=150/250] [Need: 148:08:41] LR=0.0010 ~ 0.0010, Batch=128 + train[2018-10-19-20:36:52] Epoch: [150][000/10010] Time 5.01 (5.01) Data 4.37 (4.37) Loss 3.050 (3.050) Prec@1 67.97 (67.97) Prec@5 90.62 (90.62) + train[2018-10-19-20:38:37] Epoch: [150][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 2.975 (2.950) Prec@1 70.31 (75.07) Prec@5 92.97 (91.05) + train[2018-10-19-20:40:23] Epoch: [150][400/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.910 (2.954) Prec@1 75.78 (75.00) Prec@5 90.62 (90.96) + train[2018-10-19-20:42:08] Epoch: [150][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.057 (2.958) Prec@1 71.88 (74.93) Prec@5 89.84 (90.87) + train[2018-10-19-20:43:53] Epoch: [150][800/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.038 (2.955) Prec@1 74.22 (74.93) Prec@5 92.97 (90.92) + train[2018-10-19-20:45:38] Epoch: [150][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.915 (2.956) Prec@1 78.12 (74.92) Prec@5 92.19 (90.90) + train[2018-10-19-20:47:24] Epoch: [150][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.823 (2.960) Prec@1 78.91 (74.82) Prec@5 93.75 (90.87) + train[2018-10-19-20:49:09] Epoch: [150][1400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.199 (2.962) Prec@1 74.22 (74.82) Prec@5 85.94 (90.81) + train[2018-10-19-20:50:54] Epoch: [150][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.879 (2.963) Prec@1 75.78 (74.80) Prec@5 92.19 (90.80) + train[2018-10-19-20:52:40] Epoch: [150][1800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.857 (2.964) Prec@1 71.88 (74.78) Prec@5 92.19 (90.77) + train[2018-10-19-20:54:25] Epoch: [150][2000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.933 (2.964) Prec@1 71.88 (74.81) Prec@5 91.41 (90.76) + train[2018-10-19-20:56:12] Epoch: [150][2200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.300 (2.966) Prec@1 71.09 (74.76) Prec@5 84.38 (90.73) + train[2018-10-19-20:57:59] Epoch: [150][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.945 (2.967) Prec@1 75.78 (74.74) Prec@5 88.28 (90.73) + train[2018-10-19-20:59:46] Epoch: [150][2600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.730 (2.969) Prec@1 82.03 (74.70) Prec@5 95.31 (90.70) + train[2018-10-19-21:01:33] Epoch: [150][2800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.895 (2.971) Prec@1 80.47 (74.63) Prec@5 92.97 (90.69) + train[2018-10-19-21:03:19] Epoch: [150][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.841 (2.971) Prec@1 72.66 (74.63) Prec@5 91.41 (90.70) + train[2018-10-19-21:05:05] Epoch: [150][3200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.584 (2.970) Prec@1 63.28 (74.66) Prec@5 84.38 (90.70) + train[2018-10-19-21:06:51] Epoch: [150][3400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.081 (2.970) Prec@1 75.00 (74.67) Prec@5 89.06 (90.70) + train[2018-10-19-21:08:38] Epoch: [150][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.965 (2.969) Prec@1 73.44 (74.68) Prec@5 89.84 (90.70) + train[2018-10-19-21:10:25] Epoch: [150][3800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.572 (2.968) Prec@1 82.81 (74.70) Prec@5 92.97 (90.70) + train[2018-10-19-21:12:12] Epoch: [150][4000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.992 (2.968) Prec@1 72.66 (74.70) Prec@5 92.19 (90.71) + train[2018-10-19-21:13:59] Epoch: [150][4200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.212 (2.967) Prec@1 74.22 (74.72) Prec@5 85.94 (90.71) + train[2018-10-19-21:15:46] Epoch: [150][4400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.045 (2.967) Prec@1 71.88 (74.72) Prec@5 92.97 (90.72) + train[2018-10-19-21:17:34] Epoch: [150][4600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.925 (2.966) Prec@1 82.03 (74.74) Prec@5 91.41 (90.73) + train[2018-10-19-21:19:22] Epoch: [150][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.936 (2.965) Prec@1 71.88 (74.74) Prec@5 89.84 (90.73) + train[2018-10-19-21:21:09] Epoch: [150][5000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.836 (2.965) Prec@1 76.56 (74.73) Prec@5 94.53 (90.73) + train[2018-10-19-21:22:56] Epoch: [150][5200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.021 (2.965) Prec@1 71.88 (74.74) Prec@5 89.06 (90.72) + train[2018-10-19-21:24:44] Epoch: [150][5400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.722 (2.965) Prec@1 77.34 (74.74) Prec@5 92.97 (90.72) + train[2018-10-19-21:26:33] Epoch: [150][5600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.664 (2.965) Prec@1 79.69 (74.73) Prec@5 95.31 (90.72) + train[2018-10-19-21:28:21] Epoch: [150][5800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.911 (2.966) Prec@1 69.53 (74.72) Prec@5 89.06 (90.71) + train[2018-10-19-21:30:09] Epoch: [150][6000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.234 (2.965) Prec@1 73.44 (74.72) Prec@5 85.16 (90.71) + train[2018-10-19-21:31:57] Epoch: [150][6200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.693 (2.966) Prec@1 79.69 (74.72) Prec@5 92.97 (90.71) + train[2018-10-19-21:33:44] Epoch: [150][6400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.908 (2.965) Prec@1 80.47 (74.73) Prec@5 91.41 (90.71) + train[2018-10-19-21:35:32] Epoch: [150][6600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.970 (2.966) Prec@1 75.00 (74.72) Prec@5 89.06 (90.70) + train[2018-10-19-21:37:19] Epoch: [150][6800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.878 (2.966) Prec@1 76.56 (74.71) Prec@5 92.97 (90.70) + train[2018-10-19-21:39:07] Epoch: [150][7000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.009 (2.966) Prec@1 75.78 (74.71) Prec@5 89.06 (90.70) + train[2018-10-19-21:40:54] Epoch: [150][7200/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 3.156 (2.965) Prec@1 72.66 (74.71) Prec@5 90.62 (90.71) + train[2018-10-19-21:42:40] Epoch: [150][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.901 (2.965) Prec@1 76.56 (74.72) Prec@5 92.97 (90.72) + train[2018-10-19-21:44:26] Epoch: [150][7600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.092 (2.965) Prec@1 69.53 (74.71) Prec@5 86.72 (90.72) + train[2018-10-19-21:46:13] Epoch: [150][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.786 (2.965) Prec@1 82.81 (74.71) Prec@5 92.97 (90.71) + train[2018-10-19-21:47:59] Epoch: [150][8000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.107 (2.965) Prec@1 73.44 (74.71) Prec@5 88.28 (90.72) + train[2018-10-19-21:49:46] Epoch: [150][8200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.172 (2.965) Prec@1 69.53 (74.70) Prec@5 89.06 (90.72) + train[2018-10-19-21:51:34] Epoch: [150][8400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.989 (2.966) Prec@1 70.31 (74.70) Prec@5 91.41 (90.72) + train[2018-10-19-21:53:22] Epoch: [150][8600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.920 (2.966) Prec@1 71.09 (74.69) Prec@5 92.97 (90.71) + train[2018-10-19-21:55:10] Epoch: [150][8800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.753 (2.967) Prec@1 75.00 (74.68) Prec@5 92.19 (90.70) + train[2018-10-19-21:56:57] Epoch: [150][9000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.788 (2.967) Prec@1 78.12 (74.68) Prec@5 92.19 (90.70) + train[2018-10-19-21:58:45] Epoch: [150][9200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.025 (2.967) Prec@1 75.78 (74.67) Prec@5 92.19 (90.69) + train[2018-10-19-22:00:33] Epoch: [150][9400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.017 (2.967) Prec@1 78.12 (74.67) Prec@5 89.06 (90.69) + train[2018-10-19-22:02:21] Epoch: [150][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.008 (2.968) Prec@1 75.78 (74.66) Prec@5 89.84 (90.68) + train[2018-10-19-22:04:08] Epoch: [150][9800/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.054 (2.968) Prec@1 74.22 (74.67) Prec@5 85.94 (90.68) + train[2018-10-19-22:05:55] Epoch: [150][10000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.988 (2.968) Prec@1 70.31 (74.66) Prec@5 91.41 (90.68) + train[2018-10-19-22:06:00] Epoch: [150][10009/10010] Time 0.23 (0.53) Data 0.00 (0.00) Loss 3.426 (2.968) Prec@1 73.33 (74.66) Prec@5 86.67 (90.68) +[2018-10-19-22:06:00] **train** Prec@1 74.66 Prec@5 90.68 Error@1 25.34 Error@5 9.32 Loss:2.968 + test [2018-10-19-22:06:04] Epoch: [150][000/391] Time 3.96 (3.96) Data 3.82 (3.82) Loss 0.545 (0.545) Prec@1 89.84 (89.84) Prec@5 97.66 (97.66) + test [2018-10-19-22:06:30] Epoch: [150][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.222 (1.001) Prec@1 64.06 (77.02) Prec@5 92.97 (93.39) + test [2018-10-19-22:06:56] Epoch: [150][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.203 (1.171) Prec@1 42.50 (73.46) Prec@5 82.50 (91.25) +[2018-10-19-22:06:56] **test** Prec@1 73.46 Prec@5 91.25 Error@1 26.54 Error@5 8.75 Loss:1.171 +----> Best Accuracy : Acc@1=73.46, Acc@5=91.25, Error@1=26.54, Error@5=8.75 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-19-22:06:56] [Epoch=151/250] [Need: 148:43:58] LR=0.0010 ~ 0.0010, Batch=128 + train[2018-10-19-22:07:00] Epoch: [151][000/10010] Time 4.51 (4.51) Data 3.89 (3.89) Loss 2.829 (2.829) Prec@1 73.44 (73.44) Prec@5 92.19 (92.19) + train[2018-10-19-22:08:46] Epoch: [151][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 2.981 (2.939) Prec@1 74.22 (75.30) Prec@5 89.84 (91.18) + train[2018-10-19-22:10:31] Epoch: [151][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 3.158 (2.958) Prec@1 67.19 (74.90) Prec@5 86.72 (90.87) + train[2018-10-19-22:12:16] Epoch: [151][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 2.949 (2.961) Prec@1 71.88 (74.80) Prec@5 91.41 (90.83) + train[2018-10-19-22:14:01] Epoch: [151][800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.761 (2.955) Prec@1 79.69 (74.87) Prec@5 92.97 (90.91) + train[2018-10-19-22:15:46] Epoch: [151][1000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.954 (2.951) Prec@1 76.56 (75.02) Prec@5 91.41 (90.94) + train[2018-10-19-22:17:31] Epoch: [151][1200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.855 (2.954) Prec@1 76.56 (74.98) Prec@5 92.19 (90.92) + train[2018-10-19-22:19:17] Epoch: [151][1400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.841 (2.956) Prec@1 78.12 (74.93) Prec@5 92.19 (90.90) + train[2018-10-19-22:21:02] Epoch: [151][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.767 (2.954) Prec@1 79.69 (74.96) Prec@5 94.53 (90.91) + train[2018-10-19-22:22:47] Epoch: [151][1800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.973 (2.955) Prec@1 71.09 (74.92) Prec@5 89.84 (90.88) + train[2018-10-19-22:24:31] Epoch: [151][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.907 (2.954) Prec@1 73.44 (74.95) Prec@5 92.19 (90.89) + train[2018-10-19-22:26:16] Epoch: [151][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.403 (2.956) Prec@1 68.75 (74.94) Prec@5 85.94 (90.87) + train[2018-10-19-22:28:02] Epoch: [151][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.826 (2.956) Prec@1 75.78 (74.92) Prec@5 89.84 (90.85) + train[2018-10-19-22:29:48] Epoch: [151][2600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.742 (2.957) Prec@1 79.69 (74.90) Prec@5 95.31 (90.83) + train[2018-10-19-22:31:32] Epoch: [151][2800/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 2.856 (2.957) Prec@1 71.88 (74.90) Prec@5 91.41 (90.83) + train[2018-10-19-22:33:17] Epoch: [151][3000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.018 (2.956) Prec@1 71.88 (74.93) Prec@5 91.41 (90.86) + train[2018-10-19-22:35:03] Epoch: [151][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.690 (2.955) Prec@1 85.16 (74.94) Prec@5 93.75 (90.88) + train[2018-10-19-22:36:49] Epoch: [151][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.869 (2.956) Prec@1 75.00 (74.93) Prec@5 92.97 (90.88) + train[2018-10-19-22:38:36] Epoch: [151][3600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.172 (2.955) Prec@1 74.22 (74.94) Prec@5 90.62 (90.88) + train[2018-10-19-22:40:22] Epoch: [151][3800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.883 (2.955) Prec@1 76.56 (74.94) Prec@5 92.97 (90.87) + train[2018-10-19-22:42:08] Epoch: [151][4000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.281 (2.956) Prec@1 71.88 (74.93) Prec@5 85.16 (90.87) + train[2018-10-19-22:43:55] Epoch: [151][4200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.687 (2.956) Prec@1 75.78 (74.93) Prec@5 96.09 (90.86) + train[2018-10-19-22:45:42] Epoch: [151][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.776 (2.956) Prec@1 79.69 (74.91) Prec@5 93.75 (90.85) + train[2018-10-19-22:47:29] Epoch: [151][4600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.953 (2.956) Prec@1 71.88 (74.92) Prec@5 89.84 (90.85) + train[2018-10-19-22:49:17] Epoch: [151][4800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.061 (2.956) Prec@1 71.09 (74.91) Prec@5 92.19 (90.84) + train[2018-10-19-22:51:04] Epoch: [151][5000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.648 (2.956) Prec@1 78.91 (74.92) Prec@5 93.75 (90.84) + train[2018-10-19-22:52:51] Epoch: [151][5200/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 2.766 (2.956) Prec@1 78.91 (74.91) Prec@5 92.97 (90.85) + train[2018-10-19-22:54:38] Epoch: [151][5400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.854 (2.956) Prec@1 74.22 (74.90) Prec@5 92.19 (90.84) + train[2018-10-19-22:56:24] Epoch: [151][5600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.781 (2.956) Prec@1 78.12 (74.90) Prec@5 92.97 (90.84) + train[2018-10-19-22:58:12] Epoch: [151][5800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.207 (2.956) Prec@1 73.44 (74.91) Prec@5 89.06 (90.84) + train[2018-10-19-22:59:59] Epoch: [151][6000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.834 (2.956) Prec@1 75.00 (74.91) Prec@5 93.75 (90.83) + train[2018-10-19-23:01:47] Epoch: [151][6200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.553 (2.956) Prec@1 81.25 (74.91) Prec@5 97.66 (90.84) + train[2018-10-19-23:03:34] Epoch: [151][6400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.700 (2.956) Prec@1 79.69 (74.90) Prec@5 92.19 (90.83) + train[2018-10-19-23:05:21] Epoch: [151][6600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.946 (2.956) Prec@1 73.44 (74.91) Prec@5 92.97 (90.83) + train[2018-10-19-23:07:08] Epoch: [151][6800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.176 (2.956) Prec@1 72.66 (74.91) Prec@5 86.72 (90.83) + train[2018-10-19-23:08:56] Epoch: [151][7000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.636 (2.956) Prec@1 80.47 (74.91) Prec@5 94.53 (90.83) + train[2018-10-19-23:10:42] Epoch: [151][7200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.856 (2.956) Prec@1 80.47 (74.89) Prec@5 93.75 (90.82) + train[2018-10-19-23:12:29] Epoch: [151][7400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.974 (2.957) Prec@1 75.78 (74.89) Prec@5 92.97 (90.82) + train[2018-10-19-23:14:15] Epoch: [151][7600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.178 (2.958) Prec@1 70.31 (74.87) Prec@5 86.72 (90.81) + train[2018-10-19-23:16:02] Epoch: [151][7800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.758 (2.958) Prec@1 78.91 (74.86) Prec@5 92.19 (90.80) + train[2018-10-19-23:17:48] Epoch: [151][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.143 (2.959) Prec@1 71.09 (74.84) Prec@5 89.84 (90.80) + train[2018-10-19-23:19:34] Epoch: [151][8200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.868 (2.959) Prec@1 74.22 (74.84) Prec@5 92.97 (90.80) + train[2018-10-19-23:21:19] Epoch: [151][8400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.902 (2.959) Prec@1 75.78 (74.83) Prec@5 89.06 (90.79) + train[2018-10-19-23:23:05] Epoch: [151][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.298 (2.959) Prec@1 71.88 (74.83) Prec@5 87.50 (90.79) + train[2018-10-19-23:24:48] Epoch: [151][8800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.594 (2.960) Prec@1 78.12 (74.82) Prec@5 95.31 (90.79) + train[2018-10-19-23:26:32] Epoch: [151][9000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.165 (2.959) Prec@1 71.09 (74.82) Prec@5 88.28 (90.79) + train[2018-10-19-23:28:18] Epoch: [151][9200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.865 (2.960) Prec@1 70.31 (74.81) Prec@5 94.53 (90.78) + train[2018-10-19-23:30:04] Epoch: [151][9400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.031 (2.960) Prec@1 79.69 (74.81) Prec@5 88.28 (90.78) + train[2018-10-19-23:31:50] Epoch: [151][9600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.133 (2.960) Prec@1 71.09 (74.80) Prec@5 89.06 (90.78) + train[2018-10-19-23:33:36] Epoch: [151][9800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.994 (2.960) Prec@1 78.12 (74.80) Prec@5 89.06 (90.77) + train[2018-10-19-23:35:22] Epoch: [151][10000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.187 (2.961) Prec@1 72.66 (74.79) Prec@5 89.84 (90.77) + train[2018-10-19-23:35:27] Epoch: [151][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.317 (2.961) Prec@1 66.67 (74.79) Prec@5 93.33 (90.77) +[2018-10-19-23:35:27] **train** Prec@1 74.79 Prec@5 90.77 Error@1 25.21 Error@5 9.23 Loss:2.961 + test [2018-10-19-23:35:31] Epoch: [151][000/391] Time 4.24 (4.24) Data 4.10 (4.10) Loss 0.577 (0.577) Prec@1 89.06 (89.06) Prec@5 96.09 (96.09) + test [2018-10-19-23:35:58] Epoch: [151][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.213 (1.010) Prec@1 68.75 (76.70) Prec@5 90.62 (93.47) + test [2018-10-19-23:36:22] Epoch: [151][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.103 (1.178) Prec@1 47.50 (73.19) Prec@5 82.50 (91.26) +[2018-10-19-23:36:22] **test** Prec@1 73.19 Prec@5 91.26 Error@1 26.81 Error@5 8.74 Loss:1.178 +----> Best Accuracy : Acc@1=73.46, Acc@5=91.25, Error@1=26.54, Error@5=8.75 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-19-23:36:22] [Epoch=152/250] [Need: 146:04:46] LR=0.0010 ~ 0.0010, Batch=128 + train[2018-10-19-23:36:27] Epoch: [152][000/10010] Time 4.90 (4.90) Data 4.20 (4.20) Loss 3.121 (3.121) Prec@1 69.53 (69.53) Prec@5 85.94 (85.94) + train[2018-10-19-23:38:13] Epoch: [152][200/10010] Time 0.61 (0.55) Data 0.00 (0.02) Loss 2.973 (2.959) Prec@1 73.44 (74.88) Prec@5 90.62 (90.93) + train[2018-10-19-23:39:57] Epoch: [152][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.995 (2.952) Prec@1 75.00 (74.86) Prec@5 86.72 (90.95) + train[2018-10-19-23:41:42] Epoch: [152][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.843 (2.951) Prec@1 74.22 (74.88) Prec@5 92.19 (90.88) + train[2018-10-19-23:43:27] Epoch: [152][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.188 (2.956) Prec@1 68.75 (74.82) Prec@5 85.16 (90.89) + train[2018-10-19-23:45:12] Epoch: [152][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.618 (2.954) Prec@1 82.81 (74.89) Prec@5 93.75 (90.92) + train[2018-10-19-23:46:57] Epoch: [152][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.175 (2.952) Prec@1 71.09 (74.92) Prec@5 87.50 (90.96) + train[2018-10-19-23:48:42] Epoch: [152][1400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.942 (2.954) Prec@1 76.56 (74.90) Prec@5 89.06 (90.92) + train[2018-10-19-23:50:27] Epoch: [152][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.448 (2.952) Prec@1 82.81 (74.97) Prec@5 95.31 (90.94) + train[2018-10-19-23:52:12] Epoch: [152][1800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.970 (2.952) Prec@1 75.00 (74.96) Prec@5 90.62 (90.92) + train[2018-10-19-23:53:58] Epoch: [152][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.953 (2.951) Prec@1 78.91 (75.01) Prec@5 90.62 (90.93) + train[2018-10-19-23:55:44] Epoch: [152][2200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.106 (2.953) Prec@1 71.88 (75.00) Prec@5 90.62 (90.90) + train[2018-10-19-23:57:28] Epoch: [152][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.956 (2.955) Prec@1 71.88 (74.96) Prec@5 88.28 (90.88) + train[2018-10-19-23:59:14] Epoch: [152][2600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.898 (2.955) Prec@1 78.91 (74.94) Prec@5 91.41 (90.88) + train[2018-10-20-00:00:59] Epoch: [152][2800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.842 (2.954) Prec@1 75.78 (74.94) Prec@5 92.97 (90.90) + train[2018-10-20-00:02:44] Epoch: [152][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.960 (2.954) Prec@1 71.88 (74.93) Prec@5 90.62 (90.88) + train[2018-10-20-00:04:30] Epoch: [152][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.134 (2.954) Prec@1 72.66 (74.93) Prec@5 88.28 (90.88) + train[2018-10-20-00:06:16] Epoch: [152][3400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.114 (2.955) Prec@1 74.22 (74.91) Prec@5 90.62 (90.86) + train[2018-10-20-00:08:03] Epoch: [152][3600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.972 (2.954) Prec@1 75.78 (74.93) Prec@5 92.97 (90.87) + train[2018-10-20-00:09:49] Epoch: [152][3800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.002 (2.955) Prec@1 78.91 (74.93) Prec@5 88.28 (90.87) + train[2018-10-20-00:11:35] Epoch: [152][4000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.930 (2.954) Prec@1 75.00 (74.92) Prec@5 93.75 (90.86) + train[2018-10-20-00:13:20] Epoch: [152][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.027 (2.953) Prec@1 75.78 (74.94) Prec@5 89.06 (90.87) + train[2018-10-20-00:15:08] Epoch: [152][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.029 (2.954) Prec@1 71.09 (74.93) Prec@5 89.06 (90.86) + train[2018-10-20-00:16:55] Epoch: [152][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.040 (2.954) Prec@1 74.22 (74.93) Prec@5 92.19 (90.86) + train[2018-10-20-00:18:42] Epoch: [152][4800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.135 (2.955) Prec@1 75.00 (74.91) Prec@5 89.06 (90.85) + train[2018-10-20-00:20:27] Epoch: [152][5000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.066 (2.955) Prec@1 75.78 (74.93) Prec@5 87.50 (90.84) + train[2018-10-20-00:22:13] Epoch: [152][5200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.961 (2.956) Prec@1 78.91 (74.92) Prec@5 92.97 (90.83) + train[2018-10-20-00:24:01] Epoch: [152][5400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.628 (2.956) Prec@1 83.59 (74.91) Prec@5 90.62 (90.82) + train[2018-10-20-00:25:47] Epoch: [152][5600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.860 (2.956) Prec@1 78.91 (74.93) Prec@5 92.97 (90.83) + train[2018-10-20-00:27:35] Epoch: [152][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.976 (2.956) Prec@1 77.34 (74.93) Prec@5 89.84 (90.83) + train[2018-10-20-00:29:21] Epoch: [152][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.751 (2.956) Prec@1 78.12 (74.93) Prec@5 92.97 (90.83) + train[2018-10-20-00:31:08] Epoch: [152][6200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.163 (2.957) Prec@1 70.31 (74.92) Prec@5 90.62 (90.82) + train[2018-10-20-00:32:55] Epoch: [152][6400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.862 (2.957) Prec@1 74.22 (74.92) Prec@5 89.84 (90.83) + train[2018-10-20-00:34:41] Epoch: [152][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.977 (2.957) Prec@1 70.31 (74.91) Prec@5 93.75 (90.83) + train[2018-10-20-00:36:27] Epoch: [152][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.993 (2.957) Prec@1 75.00 (74.90) Prec@5 91.41 (90.83) + train[2018-10-20-00:38:14] Epoch: [152][7000/10010] Time 0.62 (0.53) Data 0.00 (0.00) Loss 3.160 (2.958) Prec@1 70.31 (74.89) Prec@5 86.72 (90.82) + train[2018-10-20-00:40:00] Epoch: [152][7200/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 3.241 (2.958) Prec@1 73.44 (74.88) Prec@5 85.16 (90.82) + train[2018-10-20-00:41:46] Epoch: [152][7400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.133 (2.958) Prec@1 69.53 (74.87) Prec@5 90.62 (90.82) + train[2018-10-20-00:43:32] Epoch: [152][7600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.932 (2.958) Prec@1 73.44 (74.88) Prec@5 91.41 (90.82) + train[2018-10-20-00:45:18] Epoch: [152][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.233 (2.959) Prec@1 75.00 (74.87) Prec@5 85.16 (90.81) + train[2018-10-20-00:47:04] Epoch: [152][8000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.900 (2.959) Prec@1 79.69 (74.87) Prec@5 91.41 (90.81) + train[2018-10-20-00:48:50] Epoch: [152][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.990 (2.959) Prec@1 72.66 (74.86) Prec@5 91.41 (90.81) + train[2018-10-20-00:50:37] Epoch: [152][8400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.857 (2.958) Prec@1 75.78 (74.88) Prec@5 89.06 (90.82) + train[2018-10-20-00:52:23] Epoch: [152][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.162 (2.959) Prec@1 71.09 (74.87) Prec@5 88.28 (90.82) + train[2018-10-20-00:54:09] Epoch: [152][8800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.662 (2.958) Prec@1 78.12 (74.86) Prec@5 96.09 (90.83) + train[2018-10-20-00:55:56] Epoch: [152][9000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.915 (2.958) Prec@1 75.78 (74.86) Prec@5 92.19 (90.83) + train[2018-10-20-00:57:42] Epoch: [152][9200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.839 (2.959) Prec@1 75.78 (74.86) Prec@5 94.53 (90.82) + train[2018-10-20-00:59:29] Epoch: [152][9400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.058 (2.959) Prec@1 75.00 (74.84) Prec@5 89.06 (90.82) + train[2018-10-20-01:01:15] Epoch: [152][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.953 (2.959) Prec@1 78.12 (74.85) Prec@5 90.62 (90.82) + train[2018-10-20-01:03:02] Epoch: [152][9800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.100 (2.960) Prec@1 70.31 (74.82) Prec@5 87.50 (90.81) + train[2018-10-20-01:04:47] Epoch: [152][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.277 (2.961) Prec@1 71.09 (74.81) Prec@5 88.28 (90.81) + train[2018-10-20-01:04:52] Epoch: [152][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 3.817 (2.961) Prec@1 53.33 (74.81) Prec@5 80.00 (90.81) +[2018-10-20-01:04:52] **train** Prec@1 74.81 Prec@5 90.81 Error@1 25.19 Error@5 9.19 Loss:2.961 + test [2018-10-20-01:04:56] Epoch: [152][000/391] Time 4.20 (4.20) Data 4.07 (4.07) Loss 0.582 (0.582) Prec@1 90.62 (90.62) Prec@5 97.66 (97.66) + test [2018-10-20-01:05:23] Epoch: [152][200/391] Time 0.12 (0.16) Data 0.00 (0.02) Loss 1.270 (1.010) Prec@1 67.97 (76.94) Prec@5 91.41 (93.34) + test [2018-10-20-01:05:49] Epoch: [152][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.012 (1.174) Prec@1 48.75 (73.42) Prec@5 82.50 (91.19) +[2018-10-20-01:05:49] **test** Prec@1 73.42 Prec@5 91.19 Error@1 26.58 Error@5 8.81 Loss:1.174 +----> Best Accuracy : Acc@1=73.46, Acc@5=91.25, Error@1=26.54, Error@5=8.75 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-20-01:05:49] [Epoch=153/250] [Need: 144:36:08] LR=0.0009 ~ 0.0009, Batch=128 + train[2018-10-20-01:05:54] Epoch: [153][000/10010] Time 5.25 (5.25) Data 4.69 (4.69) Loss 2.866 (2.866) Prec@1 75.78 (75.78) Prec@5 88.28 (88.28) + train[2018-10-20-01:07:39] Epoch: [153][200/10010] Time 0.51 (0.55) Data 0.00 (0.02) Loss 2.744 (2.951) Prec@1 78.12 (75.36) Prec@5 92.97 (91.07) + train[2018-10-20-01:09:24] Epoch: [153][400/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.840 (2.944) Prec@1 75.78 (75.26) Prec@5 92.19 (90.99) + train[2018-10-20-01:11:10] Epoch: [153][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.048 (2.939) Prec@1 68.75 (75.32) Prec@5 92.97 (91.03) + train[2018-10-20-01:12:55] Epoch: [153][800/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.205 (2.942) Prec@1 67.97 (75.26) Prec@5 88.28 (91.02) + train[2018-10-20-01:14:40] Epoch: [153][1000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.824 (2.943) Prec@1 74.22 (75.20) Prec@5 92.97 (90.99) + train[2018-10-20-01:16:26] Epoch: [153][1200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.905 (2.945) Prec@1 75.78 (75.13) Prec@5 92.97 (90.97) + train[2018-10-20-01:18:11] Epoch: [153][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.097 (2.942) Prec@1 75.00 (75.13) Prec@5 92.19 (90.97) + train[2018-10-20-01:19:56] Epoch: [153][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.551 (2.941) Prec@1 82.81 (75.15) Prec@5 96.09 (90.98) + train[2018-10-20-01:21:40] Epoch: [153][1800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.942 (2.943) Prec@1 74.22 (75.09) Prec@5 92.97 (90.95) + train[2018-10-20-01:23:26] Epoch: [153][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.068 (2.946) Prec@1 71.88 (75.06) Prec@5 90.62 (90.91) + train[2018-10-20-01:25:11] Epoch: [153][2200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.110 (2.947) Prec@1 71.09 (75.04) Prec@5 89.06 (90.90) + train[2018-10-20-01:26:57] Epoch: [153][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.623 (2.949) Prec@1 86.72 (75.00) Prec@5 91.41 (90.87) + train[2018-10-20-01:28:42] Epoch: [153][2600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.773 (2.948) Prec@1 79.69 (75.00) Prec@5 94.53 (90.90) + train[2018-10-20-01:30:29] Epoch: [153][2800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.050 (2.949) Prec@1 72.66 (74.99) Prec@5 88.28 (90.87) + train[2018-10-20-01:32:14] Epoch: [153][3000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.856 (2.950) Prec@1 72.66 (74.97) Prec@5 93.75 (90.86) + train[2018-10-20-01:34:00] Epoch: [153][3200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.859 (2.951) Prec@1 78.91 (74.96) Prec@5 92.97 (90.85) + train[2018-10-20-01:35:44] Epoch: [153][3400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.780 (2.951) Prec@1 74.22 (74.96) Prec@5 92.97 (90.85) + train[2018-10-20-01:37:30] Epoch: [153][3600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.057 (2.950) Prec@1 71.09 (74.99) Prec@5 85.94 (90.86) + train[2018-10-20-01:39:15] Epoch: [153][3800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.061 (2.950) Prec@1 73.44 (74.99) Prec@5 89.06 (90.85) + train[2018-10-20-01:41:00] Epoch: [153][4000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.890 (2.950) Prec@1 72.66 (74.99) Prec@5 92.19 (90.85) + train[2018-10-20-01:42:46] Epoch: [153][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.987 (2.951) Prec@1 74.22 (74.98) Prec@5 91.41 (90.85) + train[2018-10-20-01:44:33] Epoch: [153][4400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.733 (2.951) Prec@1 81.25 (75.00) Prec@5 93.75 (90.84) + train[2018-10-20-01:46:19] Epoch: [153][4600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.921 (2.950) Prec@1 71.09 (75.00) Prec@5 92.19 (90.85) + train[2018-10-20-01:48:06] Epoch: [153][4800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.902 (2.951) Prec@1 75.78 (74.97) Prec@5 88.28 (90.84) + train[2018-10-20-01:49:53] Epoch: [153][5000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.936 (2.950) Prec@1 76.56 (75.00) Prec@5 92.19 (90.84) + train[2018-10-20-01:51:41] Epoch: [153][5200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.964 (2.950) Prec@1 74.22 (75.00) Prec@5 92.97 (90.84) + train[2018-10-20-01:53:29] Epoch: [153][5400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.910 (2.951) Prec@1 76.56 (74.98) Prec@5 92.19 (90.83) + train[2018-10-20-01:55:17] Epoch: [153][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.567 (2.951) Prec@1 82.03 (74.98) Prec@5 96.88 (90.83) + train[2018-10-20-01:57:04] Epoch: [153][5800/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.745 (2.951) Prec@1 77.34 (74.98) Prec@5 91.41 (90.82) + train[2018-10-20-01:58:51] Epoch: [153][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.954 (2.952) Prec@1 76.56 (74.97) Prec@5 91.41 (90.81) + train[2018-10-20-02:00:38] Epoch: [153][6200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.837 (2.953) Prec@1 79.69 (74.96) Prec@5 89.84 (90.80) + train[2018-10-20-02:02:25] Epoch: [153][6400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.996 (2.953) Prec@1 77.34 (74.95) Prec@5 91.41 (90.80) + train[2018-10-20-02:04:13] Epoch: [153][6600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.895 (2.953) Prec@1 74.22 (74.94) Prec@5 89.84 (90.80) + train[2018-10-20-02:05:59] Epoch: [153][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.026 (2.953) Prec@1 71.88 (74.94) Prec@5 90.62 (90.81) + train[2018-10-20-02:07:47] Epoch: [153][7000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.162 (2.953) Prec@1 71.88 (74.94) Prec@5 90.62 (90.80) + train[2018-10-20-02:09:34] Epoch: [153][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.994 (2.953) Prec@1 73.44 (74.93) Prec@5 92.19 (90.80) + train[2018-10-20-02:11:20] Epoch: [153][7400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.737 (2.953) Prec@1 81.25 (74.92) Prec@5 92.19 (90.80) + train[2018-10-20-02:13:07] Epoch: [153][7600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.068 (2.953) Prec@1 71.09 (74.92) Prec@5 89.06 (90.80) + train[2018-10-20-02:14:53] Epoch: [153][7800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.709 (2.953) Prec@1 83.59 (74.93) Prec@5 92.19 (90.80) + train[2018-10-20-02:16:38] Epoch: [153][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.975 (2.954) Prec@1 73.44 (74.91) Prec@5 86.72 (90.79) + train[2018-10-20-02:18:25] Epoch: [153][8200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.255 (2.954) Prec@1 70.31 (74.91) Prec@5 87.50 (90.79) + train[2018-10-20-02:20:11] Epoch: [153][8400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.243 (2.955) Prec@1 71.88 (74.90) Prec@5 88.28 (90.79) + train[2018-10-20-02:21:59] Epoch: [153][8600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.916 (2.955) Prec@1 71.09 (74.90) Prec@5 92.97 (90.78) + train[2018-10-20-02:23:47] Epoch: [153][8800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.984 (2.955) Prec@1 77.34 (74.89) Prec@5 90.62 (90.78) + train[2018-10-20-02:25:35] Epoch: [153][9000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.083 (2.956) Prec@1 72.66 (74.88) Prec@5 88.28 (90.78) + train[2018-10-20-02:27:22] Epoch: [153][9200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.977 (2.956) Prec@1 79.69 (74.88) Prec@5 87.50 (90.78) + train[2018-10-20-02:29:09] Epoch: [153][9400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.802 (2.956) Prec@1 75.00 (74.88) Prec@5 91.41 (90.79) + train[2018-10-20-02:30:57] Epoch: [153][9600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.124 (2.956) Prec@1 70.31 (74.89) Prec@5 92.97 (90.79) + train[2018-10-20-02:32:44] Epoch: [153][9800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.948 (2.956) Prec@1 77.34 (74.88) Prec@5 90.62 (90.79) + train[2018-10-20-02:34:30] Epoch: [153][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.229 (2.956) Prec@1 68.75 (74.89) Prec@5 84.38 (90.79) + train[2018-10-20-02:34:35] Epoch: [153][10009/10010] Time 0.14 (0.53) Data 0.00 (0.00) Loss 3.621 (2.956) Prec@1 60.00 (74.89) Prec@5 100.00 (90.79) +[2018-10-20-02:34:35] **train** Prec@1 74.89 Prec@5 90.79 Error@1 25.11 Error@5 9.21 Loss:2.956 + test [2018-10-20-02:34:39] Epoch: [153][000/391] Time 4.22 (4.22) Data 4.08 (4.08) Loss 0.520 (0.520) Prec@1 89.84 (89.84) Prec@5 98.44 (98.44) + test [2018-10-20-02:35:05] Epoch: [153][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.215 (1.001) Prec@1 67.19 (76.87) Prec@5 93.75 (93.54) + test [2018-10-20-02:35:30] Epoch: [153][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.129 (1.169) Prec@1 45.00 (73.26) Prec@5 82.50 (91.27) +[2018-10-20-02:35:30] **test** Prec@1 73.26 Prec@5 91.27 Error@1 26.74 Error@5 8.73 Loss:1.169 +----> Best Accuracy : Acc@1=73.46, Acc@5=91.25, Error@1=26.54, Error@5=8.75 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-20-02:35:31] [Epoch=154/250] [Need: 143:31:01] LR=0.0009 ~ 0.0009, Batch=128 + train[2018-10-20-02:35:36] Epoch: [154][000/10010] Time 5.33 (5.33) Data 4.78 (4.78) Loss 2.850 (2.850) Prec@1 75.00 (75.00) Prec@5 91.41 (91.41) + train[2018-10-20-02:37:22] Epoch: [154][200/10010] Time 0.55 (0.55) Data 0.00 (0.02) Loss 2.890 (2.943) Prec@1 75.00 (75.00) Prec@5 90.62 (91.08) + train[2018-10-20-02:39:07] Epoch: [154][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.974 (2.948) Prec@1 74.22 (75.04) Prec@5 90.62 (90.98) + train[2018-10-20-02:40:52] Epoch: [154][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 2.991 (2.937) Prec@1 75.78 (75.27) Prec@5 90.62 (91.08) + train[2018-10-20-02:42:37] Epoch: [154][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.659 (2.934) Prec@1 80.47 (75.34) Prec@5 92.97 (91.09) + train[2018-10-20-02:44:23] Epoch: [154][1000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.975 (2.937) Prec@1 75.78 (75.28) Prec@5 88.28 (91.01) + train[2018-10-20-02:46:08] Epoch: [154][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.067 (2.938) Prec@1 68.75 (75.22) Prec@5 89.06 (90.99) + train[2018-10-20-02:47:52] Epoch: [154][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.903 (2.939) Prec@1 78.12 (75.20) Prec@5 88.28 (90.96) + train[2018-10-20-02:49:37] Epoch: [154][1600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.840 (2.937) Prec@1 76.56 (75.24) Prec@5 91.41 (90.99) + train[2018-10-20-02:51:22] Epoch: [154][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.932 (2.938) Prec@1 75.00 (75.23) Prec@5 91.41 (91.00) + train[2018-10-20-02:53:07] Epoch: [154][2000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.692 (2.939) Prec@1 80.47 (75.24) Prec@5 95.31 (90.98) + train[2018-10-20-02:54:53] Epoch: [154][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.930 (2.939) Prec@1 78.91 (75.23) Prec@5 92.19 (90.98) + train[2018-10-20-02:56:39] Epoch: [154][2400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.137 (2.940) Prec@1 68.75 (75.21) Prec@5 88.28 (90.96) + train[2018-10-20-02:58:24] Epoch: [154][2600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.182 (2.941) Prec@1 72.66 (75.20) Prec@5 88.28 (90.95) + train[2018-10-20-03:00:09] Epoch: [154][2800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.944 (2.941) Prec@1 76.56 (75.21) Prec@5 89.84 (90.95) + train[2018-10-20-03:01:54] Epoch: [154][3000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.892 (2.941) Prec@1 76.56 (75.20) Prec@5 92.19 (90.96) + train[2018-10-20-03:03:39] Epoch: [154][3200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.899 (2.942) Prec@1 75.00 (75.17) Prec@5 92.19 (90.95) + train[2018-10-20-03:05:25] Epoch: [154][3400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.734 (2.943) Prec@1 83.59 (75.14) Prec@5 94.53 (90.94) + train[2018-10-20-03:07:10] Epoch: [154][3600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.120 (2.943) Prec@1 71.88 (75.16) Prec@5 87.50 (90.94) + train[2018-10-20-03:08:57] Epoch: [154][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.862 (2.943) Prec@1 75.00 (75.15) Prec@5 92.97 (90.94) + train[2018-10-20-03:10:44] Epoch: [154][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.008 (2.943) Prec@1 75.00 (75.16) Prec@5 91.41 (90.94) + train[2018-10-20-03:12:32] Epoch: [154][4200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.921 (2.943) Prec@1 74.22 (75.16) Prec@5 90.62 (90.94) + train[2018-10-20-03:14:20] Epoch: [154][4400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.937 (2.943) Prec@1 73.44 (75.17) Prec@5 92.19 (90.94) + train[2018-10-20-03:16:08] Epoch: [154][4600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.962 (2.943) Prec@1 76.56 (75.16) Prec@5 89.84 (90.94) + train[2018-10-20-03:17:55] Epoch: [154][4800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.315 (2.943) Prec@1 70.31 (75.17) Prec@5 85.16 (90.94) + train[2018-10-20-03:19:42] Epoch: [154][5000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.717 (2.942) Prec@1 82.03 (75.18) Prec@5 93.75 (90.94) + train[2018-10-20-03:21:29] Epoch: [154][5200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.965 (2.943) Prec@1 75.78 (75.18) Prec@5 90.62 (90.94) + train[2018-10-20-03:23:14] Epoch: [154][5400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.064 (2.943) Prec@1 71.88 (75.17) Prec@5 91.41 (90.94) + train[2018-10-20-03:24:59] Epoch: [154][5600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.906 (2.943) Prec@1 78.12 (75.18) Prec@5 91.41 (90.94) + train[2018-10-20-03:26:45] Epoch: [154][5800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.080 (2.943) Prec@1 71.88 (75.16) Prec@5 87.50 (90.93) + train[2018-10-20-03:28:30] Epoch: [154][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.838 (2.944) Prec@1 78.91 (75.14) Prec@5 89.84 (90.92) + train[2018-10-20-03:30:16] Epoch: [154][6200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.805 (2.945) Prec@1 79.69 (75.12) Prec@5 92.19 (90.91) + train[2018-10-20-03:32:00] Epoch: [154][6400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.743 (2.945) Prec@1 80.47 (75.12) Prec@5 92.19 (90.90) + train[2018-10-20-03:33:45] Epoch: [154][6600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.144 (2.946) Prec@1 65.62 (75.10) Prec@5 88.28 (90.90) + train[2018-10-20-03:35:31] Epoch: [154][6800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.078 (2.946) Prec@1 72.66 (75.11) Prec@5 89.06 (90.91) + train[2018-10-20-03:37:14] Epoch: [154][7000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.154 (2.945) Prec@1 73.44 (75.11) Prec@5 89.06 (90.92) + train[2018-10-20-03:39:00] Epoch: [154][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.763 (2.945) Prec@1 79.69 (75.10) Prec@5 93.75 (90.92) + train[2018-10-20-03:40:45] Epoch: [154][7400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.748 (2.946) Prec@1 78.12 (75.10) Prec@5 96.09 (90.91) + train[2018-10-20-03:42:32] Epoch: [154][7600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.113 (2.946) Prec@1 73.44 (75.09) Prec@5 89.84 (90.92) + train[2018-10-20-03:44:18] Epoch: [154][7800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.068 (2.947) Prec@1 77.34 (75.08) Prec@5 88.28 (90.91) + train[2018-10-20-03:46:03] Epoch: [154][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.185 (2.947) Prec@1 67.97 (75.07) Prec@5 87.50 (90.91) + train[2018-10-20-03:47:48] Epoch: [154][8200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.089 (2.947) Prec@1 75.00 (75.06) Prec@5 88.28 (90.90) + train[2018-10-20-03:49:33] Epoch: [154][8400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.954 (2.948) Prec@1 76.56 (75.06) Prec@5 88.28 (90.90) + train[2018-10-20-03:51:18] Epoch: [154][8600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.072 (2.948) Prec@1 72.66 (75.06) Prec@5 86.72 (90.89) + train[2018-10-20-03:53:04] Epoch: [154][8800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.975 (2.948) Prec@1 70.31 (75.05) Prec@5 90.62 (90.89) + train[2018-10-20-03:54:49] Epoch: [154][9000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.801 (2.949) Prec@1 78.12 (75.04) Prec@5 91.41 (90.89) + train[2018-10-20-03:56:34] Epoch: [154][9200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.231 (2.948) Prec@1 69.53 (75.05) Prec@5 89.84 (90.89) + train[2018-10-20-03:58:19] Epoch: [154][9400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.940 (2.949) Prec@1 76.56 (75.03) Prec@5 92.19 (90.89) + train[2018-10-20-04:00:04] Epoch: [154][9600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.945 (2.949) Prec@1 75.78 (75.02) Prec@5 90.62 (90.88) + train[2018-10-20-04:01:51] Epoch: [154][9800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.797 (2.949) Prec@1 77.34 (75.02) Prec@5 92.19 (90.89) + train[2018-10-20-04:03:36] Epoch: [154][10000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.013 (2.950) Prec@1 75.00 (75.01) Prec@5 90.62 (90.88) + train[2018-10-20-04:03:40] Epoch: [154][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.125 (2.950) Prec@1 66.67 (75.01) Prec@5 80.00 (90.88) +[2018-10-20-04:03:40] **train** Prec@1 75.01 Prec@5 90.88 Error@1 24.99 Error@5 9.12 Loss:2.950 + test [2018-10-20-04:03:44] Epoch: [154][000/391] Time 3.51 (3.51) Data 3.38 (3.38) Loss 0.557 (0.557) Prec@1 91.41 (91.41) Prec@5 96.88 (96.88) + test [2018-10-20-04:04:11] Epoch: [154][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.223 (1.003) Prec@1 69.53 (76.93) Prec@5 92.19 (93.52) + test [2018-10-20-04:04:37] Epoch: [154][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.127 (1.173) Prec@1 46.25 (73.41) Prec@5 82.50 (91.25) +[2018-10-20-04:04:37] **test** Prec@1 73.41 Prec@5 91.25 Error@1 26.59 Error@5 8.75 Loss:1.173 +----> Best Accuracy : Acc@1=73.46, Acc@5=91.25, Error@1=26.54, Error@5=8.75 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-20-04:04:37] [Epoch=155/250] [Need: 141:05:02] LR=0.0009 ~ 0.0009, Batch=128 + train[2018-10-20-04:04:42] Epoch: [155][000/10010] Time 4.71 (4.71) Data 4.07 (4.07) Loss 3.117 (3.117) Prec@1 70.31 (70.31) Prec@5 89.06 (89.06) + train[2018-10-20-04:06:28] Epoch: [155][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 2.737 (2.963) Prec@1 79.69 (74.79) Prec@5 92.97 (90.69) + train[2018-10-20-04:08:13] Epoch: [155][400/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 3.022 (2.957) Prec@1 75.00 (74.93) Prec@5 89.06 (90.78) + train[2018-10-20-04:09:58] Epoch: [155][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.531 (2.952) Prec@1 64.84 (75.03) Prec@5 83.59 (90.76) + train[2018-10-20-04:11:43] Epoch: [155][800/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.057 (2.944) Prec@1 73.44 (75.13) Prec@5 91.41 (90.87) + train[2018-10-20-04:13:29] Epoch: [155][1000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.116 (2.946) Prec@1 70.31 (75.07) Prec@5 89.06 (90.84) + train[2018-10-20-04:15:14] Epoch: [155][1200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.933 (2.946) Prec@1 72.66 (75.09) Prec@5 90.62 (90.88) + train[2018-10-20-04:17:00] Epoch: [155][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.842 (2.942) Prec@1 79.69 (75.19) Prec@5 92.97 (90.92) + train[2018-10-20-04:18:45] Epoch: [155][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.924 (2.943) Prec@1 73.44 (75.18) Prec@5 89.84 (90.93) + train[2018-10-20-04:20:31] Epoch: [155][1800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.072 (2.944) Prec@1 73.44 (75.18) Prec@5 89.84 (90.94) + train[2018-10-20-04:22:16] Epoch: [155][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.098 (2.944) Prec@1 72.66 (75.17) Prec@5 88.28 (90.94) + train[2018-10-20-04:24:01] Epoch: [155][2200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.789 (2.944) Prec@1 72.66 (75.17) Prec@5 95.31 (90.95) + train[2018-10-20-04:25:46] Epoch: [155][2400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.964 (2.942) Prec@1 77.34 (75.21) Prec@5 89.06 (90.98) + train[2018-10-20-04:27:32] Epoch: [155][2600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.970 (2.941) Prec@1 75.00 (75.22) Prec@5 91.41 (90.99) + train[2018-10-20-04:29:17] Epoch: [155][2800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.148 (2.939) Prec@1 67.97 (75.25) Prec@5 89.06 (91.01) + train[2018-10-20-04:31:02] Epoch: [155][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.814 (2.939) Prec@1 78.12 (75.25) Prec@5 92.19 (91.02) + train[2018-10-20-04:32:47] Epoch: [155][3200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.050 (2.940) Prec@1 72.66 (75.24) Prec@5 86.72 (91.00) + train[2018-10-20-04:34:33] Epoch: [155][3400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.319 (2.941) Prec@1 68.75 (75.23) Prec@5 87.50 (91.00) + train[2018-10-20-04:36:19] Epoch: [155][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.821 (2.941) Prec@1 79.69 (75.24) Prec@5 92.97 (91.01) + train[2018-10-20-04:38:06] Epoch: [155][3800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.784 (2.941) Prec@1 77.34 (75.23) Prec@5 93.75 (91.01) + train[2018-10-20-04:39:53] Epoch: [155][4000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.600 (2.941) Prec@1 78.91 (75.23) Prec@5 93.75 (91.00) + train[2018-10-20-04:41:39] Epoch: [155][4200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.994 (2.941) Prec@1 74.22 (75.23) Prec@5 92.19 (91.01) + train[2018-10-20-04:43:26] Epoch: [155][4400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.073 (2.942) Prec@1 75.00 (75.20) Prec@5 88.28 (90.99) + train[2018-10-20-04:45:13] Epoch: [155][4600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.918 (2.942) Prec@1 73.44 (75.21) Prec@5 92.97 (91.00) + train[2018-10-20-04:47:00] Epoch: [155][4800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.049 (2.942) Prec@1 76.56 (75.20) Prec@5 90.62 (91.00) + train[2018-10-20-04:48:48] Epoch: [155][5000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.902 (2.942) Prec@1 75.00 (75.20) Prec@5 92.97 (90.99) + train[2018-10-20-04:50:34] Epoch: [155][5200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.093 (2.943) Prec@1 76.56 (75.17) Prec@5 89.84 (90.98) + train[2018-10-20-04:52:21] Epoch: [155][5400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.283 (2.943) Prec@1 68.75 (75.17) Prec@5 87.50 (90.98) + train[2018-10-20-04:54:08] Epoch: [155][5600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.822 (2.943) Prec@1 74.22 (75.16) Prec@5 93.75 (90.98) + train[2018-10-20-04:55:55] Epoch: [155][5800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.764 (2.944) Prec@1 78.12 (75.15) Prec@5 89.06 (90.98) + train[2018-10-20-04:57:43] Epoch: [155][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.916 (2.944) Prec@1 75.00 (75.15) Prec@5 92.19 (90.98) + train[2018-10-20-04:59:29] Epoch: [155][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.930 (2.944) Prec@1 74.22 (75.15) Prec@5 93.75 (90.98) + train[2018-10-20-05:01:15] Epoch: [155][6400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.798 (2.944) Prec@1 77.34 (75.14) Prec@5 92.97 (90.97) + train[2018-10-20-05:03:03] Epoch: [155][6600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.059 (2.945) Prec@1 68.75 (75.13) Prec@5 93.75 (90.96) + train[2018-10-20-05:04:50] Epoch: [155][6800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.988 (2.945) Prec@1 73.44 (75.12) Prec@5 92.97 (90.96) + train[2018-10-20-05:06:37] Epoch: [155][7000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.948 (2.946) Prec@1 76.56 (75.10) Prec@5 89.06 (90.95) + train[2018-10-20-05:08:24] Epoch: [155][7200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.872 (2.946) Prec@1 79.69 (75.11) Prec@5 93.75 (90.95) + train[2018-10-20-05:10:10] Epoch: [155][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.011 (2.945) Prec@1 76.56 (75.11) Prec@5 91.41 (90.96) + train[2018-10-20-05:11:57] Epoch: [155][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.081 (2.946) Prec@1 73.44 (75.10) Prec@5 89.84 (90.94) + train[2018-10-20-05:13:44] Epoch: [155][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.864 (2.946) Prec@1 79.69 (75.09) Prec@5 91.41 (90.94) + train[2018-10-20-05:15:30] Epoch: [155][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.188 (2.946) Prec@1 70.31 (75.09) Prec@5 89.06 (90.94) + train[2018-10-20-05:17:17] Epoch: [155][8200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.834 (2.947) Prec@1 75.78 (75.09) Prec@5 93.75 (90.94) + train[2018-10-20-05:19:04] Epoch: [155][8400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.938 (2.947) Prec@1 77.34 (75.09) Prec@5 91.41 (90.93) + train[2018-10-20-05:20:52] Epoch: [155][8600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.761 (2.947) Prec@1 78.12 (75.09) Prec@5 92.19 (90.94) + train[2018-10-20-05:22:38] Epoch: [155][8800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.782 (2.946) Prec@1 77.34 (75.10) Prec@5 94.53 (90.94) + train[2018-10-20-05:24:26] Epoch: [155][9000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.025 (2.946) Prec@1 73.44 (75.10) Prec@5 90.62 (90.94) + train[2018-10-20-05:26:12] Epoch: [155][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.978 (2.946) Prec@1 73.44 (75.09) Prec@5 89.06 (90.94) + train[2018-10-20-05:27:58] Epoch: [155][9400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.078 (2.947) Prec@1 72.66 (75.08) Prec@5 89.06 (90.94) + train[2018-10-20-05:29:45] Epoch: [155][9600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.104 (2.946) Prec@1 73.44 (75.08) Prec@5 87.50 (90.94) + train[2018-10-20-05:31:32] Epoch: [155][9800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.953 (2.947) Prec@1 75.78 (75.07) Prec@5 86.72 (90.92) + train[2018-10-20-05:33:19] Epoch: [155][10000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.859 (2.948) Prec@1 76.56 (75.06) Prec@5 92.19 (90.91) + train[2018-10-20-05:33:24] Epoch: [155][10009/10010] Time 0.14 (0.53) Data 0.00 (0.00) Loss 4.690 (2.947) Prec@1 46.67 (75.07) Prec@5 53.33 (90.91) +[2018-10-20-05:33:24] **train** Prec@1 75.07 Prec@5 90.91 Error@1 24.93 Error@5 9.09 Loss:2.947 + test [2018-10-20-05:33:28] Epoch: [155][000/391] Time 4.01 (4.01) Data 3.86 (3.86) Loss 0.561 (0.561) Prec@1 89.84 (89.84) Prec@5 97.66 (97.66) + test [2018-10-20-05:33:55] Epoch: [155][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.216 (1.005) Prec@1 68.75 (76.94) Prec@5 90.62 (93.47) + test [2018-10-20-05:34:19] Epoch: [155][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.041 (1.168) Prec@1 47.50 (73.45) Prec@5 81.25 (91.33) +[2018-10-20-05:34:19] **test** Prec@1 73.45 Prec@5 91.33 Error@1 26.55 Error@5 8.67 Loss:1.168 +----> Best Accuracy : Acc@1=73.46, Acc@5=91.25, Error@1=26.54, Error@5=8.75 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-20-05:34:19] [Epoch=156/250] [Need: 140:32:31] LR=0.0009 ~ 0.0009, Batch=128 + train[2018-10-20-05:34:24] Epoch: [156][000/10010] Time 4.26 (4.26) Data 3.60 (3.60) Loss 3.162 (3.162) Prec@1 72.66 (72.66) Prec@5 86.72 (86.72) + train[2018-10-20-05:36:09] Epoch: [156][200/10010] Time 0.51 (0.55) Data 0.00 (0.02) Loss 3.285 (2.944) Prec@1 68.75 (75.49) Prec@5 87.50 (90.89) + train[2018-10-20-05:37:54] Epoch: [156][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.983 (2.938) Prec@1 75.00 (75.44) Prec@5 92.19 (90.99) + train[2018-10-20-05:39:39] Epoch: [156][600/10010] Time 0.57 (0.53) Data 0.00 (0.01) Loss 2.804 (2.932) Prec@1 78.12 (75.52) Prec@5 91.41 (91.06) + train[2018-10-20-05:41:25] Epoch: [156][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 2.929 (2.933) Prec@1 75.00 (75.50) Prec@5 92.19 (91.03) + train[2018-10-20-05:43:09] Epoch: [156][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.989 (2.936) Prec@1 73.44 (75.45) Prec@5 90.62 (91.01) + train[2018-10-20-05:44:55] Epoch: [156][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.328 (2.938) Prec@1 68.75 (75.44) Prec@5 88.28 (91.02) + train[2018-10-20-05:46:39] Epoch: [156][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.735 (2.936) Prec@1 81.25 (75.48) Prec@5 92.97 (91.01) + train[2018-10-20-05:48:24] Epoch: [156][1600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.897 (2.938) Prec@1 73.44 (75.42) Prec@5 91.41 (91.00) + train[2018-10-20-05:50:09] Epoch: [156][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.910 (2.942) Prec@1 72.66 (75.31) Prec@5 87.50 (90.95) + train[2018-10-20-05:51:54] Epoch: [156][2000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.167 (2.941) Prec@1 67.97 (75.34) Prec@5 88.28 (90.96) + train[2018-10-20-05:53:39] Epoch: [156][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.835 (2.937) Prec@1 76.56 (75.39) Prec@5 95.31 (91.02) + train[2018-10-20-05:55:24] Epoch: [156][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.699 (2.936) Prec@1 79.69 (75.39) Prec@5 95.31 (91.03) + train[2018-10-20-05:57:09] Epoch: [156][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.096 (2.937) Prec@1 75.00 (75.39) Prec@5 89.06 (91.03) + train[2018-10-20-05:58:54] Epoch: [156][2800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.671 (2.937) Prec@1 82.03 (75.39) Prec@5 93.75 (91.01) + train[2018-10-20-06:00:40] Epoch: [156][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.991 (2.939) Prec@1 72.66 (75.36) Prec@5 90.62 (91.00) + train[2018-10-20-06:02:26] Epoch: [156][3200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.070 (2.939) Prec@1 69.53 (75.34) Prec@5 90.62 (91.00) + train[2018-10-20-06:04:13] Epoch: [156][3400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.117 (2.940) Prec@1 71.88 (75.33) Prec@5 87.50 (90.99) + train[2018-10-20-06:06:01] Epoch: [156][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.908 (2.940) Prec@1 74.22 (75.31) Prec@5 89.84 (90.99) + train[2018-10-20-06:07:47] Epoch: [156][3800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.834 (2.939) Prec@1 74.22 (75.32) Prec@5 92.97 (91.01) + train[2018-10-20-06:09:33] Epoch: [156][4000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.912 (2.939) Prec@1 71.88 (75.32) Prec@5 92.97 (91.00) + train[2018-10-20-06:11:20] Epoch: [156][4200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.964 (2.939) Prec@1 71.09 (75.33) Prec@5 91.41 (91.01) + train[2018-10-20-06:13:08] Epoch: [156][4400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.571 (2.940) Prec@1 85.16 (75.31) Prec@5 96.09 (90.99) + train[2018-10-20-06:14:55] Epoch: [156][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.741 (2.941) Prec@1 78.12 (75.28) Prec@5 93.75 (90.98) + train[2018-10-20-06:16:42] Epoch: [156][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.039 (2.941) Prec@1 73.44 (75.27) Prec@5 88.28 (90.98) + train[2018-10-20-06:18:29] Epoch: [156][5000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.823 (2.942) Prec@1 79.69 (75.25) Prec@5 91.41 (90.97) + train[2018-10-20-06:20:17] Epoch: [156][5200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.833 (2.943) Prec@1 80.47 (75.23) Prec@5 89.06 (90.96) + train[2018-10-20-06:22:02] Epoch: [156][5400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.556 (2.944) Prec@1 85.94 (75.22) Prec@5 92.19 (90.95) + train[2018-10-20-06:23:49] Epoch: [156][5600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.863 (2.944) Prec@1 71.88 (75.20) Prec@5 92.19 (90.95) + train[2018-10-20-06:25:35] Epoch: [156][5800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.614 (2.944) Prec@1 85.94 (75.20) Prec@5 94.53 (90.95) + train[2018-10-20-06:27:22] Epoch: [156][6000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.648 (2.944) Prec@1 80.47 (75.20) Prec@5 95.31 (90.96) + train[2018-10-20-06:29:09] Epoch: [156][6200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.809 (2.944) Prec@1 80.47 (75.18) Prec@5 92.97 (90.95) + train[2018-10-20-06:30:55] Epoch: [156][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.286 (2.944) Prec@1 70.31 (75.19) Prec@5 88.28 (90.95) + train[2018-10-20-06:32:42] Epoch: [156][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.800 (2.944) Prec@1 76.56 (75.17) Prec@5 93.75 (90.96) + train[2018-10-20-06:34:28] Epoch: [156][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.789 (2.945) Prec@1 79.69 (75.16) Prec@5 92.19 (90.95) + train[2018-10-20-06:36:15] Epoch: [156][7000/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 3.109 (2.945) Prec@1 71.09 (75.14) Prec@5 87.50 (90.94) + train[2018-10-20-06:38:01] Epoch: [156][7200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.099 (2.945) Prec@1 75.00 (75.15) Prec@5 91.41 (90.94) + train[2018-10-20-06:39:48] Epoch: [156][7400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.301 (2.945) Prec@1 67.19 (75.14) Prec@5 87.50 (90.94) + train[2018-10-20-06:41:35] Epoch: [156][7600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.183 (2.946) Prec@1 68.75 (75.14) Prec@5 88.28 (90.94) + train[2018-10-20-06:43:21] Epoch: [156][7800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.070 (2.946) Prec@1 73.44 (75.13) Prec@5 88.28 (90.94) + train[2018-10-20-06:45:09] Epoch: [156][8000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.169 (2.946) Prec@1 69.53 (75.14) Prec@5 87.50 (90.94) + train[2018-10-20-06:46:57] Epoch: [156][8200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.869 (2.945) Prec@1 76.56 (75.14) Prec@5 90.62 (90.94) + train[2018-10-20-06:48:43] Epoch: [156][8400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.887 (2.945) Prec@1 78.12 (75.14) Prec@5 90.62 (90.94) + train[2018-10-20-06:50:31] Epoch: [156][8600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.952 (2.945) Prec@1 72.66 (75.13) Prec@5 91.41 (90.94) + train[2018-10-20-06:52:18] Epoch: [156][8800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.040 (2.945) Prec@1 74.22 (75.12) Prec@5 84.38 (90.94) + train[2018-10-20-06:54:05] Epoch: [156][9000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.084 (2.945) Prec@1 71.09 (75.12) Prec@5 88.28 (90.94) + train[2018-10-20-06:55:51] Epoch: [156][9200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.215 (2.946) Prec@1 67.19 (75.11) Prec@5 85.94 (90.94) + train[2018-10-20-06:57:39] Epoch: [156][9400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.885 (2.946) Prec@1 73.44 (75.10) Prec@5 93.75 (90.93) + train[2018-10-20-06:59:27] Epoch: [156][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.893 (2.946) Prec@1 80.47 (75.09) Prec@5 89.06 (90.93) + train[2018-10-20-07:01:13] Epoch: [156][9800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.844 (2.947) Prec@1 75.00 (75.09) Prec@5 92.97 (90.93) + train[2018-10-20-07:02:59] Epoch: [156][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.070 (2.947) Prec@1 76.56 (75.09) Prec@5 89.06 (90.93) + train[2018-10-20-07:03:03] Epoch: [156][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 3.106 (2.947) Prec@1 73.33 (75.09) Prec@5 93.33 (90.93) +[2018-10-20-07:03:03] **train** Prec@1 75.09 Prec@5 90.93 Error@1 24.91 Error@5 9.07 Loss:2.947 + test [2018-10-20-07:03:07] Epoch: [156][000/391] Time 4.10 (4.10) Data 3.96 (3.96) Loss 0.572 (0.572) Prec@1 91.41 (91.41) Prec@5 97.66 (97.66) + test [2018-10-20-07:03:34] Epoch: [156][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.142 (1.003) Prec@1 70.31 (77.06) Prec@5 93.75 (93.41) + test [2018-10-20-07:03:58] Epoch: [156][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.064 (1.171) Prec@1 43.75 (73.44) Prec@5 83.75 (91.31) +[2018-10-20-07:03:58] **test** Prec@1 73.44 Prec@5 91.31 Error@1 26.56 Error@5 8.69 Loss:1.171 +----> Best Accuracy : Acc@1=73.46, Acc@5=91.25, Error@1=26.54, Error@5=8.75 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-20-07:03:59] [Epoch=157/250] [Need: 138:57:47] LR=0.0008 ~ 0.0008, Batch=128 + train[2018-10-20-07:04:04] Epoch: [157][000/10010] Time 5.24 (5.24) Data 4.57 (4.57) Loss 3.059 (3.059) Prec@1 74.22 (74.22) Prec@5 86.72 (86.72) + train[2018-10-20-07:05:49] Epoch: [157][200/10010] Time 0.51 (0.55) Data 0.00 (0.02) Loss 2.986 (2.933) Prec@1 75.78 (75.47) Prec@5 88.28 (90.82) + train[2018-10-20-07:07:34] Epoch: [157][400/10010] Time 0.54 (0.54) Data 0.00 (0.01) Loss 2.671 (2.933) Prec@1 79.69 (75.42) Prec@5 92.19 (90.92) + train[2018-10-20-07:09:20] Epoch: [157][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.938 (2.935) Prec@1 75.78 (75.35) Prec@5 89.06 (90.94) + train[2018-10-20-07:11:05] Epoch: [157][800/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 2.988 (2.938) Prec@1 74.22 (75.25) Prec@5 89.84 (90.94) + train[2018-10-20-07:12:50] Epoch: [157][1000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.698 (2.942) Prec@1 80.47 (75.21) Prec@5 94.53 (90.93) + train[2018-10-20-07:14:36] Epoch: [157][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.873 (2.940) Prec@1 76.56 (75.26) Prec@5 93.75 (90.97) + train[2018-10-20-07:16:21] Epoch: [157][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.802 (2.940) Prec@1 75.00 (75.27) Prec@5 92.97 (90.97) + train[2018-10-20-07:18:06] Epoch: [157][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.899 (2.941) Prec@1 77.34 (75.23) Prec@5 92.97 (90.95) + train[2018-10-20-07:19:51] Epoch: [157][1800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.997 (2.940) Prec@1 72.66 (75.23) Prec@5 91.41 (90.97) + train[2018-10-20-07:21:35] Epoch: [157][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.805 (2.940) Prec@1 78.12 (75.24) Prec@5 91.41 (90.97) + train[2018-10-20-07:23:21] Epoch: [157][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.756 (2.940) Prec@1 82.03 (75.23) Prec@5 91.41 (90.97) + train[2018-10-20-07:25:06] Epoch: [157][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.711 (2.941) Prec@1 77.34 (75.24) Prec@5 95.31 (90.96) + train[2018-10-20-07:26:52] Epoch: [157][2600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.764 (2.941) Prec@1 78.12 (75.24) Prec@5 94.53 (90.96) + train[2018-10-20-07:28:37] Epoch: [157][2800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.940 (2.941) Prec@1 72.66 (75.23) Prec@5 92.19 (90.97) + train[2018-10-20-07:30:24] Epoch: [157][3000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.195 (2.941) Prec@1 71.09 (75.21) Prec@5 89.84 (90.96) + train[2018-10-20-07:32:11] Epoch: [157][3200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.693 (2.941) Prec@1 81.25 (75.22) Prec@5 93.75 (90.94) + train[2018-10-20-07:33:58] Epoch: [157][3400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.948 (2.942) Prec@1 76.56 (75.20) Prec@5 86.72 (90.93) + train[2018-10-20-07:35:46] Epoch: [157][3600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.953 (2.941) Prec@1 75.00 (75.22) Prec@5 92.19 (90.93) + train[2018-10-20-07:37:33] Epoch: [157][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.775 (2.941) Prec@1 78.12 (75.21) Prec@5 92.97 (90.94) + train[2018-10-20-07:39:21] Epoch: [157][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.020 (2.942) Prec@1 75.00 (75.22) Prec@5 90.62 (90.93) + train[2018-10-20-07:41:07] Epoch: [157][4200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.837 (2.942) Prec@1 79.69 (75.21) Prec@5 93.75 (90.93) + train[2018-10-20-07:42:55] Epoch: [157][4400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.189 (2.942) Prec@1 75.00 (75.21) Prec@5 86.72 (90.94) + train[2018-10-20-07:44:43] Epoch: [157][4600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.590 (2.942) Prec@1 82.03 (75.21) Prec@5 92.19 (90.94) + train[2018-10-20-07:46:30] Epoch: [157][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.027 (2.941) Prec@1 73.44 (75.22) Prec@5 90.62 (90.96) + train[2018-10-20-07:48:17] Epoch: [157][5000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.456 (2.940) Prec@1 82.03 (75.23) Prec@5 94.53 (90.96) + train[2018-10-20-07:50:03] Epoch: [157][5200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.308 (2.941) Prec@1 71.09 (75.22) Prec@5 86.72 (90.94) + train[2018-10-20-07:51:51] Epoch: [157][5400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.989 (2.941) Prec@1 77.34 (75.21) Prec@5 88.28 (90.94) + train[2018-10-20-07:53:38] Epoch: [157][5600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.648 (2.941) Prec@1 79.69 (75.20) Prec@5 94.53 (90.95) + train[2018-10-20-07:55:24] Epoch: [157][5800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.891 (2.941) Prec@1 75.00 (75.20) Prec@5 90.62 (90.95) + train[2018-10-20-07:57:11] Epoch: [157][6000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.115 (2.942) Prec@1 74.22 (75.20) Prec@5 85.94 (90.94) + train[2018-10-20-07:58:56] Epoch: [157][6200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.198 (2.942) Prec@1 71.09 (75.19) Prec@5 88.28 (90.94) + train[2018-10-20-08:00:44] Epoch: [157][6400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.931 (2.942) Prec@1 75.00 (75.19) Prec@5 90.62 (90.94) + train[2018-10-20-08:02:32] Epoch: [157][6600/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.545 (2.942) Prec@1 86.72 (75.20) Prec@5 93.75 (90.94) + train[2018-10-20-08:04:20] Epoch: [157][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.991 (2.942) Prec@1 74.22 (75.19) Prec@5 90.62 (90.95) + train[2018-10-20-08:06:07] Epoch: [157][7000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.319 (2.942) Prec@1 71.09 (75.19) Prec@5 89.06 (90.94) + train[2018-10-20-08:07:54] Epoch: [157][7200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.977 (2.941) Prec@1 75.00 (75.20) Prec@5 89.84 (90.95) + train[2018-10-20-08:09:41] Epoch: [157][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.758 (2.942) Prec@1 76.56 (75.19) Prec@5 92.97 (90.95) + train[2018-10-20-08:11:29] Epoch: [157][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.939 (2.942) Prec@1 76.56 (75.18) Prec@5 90.62 (90.95) + train[2018-10-20-08:13:17] Epoch: [157][7800/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.671 (2.942) Prec@1 78.91 (75.17) Prec@5 93.75 (90.95) + train[2018-10-20-08:15:05] Epoch: [157][8000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.094 (2.943) Prec@1 71.09 (75.17) Prec@5 92.97 (90.94) + train[2018-10-20-08:16:53] Epoch: [157][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.803 (2.942) Prec@1 78.12 (75.17) Prec@5 91.41 (90.95) + train[2018-10-20-08:18:40] Epoch: [157][8400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.880 (2.943) Prec@1 77.34 (75.16) Prec@5 91.41 (90.95) + train[2018-10-20-08:20:28] Epoch: [157][8600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.958 (2.942) Prec@1 75.78 (75.16) Prec@5 91.41 (90.94) + train[2018-10-20-08:22:16] Epoch: [157][8800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.889 (2.942) Prec@1 70.31 (75.16) Prec@5 92.19 (90.95) + train[2018-10-20-08:24:04] Epoch: [157][9000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.965 (2.943) Prec@1 71.09 (75.16) Prec@5 91.41 (90.95) + train[2018-10-20-08:25:51] Epoch: [157][9200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.235 (2.943) Prec@1 70.31 (75.16) Prec@5 85.16 (90.95) + train[2018-10-20-08:27:37] Epoch: [157][9400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.102 (2.943) Prec@1 71.88 (75.15) Prec@5 89.84 (90.95) + train[2018-10-20-08:29:25] Epoch: [157][9600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.715 (2.943) Prec@1 76.56 (75.15) Prec@5 93.75 (90.96) + train[2018-10-20-08:31:12] Epoch: [157][9800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.791 (2.943) Prec@1 78.91 (75.14) Prec@5 91.41 (90.95) + train[2018-10-20-08:32:58] Epoch: [157][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.015 (2.944) Prec@1 74.22 (75.14) Prec@5 92.97 (90.95) + train[2018-10-20-08:33:02] Epoch: [157][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 3.078 (2.944) Prec@1 73.33 (75.14) Prec@5 93.33 (90.95) +[2018-10-20-08:33:02] **train** Prec@1 75.14 Prec@5 90.95 Error@1 24.86 Error@5 9.05 Loss:2.944 + test [2018-10-20-08:33:06] Epoch: [157][000/391] Time 4.07 (4.07) Data 3.93 (3.93) Loss 0.530 (0.530) Prec@1 92.97 (92.97) Prec@5 99.22 (99.22) + test [2018-10-20-08:33:33] Epoch: [157][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.221 (1.018) Prec@1 70.31 (77.19) Prec@5 92.19 (93.49) + test [2018-10-20-08:33:58] Epoch: [157][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.087 (1.188) Prec@1 43.75 (73.56) Prec@5 83.75 (91.28) +[2018-10-20-08:33:58] **test** Prec@1 73.56 Prec@5 91.28 Error@1 26.44 Error@5 8.72 Loss:1.188 +----> Best Accuracy : Acc@1=73.56, Acc@5=91.28, Error@1=26.44, Error@5=8.72 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-20-08:33:58] [Epoch=158/250] [Need: 137:58:40] LR=0.0008 ~ 0.0008, Batch=128 + train[2018-10-20-08:34:03] Epoch: [158][000/10010] Time 5.19 (5.19) Data 4.60 (4.60) Loss 2.941 (2.941) Prec@1 73.44 (73.44) Prec@5 89.84 (89.84) + train[2018-10-20-08:35:48] Epoch: [158][200/10010] Time 0.54 (0.55) Data 0.00 (0.02) Loss 3.094 (2.956) Prec@1 72.66 (74.95) Prec@5 92.19 (90.88) + train[2018-10-20-08:37:34] Epoch: [158][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.975 (2.943) Prec@1 75.78 (75.21) Prec@5 87.50 (90.93) + train[2018-10-20-08:39:19] Epoch: [158][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.229 (2.936) Prec@1 70.31 (75.41) Prec@5 87.50 (91.04) + train[2018-10-20-08:41:03] Epoch: [158][800/10010] Time 0.58 (0.53) Data 0.00 (0.01) Loss 2.775 (2.941) Prec@1 76.56 (75.32) Prec@5 91.41 (90.95) + train[2018-10-20-08:42:49] Epoch: [158][1000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.973 (2.943) Prec@1 75.00 (75.30) Prec@5 86.72 (90.90) + train[2018-10-20-08:44:34] Epoch: [158][1200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.085 (2.941) Prec@1 72.66 (75.30) Prec@5 89.06 (90.92) + train[2018-10-20-08:46:20] Epoch: [158][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.161 (2.938) Prec@1 73.44 (75.31) Prec@5 85.16 (90.96) + train[2018-10-20-08:48:05] Epoch: [158][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.732 (2.938) Prec@1 79.69 (75.30) Prec@5 91.41 (91.00) + train[2018-10-20-08:49:50] Epoch: [158][1800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.026 (2.938) Prec@1 74.22 (75.32) Prec@5 92.19 (91.02) + train[2018-10-20-08:51:35] Epoch: [158][2000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.038 (2.937) Prec@1 72.66 (75.31) Prec@5 90.62 (91.02) + train[2018-10-20-08:53:20] Epoch: [158][2200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.626 (2.938) Prec@1 79.69 (75.30) Prec@5 95.31 (91.02) + train[2018-10-20-08:55:06] Epoch: [158][2400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.767 (2.939) Prec@1 77.34 (75.29) Prec@5 91.41 (91.01) + train[2018-10-20-08:56:52] Epoch: [158][2600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.920 (2.938) Prec@1 74.22 (75.29) Prec@5 89.06 (91.03) + train[2018-10-20-08:58:38] Epoch: [158][2800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.836 (2.937) Prec@1 79.69 (75.32) Prec@5 92.19 (91.04) + train[2018-10-20-09:00:24] Epoch: [158][3000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.886 (2.937) Prec@1 71.09 (75.33) Prec@5 94.53 (91.03) + train[2018-10-20-09:02:11] Epoch: [158][3200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.922 (2.936) Prec@1 77.34 (75.36) Prec@5 93.75 (91.02) + train[2018-10-20-09:03:56] Epoch: [158][3400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.890 (2.937) Prec@1 78.91 (75.34) Prec@5 91.41 (91.01) + train[2018-10-20-09:05:43] Epoch: [158][3600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.817 (2.938) Prec@1 77.34 (75.32) Prec@5 93.75 (91.00) + train[2018-10-20-09:07:29] Epoch: [158][3800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.217 (2.937) Prec@1 66.41 (75.33) Prec@5 87.50 (91.01) + train[2018-10-20-09:09:15] Epoch: [158][4000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.710 (2.937) Prec@1 80.47 (75.34) Prec@5 90.62 (91.02) + train[2018-10-20-09:11:02] Epoch: [158][4200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.810 (2.936) Prec@1 78.91 (75.34) Prec@5 89.06 (91.02) + train[2018-10-20-09:12:48] Epoch: [158][4400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.012 (2.937) Prec@1 70.31 (75.33) Prec@5 89.06 (91.02) + train[2018-10-20-09:14:35] Epoch: [158][4600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.672 (2.938) Prec@1 82.81 (75.31) Prec@5 92.97 (91.01) + train[2018-10-20-09:16:21] Epoch: [158][4800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.841 (2.937) Prec@1 77.34 (75.31) Prec@5 87.50 (91.02) + train[2018-10-20-09:18:06] Epoch: [158][5000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.645 (2.938) Prec@1 80.47 (75.29) Prec@5 94.53 (91.01) + train[2018-10-20-09:19:52] Epoch: [158][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.114 (2.938) Prec@1 71.88 (75.28) Prec@5 89.06 (91.01) + train[2018-10-20-09:21:38] Epoch: [158][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.306 (2.938) Prec@1 74.22 (75.29) Prec@5 85.16 (91.01) + train[2018-10-20-09:23:25] Epoch: [158][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.986 (2.938) Prec@1 76.56 (75.29) Prec@5 89.06 (91.01) + train[2018-10-20-09:25:11] Epoch: [158][5800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.751 (2.938) Prec@1 84.38 (75.28) Prec@5 93.75 (91.01) + train[2018-10-20-09:26:57] Epoch: [158][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.920 (2.937) Prec@1 77.34 (75.30) Prec@5 91.41 (91.01) + train[2018-10-20-09:28:44] Epoch: [158][6200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.986 (2.938) Prec@1 72.66 (75.29) Prec@5 87.50 (91.01) + train[2018-10-20-09:30:31] Epoch: [158][6400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.159 (2.939) Prec@1 71.88 (75.28) Prec@5 91.41 (91.00) + train[2018-10-20-09:32:18] Epoch: [158][6600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.999 (2.939) Prec@1 71.88 (75.29) Prec@5 89.06 (91.00) + train[2018-10-20-09:34:05] Epoch: [158][6800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.862 (2.940) Prec@1 78.91 (75.27) Prec@5 92.19 (90.99) + train[2018-10-20-09:35:53] Epoch: [158][7000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.093 (2.940) Prec@1 72.66 (75.26) Prec@5 89.84 (90.99) + train[2018-10-20-09:37:39] Epoch: [158][7200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.004 (2.941) Prec@1 70.31 (75.25) Prec@5 90.62 (90.98) + train[2018-10-20-09:39:27] Epoch: [158][7400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.844 (2.940) Prec@1 78.12 (75.25) Prec@5 92.97 (90.98) + train[2018-10-20-09:41:15] Epoch: [158][7600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.220 (2.941) Prec@1 72.66 (75.25) Prec@5 88.28 (90.98) + train[2018-10-20-09:43:02] Epoch: [158][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.293 (2.941) Prec@1 67.97 (75.23) Prec@5 86.72 (90.97) + train[2018-10-20-09:44:48] Epoch: [158][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.001 (2.941) Prec@1 73.44 (75.23) Prec@5 90.62 (90.97) + train[2018-10-20-09:46:35] Epoch: [158][8200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.487 (2.941) Prec@1 66.41 (75.22) Prec@5 84.38 (90.97) + train[2018-10-20-09:48:21] Epoch: [158][8400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.858 (2.941) Prec@1 75.00 (75.22) Prec@5 91.41 (90.97) + train[2018-10-20-09:50:07] Epoch: [158][8600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.831 (2.942) Prec@1 78.12 (75.21) Prec@5 92.19 (90.96) + train[2018-10-20-09:51:54] Epoch: [158][8800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.090 (2.942) Prec@1 68.75 (75.22) Prec@5 89.06 (90.96) + train[2018-10-20-09:53:40] Epoch: [158][9000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.785 (2.942) Prec@1 73.44 (75.21) Prec@5 93.75 (90.96) + train[2018-10-20-09:55:27] Epoch: [158][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.287 (2.942) Prec@1 71.09 (75.20) Prec@5 86.72 (90.96) + train[2018-10-20-09:57:13] Epoch: [158][9400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.067 (2.942) Prec@1 71.09 (75.20) Prec@5 89.84 (90.96) + train[2018-10-20-09:58:59] Epoch: [158][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.019 (2.942) Prec@1 75.00 (75.20) Prec@5 89.06 (90.95) + train[2018-10-20-10:00:45] Epoch: [158][9800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.185 (2.942) Prec@1 69.53 (75.19) Prec@5 90.62 (90.95) + train[2018-10-20-10:02:31] Epoch: [158][10000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.028 (2.943) Prec@1 75.78 (75.18) Prec@5 89.84 (90.95) + train[2018-10-20-10:02:35] Epoch: [158][10009/10010] Time 0.21 (0.53) Data 0.00 (0.00) Loss 3.585 (2.943) Prec@1 73.33 (75.18) Prec@5 80.00 (90.95) +[2018-10-20-10:02:35] **train** Prec@1 75.18 Prec@5 90.95 Error@1 24.82 Error@5 9.05 Loss:2.943 + test [2018-10-20-10:02:39] Epoch: [158][000/391] Time 4.07 (4.07) Data 3.94 (3.94) Loss 0.517 (0.517) Prec@1 91.41 (91.41) Prec@5 98.44 (98.44) + test [2018-10-20-10:03:06] Epoch: [158][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.207 (1.011) Prec@1 66.41 (77.07) Prec@5 92.97 (93.70) + test [2018-10-20-10:03:32] Epoch: [158][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.049 (1.175) Prec@1 47.50 (73.58) Prec@5 82.50 (91.48) +[2018-10-20-10:03:32] **test** Prec@1 73.58 Prec@5 91.48 Error@1 26.42 Error@5 8.52 Loss:1.175 +----> Best Accuracy : Acc@1=73.58, Acc@5=91.48, Error@1=26.42, Error@5=8.52 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-20-10:03:32] [Epoch=159/250] [Need: 135:50:33] LR=0.0008 ~ 0.0008, Batch=128 + train[2018-10-20-10:03:37] Epoch: [159][000/10010] Time 5.04 (5.04) Data 4.47 (4.47) Loss 3.322 (3.322) Prec@1 71.09 (71.09) Prec@5 85.94 (85.94) + train[2018-10-20-10:05:22] Epoch: [159][200/10010] Time 0.55 (0.55) Data 0.00 (0.02) Loss 2.931 (2.941) Prec@1 76.56 (75.18) Prec@5 91.41 (90.96) + train[2018-10-20-10:07:08] Epoch: [159][400/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 2.987 (2.941) Prec@1 71.09 (75.21) Prec@5 88.28 (90.98) + train[2018-10-20-10:08:53] Epoch: [159][600/10010] Time 0.58 (0.54) Data 0.00 (0.01) Loss 2.921 (2.938) Prec@1 75.78 (75.32) Prec@5 90.62 (91.04) + train[2018-10-20-10:10:39] Epoch: [159][800/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 2.815 (2.941) Prec@1 80.47 (75.29) Prec@5 91.41 (91.00) + train[2018-10-20-10:12:25] Epoch: [159][1000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.232 (2.936) Prec@1 67.97 (75.32) Prec@5 86.72 (91.05) + train[2018-10-20-10:14:10] Epoch: [159][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.861 (2.938) Prec@1 77.34 (75.35) Prec@5 92.19 (91.02) + train[2018-10-20-10:15:55] Epoch: [159][1400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.763 (2.936) Prec@1 81.25 (75.32) Prec@5 92.97 (91.05) + train[2018-10-20-10:17:41] Epoch: [159][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.741 (2.937) Prec@1 80.47 (75.31) Prec@5 91.41 (91.01) + train[2018-10-20-10:19:26] Epoch: [159][1800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.029 (2.936) Prec@1 75.00 (75.35) Prec@5 89.84 (91.02) + train[2018-10-20-10:21:12] Epoch: [159][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.962 (2.937) Prec@1 75.00 (75.32) Prec@5 89.06 (90.99) + train[2018-10-20-10:22:57] Epoch: [159][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.914 (2.940) Prec@1 74.22 (75.29) Prec@5 92.97 (90.96) + train[2018-10-20-10:24:42] Epoch: [159][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.102 (2.942) Prec@1 73.44 (75.26) Prec@5 89.84 (90.95) + train[2018-10-20-10:26:26] Epoch: [159][2600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.307 (2.941) Prec@1 70.31 (75.31) Prec@5 87.50 (90.95) + train[2018-10-20-10:28:12] Epoch: [159][2800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.969 (2.940) Prec@1 76.56 (75.32) Prec@5 91.41 (90.97) + train[2018-10-20-10:29:58] Epoch: [159][3000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.768 (2.941) Prec@1 79.69 (75.31) Prec@5 94.53 (90.95) + train[2018-10-20-10:31:45] Epoch: [159][3200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.030 (2.941) Prec@1 71.09 (75.31) Prec@5 90.62 (90.96) + train[2018-10-20-10:33:33] Epoch: [159][3400/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 3.299 (2.940) Prec@1 68.75 (75.31) Prec@5 87.50 (90.97) + train[2018-10-20-10:35:21] Epoch: [159][3600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.861 (2.938) Prec@1 79.69 (75.33) Prec@5 89.84 (91.00) + train[2018-10-20-10:37:08] Epoch: [159][3800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.639 (2.938) Prec@1 81.25 (75.34) Prec@5 95.31 (91.01) + train[2018-10-20-10:38:55] Epoch: [159][4000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.781 (2.938) Prec@1 78.12 (75.32) Prec@5 92.97 (91.00) + train[2018-10-20-10:40:42] Epoch: [159][4200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.000 (2.938) Prec@1 72.66 (75.32) Prec@5 92.19 (91.01) + train[2018-10-20-10:42:29] Epoch: [159][4400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.341 (2.938) Prec@1 67.19 (75.32) Prec@5 84.38 (91.01) + train[2018-10-20-10:44:17] Epoch: [159][4600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.810 (2.938) Prec@1 75.78 (75.31) Prec@5 92.97 (91.00) + train[2018-10-20-10:46:03] Epoch: [159][4800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.900 (2.938) Prec@1 76.56 (75.31) Prec@5 92.19 (91.00) + train[2018-10-20-10:47:49] Epoch: [159][5000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.954 (2.939) Prec@1 76.56 (75.29) Prec@5 89.84 (90.99) + train[2018-10-20-10:49:35] Epoch: [159][5200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.933 (2.939) Prec@1 77.34 (75.28) Prec@5 89.06 (90.98) + train[2018-10-20-10:51:22] Epoch: [159][5400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.752 (2.939) Prec@1 78.91 (75.28) Prec@5 91.41 (90.98) + train[2018-10-20-10:53:09] Epoch: [159][5600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.236 (2.939) Prec@1 69.53 (75.28) Prec@5 87.50 (90.98) + train[2018-10-20-10:54:56] Epoch: [159][5800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.883 (2.939) Prec@1 78.91 (75.28) Prec@5 92.19 (90.97) + train[2018-10-20-10:56:42] Epoch: [159][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.851 (2.940) Prec@1 79.69 (75.26) Prec@5 89.06 (90.96) + train[2018-10-20-10:58:27] Epoch: [159][6200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.929 (2.940) Prec@1 74.22 (75.24) Prec@5 89.84 (90.95) + train[2018-10-20-11:00:13] Epoch: [159][6400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.576 (2.939) Prec@1 82.03 (75.25) Prec@5 92.97 (90.97) + train[2018-10-20-11:02:00] Epoch: [159][6600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.142 (2.938) Prec@1 70.31 (75.26) Prec@5 90.62 (90.98) + train[2018-10-20-11:03:46] Epoch: [159][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.056 (2.938) Prec@1 75.00 (75.27) Prec@5 86.72 (90.99) + train[2018-10-20-11:05:32] Epoch: [159][7000/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 3.056 (2.938) Prec@1 71.88 (75.28) Prec@5 90.62 (91.00) + train[2018-10-20-11:07:17] Epoch: [159][7200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.945 (2.938) Prec@1 71.09 (75.27) Prec@5 92.19 (90.99) + train[2018-10-20-11:09:02] Epoch: [159][7400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.850 (2.938) Prec@1 75.00 (75.26) Prec@5 91.41 (90.99) + train[2018-10-20-11:10:49] Epoch: [159][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.022 (2.938) Prec@1 74.22 (75.26) Prec@5 89.84 (90.99) + train[2018-10-20-11:12:35] Epoch: [159][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.101 (2.938) Prec@1 71.88 (75.26) Prec@5 89.84 (91.00) + train[2018-10-20-11:14:21] Epoch: [159][8000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.346 (2.938) Prec@1 71.88 (75.25) Prec@5 86.72 (91.00) + train[2018-10-20-11:16:06] Epoch: [159][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.639 (2.939) Prec@1 82.03 (75.24) Prec@5 95.31 (90.99) + train[2018-10-20-11:17:52] Epoch: [159][8400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.007 (2.939) Prec@1 71.88 (75.25) Prec@5 86.72 (90.99) + train[2018-10-20-11:19:39] Epoch: [159][8600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.725 (2.939) Prec@1 79.69 (75.25) Prec@5 92.19 (90.99) + train[2018-10-20-11:21:26] Epoch: [159][8800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.697 (2.939) Prec@1 77.34 (75.25) Prec@5 91.41 (91.00) + train[2018-10-20-11:23:13] Epoch: [159][9000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.778 (2.939) Prec@1 79.69 (75.24) Prec@5 91.41 (90.99) + train[2018-10-20-11:25:01] Epoch: [159][9200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.732 (2.939) Prec@1 77.34 (75.24) Prec@5 94.53 (90.99) + train[2018-10-20-11:26:49] Epoch: [159][9400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.993 (2.940) Prec@1 75.00 (75.23) Prec@5 92.19 (90.98) + train[2018-10-20-11:28:37] Epoch: [159][9600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.973 (2.940) Prec@1 71.09 (75.22) Prec@5 91.41 (90.99) + train[2018-10-20-11:30:25] Epoch: [159][9800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.948 (2.940) Prec@1 73.44 (75.22) Prec@5 91.41 (90.98) + train[2018-10-20-11:32:11] Epoch: [159][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.093 (2.940) Prec@1 75.00 (75.21) Prec@5 89.84 (90.98) + train[2018-10-20-11:32:15] Epoch: [159][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 2.941 (2.940) Prec@1 73.33 (75.21) Prec@5 86.67 (90.98) +[2018-10-20-11:32:15] **train** Prec@1 75.21 Prec@5 90.98 Error@1 24.79 Error@5 9.02 Loss:2.940 + test [2018-10-20-11:32:19] Epoch: [159][000/391] Time 4.26 (4.26) Data 4.13 (4.13) Loss 0.470 (0.470) Prec@1 94.53 (94.53) Prec@5 99.22 (99.22) + test [2018-10-20-11:32:46] Epoch: [159][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.203 (0.990) Prec@1 63.28 (77.15) Prec@5 92.97 (93.72) + test [2018-10-20-11:33:10] Epoch: [159][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.142 (1.159) Prec@1 41.25 (73.51) Prec@5 82.50 (91.39) +[2018-10-20-11:33:11] **test** Prec@1 73.51 Prec@5 91.39 Error@1 26.49 Error@5 8.61 Loss:1.159 +----> Best Accuracy : Acc@1=73.58, Acc@5=91.48, Error@1=26.42, Error@5=8.52 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-20-11:33:11] [Epoch=160/250] [Need: 134:28:23] LR=0.0008 ~ 0.0008, Batch=128 + train[2018-10-20-11:33:15] Epoch: [160][000/10010] Time 4.68 (4.68) Data 4.05 (4.05) Loss 2.737 (2.737) Prec@1 77.34 (77.34) Prec@5 94.53 (94.53) + train[2018-10-20-11:35:01] Epoch: [160][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 2.986 (2.934) Prec@1 75.78 (75.50) Prec@5 89.06 (90.99) + train[2018-10-20-11:36:46] Epoch: [160][400/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.971 (2.928) Prec@1 77.34 (75.55) Prec@5 87.50 (91.01) + train[2018-10-20-11:38:32] Epoch: [160][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 2.846 (2.926) Prec@1 78.12 (75.65) Prec@5 91.41 (91.08) + train[2018-10-20-11:40:16] Epoch: [160][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.852 (2.928) Prec@1 78.91 (75.59) Prec@5 89.84 (91.04) + train[2018-10-20-11:42:01] Epoch: [160][1000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.818 (2.928) Prec@1 74.22 (75.64) Prec@5 92.97 (91.03) + train[2018-10-20-11:43:46] Epoch: [160][1200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.918 (2.924) Prec@1 78.91 (75.67) Prec@5 89.84 (91.10) + train[2018-10-20-11:45:32] Epoch: [160][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.837 (2.924) Prec@1 77.34 (75.64) Prec@5 92.97 (91.11) + train[2018-10-20-11:47:18] Epoch: [160][1600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.080 (2.924) Prec@1 73.44 (75.59) Prec@5 90.62 (91.10) + train[2018-10-20-11:49:03] Epoch: [160][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.012 (2.926) Prec@1 73.44 (75.53) Prec@5 89.06 (91.10) + train[2018-10-20-11:50:48] Epoch: [160][2000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.040 (2.926) Prec@1 73.44 (75.52) Prec@5 90.62 (91.10) + train[2018-10-20-11:52:34] Epoch: [160][2200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.988 (2.926) Prec@1 70.31 (75.52) Prec@5 92.97 (91.09) + train[2018-10-20-11:54:20] Epoch: [160][2400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.026 (2.928) Prec@1 72.66 (75.48) Prec@5 86.72 (91.08) + train[2018-10-20-11:56:07] Epoch: [160][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.353 (2.929) Prec@1 67.19 (75.46) Prec@5 89.06 (91.07) + train[2018-10-20-11:57:52] Epoch: [160][2800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.858 (2.929) Prec@1 77.34 (75.46) Prec@5 92.19 (91.07) + train[2018-10-20-11:59:38] Epoch: [160][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.904 (2.930) Prec@1 71.09 (75.45) Prec@5 92.19 (91.06) + train[2018-10-20-12:01:24] Epoch: [160][3200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.793 (2.930) Prec@1 81.25 (75.44) Prec@5 89.84 (91.05) + train[2018-10-20-12:03:09] Epoch: [160][3400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.856 (2.929) Prec@1 78.91 (75.44) Prec@5 90.62 (91.06) + train[2018-10-20-12:04:55] Epoch: [160][3600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.884 (2.930) Prec@1 79.69 (75.44) Prec@5 90.62 (91.06) + train[2018-10-20-12:06:40] Epoch: [160][3800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.804 (2.929) Prec@1 79.69 (75.45) Prec@5 91.41 (91.08) + train[2018-10-20-12:08:26] Epoch: [160][4000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.980 (2.929) Prec@1 77.34 (75.47) Prec@5 88.28 (91.07) + train[2018-10-20-12:10:11] Epoch: [160][4200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.201 (2.930) Prec@1 68.75 (75.45) Prec@5 89.06 (91.07) + train[2018-10-20-12:11:58] Epoch: [160][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.052 (2.931) Prec@1 75.78 (75.42) Prec@5 89.06 (91.06) + train[2018-10-20-12:13:46] Epoch: [160][4600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.932 (2.933) Prec@1 73.44 (75.40) Prec@5 85.94 (91.04) + train[2018-10-20-12:15:34] Epoch: [160][4800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.677 (2.932) Prec@1 79.69 (75.41) Prec@5 92.19 (91.04) + train[2018-10-20-12:17:19] Epoch: [160][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.716 (2.931) Prec@1 75.78 (75.41) Prec@5 95.31 (91.05) + train[2018-10-20-12:19:05] Epoch: [160][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.920 (2.932) Prec@1 73.44 (75.41) Prec@5 89.84 (91.04) + train[2018-10-20-12:20:50] Epoch: [160][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.334 (2.931) Prec@1 64.84 (75.41) Prec@5 89.84 (91.05) + train[2018-10-20-12:22:36] Epoch: [160][5600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.971 (2.931) Prec@1 73.44 (75.42) Prec@5 90.62 (91.06) + train[2018-10-20-12:24:21] Epoch: [160][5800/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.980 (2.931) Prec@1 75.78 (75.40) Prec@5 93.75 (91.06) + train[2018-10-20-12:26:07] Epoch: [160][6000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.029 (2.931) Prec@1 75.00 (75.39) Prec@5 92.19 (91.06) + train[2018-10-20-12:27:52] Epoch: [160][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.749 (2.931) Prec@1 74.22 (75.39) Prec@5 94.53 (91.06) + train[2018-10-20-12:29:37] Epoch: [160][6400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.971 (2.931) Prec@1 75.00 (75.37) Prec@5 89.84 (91.06) + train[2018-10-20-12:31:23] Epoch: [160][6600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.071 (2.931) Prec@1 73.44 (75.37) Prec@5 88.28 (91.06) + train[2018-10-20-12:33:08] Epoch: [160][6800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.981 (2.932) Prec@1 69.53 (75.36) Prec@5 91.41 (91.05) + train[2018-10-20-12:34:53] Epoch: [160][7000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.724 (2.932) Prec@1 81.25 (75.36) Prec@5 93.75 (91.05) + train[2018-10-20-12:36:38] Epoch: [160][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.091 (2.932) Prec@1 71.09 (75.35) Prec@5 86.72 (91.05) + train[2018-10-20-12:38:24] Epoch: [160][7400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.947 (2.932) Prec@1 76.56 (75.34) Prec@5 90.62 (91.06) + train[2018-10-20-12:40:09] Epoch: [160][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.116 (2.933) Prec@1 69.53 (75.34) Prec@5 88.28 (91.05) + train[2018-10-20-12:41:54] Epoch: [160][7800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.071 (2.934) Prec@1 68.75 (75.31) Prec@5 92.19 (91.03) + train[2018-10-20-12:43:40] Epoch: [160][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.640 (2.934) Prec@1 80.47 (75.31) Prec@5 94.53 (91.03) + train[2018-10-20-12:45:26] Epoch: [160][8200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.735 (2.934) Prec@1 79.69 (75.30) Prec@5 93.75 (91.03) + train[2018-10-20-12:47:13] Epoch: [160][8400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.923 (2.935) Prec@1 75.00 (75.30) Prec@5 92.97 (91.02) + train[2018-10-20-12:48:59] Epoch: [160][8600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.207 (2.935) Prec@1 66.41 (75.30) Prec@5 92.19 (91.02) + train[2018-10-20-12:50:46] Epoch: [160][8800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.070 (2.935) Prec@1 75.00 (75.29) Prec@5 87.50 (91.02) + train[2018-10-20-12:52:33] Epoch: [160][9000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.694 (2.935) Prec@1 78.91 (75.30) Prec@5 95.31 (91.02) + train[2018-10-20-12:54:19] Epoch: [160][9200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.641 (2.935) Prec@1 78.12 (75.30) Prec@5 95.31 (91.02) + train[2018-10-20-12:56:06] Epoch: [160][9400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.949 (2.935) Prec@1 75.00 (75.30) Prec@5 89.06 (91.02) + train[2018-10-20-12:57:52] Epoch: [160][9600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.875 (2.935) Prec@1 77.34 (75.29) Prec@5 92.97 (91.02) + train[2018-10-20-12:59:39] Epoch: [160][9800/10010] Time 0.61 (0.53) Data 0.00 (0.00) Loss 2.879 (2.936) Prec@1 75.00 (75.28) Prec@5 89.84 (91.01) + train[2018-10-20-13:01:25] Epoch: [160][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.860 (2.936) Prec@1 75.78 (75.27) Prec@5 93.75 (91.01) + train[2018-10-20-13:01:29] Epoch: [160][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 3.243 (2.936) Prec@1 80.00 (75.27) Prec@5 86.67 (91.01) +[2018-10-20-13:01:29] **train** Prec@1 75.27 Prec@5 91.01 Error@1 24.73 Error@5 8.99 Loss:2.936 + test [2018-10-20-13:01:33] Epoch: [160][000/391] Time 3.99 (3.99) Data 3.86 (3.86) Loss 0.556 (0.556) Prec@1 92.19 (92.19) Prec@5 97.66 (97.66) + test [2018-10-20-13:02:00] Epoch: [160][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.184 (0.994) Prec@1 67.19 (77.26) Prec@5 92.97 (93.59) + test [2018-10-20-13:02:26] Epoch: [160][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.159 (1.163) Prec@1 42.50 (73.60) Prec@5 81.25 (91.34) +[2018-10-20-13:02:26] **test** Prec@1 73.60 Prec@5 91.34 Error@1 26.40 Error@5 8.66 Loss:1.163 +----> Best Accuracy : Acc@1=73.60, Acc@5=91.34, Error@1=26.40, Error@5=8.66 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-20-13:02:26] [Epoch=161/250] [Need: 132:23:17] LR=0.0007 ~ 0.0007, Batch=128 + train[2018-10-20-13:02:31] Epoch: [161][000/10010] Time 5.43 (5.43) Data 4.86 (4.86) Loss 2.932 (2.932) Prec@1 75.78 (75.78) Prec@5 91.41 (91.41) + train[2018-10-20-13:04:16] Epoch: [161][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.160 (2.906) Prec@1 71.88 (76.00) Prec@5 87.50 (91.41) + train[2018-10-20-13:06:01] Epoch: [161][400/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.823 (2.918) Prec@1 80.47 (75.76) Prec@5 93.75 (91.15) + train[2018-10-20-13:07:46] Epoch: [161][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 2.867 (2.932) Prec@1 72.66 (75.56) Prec@5 91.41 (90.96) + train[2018-10-20-13:09:31] Epoch: [161][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.937 (2.932) Prec@1 75.00 (75.54) Prec@5 92.19 (91.00) + train[2018-10-20-13:11:17] Epoch: [161][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.151 (2.931) Prec@1 71.09 (75.53) Prec@5 87.50 (91.04) + train[2018-10-20-13:13:02] Epoch: [161][1200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.781 (2.929) Prec@1 80.47 (75.56) Prec@5 92.19 (91.07) + train[2018-10-20-13:14:47] Epoch: [161][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.764 (2.928) Prec@1 80.47 (75.57) Prec@5 94.53 (91.08) + train[2018-10-20-13:16:32] Epoch: [161][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.969 (2.929) Prec@1 78.12 (75.56) Prec@5 92.19 (91.08) + train[2018-10-20-13:18:17] Epoch: [161][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.077 (2.929) Prec@1 73.44 (75.50) Prec@5 87.50 (91.09) + train[2018-10-20-13:20:02] Epoch: [161][2000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.637 (2.929) Prec@1 77.34 (75.51) Prec@5 93.75 (91.09) + train[2018-10-20-13:21:47] Epoch: [161][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.103 (2.929) Prec@1 75.00 (75.51) Prec@5 88.28 (91.08) + train[2018-10-20-13:23:31] Epoch: [161][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.121 (2.929) Prec@1 71.88 (75.50) Prec@5 89.84 (91.09) + train[2018-10-20-13:25:17] Epoch: [161][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.852 (2.930) Prec@1 78.12 (75.49) Prec@5 93.75 (91.08) + train[2018-10-20-13:27:03] Epoch: [161][2800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.851 (2.931) Prec@1 75.78 (75.47) Prec@5 92.19 (91.07) + train[2018-10-20-13:28:48] Epoch: [161][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.810 (2.933) Prec@1 75.78 (75.44) Prec@5 92.19 (91.05) + train[2018-10-20-13:30:33] Epoch: [161][3200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.075 (2.933) Prec@1 72.66 (75.43) Prec@5 87.50 (91.03) + train[2018-10-20-13:32:19] Epoch: [161][3400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.066 (2.933) Prec@1 71.88 (75.42) Prec@5 88.28 (91.03) + train[2018-10-20-13:34:04] Epoch: [161][3600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.854 (2.933) Prec@1 75.78 (75.42) Prec@5 93.75 (91.03) + train[2018-10-20-13:35:50] Epoch: [161][3800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.101 (2.933) Prec@1 74.22 (75.42) Prec@5 89.06 (91.03) + train[2018-10-20-13:37:35] Epoch: [161][4000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.145 (2.934) Prec@1 72.66 (75.42) Prec@5 89.84 (91.03) + train[2018-10-20-13:39:20] Epoch: [161][4200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.723 (2.933) Prec@1 78.12 (75.42) Prec@5 93.75 (91.03) + train[2018-10-20-13:41:05] Epoch: [161][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.955 (2.934) Prec@1 77.34 (75.40) Prec@5 90.62 (91.03) + train[2018-10-20-13:42:51] Epoch: [161][4600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.024 (2.934) Prec@1 76.56 (75.41) Prec@5 90.62 (91.03) + train[2018-10-20-13:44:37] Epoch: [161][4800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.688 (2.933) Prec@1 78.12 (75.39) Prec@5 95.31 (91.03) + train[2018-10-20-13:46:23] Epoch: [161][5000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.094 (2.934) Prec@1 66.41 (75.39) Prec@5 87.50 (91.04) + train[2018-10-20-13:48:09] Epoch: [161][5200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.955 (2.933) Prec@1 75.78 (75.39) Prec@5 92.97 (91.05) + train[2018-10-20-13:49:56] Epoch: [161][5400/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.882 (2.933) Prec@1 74.22 (75.38) Prec@5 91.41 (91.05) + train[2018-10-20-13:51:41] Epoch: [161][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.029 (2.933) Prec@1 73.44 (75.39) Prec@5 87.50 (91.06) + train[2018-10-20-13:53:26] Epoch: [161][5800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.786 (2.933) Prec@1 75.78 (75.39) Prec@5 93.75 (91.06) + train[2018-10-20-13:55:11] Epoch: [161][6000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.019 (2.933) Prec@1 72.66 (75.39) Prec@5 90.62 (91.06) + train[2018-10-20-13:56:56] Epoch: [161][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.120 (2.933) Prec@1 72.66 (75.38) Prec@5 86.72 (91.06) + train[2018-10-20-13:58:41] Epoch: [161][6400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.877 (2.933) Prec@1 76.56 (75.38) Prec@5 91.41 (91.06) + train[2018-10-20-14:00:26] Epoch: [161][6600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.000 (2.933) Prec@1 71.88 (75.37) Prec@5 92.19 (91.05) + train[2018-10-20-14:02:12] Epoch: [161][6800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.724 (2.933) Prec@1 78.12 (75.36) Prec@5 92.19 (91.04) + train[2018-10-20-14:03:58] Epoch: [161][7000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.900 (2.933) Prec@1 80.47 (75.37) Prec@5 89.06 (91.04) + train[2018-10-20-14:05:43] Epoch: [161][7200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.607 (2.933) Prec@1 82.81 (75.37) Prec@5 93.75 (91.05) + train[2018-10-20-14:07:28] Epoch: [161][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.128 (2.933) Prec@1 71.88 (75.37) Prec@5 86.72 (91.04) + train[2018-10-20-14:09:13] Epoch: [161][7600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.994 (2.933) Prec@1 76.56 (75.37) Prec@5 90.62 (91.05) + train[2018-10-20-14:10:58] Epoch: [161][7800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.040 (2.933) Prec@1 76.56 (75.37) Prec@5 89.06 (91.04) + train[2018-10-20-14:12:43] Epoch: [161][8000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.159 (2.933) Prec@1 75.78 (75.38) Prec@5 88.28 (91.04) + train[2018-10-20-14:14:28] Epoch: [161][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.124 (2.933) Prec@1 72.66 (75.37) Prec@5 88.28 (91.04) + train[2018-10-20-14:16:13] Epoch: [161][8400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.191 (2.934) Prec@1 67.19 (75.36) Prec@5 88.28 (91.04) + train[2018-10-20-14:17:59] Epoch: [161][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.780 (2.934) Prec@1 75.78 (75.36) Prec@5 93.75 (91.04) + train[2018-10-20-14:19:44] Epoch: [161][8800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.932 (2.934) Prec@1 76.56 (75.36) Prec@5 87.50 (91.04) + train[2018-10-20-14:21:30] Epoch: [161][9000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.861 (2.934) Prec@1 77.34 (75.35) Prec@5 92.19 (91.04) + train[2018-10-20-14:23:15] Epoch: [161][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.839 (2.934) Prec@1 75.78 (75.36) Prec@5 92.19 (91.04) + train[2018-10-20-14:25:01] Epoch: [161][9400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.856 (2.934) Prec@1 73.44 (75.37) Prec@5 92.19 (91.04) + train[2018-10-20-14:26:47] Epoch: [161][9600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.114 (2.934) Prec@1 69.53 (75.36) Prec@5 90.62 (91.03) + train[2018-10-20-14:28:33] Epoch: [161][9800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.136 (2.934) Prec@1 73.44 (75.37) Prec@5 89.84 (91.03) + train[2018-10-20-14:30:17] Epoch: [161][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.991 (2.935) Prec@1 73.44 (75.35) Prec@5 92.19 (91.02) + train[2018-10-20-14:30:22] Epoch: [161][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.237 (2.935) Prec@1 86.67 (75.35) Prec@5 93.33 (91.02) +[2018-10-20-14:30:22] **train** Prec@1 75.35 Prec@5 91.02 Error@1 24.65 Error@5 8.98 Loss:2.935 + test [2018-10-20-14:30:25] Epoch: [161][000/391] Time 3.89 (3.89) Data 3.76 (3.76) Loss 0.541 (0.541) Prec@1 92.19 (92.19) Prec@5 96.88 (96.88) + test [2018-10-20-14:30:52] Epoch: [161][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.186 (1.005) Prec@1 67.97 (77.07) Prec@5 92.97 (93.57) + test [2018-10-20-14:31:17] Epoch: [161][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.099 (1.166) Prec@1 46.25 (73.62) Prec@5 82.50 (91.32) +[2018-10-20-14:31:17] **test** Prec@1 73.62 Prec@5 91.32 Error@1 26.38 Error@5 8.68 Loss:1.166 +----> Best Accuracy : Acc@1=73.62, Acc@5=91.32, Error@1=26.38, Error@5=8.68 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-20-14:31:17] [Epoch=162/250] [Need: 130:19:55] LR=0.0007 ~ 0.0007, Batch=128 + train[2018-10-20-14:31:23] Epoch: [162][000/10010] Time 5.50 (5.50) Data 4.94 (4.94) Loss 2.976 (2.976) Prec@1 75.78 (75.78) Prec@5 90.62 (90.62) + train[2018-10-20-14:33:08] Epoch: [162][200/10010] Time 0.58 (0.55) Data 0.00 (0.02) Loss 2.990 (2.940) Prec@1 77.34 (75.42) Prec@5 91.41 (90.87) + train[2018-10-20-14:34:53] Epoch: [162][400/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.808 (2.933) Prec@1 81.25 (75.52) Prec@5 91.41 (91.05) + train[2018-10-20-14:36:38] Epoch: [162][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.024 (2.933) Prec@1 75.78 (75.48) Prec@5 89.06 (91.01) + train[2018-10-20-14:38:22] Epoch: [162][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.054 (2.928) Prec@1 70.31 (75.48) Prec@5 91.41 (91.09) + train[2018-10-20-14:40:07] Epoch: [162][1000/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.965 (2.933) Prec@1 76.56 (75.40) Prec@5 90.62 (91.04) + train[2018-10-20-14:41:52] Epoch: [162][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.874 (2.930) Prec@1 73.44 (75.45) Prec@5 95.31 (91.10) + train[2018-10-20-14:43:37] Epoch: [162][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.964 (2.931) Prec@1 74.22 (75.46) Prec@5 89.84 (91.08) + train[2018-10-20-14:45:23] Epoch: [162][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.854 (2.930) Prec@1 78.91 (75.47) Prec@5 94.53 (91.06) + train[2018-10-20-14:47:08] Epoch: [162][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.132 (2.930) Prec@1 70.31 (75.46) Prec@5 88.28 (91.05) + train[2018-10-20-14:48:53] Epoch: [162][2000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.930 (2.929) Prec@1 74.22 (75.48) Prec@5 92.19 (91.09) + train[2018-10-20-14:50:39] Epoch: [162][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.094 (2.929) Prec@1 74.22 (75.50) Prec@5 88.28 (91.09) + train[2018-10-20-14:52:24] Epoch: [162][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.759 (2.930) Prec@1 77.34 (75.47) Prec@5 92.19 (91.06) + train[2018-10-20-14:54:10] Epoch: [162][2600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.079 (2.931) Prec@1 71.88 (75.43) Prec@5 89.06 (91.05) + train[2018-10-20-14:55:55] Epoch: [162][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.823 (2.930) Prec@1 77.34 (75.43) Prec@5 93.75 (91.08) + train[2018-10-20-14:57:40] Epoch: [162][3000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.919 (2.930) Prec@1 75.00 (75.44) Prec@5 92.19 (91.08) + train[2018-10-20-14:59:25] Epoch: [162][3200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.718 (2.930) Prec@1 78.12 (75.44) Prec@5 93.75 (91.09) + train[2018-10-20-15:01:11] Epoch: [162][3400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.576 (2.930) Prec@1 78.12 (75.45) Prec@5 98.44 (91.08) + train[2018-10-20-15:02:57] Epoch: [162][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.565 (2.930) Prec@1 82.03 (75.45) Prec@5 96.88 (91.08) + train[2018-10-20-15:04:42] Epoch: [162][3800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.868 (2.930) Prec@1 78.91 (75.45) Prec@5 92.97 (91.08) + train[2018-10-20-15:06:27] Epoch: [162][4000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.970 (2.930) Prec@1 74.22 (75.45) Prec@5 91.41 (91.07) + train[2018-10-20-15:08:13] Epoch: [162][4200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.800 (2.931) Prec@1 77.34 (75.43) Prec@5 92.19 (91.06) + train[2018-10-20-15:09:57] Epoch: [162][4400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.738 (2.931) Prec@1 79.69 (75.42) Prec@5 91.41 (91.05) + train[2018-10-20-15:11:43] Epoch: [162][4600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.162 (2.931) Prec@1 73.44 (75.42) Prec@5 90.62 (91.06) + train[2018-10-20-15:13:28] Epoch: [162][4800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.893 (2.931) Prec@1 75.78 (75.41) Prec@5 90.62 (91.06) + train[2018-10-20-15:15:13] Epoch: [162][5000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.129 (2.931) Prec@1 72.66 (75.42) Prec@5 86.72 (91.06) + train[2018-10-20-15:16:59] Epoch: [162][5200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.088 (2.931) Prec@1 75.00 (75.40) Prec@5 89.06 (91.05) + train[2018-10-20-15:18:44] Epoch: [162][5400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.699 (2.931) Prec@1 80.47 (75.40) Prec@5 92.19 (91.05) + train[2018-10-20-15:20:29] Epoch: [162][5600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.174 (2.931) Prec@1 71.09 (75.41) Prec@5 89.84 (91.06) + train[2018-10-20-15:22:15] Epoch: [162][5800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.884 (2.931) Prec@1 76.56 (75.40) Prec@5 91.41 (91.07) + train[2018-10-20-15:24:02] Epoch: [162][6000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.871 (2.930) Prec@1 77.34 (75.42) Prec@5 91.41 (91.07) + train[2018-10-20-15:25:48] Epoch: [162][6200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.699 (2.930) Prec@1 83.59 (75.42) Prec@5 94.53 (91.08) + train[2018-10-20-15:27:33] Epoch: [162][6400/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.795 (2.931) Prec@1 74.22 (75.41) Prec@5 92.97 (91.07) + train[2018-10-20-15:29:18] Epoch: [162][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.727 (2.931) Prec@1 79.69 (75.39) Prec@5 93.75 (91.06) + train[2018-10-20-15:31:03] Epoch: [162][6800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.711 (2.931) Prec@1 78.12 (75.39) Prec@5 92.19 (91.06) + train[2018-10-20-15:32:48] Epoch: [162][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.018 (2.931) Prec@1 76.56 (75.39) Prec@5 89.84 (91.06) + train[2018-10-20-15:34:33] Epoch: [162][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.092 (2.932) Prec@1 70.31 (75.37) Prec@5 90.62 (91.06) + train[2018-10-20-15:36:19] Epoch: [162][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.153 (2.932) Prec@1 71.09 (75.37) Prec@5 92.97 (91.06) + train[2018-10-20-15:38:05] Epoch: [162][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.851 (2.932) Prec@1 79.69 (75.38) Prec@5 92.19 (91.06) + train[2018-10-20-15:39:50] Epoch: [162][7800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.807 (2.932) Prec@1 76.56 (75.39) Prec@5 93.75 (91.06) + train[2018-10-20-15:41:35] Epoch: [162][8000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.819 (2.932) Prec@1 78.12 (75.39) Prec@5 94.53 (91.06) + train[2018-10-20-15:43:21] Epoch: [162][8200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.750 (2.932) Prec@1 76.56 (75.39) Prec@5 93.75 (91.05) + train[2018-10-20-15:45:06] Epoch: [162][8400/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.227 (2.932) Prec@1 71.09 (75.38) Prec@5 87.50 (91.06) + train[2018-10-20-15:46:52] Epoch: [162][8600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.116 (2.932) Prec@1 73.44 (75.38) Prec@5 90.62 (91.06) + train[2018-10-20-15:48:37] Epoch: [162][8800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.960 (2.932) Prec@1 78.91 (75.39) Prec@5 89.06 (91.06) + train[2018-10-20-15:50:22] Epoch: [162][9000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.839 (2.932) Prec@1 77.34 (75.38) Prec@5 93.75 (91.06) + train[2018-10-20-15:52:08] Epoch: [162][9200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.957 (2.932) Prec@1 71.09 (75.38) Prec@5 89.84 (91.06) + train[2018-10-20-15:53:53] Epoch: [162][9400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.286 (2.933) Prec@1 71.88 (75.36) Prec@5 85.94 (91.06) + train[2018-10-20-15:55:38] Epoch: [162][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.072 (2.933) Prec@1 68.75 (75.36) Prec@5 90.62 (91.06) + train[2018-10-20-15:57:23] Epoch: [162][9800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.927 (2.933) Prec@1 75.00 (75.36) Prec@5 90.62 (91.06) + train[2018-10-20-15:59:10] Epoch: [162][10000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.866 (2.933) Prec@1 74.22 (75.35) Prec@5 91.41 (91.06) + train[2018-10-20-15:59:15] Epoch: [162][10009/10010] Time 0.31 (0.53) Data 0.00 (0.00) Loss 3.896 (2.933) Prec@1 60.00 (75.35) Prec@5 86.67 (91.06) +[2018-10-20-15:59:15] **train** Prec@1 75.35 Prec@5 91.06 Error@1 24.65 Error@5 8.94 Loss:2.933 + test [2018-10-20-15:59:18] Epoch: [162][000/391] Time 3.51 (3.51) Data 3.37 (3.37) Loss 0.518 (0.518) Prec@1 93.75 (93.75) Prec@5 97.66 (97.66) + test [2018-10-20-15:59:45] Epoch: [162][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.192 (1.003) Prec@1 67.97 (77.01) Prec@5 92.19 (93.51) + test [2018-10-20-16:00:10] Epoch: [162][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.160 (1.168) Prec@1 41.25 (73.51) Prec@5 82.50 (91.32) +[2018-10-20-16:00:10] **test** Prec@1 73.51 Prec@5 91.32 Error@1 26.49 Error@5 8.68 Loss:1.168 +----> Best Accuracy : Acc@1=73.62, Acc@5=91.32, Error@1=26.38, Error@5=8.68 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-20-16:00:10] [Epoch=163/250] [Need: 128:52:01] LR=0.0007 ~ 0.0007, Batch=128 + train[2018-10-20-16:00:15] Epoch: [163][000/10010] Time 4.59 (4.59) Data 3.95 (3.95) Loss 2.800 (2.800) Prec@1 71.88 (71.88) Prec@5 93.75 (93.75) + train[2018-10-20-16:02:00] Epoch: [163][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.233 (2.936) Prec@1 67.97 (75.34) Prec@5 89.84 (91.02) + train[2018-10-20-16:03:44] Epoch: [163][400/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.098 (2.926) Prec@1 72.66 (75.43) Prec@5 85.94 (91.05) + train[2018-10-20-16:05:30] Epoch: [163][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.756 (2.923) Prec@1 80.47 (75.43) Prec@5 92.97 (91.08) + train[2018-10-20-16:07:15] Epoch: [163][800/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.077 (2.924) Prec@1 69.53 (75.52) Prec@5 89.84 (91.11) + train[2018-10-20-16:09:00] Epoch: [163][1000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.706 (2.925) Prec@1 75.78 (75.50) Prec@5 95.31 (91.09) + train[2018-10-20-16:10:45] Epoch: [163][1200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.859 (2.927) Prec@1 71.88 (75.49) Prec@5 92.19 (91.07) + train[2018-10-20-16:12:31] Epoch: [163][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.840 (2.928) Prec@1 79.69 (75.45) Prec@5 92.19 (91.08) + train[2018-10-20-16:14:16] Epoch: [163][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.524 (2.930) Prec@1 81.25 (75.39) Prec@5 96.88 (91.05) + train[2018-10-20-16:16:00] Epoch: [163][1800/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 2.918 (2.930) Prec@1 75.78 (75.43) Prec@5 90.62 (91.07) + train[2018-10-20-16:17:45] Epoch: [163][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.869 (2.929) Prec@1 77.34 (75.43) Prec@5 92.19 (91.09) + train[2018-10-20-16:19:31] Epoch: [163][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.730 (2.927) Prec@1 78.91 (75.48) Prec@5 91.41 (91.09) + train[2018-10-20-16:21:15] Epoch: [163][2400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.764 (2.927) Prec@1 78.91 (75.46) Prec@5 93.75 (91.10) + train[2018-10-20-16:23:00] Epoch: [163][2600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.881 (2.928) Prec@1 75.00 (75.46) Prec@5 91.41 (91.10) + train[2018-10-20-16:24:46] Epoch: [163][2800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.889 (2.928) Prec@1 77.34 (75.44) Prec@5 92.97 (91.10) + train[2018-10-20-16:26:33] Epoch: [163][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.127 (2.929) Prec@1 75.78 (75.44) Prec@5 90.62 (91.08) + train[2018-10-20-16:28:19] Epoch: [163][3200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.764 (2.930) Prec@1 76.56 (75.43) Prec@5 92.97 (91.08) + train[2018-10-20-16:30:05] Epoch: [163][3400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.987 (2.930) Prec@1 73.44 (75.40) Prec@5 89.06 (91.08) + train[2018-10-20-16:31:51] Epoch: [163][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.842 (2.929) Prec@1 77.34 (75.42) Prec@5 92.19 (91.09) + train[2018-10-20-16:33:38] Epoch: [163][3800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.895 (2.929) Prec@1 77.34 (75.41) Prec@5 90.62 (91.09) + train[2018-10-20-16:35:25] Epoch: [163][4000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.522 (2.929) Prec@1 80.47 (75.42) Prec@5 96.88 (91.08) + train[2018-10-20-16:37:11] Epoch: [163][4200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.851 (2.929) Prec@1 74.22 (75.44) Prec@5 93.75 (91.08) + train[2018-10-20-16:38:57] Epoch: [163][4400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.003 (2.929) Prec@1 70.31 (75.43) Prec@5 91.41 (91.08) + train[2018-10-20-16:40:44] Epoch: [163][4600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.772 (2.930) Prec@1 75.78 (75.41) Prec@5 95.31 (91.08) + train[2018-10-20-16:42:31] Epoch: [163][4800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.990 (2.930) Prec@1 78.91 (75.39) Prec@5 89.84 (91.07) + train[2018-10-20-16:44:19] Epoch: [163][5000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.826 (2.931) Prec@1 75.78 (75.39) Prec@5 92.19 (91.07) + train[2018-10-20-16:46:05] Epoch: [163][5200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.946 (2.931) Prec@1 75.78 (75.38) Prec@5 91.41 (91.07) + train[2018-10-20-16:47:52] Epoch: [163][5400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.325 (2.931) Prec@1 66.41 (75.37) Prec@5 84.38 (91.07) + train[2018-10-20-16:49:40] Epoch: [163][5600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.783 (2.930) Prec@1 83.59 (75.39) Prec@5 92.97 (91.08) + train[2018-10-20-16:51:27] Epoch: [163][5800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.696 (2.930) Prec@1 80.47 (75.38) Prec@5 96.09 (91.08) + train[2018-10-20-16:53:15] Epoch: [163][6000/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 3.112 (2.931) Prec@1 71.88 (75.38) Prec@5 91.41 (91.08) + train[2018-10-20-16:55:02] Epoch: [163][6200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.995 (2.931) Prec@1 77.34 (75.38) Prec@5 89.06 (91.08) + train[2018-10-20-16:56:49] Epoch: [163][6400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.040 (2.931) Prec@1 70.31 (75.38) Prec@5 92.97 (91.08) + train[2018-10-20-16:58:36] Epoch: [163][6600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.953 (2.930) Prec@1 73.44 (75.39) Prec@5 89.06 (91.09) + train[2018-10-20-17:00:23] Epoch: [163][6800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.233 (2.931) Prec@1 69.53 (75.38) Prec@5 87.50 (91.09) + train[2018-10-20-17:02:09] Epoch: [163][7000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.878 (2.931) Prec@1 76.56 (75.38) Prec@5 88.28 (91.08) + train[2018-10-20-17:03:55] Epoch: [163][7200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.887 (2.931) Prec@1 71.09 (75.38) Prec@5 92.97 (91.08) + train[2018-10-20-17:05:42] Epoch: [163][7400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.069 (2.931) Prec@1 75.00 (75.38) Prec@5 91.41 (91.08) + train[2018-10-20-17:07:29] Epoch: [163][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.983 (2.931) Prec@1 77.34 (75.38) Prec@5 92.19 (91.08) + train[2018-10-20-17:09:16] Epoch: [163][7800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.102 (2.931) Prec@1 74.22 (75.38) Prec@5 92.19 (91.07) + train[2018-10-20-17:11:03] Epoch: [163][8000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.948 (2.931) Prec@1 73.44 (75.38) Prec@5 92.19 (91.08) + train[2018-10-20-17:12:50] Epoch: [163][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.852 (2.931) Prec@1 76.56 (75.38) Prec@5 94.53 (91.08) + train[2018-10-20-17:14:37] Epoch: [163][8400/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.849 (2.931) Prec@1 75.78 (75.38) Prec@5 90.62 (91.08) + train[2018-10-20-17:16:25] Epoch: [163][8600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.022 (2.931) Prec@1 70.31 (75.38) Prec@5 90.62 (91.08) + train[2018-10-20-17:18:12] Epoch: [163][8800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.040 (2.931) Prec@1 79.69 (75.38) Prec@5 88.28 (91.08) + train[2018-10-20-17:19:58] Epoch: [163][9000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.654 (2.931) Prec@1 82.81 (75.38) Prec@5 93.75 (91.08) + train[2018-10-20-17:21:45] Epoch: [163][9200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.937 (2.931) Prec@1 77.34 (75.38) Prec@5 88.28 (91.08) + train[2018-10-20-17:23:31] Epoch: [163][9400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.518 (2.931) Prec@1 82.03 (75.37) Prec@5 96.09 (91.08) + train[2018-10-20-17:25:19] Epoch: [163][9600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.734 (2.931) Prec@1 78.12 (75.38) Prec@5 93.75 (91.08) + train[2018-10-20-17:27:06] Epoch: [163][9800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.914 (2.931) Prec@1 75.00 (75.37) Prec@5 91.41 (91.07) + train[2018-10-20-17:28:53] Epoch: [163][10000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.026 (2.931) Prec@1 71.88 (75.37) Prec@5 92.97 (91.07) + train[2018-10-20-17:28:58] Epoch: [163][10009/10010] Time 0.14 (0.53) Data 0.00 (0.00) Loss 4.198 (2.931) Prec@1 46.67 (75.37) Prec@5 73.33 (91.07) +[2018-10-20-17:28:58] **train** Prec@1 75.37 Prec@5 91.07 Error@1 24.63 Error@5 8.93 Loss:2.931 + test [2018-10-20-17:29:02] Epoch: [163][000/391] Time 4.23 (4.23) Data 4.10 (4.10) Loss 0.525 (0.525) Prec@1 92.97 (92.97) Prec@5 98.44 (98.44) + test [2018-10-20-17:29:28] Epoch: [163][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.216 (1.000) Prec@1 67.19 (77.14) Prec@5 92.19 (93.52) + test [2018-10-20-17:29:53] Epoch: [163][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.178 (1.164) Prec@1 42.50 (73.54) Prec@5 82.50 (91.32) +[2018-10-20-17:29:53] **test** Prec@1 73.54 Prec@5 91.32 Error@1 26.46 Error@5 8.68 Loss:1.164 +----> Best Accuracy : Acc@1=73.62, Acc@5=91.32, Error@1=26.38, Error@5=8.68 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-20-17:29:54] [Epoch=164/250] [Need: 128:36:38] LR=0.0007 ~ 0.0007, Batch=128 + train[2018-10-20-17:29:59] Epoch: [164][000/10010] Time 5.55 (5.55) Data 4.98 (4.98) Loss 2.818 (2.818) Prec@1 77.34 (77.34) Prec@5 94.53 (94.53) + train[2018-10-20-17:31:46] Epoch: [164][200/10010] Time 0.53 (0.56) Data 0.00 (0.02) Loss 3.118 (2.945) Prec@1 71.88 (75.09) Prec@5 89.84 (90.93) + train[2018-10-20-17:33:32] Epoch: [164][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 3.038 (2.926) Prec@1 77.34 (75.52) Prec@5 88.28 (91.10) + train[2018-10-20-17:35:17] Epoch: [164][600/10010] Time 0.54 (0.54) Data 0.00 (0.01) Loss 3.183 (2.920) Prec@1 67.97 (75.49) Prec@5 86.72 (91.18) + train[2018-10-20-17:37:02] Epoch: [164][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.871 (2.916) Prec@1 75.00 (75.64) Prec@5 90.62 (91.26) + train[2018-10-20-17:38:46] Epoch: [164][1000/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.841 (2.919) Prec@1 80.47 (75.59) Prec@5 91.41 (91.22) + train[2018-10-20-17:40:30] Epoch: [164][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.991 (2.918) Prec@1 74.22 (75.63) Prec@5 91.41 (91.24) + train[2018-10-20-17:42:16] Epoch: [164][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.290 (2.916) Prec@1 68.75 (75.64) Prec@5 88.28 (91.26) + train[2018-10-20-17:44:01] Epoch: [164][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.627 (2.919) Prec@1 82.81 (75.61) Prec@5 93.75 (91.22) + train[2018-10-20-17:45:47] Epoch: [164][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.700 (2.921) Prec@1 80.47 (75.61) Prec@5 95.31 (91.19) + train[2018-10-20-17:47:33] Epoch: [164][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.074 (2.920) Prec@1 69.53 (75.60) Prec@5 88.28 (91.20) + train[2018-10-20-17:49:18] Epoch: [164][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.638 (2.921) Prec@1 84.38 (75.60) Prec@5 92.97 (91.20) + train[2018-10-20-17:51:04] Epoch: [164][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.023 (2.921) Prec@1 76.56 (75.60) Prec@5 89.84 (91.20) + train[2018-10-20-17:52:50] Epoch: [164][2600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.707 (2.921) Prec@1 75.00 (75.63) Prec@5 92.19 (91.18) + train[2018-10-20-17:54:36] Epoch: [164][2800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.663 (2.920) Prec@1 77.34 (75.65) Prec@5 93.75 (91.20) + train[2018-10-20-17:56:23] Epoch: [164][3000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.913 (2.919) Prec@1 71.09 (75.67) Prec@5 93.75 (91.20) + train[2018-10-20-17:58:09] Epoch: [164][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.909 (2.920) Prec@1 74.22 (75.65) Prec@5 92.19 (91.19) + train[2018-10-20-17:59:56] Epoch: [164][3400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.280 (2.920) Prec@1 67.97 (75.63) Prec@5 89.06 (91.19) + train[2018-10-20-18:01:41] Epoch: [164][3600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.802 (2.920) Prec@1 78.12 (75.62) Prec@5 90.62 (91.19) + train[2018-10-20-18:03:26] Epoch: [164][3800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.664 (2.921) Prec@1 81.25 (75.62) Prec@5 94.53 (91.18) + train[2018-10-20-18:05:11] Epoch: [164][4000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.897 (2.920) Prec@1 75.78 (75.61) Prec@5 92.97 (91.19) + train[2018-10-20-18:06:57] Epoch: [164][4200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.039 (2.920) Prec@1 77.34 (75.62) Prec@5 91.41 (91.19) + train[2018-10-20-18:08:42] Epoch: [164][4400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.856 (2.922) Prec@1 76.56 (75.61) Prec@5 92.97 (91.18) + train[2018-10-20-18:10:27] Epoch: [164][4600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.630 (2.923) Prec@1 80.47 (75.61) Prec@5 94.53 (91.17) + train[2018-10-20-18:12:13] Epoch: [164][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.897 (2.923) Prec@1 77.34 (75.60) Prec@5 89.06 (91.16) + train[2018-10-20-18:13:59] Epoch: [164][5000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.143 (2.924) Prec@1 74.22 (75.59) Prec@5 90.62 (91.15) + train[2018-10-20-18:15:44] Epoch: [164][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.006 (2.924) Prec@1 74.22 (75.59) Prec@5 89.06 (91.15) + train[2018-10-20-18:17:29] Epoch: [164][5400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.847 (2.924) Prec@1 78.12 (75.60) Prec@5 90.62 (91.14) + train[2018-10-20-18:19:14] Epoch: [164][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.982 (2.924) Prec@1 78.12 (75.60) Prec@5 89.84 (91.15) + train[2018-10-20-18:21:00] Epoch: [164][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.927 (2.923) Prec@1 72.66 (75.60) Prec@5 92.97 (91.15) + train[2018-10-20-18:22:45] Epoch: [164][6000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.913 (2.924) Prec@1 75.00 (75.58) Prec@5 90.62 (91.14) + train[2018-10-20-18:24:30] Epoch: [164][6200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.924 (2.924) Prec@1 75.78 (75.58) Prec@5 90.62 (91.14) + train[2018-10-20-18:26:16] Epoch: [164][6400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.849 (2.924) Prec@1 73.44 (75.57) Prec@5 89.84 (91.14) + train[2018-10-20-18:28:00] Epoch: [164][6600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.972 (2.925) Prec@1 74.22 (75.55) Prec@5 92.19 (91.13) + train[2018-10-20-18:29:45] Epoch: [164][6800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.863 (2.925) Prec@1 80.47 (75.55) Prec@5 91.41 (91.13) + train[2018-10-20-18:31:31] Epoch: [164][7000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.137 (2.925) Prec@1 71.09 (75.55) Prec@5 89.84 (91.13) + train[2018-10-20-18:33:16] Epoch: [164][7200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.577 (2.926) Prec@1 81.25 (75.55) Prec@5 92.97 (91.12) + train[2018-10-20-18:35:01] Epoch: [164][7400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.042 (2.927) Prec@1 71.88 (75.53) Prec@5 88.28 (91.11) + train[2018-10-20-18:36:46] Epoch: [164][7600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.845 (2.926) Prec@1 71.88 (75.54) Prec@5 89.84 (91.11) + train[2018-10-20-18:38:32] Epoch: [164][7800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.715 (2.927) Prec@1 81.25 (75.54) Prec@5 93.75 (91.11) + train[2018-10-20-18:40:17] Epoch: [164][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.789 (2.926) Prec@1 75.78 (75.54) Prec@5 92.97 (91.12) + train[2018-10-20-18:42:03] Epoch: [164][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.402 (2.927) Prec@1 66.41 (75.53) Prec@5 86.72 (91.11) + train[2018-10-20-18:43:51] Epoch: [164][8400/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 3.078 (2.927) Prec@1 69.53 (75.53) Prec@5 89.06 (91.12) + train[2018-10-20-18:45:39] Epoch: [164][8600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.857 (2.927) Prec@1 77.34 (75.52) Prec@5 89.84 (91.12) + train[2018-10-20-18:47:27] Epoch: [164][8800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.933 (2.927) Prec@1 71.09 (75.52) Prec@5 92.19 (91.11) + train[2018-10-20-18:49:15] Epoch: [164][9000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.033 (2.927) Prec@1 72.66 (75.51) Prec@5 91.41 (91.11) + train[2018-10-20-18:51:02] Epoch: [164][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.952 (2.928) Prec@1 74.22 (75.50) Prec@5 92.19 (91.10) + train[2018-10-20-18:52:49] Epoch: [164][9400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.768 (2.928) Prec@1 78.12 (75.51) Prec@5 93.75 (91.10) + train[2018-10-20-18:54:36] Epoch: [164][9600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.203 (2.927) Prec@1 67.97 (75.50) Prec@5 85.94 (91.10) + train[2018-10-20-18:56:22] Epoch: [164][9800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.849 (2.927) Prec@1 76.56 (75.50) Prec@5 91.41 (91.10) + train[2018-10-20-18:58:10] Epoch: [164][10000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.207 (2.928) Prec@1 69.53 (75.49) Prec@5 90.62 (91.10) + train[2018-10-20-18:58:14] Epoch: [164][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 3.374 (2.928) Prec@1 73.33 (75.49) Prec@5 86.67 (91.10) +[2018-10-20-18:58:14] **train** Prec@1 75.49 Prec@5 91.10 Error@1 24.51 Error@5 8.90 Loss:2.928 + test [2018-10-20-18:58:18] Epoch: [164][000/391] Time 3.80 (3.80) Data 3.67 (3.67) Loss 0.545 (0.545) Prec@1 94.53 (94.53) Prec@5 98.44 (98.44) + test [2018-10-20-18:58:45] Epoch: [164][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.167 (1.012) Prec@1 67.97 (77.13) Prec@5 92.19 (93.63) + test [2018-10-20-18:59:10] Epoch: [164][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.208 (1.179) Prec@1 41.25 (73.56) Prec@5 82.50 (91.42) +[2018-10-20-18:59:10] **test** Prec@1 73.56 Prec@5 91.42 Error@1 26.44 Error@5 8.58 Loss:1.179 +----> Best Accuracy : Acc@1=73.62, Acc@5=91.32, Error@1=26.38, Error@5=8.68 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-20-18:59:10] [Epoch=165/250] [Need: 126:28:53] LR=0.0007 ~ 0.0007, Batch=128 + train[2018-10-20-18:59:16] Epoch: [165][000/10010] Time 5.11 (5.11) Data 4.53 (4.53) Loss 3.153 (3.153) Prec@1 65.62 (65.62) Prec@5 89.06 (89.06) + train[2018-10-20-19:01:00] Epoch: [165][200/10010] Time 0.55 (0.54) Data 0.00 (0.02) Loss 3.001 (2.937) Prec@1 69.53 (75.26) Prec@5 92.97 (91.12) + train[2018-10-20-19:02:46] Epoch: [165][400/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 2.991 (2.925) Prec@1 71.88 (75.46) Prec@5 91.41 (91.33) + train[2018-10-20-19:04:31] Epoch: [165][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 2.709 (2.921) Prec@1 82.03 (75.56) Prec@5 92.97 (91.28) + train[2018-10-20-19:06:16] Epoch: [165][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.024 (2.923) Prec@1 74.22 (75.57) Prec@5 89.84 (91.24) + train[2018-10-20-19:08:02] Epoch: [165][1000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.371 (2.922) Prec@1 85.94 (75.63) Prec@5 96.09 (91.24) + train[2018-10-20-19:09:46] Epoch: [165][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.849 (2.927) Prec@1 73.44 (75.48) Prec@5 91.41 (91.16) + train[2018-10-20-19:11:31] Epoch: [165][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.858 (2.926) Prec@1 76.56 (75.49) Prec@5 92.19 (91.16) + train[2018-10-20-19:13:16] Epoch: [165][1600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.889 (2.924) Prec@1 76.56 (75.52) Prec@5 90.62 (91.16) + train[2018-10-20-19:15:01] Epoch: [165][1800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.134 (2.923) Prec@1 67.97 (75.56) Prec@5 88.28 (91.15) + train[2018-10-20-19:16:46] Epoch: [165][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.193 (2.922) Prec@1 72.66 (75.60) Prec@5 86.72 (91.14) + train[2018-10-20-19:18:31] Epoch: [165][2200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.864 (2.925) Prec@1 78.12 (75.56) Prec@5 91.41 (91.11) + train[2018-10-20-19:20:18] Epoch: [165][2400/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.941 (2.925) Prec@1 76.56 (75.58) Prec@5 89.84 (91.12) + train[2018-10-20-19:22:04] Epoch: [165][2600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.889 (2.925) Prec@1 74.22 (75.56) Prec@5 92.19 (91.12) + train[2018-10-20-19:23:51] Epoch: [165][2800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.029 (2.925) Prec@1 75.78 (75.58) Prec@5 91.41 (91.13) + train[2018-10-20-19:25:38] Epoch: [165][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.979 (2.923) Prec@1 75.78 (75.60) Prec@5 88.28 (91.16) + train[2018-10-20-19:27:24] Epoch: [165][3200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.007 (2.922) Prec@1 72.66 (75.60) Prec@5 89.06 (91.18) + train[2018-10-20-19:29:10] Epoch: [165][3400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.728 (2.922) Prec@1 82.81 (75.60) Prec@5 93.75 (91.19) + train[2018-10-20-19:30:57] Epoch: [165][3600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.966 (2.922) Prec@1 74.22 (75.61) Prec@5 91.41 (91.18) + train[2018-10-20-19:32:43] Epoch: [165][3800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.226 (2.921) Prec@1 69.53 (75.61) Prec@5 88.28 (91.19) + train[2018-10-20-19:34:29] Epoch: [165][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.760 (2.921) Prec@1 81.25 (75.61) Prec@5 93.75 (91.20) + train[2018-10-20-19:36:13] Epoch: [165][4200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.873 (2.920) Prec@1 79.69 (75.62) Prec@5 89.84 (91.20) + train[2018-10-20-19:37:59] Epoch: [165][4400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.909 (2.921) Prec@1 76.56 (75.61) Prec@5 92.97 (91.20) + train[2018-10-20-19:39:47] Epoch: [165][4600/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 2.705 (2.921) Prec@1 75.78 (75.59) Prec@5 93.75 (91.19) + train[2018-10-20-19:41:35] Epoch: [165][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.787 (2.920) Prec@1 75.00 (75.62) Prec@5 93.75 (91.21) + train[2018-10-20-19:43:23] Epoch: [165][5000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.990 (2.920) Prec@1 75.78 (75.62) Prec@5 89.84 (91.22) + train[2018-10-20-19:45:11] Epoch: [165][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.047 (2.920) Prec@1 75.78 (75.60) Prec@5 92.19 (91.21) + train[2018-10-20-19:46:58] Epoch: [165][5400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.810 (2.920) Prec@1 78.12 (75.60) Prec@5 92.97 (91.21) + train[2018-10-20-19:48:46] Epoch: [165][5600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.891 (2.920) Prec@1 76.56 (75.59) Prec@5 91.41 (91.21) + train[2018-10-20-19:50:34] Epoch: [165][5800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.735 (2.920) Prec@1 75.78 (75.60) Prec@5 96.09 (91.21) + train[2018-10-20-19:52:22] Epoch: [165][6000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.763 (2.920) Prec@1 75.00 (75.59) Prec@5 94.53 (91.21) + train[2018-10-20-19:54:10] Epoch: [165][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.979 (2.922) Prec@1 71.88 (75.58) Prec@5 90.62 (91.19) + train[2018-10-20-19:55:57] Epoch: [165][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.754 (2.922) Prec@1 81.25 (75.58) Prec@5 94.53 (91.19) + train[2018-10-20-19:57:42] Epoch: [165][6600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.899 (2.922) Prec@1 77.34 (75.57) Prec@5 89.84 (91.18) + train[2018-10-20-19:59:27] Epoch: [165][6800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.811 (2.922) Prec@1 79.69 (75.57) Prec@5 91.41 (91.18) + train[2018-10-20-20:01:13] Epoch: [165][7000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.695 (2.921) Prec@1 79.69 (75.57) Prec@5 95.31 (91.18) + train[2018-10-20-20:02:58] Epoch: [165][7200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.084 (2.922) Prec@1 73.44 (75.57) Prec@5 86.72 (91.18) + train[2018-10-20-20:04:43] Epoch: [165][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.976 (2.921) Prec@1 73.44 (75.58) Prec@5 89.06 (91.18) + train[2018-10-20-20:06:28] Epoch: [165][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.741 (2.922) Prec@1 78.91 (75.57) Prec@5 94.53 (91.18) + train[2018-10-20-20:08:14] Epoch: [165][7800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.900 (2.922) Prec@1 73.44 (75.56) Prec@5 92.19 (91.18) + train[2018-10-20-20:10:01] Epoch: [165][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.671 (2.922) Prec@1 81.25 (75.56) Prec@5 93.75 (91.18) + train[2018-10-20-20:11:46] Epoch: [165][8200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.179 (2.922) Prec@1 77.34 (75.56) Prec@5 85.94 (91.18) + train[2018-10-20-20:13:32] Epoch: [165][8400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.071 (2.923) Prec@1 73.44 (75.54) Prec@5 92.19 (91.17) + train[2018-10-20-20:15:17] Epoch: [165][8600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.932 (2.923) Prec@1 79.69 (75.53) Prec@5 93.75 (91.17) + train[2018-10-20-20:17:01] Epoch: [165][8800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.560 (2.924) Prec@1 81.25 (75.53) Prec@5 96.09 (91.16) + train[2018-10-20-20:18:46] Epoch: [165][9000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.140 (2.924) Prec@1 73.44 (75.53) Prec@5 89.06 (91.15) + train[2018-10-20-20:20:31] Epoch: [165][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.261 (2.924) Prec@1 72.66 (75.52) Prec@5 85.94 (91.15) + train[2018-10-20-20:22:17] Epoch: [165][9400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.866 (2.924) Prec@1 72.66 (75.51) Prec@5 93.75 (91.15) + train[2018-10-20-20:24:04] Epoch: [165][9600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.023 (2.925) Prec@1 75.00 (75.51) Prec@5 92.97 (91.14) + train[2018-10-20-20:25:51] Epoch: [165][9800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.963 (2.925) Prec@1 72.66 (75.49) Prec@5 92.19 (91.13) + train[2018-10-20-20:27:36] Epoch: [165][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.135 (2.925) Prec@1 75.00 (75.49) Prec@5 88.28 (91.13) + train[2018-10-20-20:27:40] Epoch: [165][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.603 (2.925) Prec@1 66.67 (75.49) Prec@5 73.33 (91.13) +[2018-10-20-20:27:40] **train** Prec@1 75.49 Prec@5 91.13 Error@1 24.51 Error@5 8.87 Loss:2.925 + test [2018-10-20-20:27:45] Epoch: [165][000/391] Time 4.21 (4.21) Data 4.07 (4.07) Loss 0.498 (0.498) Prec@1 93.75 (93.75) Prec@5 99.22 (99.22) + test [2018-10-20-20:28:11] Epoch: [165][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.132 (0.986) Prec@1 71.09 (77.34) Prec@5 92.19 (93.67) + test [2018-10-20-20:28:37] Epoch: [165][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.193 (1.158) Prec@1 43.75 (73.54) Prec@5 81.25 (91.36) +[2018-10-20-20:28:37] **test** Prec@1 73.54 Prec@5 91.36 Error@1 26.46 Error@5 8.64 Loss:1.158 +----> Best Accuracy : Acc@1=73.62, Acc@5=91.32, Error@1=26.38, Error@5=8.68 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-20-20:28:37] [Epoch=166/250] [Need: 125:12:46] LR=0.0006 ~ 0.0006, Batch=128 + train[2018-10-20-20:28:42] Epoch: [166][000/10010] Time 4.80 (4.80) Data 4.22 (4.22) Loss 3.010 (3.010) Prec@1 74.22 (74.22) Prec@5 89.06 (89.06) + train[2018-10-20-20:30:27] Epoch: [166][200/10010] Time 0.51 (0.55) Data 0.00 (0.02) Loss 2.837 (2.933) Prec@1 79.69 (75.31) Prec@5 92.97 (91.06) + train[2018-10-20-20:32:14] Epoch: [166][400/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 3.200 (2.918) Prec@1 74.22 (75.57) Prec@5 86.72 (91.27) + train[2018-10-20-20:34:00] Epoch: [166][600/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.736 (2.919) Prec@1 80.47 (75.67) Prec@5 92.97 (91.16) + train[2018-10-20-20:35:45] Epoch: [166][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.994 (2.920) Prec@1 72.66 (75.66) Prec@5 88.28 (91.15) + train[2018-10-20-20:37:30] Epoch: [166][1000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.885 (2.919) Prec@1 71.88 (75.61) Prec@5 90.62 (91.16) + train[2018-10-20-20:39:16] Epoch: [166][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.054 (2.917) Prec@1 75.00 (75.63) Prec@5 88.28 (91.18) + train[2018-10-20-20:41:02] Epoch: [166][1400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.727 (2.914) Prec@1 76.56 (75.72) Prec@5 92.97 (91.22) + train[2018-10-20-20:42:47] Epoch: [166][1600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.921 (2.912) Prec@1 73.44 (75.79) Prec@5 92.19 (91.23) + train[2018-10-20-20:44:32] Epoch: [166][1800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.056 (2.912) Prec@1 73.44 (75.76) Prec@5 90.62 (91.23) + train[2018-10-20-20:46:18] Epoch: [166][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.690 (2.913) Prec@1 80.47 (75.74) Prec@5 93.75 (91.21) + train[2018-10-20-20:48:04] Epoch: [166][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.604 (2.914) Prec@1 78.91 (75.71) Prec@5 96.09 (91.21) + train[2018-10-20-20:49:51] Epoch: [166][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.952 (2.914) Prec@1 75.00 (75.70) Prec@5 87.50 (91.21) + train[2018-10-20-20:51:36] Epoch: [166][2600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.590 (2.915) Prec@1 84.38 (75.69) Prec@5 97.66 (91.22) + train[2018-10-20-20:53:23] Epoch: [166][2800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.825 (2.915) Prec@1 78.12 (75.70) Prec@5 93.75 (91.23) + train[2018-10-20-20:55:10] Epoch: [166][3000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.885 (2.914) Prec@1 74.22 (75.69) Prec@5 93.75 (91.24) + train[2018-10-20-20:56:57] Epoch: [166][3200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.876 (2.916) Prec@1 71.09 (75.66) Prec@5 96.09 (91.22) + train[2018-10-20-20:58:44] Epoch: [166][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.599 (2.916) Prec@1 83.59 (75.67) Prec@5 96.88 (91.23) + train[2018-10-20-21:00:30] Epoch: [166][3600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.336 (2.917) Prec@1 65.62 (75.64) Prec@5 86.72 (91.21) + train[2018-10-20-21:02:17] Epoch: [166][3800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.824 (2.917) Prec@1 79.69 (75.65) Prec@5 92.19 (91.22) + train[2018-10-20-21:04:03] Epoch: [166][4000/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.916 (2.917) Prec@1 75.00 (75.67) Prec@5 92.97 (91.22) + train[2018-10-20-21:05:50] Epoch: [166][4200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.163 (2.917) Prec@1 71.88 (75.65) Prec@5 83.59 (91.22) + train[2018-10-20-21:07:36] Epoch: [166][4400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.922 (2.917) Prec@1 70.31 (75.65) Prec@5 91.41 (91.22) + train[2018-10-20-21:09:23] Epoch: [166][4600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.979 (2.916) Prec@1 71.09 (75.66) Prec@5 90.62 (91.22) + train[2018-10-20-21:11:09] Epoch: [166][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.976 (2.916) Prec@1 73.44 (75.67) Prec@5 89.84 (91.23) + train[2018-10-20-21:12:57] Epoch: [166][5000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.817 (2.916) Prec@1 78.91 (75.67) Prec@5 92.97 (91.22) + train[2018-10-20-21:14:44] Epoch: [166][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.101 (2.917) Prec@1 77.34 (75.66) Prec@5 89.84 (91.21) + train[2018-10-20-21:16:31] Epoch: [166][5400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.951 (2.917) Prec@1 77.34 (75.66) Prec@5 92.19 (91.21) + train[2018-10-20-21:18:19] Epoch: [166][5600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.591 (2.916) Prec@1 79.69 (75.68) Prec@5 95.31 (91.21) + train[2018-10-20-21:20:07] Epoch: [166][5800/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 3.068 (2.917) Prec@1 75.00 (75.67) Prec@5 89.84 (91.21) + train[2018-10-20-21:21:53] Epoch: [166][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.853 (2.917) Prec@1 73.44 (75.67) Prec@5 92.19 (91.21) + train[2018-10-20-21:23:40] Epoch: [166][6200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.989 (2.918) Prec@1 75.00 (75.65) Prec@5 89.84 (91.20) + train[2018-10-20-21:25:25] Epoch: [166][6400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.786 (2.918) Prec@1 76.56 (75.64) Prec@5 93.75 (91.20) + train[2018-10-20-21:27:13] Epoch: [166][6600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.755 (2.919) Prec@1 80.47 (75.63) Prec@5 89.84 (91.19) + train[2018-10-20-21:28:59] Epoch: [166][6800/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 2.798 (2.920) Prec@1 82.03 (75.63) Prec@5 96.09 (91.19) + train[2018-10-20-21:30:47] Epoch: [166][7000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.092 (2.920) Prec@1 75.78 (75.63) Prec@5 91.41 (91.19) + train[2018-10-20-21:32:35] Epoch: [166][7200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.562 (2.920) Prec@1 85.94 (75.62) Prec@5 93.75 (91.19) + train[2018-10-20-21:34:21] Epoch: [166][7400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.914 (2.920) Prec@1 75.00 (75.61) Prec@5 92.19 (91.19) + train[2018-10-20-21:36:08] Epoch: [166][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.868 (2.921) Prec@1 77.34 (75.61) Prec@5 90.62 (91.19) + train[2018-10-20-21:37:55] Epoch: [166][7800/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 2.852 (2.920) Prec@1 75.00 (75.62) Prec@5 90.62 (91.19) + train[2018-10-20-21:39:41] Epoch: [166][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.778 (2.921) Prec@1 78.12 (75.61) Prec@5 92.19 (91.19) + train[2018-10-20-21:41:28] Epoch: [166][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.694 (2.921) Prec@1 76.56 (75.61) Prec@5 93.75 (91.19) + train[2018-10-20-21:43:15] Epoch: [166][8400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.110 (2.921) Prec@1 71.09 (75.60) Prec@5 89.84 (91.19) + train[2018-10-20-21:45:02] Epoch: [166][8600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.608 (2.921) Prec@1 81.25 (75.59) Prec@5 96.09 (91.18) + train[2018-10-20-21:46:48] Epoch: [166][8800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.129 (2.921) Prec@1 71.09 (75.59) Prec@5 90.62 (91.18) + train[2018-10-20-21:48:35] Epoch: [166][9000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.841 (2.921) Prec@1 76.56 (75.59) Prec@5 92.19 (91.18) + train[2018-10-20-21:50:22] Epoch: [166][9200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.843 (2.921) Prec@1 75.00 (75.60) Prec@5 95.31 (91.18) + train[2018-10-20-21:52:08] Epoch: [166][9400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.959 (2.921) Prec@1 77.34 (75.60) Prec@5 90.62 (91.18) + train[2018-10-20-21:53:55] Epoch: [166][9600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.908 (2.921) Prec@1 75.78 (75.60) Prec@5 92.97 (91.18) + train[2018-10-20-21:55:42] Epoch: [166][9800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.854 (2.922) Prec@1 75.00 (75.59) Prec@5 90.62 (91.18) + train[2018-10-20-21:57:29] Epoch: [166][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.847 (2.922) Prec@1 74.22 (75.58) Prec@5 91.41 (91.18) + train[2018-10-20-21:57:33] Epoch: [166][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 4.210 (2.922) Prec@1 66.67 (75.58) Prec@5 80.00 (91.18) +[2018-10-20-21:57:33] **train** Prec@1 75.58 Prec@5 91.18 Error@1 24.42 Error@5 8.82 Loss:2.922 + test [2018-10-20-21:57:37] Epoch: [166][000/391] Time 4.14 (4.14) Data 4.01 (4.01) Loss 0.562 (0.562) Prec@1 89.84 (89.84) Prec@5 97.66 (97.66) + test [2018-10-20-21:58:03] Epoch: [166][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.209 (0.997) Prec@1 68.75 (77.35) Prec@5 91.41 (93.49) + test [2018-10-20-21:58:28] Epoch: [166][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.170 (1.167) Prec@1 47.50 (73.61) Prec@5 82.50 (91.27) +[2018-10-20-21:58:28] **test** Prec@1 73.61 Prec@5 91.27 Error@1 26.39 Error@5 8.73 Loss:1.167 +----> Best Accuracy : Acc@1=73.62, Acc@5=91.32, Error@1=26.38, Error@5=8.68 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-20-21:58:28] [Epoch=167/250] [Need: 124:18:12] LR=0.0006 ~ 0.0006, Batch=128 + train[2018-10-20-21:58:33] Epoch: [167][000/10010] Time 4.82 (4.82) Data 4.13 (4.13) Loss 2.759 (2.759) Prec@1 78.12 (78.12) Prec@5 93.75 (93.75) + train[2018-10-20-22:00:20] Epoch: [167][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.041 (2.885) Prec@1 72.66 (76.31) Prec@5 90.62 (91.53) + train[2018-10-20-22:02:05] Epoch: [167][400/10010] Time 0.57 (0.54) Data 0.00 (0.01) Loss 2.796 (2.905) Prec@1 74.22 (75.95) Prec@5 93.75 (91.38) + train[2018-10-20-22:03:50] Epoch: [167][600/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.626 (2.905) Prec@1 81.25 (76.04) Prec@5 92.97 (91.36) + train[2018-10-20-22:05:35] Epoch: [167][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.664 (2.905) Prec@1 84.38 (76.05) Prec@5 93.75 (91.35) + train[2018-10-20-22:07:21] Epoch: [167][1000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.806 (2.910) Prec@1 75.00 (75.95) Prec@5 93.75 (91.33) + train[2018-10-20-22:09:06] Epoch: [167][1200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.838 (2.910) Prec@1 75.78 (75.92) Prec@5 92.97 (91.32) + train[2018-10-20-22:10:51] Epoch: [167][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.942 (2.912) Prec@1 78.91 (75.88) Prec@5 90.62 (91.27) + train[2018-10-20-22:12:37] Epoch: [167][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.961 (2.915) Prec@1 72.66 (75.84) Prec@5 90.62 (91.25) + train[2018-10-20-22:14:23] Epoch: [167][1800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.859 (2.916) Prec@1 75.00 (75.82) Prec@5 92.19 (91.25) + train[2018-10-20-22:16:07] Epoch: [167][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.835 (2.916) Prec@1 79.69 (75.80) Prec@5 91.41 (91.23) + train[2018-10-20-22:17:52] Epoch: [167][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.641 (2.915) Prec@1 78.91 (75.82) Prec@5 93.75 (91.25) + train[2018-10-20-22:19:37] Epoch: [167][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.057 (2.917) Prec@1 72.66 (75.79) Prec@5 90.62 (91.21) + train[2018-10-20-22:21:22] Epoch: [167][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.856 (2.918) Prec@1 75.00 (75.74) Prec@5 91.41 (91.20) + train[2018-10-20-22:23:08] Epoch: [167][2800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.256 (2.917) Prec@1 70.31 (75.75) Prec@5 87.50 (91.21) + train[2018-10-20-22:24:53] Epoch: [167][3000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.634 (2.919) Prec@1 78.91 (75.73) Prec@5 94.53 (91.19) + train[2018-10-20-22:26:39] Epoch: [167][3200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.597 (2.919) Prec@1 83.59 (75.73) Prec@5 94.53 (91.20) + train[2018-10-20-22:28:24] Epoch: [167][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.019 (2.920) Prec@1 71.88 (75.70) Prec@5 90.62 (91.18) + train[2018-10-20-22:30:10] Epoch: [167][3600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.293 (2.920) Prec@1 64.06 (75.69) Prec@5 83.59 (91.19) + train[2018-10-20-22:31:56] Epoch: [167][3800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.844 (2.919) Prec@1 76.56 (75.69) Prec@5 92.19 (91.18) + train[2018-10-20-22:33:43] Epoch: [167][4000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.028 (2.920) Prec@1 69.53 (75.67) Prec@5 89.06 (91.18) + train[2018-10-20-22:35:30] Epoch: [167][4200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.581 (2.919) Prec@1 81.25 (75.69) Prec@5 92.97 (91.18) + train[2018-10-20-22:37:18] Epoch: [167][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.748 (2.919) Prec@1 80.47 (75.71) Prec@5 91.41 (91.18) + train[2018-10-20-22:39:06] Epoch: [167][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.658 (2.918) Prec@1 80.47 (75.72) Prec@5 96.09 (91.18) + train[2018-10-20-22:40:53] Epoch: [167][4800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.918 (2.919) Prec@1 76.56 (75.71) Prec@5 91.41 (91.18) + train[2018-10-20-22:42:40] Epoch: [167][5000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.597 (2.918) Prec@1 85.16 (75.71) Prec@5 94.53 (91.18) + train[2018-10-20-22:44:27] Epoch: [167][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.887 (2.918) Prec@1 78.12 (75.71) Prec@5 92.97 (91.19) + train[2018-10-20-22:46:14] Epoch: [167][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.920 (2.918) Prec@1 76.56 (75.71) Prec@5 90.62 (91.18) + train[2018-10-20-22:48:02] Epoch: [167][5600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.704 (2.918) Prec@1 76.56 (75.70) Prec@5 92.97 (91.19) + train[2018-10-20-22:49:50] Epoch: [167][5800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.083 (2.918) Prec@1 75.00 (75.69) Prec@5 90.62 (91.19) + train[2018-10-20-22:51:37] Epoch: [167][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.730 (2.919) Prec@1 80.47 (75.69) Prec@5 92.97 (91.18) + train[2018-10-20-22:53:25] Epoch: [167][6200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.005 (2.919) Prec@1 75.78 (75.67) Prec@5 91.41 (91.17) + train[2018-10-20-22:55:13] Epoch: [167][6400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.940 (2.919) Prec@1 73.44 (75.67) Prec@5 91.41 (91.17) + train[2018-10-20-22:57:00] Epoch: [167][6600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.940 (2.919) Prec@1 73.44 (75.67) Prec@5 91.41 (91.17) + train[2018-10-20-22:58:46] Epoch: [167][6800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.048 (2.919) Prec@1 73.44 (75.67) Prec@5 89.06 (91.17) + train[2018-10-20-23:00:33] Epoch: [167][7000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.593 (2.919) Prec@1 82.81 (75.67) Prec@5 94.53 (91.18) + train[2018-10-20-23:02:19] Epoch: [167][7200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.072 (2.919) Prec@1 75.00 (75.67) Prec@5 92.19 (91.17) + train[2018-10-20-23:04:04] Epoch: [167][7400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.901 (2.920) Prec@1 77.34 (75.66) Prec@5 90.62 (91.16) + train[2018-10-20-23:05:50] Epoch: [167][7600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.934 (2.920) Prec@1 72.66 (75.66) Prec@5 92.19 (91.15) + train[2018-10-20-23:07:38] Epoch: [167][7800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.958 (2.921) Prec@1 77.34 (75.65) Prec@5 90.62 (91.15) + train[2018-10-20-23:09:25] Epoch: [167][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.233 (2.921) Prec@1 69.53 (75.64) Prec@5 86.72 (91.15) + train[2018-10-20-23:11:10] Epoch: [167][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.926 (2.921) Prec@1 76.56 (75.64) Prec@5 92.19 (91.15) + train[2018-10-20-23:12:57] Epoch: [167][8400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.842 (2.921) Prec@1 78.91 (75.63) Prec@5 92.19 (91.15) + train[2018-10-20-23:14:44] Epoch: [167][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.939 (2.921) Prec@1 73.44 (75.64) Prec@5 87.50 (91.15) + train[2018-10-20-23:16:31] Epoch: [167][8800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.106 (2.921) Prec@1 67.97 (75.63) Prec@5 89.84 (91.16) + train[2018-10-20-23:18:17] Epoch: [167][9000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.870 (2.921) Prec@1 75.78 (75.62) Prec@5 92.97 (91.15) + train[2018-10-20-23:20:02] Epoch: [167][9200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.000 (2.921) Prec@1 70.31 (75.62) Prec@5 91.41 (91.15) + train[2018-10-20-23:21:48] Epoch: [167][9400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.955 (2.922) Prec@1 75.00 (75.61) Prec@5 91.41 (91.15) + train[2018-10-20-23:23:34] Epoch: [167][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.829 (2.922) Prec@1 78.12 (75.61) Prec@5 91.41 (91.15) + train[2018-10-20-23:25:18] Epoch: [167][9800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.839 (2.922) Prec@1 75.00 (75.61) Prec@5 93.75 (91.15) + train[2018-10-20-23:27:02] Epoch: [167][10000/10010] Time 0.49 (0.53) Data 0.00 (0.00) Loss 3.178 (2.922) Prec@1 68.75 (75.61) Prec@5 89.06 (91.15) + train[2018-10-20-23:27:07] Epoch: [167][10009/10010] Time 0.13 (0.53) Data 0.00 (0.00) Loss 4.487 (2.922) Prec@1 53.33 (75.61) Prec@5 66.67 (91.15) +[2018-10-20-23:27:07] **train** Prec@1 75.61 Prec@5 91.15 Error@1 24.39 Error@5 8.85 Loss:2.922 + test [2018-10-20-23:27:11] Epoch: [167][000/391] Time 3.94 (3.94) Data 3.79 (3.79) Loss 0.548 (0.548) Prec@1 89.84 (89.84) Prec@5 98.44 (98.44) + test [2018-10-20-23:27:37] Epoch: [167][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.174 (1.005) Prec@1 71.88 (77.22) Prec@5 92.19 (93.61) + test [2018-10-20-23:28:03] Epoch: [167][390/391] Time 0.09 (0.14) Data 0.00 (0.02) Loss 2.191 (1.172) Prec@1 45.00 (73.57) Prec@5 81.25 (91.40) +[2018-10-20-23:28:03] **test** Prec@1 73.57 Prec@5 91.40 Error@1 26.43 Error@5 8.60 Loss:1.172 +----> Best Accuracy : Acc@1=73.62, Acc@5=91.32, Error@1=26.38, Error@5=8.68 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-20-23:28:03] [Epoch=168/250] [Need: 122:26:00] LR=0.0006 ~ 0.0006, Batch=128 + train[2018-10-20-23:28:09] Epoch: [168][000/10010] Time 5.32 (5.32) Data 4.71 (4.71) Loss 2.844 (2.844) Prec@1 78.12 (78.12) Prec@5 95.31 (95.31) + train[2018-10-20-23:29:53] Epoch: [168][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 2.987 (2.906) Prec@1 78.91 (75.94) Prec@5 90.62 (91.35) + train[2018-10-20-23:31:38] Epoch: [168][400/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.958 (2.908) Prec@1 71.88 (76.05) Prec@5 93.75 (91.24) + train[2018-10-20-23:33:24] Epoch: [168][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.267 (2.910) Prec@1 70.31 (76.00) Prec@5 86.72 (91.23) + train[2018-10-20-23:35:09] Epoch: [168][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.837 (2.916) Prec@1 73.44 (75.89) Prec@5 92.19 (91.17) + train[2018-10-20-23:36:54] Epoch: [168][1000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.739 (2.915) Prec@1 79.69 (75.82) Prec@5 91.41 (91.17) + train[2018-10-20-23:38:39] Epoch: [168][1200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.964 (2.919) Prec@1 75.00 (75.77) Prec@5 90.62 (91.15) + train[2018-10-20-23:40:24] Epoch: [168][1400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.666 (2.919) Prec@1 82.03 (75.74) Prec@5 94.53 (91.16) + train[2018-10-20-23:42:09] Epoch: [168][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.835 (2.920) Prec@1 79.69 (75.71) Prec@5 91.41 (91.15) + train[2018-10-20-23:43:54] Epoch: [168][1800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.742 (2.919) Prec@1 77.34 (75.72) Prec@5 92.97 (91.17) + train[2018-10-20-23:45:39] Epoch: [168][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.835 (2.919) Prec@1 79.69 (75.70) Prec@5 91.41 (91.17) + train[2018-10-20-23:47:24] Epoch: [168][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.804 (2.919) Prec@1 75.00 (75.71) Prec@5 91.41 (91.18) + train[2018-10-20-23:49:10] Epoch: [168][2400/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.787 (2.921) Prec@1 73.44 (75.67) Prec@5 92.97 (91.16) + train[2018-10-20-23:50:56] Epoch: [168][2600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.913 (2.921) Prec@1 75.78 (75.65) Prec@5 88.28 (91.16) + train[2018-10-20-23:52:41] Epoch: [168][2800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.886 (2.922) Prec@1 76.56 (75.62) Prec@5 91.41 (91.14) + train[2018-10-20-23:54:27] Epoch: [168][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.353 (2.920) Prec@1 75.78 (75.66) Prec@5 85.94 (91.16) + train[2018-10-20-23:56:13] Epoch: [168][3200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.811 (2.920) Prec@1 77.34 (75.65) Prec@5 91.41 (91.16) + train[2018-10-20-23:57:59] Epoch: [168][3400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.996 (2.919) Prec@1 74.22 (75.66) Prec@5 90.62 (91.17) + train[2018-10-20-23:59:45] Epoch: [168][3600/10010] Time 0.61 (0.53) Data 0.00 (0.00) Loss 2.715 (2.918) Prec@1 75.78 (75.68) Prec@5 96.09 (91.17) + train[2018-10-21-00:01:30] Epoch: [168][3800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.674 (2.919) Prec@1 78.91 (75.67) Prec@5 94.53 (91.16) + train[2018-10-21-00:03:16] Epoch: [168][4000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.862 (2.917) Prec@1 75.00 (75.68) Prec@5 91.41 (91.18) + train[2018-10-21-00:05:01] Epoch: [168][4200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.118 (2.919) Prec@1 73.44 (75.65) Prec@5 88.28 (91.18) + train[2018-10-21-00:06:47] Epoch: [168][4400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.082 (2.918) Prec@1 71.88 (75.66) Prec@5 89.84 (91.18) + train[2018-10-21-00:08:32] Epoch: [168][4600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.935 (2.919) Prec@1 75.78 (75.65) Prec@5 92.97 (91.18) + train[2018-10-21-00:10:17] Epoch: [168][4800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.745 (2.918) Prec@1 78.91 (75.66) Prec@5 92.97 (91.18) + train[2018-10-21-00:12:01] Epoch: [168][5000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.975 (2.918) Prec@1 72.66 (75.66) Prec@5 90.62 (91.19) + train[2018-10-21-00:13:46] Epoch: [168][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.113 (2.919) Prec@1 75.00 (75.64) Prec@5 87.50 (91.18) + train[2018-10-21-00:15:31] Epoch: [168][5400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.937 (2.919) Prec@1 76.56 (75.65) Prec@5 89.06 (91.19) + train[2018-10-21-00:17:16] Epoch: [168][5600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.828 (2.919) Prec@1 78.91 (75.65) Prec@5 90.62 (91.19) + train[2018-10-21-00:19:01] Epoch: [168][5800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.788 (2.919) Prec@1 78.91 (75.65) Prec@5 92.19 (91.19) + train[2018-10-21-00:20:47] Epoch: [168][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.792 (2.919) Prec@1 80.47 (75.65) Prec@5 91.41 (91.19) + train[2018-10-21-00:22:32] Epoch: [168][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.890 (2.919) Prec@1 78.91 (75.66) Prec@5 90.62 (91.18) + train[2018-10-21-00:24:17] Epoch: [168][6400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.968 (2.920) Prec@1 75.78 (75.65) Prec@5 86.72 (91.18) + train[2018-10-21-00:26:03] Epoch: [168][6600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.058 (2.920) Prec@1 72.66 (75.64) Prec@5 89.06 (91.17) + train[2018-10-21-00:27:48] Epoch: [168][6800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.911 (2.920) Prec@1 74.22 (75.65) Prec@5 90.62 (91.17) + train[2018-10-21-00:29:33] Epoch: [168][7000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.924 (2.920) Prec@1 74.22 (75.66) Prec@5 92.19 (91.17) + train[2018-10-21-00:31:19] Epoch: [168][7200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.110 (2.920) Prec@1 77.34 (75.65) Prec@5 89.84 (91.17) + train[2018-10-21-00:33:05] Epoch: [168][7400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.112 (2.920) Prec@1 78.12 (75.66) Prec@5 87.50 (91.17) + train[2018-10-21-00:34:51] Epoch: [168][7600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.724 (2.920) Prec@1 80.47 (75.65) Prec@5 94.53 (91.17) + train[2018-10-21-00:36:35] Epoch: [168][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.788 (2.920) Prec@1 77.34 (75.65) Prec@5 90.62 (91.17) + train[2018-10-21-00:38:21] Epoch: [168][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.945 (2.920) Prec@1 78.12 (75.64) Prec@5 88.28 (91.17) + train[2018-10-21-00:40:06] Epoch: [168][8200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.146 (2.920) Prec@1 69.53 (75.65) Prec@5 87.50 (91.17) + train[2018-10-21-00:41:51] Epoch: [168][8400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.115 (2.920) Prec@1 75.00 (75.65) Prec@5 89.84 (91.17) + train[2018-10-21-00:43:37] Epoch: [168][8600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.828 (2.920) Prec@1 79.69 (75.64) Prec@5 91.41 (91.17) + train[2018-10-21-00:45:24] Epoch: [168][8800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.768 (2.920) Prec@1 78.12 (75.64) Prec@5 91.41 (91.17) + train[2018-10-21-00:47:10] Epoch: [168][9000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.690 (2.920) Prec@1 78.91 (75.65) Prec@5 95.31 (91.17) + train[2018-10-21-00:48:56] Epoch: [168][9200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.987 (2.920) Prec@1 77.34 (75.64) Prec@5 89.84 (91.16) + train[2018-10-21-00:50:43] Epoch: [168][9400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.132 (2.921) Prec@1 72.66 (75.63) Prec@5 88.28 (91.16) + train[2018-10-21-00:52:28] Epoch: [168][9600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.734 (2.920) Prec@1 77.34 (75.64) Prec@5 94.53 (91.17) + train[2018-10-21-00:54:16] Epoch: [168][9800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.187 (2.920) Prec@1 75.00 (75.66) Prec@5 88.28 (91.17) + train[2018-10-21-00:56:01] Epoch: [168][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.342 (2.920) Prec@1 65.62 (75.65) Prec@5 85.16 (91.17) + train[2018-10-21-00:56:05] Epoch: [168][10009/10010] Time 0.21 (0.53) Data 0.00 (0.00) Loss 4.695 (2.920) Prec@1 60.00 (75.65) Prec@5 73.33 (91.17) +[2018-10-21-00:56:05] **train** Prec@1 75.65 Prec@5 91.17 Error@1 24.35 Error@5 8.83 Loss:2.920 + test [2018-10-21-00:56:09] Epoch: [168][000/391] Time 3.70 (3.70) Data 3.56 (3.56) Loss 0.594 (0.594) Prec@1 90.62 (90.62) Prec@5 98.44 (98.44) + test [2018-10-21-00:56:36] Epoch: [168][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.198 (1.007) Prec@1 66.41 (77.26) Prec@5 93.75 (93.71) + test [2018-10-21-00:57:01] Epoch: [168][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.118 (1.179) Prec@1 46.25 (73.67) Prec@5 82.50 (91.37) +[2018-10-21-00:57:01] **test** Prec@1 73.67 Prec@5 91.37 Error@1 26.33 Error@5 8.63 Loss:1.179 +----> Best Accuracy : Acc@1=73.67, Acc@5=91.37, Error@1=26.33, Error@5=8.63 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-21-00:57:01] [Epoch=169/250] [Need: 120:06:20] LR=0.0006 ~ 0.0006, Batch=128 + train[2018-10-21-00:57:07] Epoch: [169][000/10010] Time 5.44 (5.44) Data 4.81 (4.81) Loss 2.737 (2.737) Prec@1 75.78 (75.78) Prec@5 94.53 (94.53) + train[2018-10-21-00:58:52] Epoch: [169][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 2.851 (2.921) Prec@1 80.47 (75.66) Prec@5 93.75 (91.15) + train[2018-10-21-01:00:36] Epoch: [169][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 3.197 (2.915) Prec@1 67.97 (75.82) Prec@5 89.06 (91.35) + train[2018-10-21-01:02:21] Epoch: [169][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.079 (2.912) Prec@1 71.88 (75.88) Prec@5 92.19 (91.33) + train[2018-10-21-01:04:06] Epoch: [169][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.126 (2.915) Prec@1 74.22 (75.87) Prec@5 89.06 (91.30) + train[2018-10-21-01:05:51] Epoch: [169][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.070 (2.914) Prec@1 67.19 (75.89) Prec@5 91.41 (91.33) + train[2018-10-21-01:07:36] Epoch: [169][1200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.909 (2.920) Prec@1 75.78 (75.71) Prec@5 90.62 (91.25) + train[2018-10-21-01:09:22] Epoch: [169][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.991 (2.916) Prec@1 74.22 (75.78) Prec@5 91.41 (91.30) + train[2018-10-21-01:11:08] Epoch: [169][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.875 (2.916) Prec@1 76.56 (75.80) Prec@5 92.97 (91.31) + train[2018-10-21-01:12:53] Epoch: [169][1800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.811 (2.917) Prec@1 79.69 (75.81) Prec@5 92.97 (91.29) + train[2018-10-21-01:14:37] Epoch: [169][2000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.962 (2.917) Prec@1 75.78 (75.78) Prec@5 89.84 (91.27) + train[2018-10-21-01:16:22] Epoch: [169][2200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.159 (2.917) Prec@1 70.31 (75.79) Prec@5 87.50 (91.27) + train[2018-10-21-01:18:10] Epoch: [169][2400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.031 (2.917) Prec@1 71.88 (75.77) Prec@5 89.06 (91.26) + train[2018-10-21-01:19:57] Epoch: [169][2600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.854 (2.919) Prec@1 75.00 (75.74) Prec@5 92.97 (91.23) + train[2018-10-21-01:21:45] Epoch: [169][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.112 (2.917) Prec@1 77.34 (75.78) Prec@5 87.50 (91.23) + train[2018-10-21-01:23:32] Epoch: [169][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.957 (2.917) Prec@1 75.00 (75.79) Prec@5 92.19 (91.23) + train[2018-10-21-01:25:20] Epoch: [169][3200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.636 (2.917) Prec@1 79.69 (75.78) Prec@5 93.75 (91.24) + train[2018-10-21-01:27:08] Epoch: [169][3400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.064 (2.918) Prec@1 75.00 (75.75) Prec@5 90.62 (91.23) + train[2018-10-21-01:28:56] Epoch: [169][3600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.747 (2.918) Prec@1 78.91 (75.75) Prec@5 92.19 (91.24) + train[2018-10-21-01:30:43] Epoch: [169][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.738 (2.917) Prec@1 77.34 (75.76) Prec@5 92.97 (91.25) + train[2018-10-21-01:32:30] Epoch: [169][4000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.650 (2.917) Prec@1 81.25 (75.75) Prec@5 93.75 (91.23) + train[2018-10-21-01:34:18] Epoch: [169][4200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.691 (2.918) Prec@1 76.56 (75.75) Prec@5 95.31 (91.22) + train[2018-10-21-01:36:07] Epoch: [169][4400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.881 (2.919) Prec@1 75.00 (75.74) Prec@5 92.97 (91.21) + train[2018-10-21-01:37:55] Epoch: [169][4600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.658 (2.919) Prec@1 79.69 (75.73) Prec@5 93.75 (91.21) + train[2018-10-21-01:39:44] Epoch: [169][4800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.898 (2.918) Prec@1 75.78 (75.75) Prec@5 92.19 (91.21) + train[2018-10-21-01:41:31] Epoch: [169][5000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.056 (2.918) Prec@1 77.34 (75.76) Prec@5 90.62 (91.23) + train[2018-10-21-01:43:20] Epoch: [169][5200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.615 (2.917) Prec@1 81.25 (75.76) Prec@5 94.53 (91.24) + train[2018-10-21-01:45:08] Epoch: [169][5400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.870 (2.917) Prec@1 78.91 (75.76) Prec@5 92.97 (91.23) + train[2018-10-21-01:46:55] Epoch: [169][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.051 (2.918) Prec@1 71.09 (75.75) Prec@5 90.62 (91.22) + train[2018-10-21-01:48:42] Epoch: [169][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.736 (2.917) Prec@1 79.69 (75.77) Prec@5 91.41 (91.22) + train[2018-10-21-01:50:27] Epoch: [169][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.775 (2.917) Prec@1 82.03 (75.76) Prec@5 92.19 (91.22) + train[2018-10-21-01:52:13] Epoch: [169][6200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.987 (2.917) Prec@1 76.56 (75.75) Prec@5 94.53 (91.21) + train[2018-10-21-01:53:58] Epoch: [169][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.055 (2.918) Prec@1 70.31 (75.74) Prec@5 92.19 (91.21) + train[2018-10-21-01:55:43] Epoch: [169][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.115 (2.918) Prec@1 71.88 (75.74) Prec@5 84.38 (91.21) + train[2018-10-21-01:57:28] Epoch: [169][6800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.696 (2.918) Prec@1 77.34 (75.73) Prec@5 92.19 (91.21) + train[2018-10-21-01:59:13] Epoch: [169][7000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.950 (2.918) Prec@1 71.09 (75.72) Prec@5 92.19 (91.21) + train[2018-10-21-02:00:58] Epoch: [169][7200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.638 (2.919) Prec@1 81.25 (75.71) Prec@5 95.31 (91.20) + train[2018-10-21-02:02:45] Epoch: [169][7400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.712 (2.918) Prec@1 77.34 (75.71) Prec@5 95.31 (91.21) + train[2018-10-21-02:04:32] Epoch: [169][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.852 (2.918) Prec@1 78.91 (75.71) Prec@5 92.97 (91.21) + train[2018-10-21-02:06:17] Epoch: [169][7800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.170 (2.918) Prec@1 71.09 (75.72) Prec@5 88.28 (91.21) + train[2018-10-21-02:08:02] Epoch: [169][8000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.924 (2.919) Prec@1 77.34 (75.70) Prec@5 89.84 (91.20) + train[2018-10-21-02:09:49] Epoch: [169][8200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.866 (2.919) Prec@1 74.22 (75.70) Prec@5 92.19 (91.20) + train[2018-10-21-02:11:35] Epoch: [169][8400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.838 (2.919) Prec@1 76.56 (75.69) Prec@5 90.62 (91.20) + train[2018-10-21-02:13:20] Epoch: [169][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.193 (2.919) Prec@1 65.62 (75.69) Prec@5 88.28 (91.20) + train[2018-10-21-02:15:05] Epoch: [169][8800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.144 (2.919) Prec@1 71.88 (75.68) Prec@5 89.06 (91.19) + train[2018-10-21-02:16:50] Epoch: [169][9000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.939 (2.920) Prec@1 75.00 (75.69) Prec@5 89.84 (91.19) + train[2018-10-21-02:18:35] Epoch: [169][9200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.964 (2.919) Prec@1 71.88 (75.68) Prec@5 88.28 (91.19) + train[2018-10-21-02:20:20] Epoch: [169][9400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.025 (2.919) Prec@1 75.78 (75.69) Prec@5 88.28 (91.19) + train[2018-10-21-02:22:05] Epoch: [169][9600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.960 (2.919) Prec@1 75.78 (75.69) Prec@5 89.84 (91.19) + train[2018-10-21-02:23:50] Epoch: [169][9800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.862 (2.919) Prec@1 78.12 (75.68) Prec@5 94.53 (91.19) + train[2018-10-21-02:25:35] Epoch: [169][10000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.028 (2.919) Prec@1 71.09 (75.68) Prec@5 91.41 (91.19) + train[2018-10-21-02:25:40] Epoch: [169][10009/10010] Time 0.24 (0.53) Data 0.00 (0.00) Loss 3.041 (2.919) Prec@1 73.33 (75.68) Prec@5 100.00 (91.19) +[2018-10-21-02:25:40] **train** Prec@1 75.68 Prec@5 91.19 Error@1 24.32 Error@5 8.81 Loss:2.919 + test [2018-10-21-02:25:44] Epoch: [169][000/391] Time 4.16 (4.16) Data 4.03 (4.03) Loss 0.544 (0.544) Prec@1 89.84 (89.84) Prec@5 98.44 (98.44) + test [2018-10-21-02:26:11] Epoch: [169][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.255 (1.000) Prec@1 67.97 (77.30) Prec@5 92.19 (93.55) + test [2018-10-21-02:26:36] Epoch: [169][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.208 (1.166) Prec@1 46.25 (73.71) Prec@5 83.75 (91.30) +[2018-10-21-02:26:36] **test** Prec@1 73.71 Prec@5 91.30 Error@1 26.29 Error@5 8.70 Loss:1.166 +----> Best Accuracy : Acc@1=73.71, Acc@5=91.30, Error@1=26.29, Error@5=8.70 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-21-02:26:36] [Epoch=170/250] [Need: 119:25:49] LR=0.0006 ~ 0.0006, Batch=128 + train[2018-10-21-02:26:41] Epoch: [170][000/10010] Time 5.09 (5.09) Data 4.51 (4.51) Loss 3.058 (3.058) Prec@1 72.66 (72.66) Prec@5 89.06 (89.06) + train[2018-10-21-02:28:26] Epoch: [170][200/10010] Time 0.51 (0.55) Data 0.00 (0.02) Loss 2.594 (2.890) Prec@1 83.59 (76.54) Prec@5 96.09 (91.38) + train[2018-10-21-02:30:11] Epoch: [170][400/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.960 (2.901) Prec@1 72.66 (76.17) Prec@5 89.06 (91.39) + train[2018-10-21-02:31:56] Epoch: [170][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.806 (2.908) Prec@1 78.91 (75.93) Prec@5 91.41 (91.34) + train[2018-10-21-02:33:42] Epoch: [170][800/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 2.890 (2.908) Prec@1 78.91 (75.93) Prec@5 93.75 (91.31) + train[2018-10-21-02:35:28] Epoch: [170][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.359 (2.908) Prec@1 71.09 (75.94) Prec@5 87.50 (91.28) + train[2018-10-21-02:37:14] Epoch: [170][1200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.715 (2.912) Prec@1 78.91 (75.87) Prec@5 92.97 (91.24) + train[2018-10-21-02:39:00] Epoch: [170][1400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.555 (2.913) Prec@1 82.81 (75.84) Prec@5 94.53 (91.25) + train[2018-10-21-02:40:45] Epoch: [170][1600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.818 (2.911) Prec@1 77.34 (75.90) Prec@5 92.97 (91.29) + train[2018-10-21-02:42:31] Epoch: [170][1800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.026 (2.913) Prec@1 75.00 (75.88) Prec@5 90.62 (91.26) + train[2018-10-21-02:44:17] Epoch: [170][2000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.945 (2.913) Prec@1 74.22 (75.87) Prec@5 92.97 (91.25) + train[2018-10-21-02:46:03] Epoch: [170][2200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.918 (2.912) Prec@1 76.56 (75.88) Prec@5 89.84 (91.28) + train[2018-10-21-02:47:49] Epoch: [170][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.953 (2.912) Prec@1 74.22 (75.88) Prec@5 92.19 (91.28) + train[2018-10-21-02:49:35] Epoch: [170][2600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.750 (2.912) Prec@1 78.12 (75.88) Prec@5 92.19 (91.29) + train[2018-10-21-02:51:19] Epoch: [170][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.105 (2.912) Prec@1 73.44 (75.89) Prec@5 86.72 (91.27) + train[2018-10-21-02:53:05] Epoch: [170][3000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.748 (2.913) Prec@1 78.12 (75.89) Prec@5 93.75 (91.26) + train[2018-10-21-02:54:50] Epoch: [170][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.975 (2.913) Prec@1 77.34 (75.87) Prec@5 91.41 (91.26) + train[2018-10-21-02:56:35] Epoch: [170][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.990 (2.913) Prec@1 72.66 (75.87) Prec@5 89.06 (91.26) + train[2018-10-21-02:58:21] Epoch: [170][3600/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.913 (2.913) Prec@1 76.56 (75.85) Prec@5 91.41 (91.26) + train[2018-10-21-03:00:07] Epoch: [170][3800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.899 (2.912) Prec@1 73.44 (75.87) Prec@5 92.19 (91.27) + train[2018-10-21-03:01:52] Epoch: [170][4000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.607 (2.912) Prec@1 77.34 (75.87) Prec@5 94.53 (91.27) + train[2018-10-21-03:03:38] Epoch: [170][4200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.980 (2.912) Prec@1 74.22 (75.86) Prec@5 89.84 (91.26) + train[2018-10-21-03:05:23] Epoch: [170][4400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.758 (2.912) Prec@1 77.34 (75.85) Prec@5 96.09 (91.27) + train[2018-10-21-03:07:09] Epoch: [170][4600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.761 (2.912) Prec@1 77.34 (75.84) Prec@5 92.19 (91.26) + train[2018-10-21-03:08:54] Epoch: [170][4800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.034 (2.912) Prec@1 71.09 (75.85) Prec@5 90.62 (91.26) + train[2018-10-21-03:10:40] Epoch: [170][5000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.488 (2.912) Prec@1 85.16 (75.84) Prec@5 96.88 (91.25) + train[2018-10-21-03:12:24] Epoch: [170][5200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.724 (2.912) Prec@1 76.56 (75.84) Prec@5 92.97 (91.26) + train[2018-10-21-03:14:09] Epoch: [170][5400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.921 (2.913) Prec@1 78.12 (75.83) Prec@5 92.19 (91.25) + train[2018-10-21-03:15:54] Epoch: [170][5600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.139 (2.913) Prec@1 74.22 (75.82) Prec@5 88.28 (91.24) + train[2018-10-21-03:17:40] Epoch: [170][5800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.841 (2.913) Prec@1 78.12 (75.82) Prec@5 91.41 (91.24) + train[2018-10-21-03:19:26] Epoch: [170][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.729 (2.913) Prec@1 80.47 (75.81) Prec@5 94.53 (91.24) + train[2018-10-21-03:21:12] Epoch: [170][6200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.718 (2.914) Prec@1 78.12 (75.80) Prec@5 92.97 (91.24) + train[2018-10-21-03:22:57] Epoch: [170][6400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.943 (2.914) Prec@1 71.09 (75.80) Prec@5 91.41 (91.24) + train[2018-10-21-03:24:43] Epoch: [170][6600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.853 (2.914) Prec@1 76.56 (75.79) Prec@5 92.97 (91.24) + train[2018-10-21-03:26:29] Epoch: [170][6800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.951 (2.914) Prec@1 77.34 (75.80) Prec@5 91.41 (91.24) + train[2018-10-21-03:28:14] Epoch: [170][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.901 (2.914) Prec@1 75.00 (75.80) Prec@5 92.97 (91.24) + train[2018-10-21-03:30:00] Epoch: [170][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.112 (2.914) Prec@1 71.88 (75.80) Prec@5 85.16 (91.24) + train[2018-10-21-03:31:45] Epoch: [170][7400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.328 (2.913) Prec@1 64.06 (75.81) Prec@5 87.50 (91.25) + train[2018-10-21-03:33:30] Epoch: [170][7600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.950 (2.913) Prec@1 74.22 (75.81) Prec@5 91.41 (91.25) + train[2018-10-21-03:35:15] Epoch: [170][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.122 (2.914) Prec@1 68.75 (75.81) Prec@5 87.50 (91.23) + train[2018-10-21-03:37:00] Epoch: [170][8000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.967 (2.914) Prec@1 78.12 (75.80) Prec@5 88.28 (91.23) + train[2018-10-21-03:38:46] Epoch: [170][8200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.829 (2.914) Prec@1 76.56 (75.80) Prec@5 95.31 (91.23) + train[2018-10-21-03:40:32] Epoch: [170][8400/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.701 (2.914) Prec@1 77.34 (75.79) Prec@5 94.53 (91.23) + train[2018-10-21-03:42:18] Epoch: [170][8600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.899 (2.914) Prec@1 77.34 (75.79) Prec@5 89.84 (91.24) + train[2018-10-21-03:44:04] Epoch: [170][8800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.791 (2.915) Prec@1 81.25 (75.78) Prec@5 92.97 (91.23) + train[2018-10-21-03:45:49] Epoch: [170][9000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.813 (2.914) Prec@1 77.34 (75.78) Prec@5 95.31 (91.24) + train[2018-10-21-03:47:34] Epoch: [170][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.102 (2.915) Prec@1 67.19 (75.78) Prec@5 92.97 (91.24) + train[2018-10-21-03:49:19] Epoch: [170][9400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.993 (2.915) Prec@1 77.34 (75.77) Prec@5 92.19 (91.23) + train[2018-10-21-03:51:03] Epoch: [170][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.266 (2.915) Prec@1 68.75 (75.78) Prec@5 88.28 (91.24) + train[2018-10-21-03:52:49] Epoch: [170][9800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.711 (2.915) Prec@1 82.81 (75.78) Prec@5 92.97 (91.23) + train[2018-10-21-03:54:34] Epoch: [170][10000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.045 (2.915) Prec@1 74.22 (75.78) Prec@5 90.62 (91.23) + train[2018-10-21-03:54:38] Epoch: [170][10009/10010] Time 0.16 (0.53) Data 0.00 (0.00) Loss 3.419 (2.915) Prec@1 66.67 (75.78) Prec@5 93.33 (91.23) +[2018-10-21-03:54:38] **train** Prec@1 75.78 Prec@5 91.23 Error@1 24.22 Error@5 8.77 Loss:2.915 + test [2018-10-21-03:54:42] Epoch: [170][000/391] Time 4.39 (4.39) Data 4.25 (4.25) Loss 0.533 (0.533) Prec@1 92.97 (92.97) Prec@5 98.44 (98.44) + test [2018-10-21-03:55:09] Epoch: [170][200/391] Time 0.14 (0.15) Data 0.00 (0.03) Loss 1.183 (0.985) Prec@1 69.53 (77.38) Prec@5 92.19 (93.58) + test [2018-10-21-03:55:34] Epoch: [170][390/391] Time 0.09 (0.14) Data 0.00 (0.02) Loss 2.145 (1.159) Prec@1 43.75 (73.64) Prec@5 83.75 (91.35) +[2018-10-21-03:55:34] **test** Prec@1 73.64 Prec@5 91.35 Error@1 26.36 Error@5 8.65 Loss:1.159 +----> Best Accuracy : Acc@1=73.71, Acc@5=91.30, Error@1=26.29, Error@5=8.70 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-21-03:55:35] [Epoch=171/250] [Need: 117:09:28] LR=0.0005 ~ 0.0005, Batch=128 + train[2018-10-21-03:55:39] Epoch: [171][000/10010] Time 4.28 (4.28) Data 3.63 (3.63) Loss 2.693 (2.693) Prec@1 82.03 (82.03) Prec@5 93.75 (93.75) + train[2018-10-21-03:57:23] Epoch: [171][200/10010] Time 0.53 (0.54) Data 0.00 (0.02) Loss 2.644 (2.899) Prec@1 79.69 (76.28) Prec@5 97.66 (91.46) + train[2018-10-21-03:59:08] Epoch: [171][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.965 (2.903) Prec@1 72.66 (76.07) Prec@5 91.41 (91.41) + train[2018-10-21-04:00:54] Epoch: [171][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 2.949 (2.902) Prec@1 73.44 (76.00) Prec@5 91.41 (91.44) + train[2018-10-21-04:02:39] Epoch: [171][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.097 (2.908) Prec@1 75.78 (75.86) Prec@5 88.28 (91.34) + train[2018-10-21-04:04:24] Epoch: [171][1000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.288 (2.908) Prec@1 72.66 (75.88) Prec@5 85.94 (91.32) + train[2018-10-21-04:06:08] Epoch: [171][1200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.874 (2.910) Prec@1 72.66 (75.87) Prec@5 94.53 (91.30) + train[2018-10-21-04:07:52] Epoch: [171][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.902 (2.911) Prec@1 76.56 (75.81) Prec@5 90.62 (91.29) + train[2018-10-21-04:09:38] Epoch: [171][1600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.834 (2.909) Prec@1 74.22 (75.89) Prec@5 92.97 (91.31) + train[2018-10-21-04:11:23] Epoch: [171][1800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.005 (2.909) Prec@1 75.00 (75.92) Prec@5 92.19 (91.32) + train[2018-10-21-04:13:09] Epoch: [171][2000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.848 (2.909) Prec@1 77.34 (75.89) Prec@5 90.62 (91.32) + train[2018-10-21-04:14:54] Epoch: [171][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.964 (2.910) Prec@1 74.22 (75.87) Prec@5 92.19 (91.31) + train[2018-10-21-04:16:39] Epoch: [171][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.613 (2.911) Prec@1 85.94 (75.85) Prec@5 92.97 (91.31) + train[2018-10-21-04:18:25] Epoch: [171][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.792 (2.912) Prec@1 77.34 (75.81) Prec@5 91.41 (91.29) + train[2018-10-21-04:20:11] Epoch: [171][2800/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.975 (2.912) Prec@1 77.34 (75.80) Prec@5 90.62 (91.28) + train[2018-10-21-04:21:56] Epoch: [171][3000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.793 (2.914) Prec@1 82.03 (75.77) Prec@5 90.62 (91.26) + train[2018-10-21-04:23:41] Epoch: [171][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.972 (2.914) Prec@1 76.56 (75.77) Prec@5 88.28 (91.26) + train[2018-10-21-04:25:27] Epoch: [171][3400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.834 (2.913) Prec@1 78.12 (75.78) Prec@5 92.97 (91.27) + train[2018-10-21-04:27:12] Epoch: [171][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.124 (2.913) Prec@1 72.66 (75.77) Prec@5 90.62 (91.26) + train[2018-10-21-04:28:57] Epoch: [171][3800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.827 (2.914) Prec@1 76.56 (75.77) Prec@5 91.41 (91.26) + train[2018-10-21-04:30:41] Epoch: [171][4000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.703 (2.913) Prec@1 77.34 (75.77) Prec@5 93.75 (91.27) + train[2018-10-21-04:32:26] Epoch: [171][4200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.913 (2.913) Prec@1 71.88 (75.78) Prec@5 93.75 (91.27) + train[2018-10-21-04:34:11] Epoch: [171][4400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.759 (2.913) Prec@1 76.56 (75.78) Prec@5 93.75 (91.26) + train[2018-10-21-04:35:57] Epoch: [171][4600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.699 (2.912) Prec@1 78.91 (75.80) Prec@5 92.97 (91.26) + train[2018-10-21-04:37:42] Epoch: [171][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.774 (2.913) Prec@1 78.12 (75.78) Prec@5 92.19 (91.26) + train[2018-10-21-04:39:28] Epoch: [171][5000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.946 (2.912) Prec@1 76.56 (75.80) Prec@5 91.41 (91.27) + train[2018-10-21-04:41:13] Epoch: [171][5200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.080 (2.912) Prec@1 71.88 (75.79) Prec@5 89.84 (91.27) + train[2018-10-21-04:42:58] Epoch: [171][5400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.842 (2.912) Prec@1 78.91 (75.80) Prec@5 93.75 (91.26) + train[2018-10-21-04:44:43] Epoch: [171][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.994 (2.912) Prec@1 71.88 (75.80) Prec@5 89.06 (91.26) + train[2018-10-21-04:46:30] Epoch: [171][5800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.906 (2.912) Prec@1 75.78 (75.82) Prec@5 92.19 (91.26) + train[2018-10-21-04:48:16] Epoch: [171][6000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.004 (2.913) Prec@1 72.66 (75.81) Prec@5 90.62 (91.25) + train[2018-10-21-04:50:04] Epoch: [171][6200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.995 (2.913) Prec@1 76.56 (75.81) Prec@5 91.41 (91.25) + train[2018-10-21-04:51:52] Epoch: [171][6400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.620 (2.913) Prec@1 80.47 (75.80) Prec@5 96.88 (91.25) + train[2018-10-21-04:53:40] Epoch: [171][6600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.073 (2.912) Prec@1 71.09 (75.83) Prec@5 88.28 (91.26) + train[2018-10-21-04:55:27] Epoch: [171][6800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.154 (2.912) Prec@1 74.22 (75.83) Prec@5 89.06 (91.26) + train[2018-10-21-04:57:15] Epoch: [171][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.102 (2.911) Prec@1 71.09 (75.84) Prec@5 90.62 (91.27) + train[2018-10-21-04:59:01] Epoch: [171][7200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.901 (2.911) Prec@1 75.00 (75.84) Prec@5 92.19 (91.27) + train[2018-10-21-05:00:49] Epoch: [171][7400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.914 (2.911) Prec@1 80.47 (75.83) Prec@5 92.97 (91.27) + train[2018-10-21-05:02:37] Epoch: [171][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.795 (2.911) Prec@1 76.56 (75.83) Prec@5 92.97 (91.27) + train[2018-10-21-05:04:26] Epoch: [171][7800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.938 (2.912) Prec@1 77.34 (75.82) Prec@5 90.62 (91.26) + train[2018-10-21-05:06:15] Epoch: [171][8000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.874 (2.912) Prec@1 72.66 (75.83) Prec@5 90.62 (91.26) + train[2018-10-21-05:08:03] Epoch: [171][8200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.913 (2.912) Prec@1 75.78 (75.82) Prec@5 91.41 (91.26) + train[2018-10-21-05:09:51] Epoch: [171][8400/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.800 (2.912) Prec@1 72.66 (75.82) Prec@5 96.09 (91.26) + train[2018-10-21-05:11:40] Epoch: [171][8600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.344 (2.913) Prec@1 68.75 (75.80) Prec@5 88.28 (91.25) + train[2018-10-21-05:13:28] Epoch: [171][8800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.257 (2.913) Prec@1 67.97 (75.80) Prec@5 85.94 (91.25) + train[2018-10-21-05:15:16] Epoch: [171][9000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.210 (2.913) Prec@1 71.09 (75.80) Prec@5 85.16 (91.25) + train[2018-10-21-05:17:04] Epoch: [171][9200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.881 (2.914) Prec@1 74.22 (75.78) Prec@5 92.97 (91.24) + train[2018-10-21-05:18:53] Epoch: [171][9400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.171 (2.914) Prec@1 71.09 (75.79) Prec@5 88.28 (91.24) + train[2018-10-21-05:20:41] Epoch: [171][9600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.761 (2.914) Prec@1 75.00 (75.78) Prec@5 95.31 (91.24) + train[2018-10-21-05:22:30] Epoch: [171][9800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.023 (2.914) Prec@1 75.00 (75.78) Prec@5 92.19 (91.24) + train[2018-10-21-05:24:18] Epoch: [171][10000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.036 (2.914) Prec@1 75.00 (75.78) Prec@5 91.41 (91.24) + train[2018-10-21-05:24:23] Epoch: [171][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 4.303 (2.914) Prec@1 73.33 (75.78) Prec@5 80.00 (91.24) +[2018-10-21-05:24:23] **train** Prec@1 75.78 Prec@5 91.24 Error@1 24.22 Error@5 8.76 Loss:2.914 + test [2018-10-21-05:24:27] Epoch: [171][000/391] Time 4.64 (4.64) Data 4.49 (4.49) Loss 0.533 (0.533) Prec@1 94.53 (94.53) Prec@5 99.22 (99.22) + test [2018-10-21-05:24:55] Epoch: [171][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.123 (1.009) Prec@1 71.88 (77.30) Prec@5 94.53 (93.64) + test [2018-10-21-05:25:21] Epoch: [171][390/391] Time 0.09 (0.15) Data 0.00 (0.02) Loss 2.165 (1.174) Prec@1 43.75 (73.60) Prec@5 81.25 (91.40) +[2018-10-21-05:25:21] **test** Prec@1 73.60 Prec@5 91.40 Error@1 26.40 Error@5 8.60 Loss:1.174 +----> Best Accuracy : Acc@1=73.71, Acc@5=91.30, Error@1=26.29, Error@5=8.70 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-21-05:25:21] [Epoch=172/250] [Need: 116:42:42] LR=0.0005 ~ 0.0005, Batch=128 + train[2018-10-21-05:25:27] Epoch: [172][000/10010] Time 5.41 (5.41) Data 4.79 (4.79) Loss 2.740 (2.740) Prec@1 75.78 (75.78) Prec@5 91.41 (91.41) + train[2018-10-21-05:27:12] Epoch: [172][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.142 (2.886) Prec@1 69.53 (76.17) Prec@5 88.28 (91.41) + train[2018-10-21-05:28:58] Epoch: [172][400/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 2.786 (2.892) Prec@1 78.91 (76.06) Prec@5 91.41 (91.43) + train[2018-10-21-05:30:43] Epoch: [172][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.783 (2.893) Prec@1 77.34 (76.14) Prec@5 92.19 (91.48) + train[2018-10-21-05:32:28] Epoch: [172][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.932 (2.897) Prec@1 76.56 (76.04) Prec@5 89.84 (91.42) + train[2018-10-21-05:34:13] Epoch: [172][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.880 (2.898) Prec@1 80.47 (76.03) Prec@5 91.41 (91.40) + train[2018-10-21-05:35:58] Epoch: [172][1200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.965 (2.903) Prec@1 74.22 (75.91) Prec@5 88.28 (91.35) + train[2018-10-21-05:37:43] Epoch: [172][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.904 (2.903) Prec@1 75.00 (75.92) Prec@5 87.50 (91.36) + train[2018-10-21-05:39:28] Epoch: [172][1600/10010] Time 0.61 (0.53) Data 0.00 (0.00) Loss 2.819 (2.902) Prec@1 76.56 (75.96) Prec@5 92.97 (91.35) + train[2018-10-21-05:41:14] Epoch: [172][1800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.863 (2.903) Prec@1 76.56 (75.93) Prec@5 89.84 (91.33) + train[2018-10-21-05:42:59] Epoch: [172][2000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.841 (2.905) Prec@1 78.12 (75.91) Prec@5 92.19 (91.32) + train[2018-10-21-05:44:44] Epoch: [172][2200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.657 (2.906) Prec@1 81.25 (75.91) Prec@5 92.97 (91.33) + train[2018-10-21-05:46:30] Epoch: [172][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.748 (2.907) Prec@1 78.91 (75.89) Prec@5 92.97 (91.33) + train[2018-10-21-05:48:14] Epoch: [172][2600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.988 (2.908) Prec@1 74.22 (75.88) Prec@5 91.41 (91.33) + train[2018-10-21-05:50:01] Epoch: [172][2800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.889 (2.907) Prec@1 75.00 (75.89) Prec@5 91.41 (91.32) + train[2018-10-21-05:51:46] Epoch: [172][3000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.699 (2.908) Prec@1 78.91 (75.87) Prec@5 92.19 (91.32) + train[2018-10-21-05:53:33] Epoch: [172][3200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.931 (2.908) Prec@1 76.56 (75.88) Prec@5 89.84 (91.33) + train[2018-10-21-05:55:19] Epoch: [172][3400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.892 (2.907) Prec@1 75.78 (75.88) Prec@5 92.19 (91.33) + train[2018-10-21-05:57:05] Epoch: [172][3600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.729 (2.908) Prec@1 71.88 (75.87) Prec@5 95.31 (91.31) + train[2018-10-21-05:58:52] Epoch: [172][3800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.990 (2.908) Prec@1 75.78 (75.88) Prec@5 89.06 (91.32) + train[2018-10-21-06:00:38] Epoch: [172][4000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.953 (2.909) Prec@1 78.12 (75.88) Prec@5 91.41 (91.31) + train[2018-10-21-06:02:23] Epoch: [172][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.134 (2.909) Prec@1 69.53 (75.86) Prec@5 86.72 (91.30) + train[2018-10-21-06:04:09] Epoch: [172][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.140 (2.910) Prec@1 67.97 (75.85) Prec@5 88.28 (91.29) + train[2018-10-21-06:05:54] Epoch: [172][4600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.424 (2.910) Prec@1 84.38 (75.85) Prec@5 96.09 (91.28) + train[2018-10-21-06:07:40] Epoch: [172][4800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.827 (2.911) Prec@1 74.22 (75.82) Prec@5 91.41 (91.27) + train[2018-10-21-06:09:25] Epoch: [172][5000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.800 (2.911) Prec@1 76.56 (75.82) Prec@5 92.97 (91.27) + train[2018-10-21-06:11:10] Epoch: [172][5200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.864 (2.911) Prec@1 75.78 (75.83) Prec@5 90.62 (91.28) + train[2018-10-21-06:12:55] Epoch: [172][5400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.307 (2.911) Prec@1 70.31 (75.81) Prec@5 87.50 (91.28) + train[2018-10-21-06:14:40] Epoch: [172][5600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.045 (2.911) Prec@1 73.44 (75.81) Prec@5 86.72 (91.28) + train[2018-10-21-06:16:25] Epoch: [172][5800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.094 (2.911) Prec@1 71.09 (75.82) Prec@5 88.28 (91.28) + train[2018-10-21-06:18:10] Epoch: [172][6000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.744 (2.912) Prec@1 80.47 (75.80) Prec@5 90.62 (91.28) + train[2018-10-21-06:19:56] Epoch: [172][6200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.932 (2.911) Prec@1 75.00 (75.82) Prec@5 91.41 (91.27) + train[2018-10-21-06:21:41] Epoch: [172][6400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.872 (2.911) Prec@1 78.12 (75.84) Prec@5 90.62 (91.28) + train[2018-10-21-06:23:26] Epoch: [172][6600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.836 (2.912) Prec@1 75.78 (75.83) Prec@5 92.97 (91.26) + train[2018-10-21-06:25:11] Epoch: [172][6800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.741 (2.912) Prec@1 81.25 (75.82) Prec@5 92.97 (91.26) + train[2018-10-21-06:26:57] Epoch: [172][7000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.901 (2.911) Prec@1 75.78 (75.83) Prec@5 92.19 (91.26) + train[2018-10-21-06:28:42] Epoch: [172][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.680 (2.911) Prec@1 81.25 (75.83) Prec@5 95.31 (91.26) + train[2018-10-21-06:30:28] Epoch: [172][7400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.932 (2.912) Prec@1 76.56 (75.82) Prec@5 92.19 (91.26) + train[2018-10-21-06:32:12] Epoch: [172][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.806 (2.911) Prec@1 78.91 (75.83) Prec@5 91.41 (91.26) + train[2018-10-21-06:33:58] Epoch: [172][7800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.666 (2.911) Prec@1 81.25 (75.83) Prec@5 93.75 (91.26) + train[2018-10-21-06:35:43] Epoch: [172][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.120 (2.911) Prec@1 74.22 (75.83) Prec@5 86.72 (91.26) + train[2018-10-21-06:37:30] Epoch: [172][8200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.644 (2.912) Prec@1 78.12 (75.82) Prec@5 93.75 (91.26) + train[2018-10-21-06:39:16] Epoch: [172][8400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.873 (2.912) Prec@1 74.22 (75.82) Prec@5 92.19 (91.26) + train[2018-10-21-06:41:02] Epoch: [172][8600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.952 (2.912) Prec@1 75.78 (75.81) Prec@5 89.84 (91.25) + train[2018-10-21-06:42:46] Epoch: [172][8800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.748 (2.912) Prec@1 82.03 (75.82) Prec@5 89.84 (91.25) + train[2018-10-21-06:44:29] Epoch: [172][9000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.051 (2.912) Prec@1 75.00 (75.82) Prec@5 89.06 (91.25) + train[2018-10-21-06:46:14] Epoch: [172][9200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.754 (2.912) Prec@1 75.78 (75.82) Prec@5 93.75 (91.25) + train[2018-10-21-06:47:59] Epoch: [172][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.005 (2.913) Prec@1 74.22 (75.81) Prec@5 91.41 (91.24) + train[2018-10-21-06:49:45] Epoch: [172][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.052 (2.913) Prec@1 71.09 (75.79) Prec@5 89.84 (91.24) + train[2018-10-21-06:51:30] Epoch: [172][9800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.886 (2.913) Prec@1 75.00 (75.78) Prec@5 91.41 (91.24) + train[2018-10-21-06:53:14] Epoch: [172][10000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.957 (2.913) Prec@1 74.22 (75.79) Prec@5 93.75 (91.25) + train[2018-10-21-06:53:19] Epoch: [172][10009/10010] Time 0.21 (0.53) Data 0.00 (0.00) Loss 3.535 (2.913) Prec@1 60.00 (75.79) Prec@5 93.33 (91.25) +[2018-10-21-06:53:19] **train** Prec@1 75.79 Prec@5 91.25 Error@1 24.21 Error@5 8.75 Loss:2.913 + test [2018-10-21-06:53:22] Epoch: [172][000/391] Time 3.70 (3.70) Data 3.57 (3.57) Loss 0.490 (0.490) Prec@1 92.97 (92.97) Prec@5 99.22 (99.22) + test [2018-10-21-06:53:49] Epoch: [172][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.202 (1.002) Prec@1 69.53 (77.24) Prec@5 90.62 (93.65) + test [2018-10-21-06:54:14] Epoch: [172][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.169 (1.170) Prec@1 46.25 (73.59) Prec@5 82.50 (91.36) +[2018-10-21-06:54:14] **test** Prec@1 73.59 Prec@5 91.36 Error@1 26.41 Error@5 8.64 Loss:1.170 +----> Best Accuracy : Acc@1=73.71, Acc@5=91.30, Error@1=26.29, Error@5=8.70 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-21-06:54:14] [Epoch=173/250] [Need: 114:03:49] LR=0.0005 ~ 0.0005, Batch=128 + train[2018-10-21-06:54:18] Epoch: [173][000/10010] Time 4.32 (4.32) Data 3.71 (3.71) Loss 2.906 (2.906) Prec@1 77.34 (77.34) Prec@5 92.97 (92.97) + train[2018-10-21-06:56:04] Epoch: [173][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.129 (2.922) Prec@1 70.31 (75.91) Prec@5 89.84 (91.23) + train[2018-10-21-06:57:50] Epoch: [173][400/10010] Time 0.58 (0.54) Data 0.00 (0.01) Loss 2.810 (2.912) Prec@1 77.34 (76.14) Prec@5 94.53 (91.36) + train[2018-10-21-06:59:35] Epoch: [173][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 2.844 (2.911) Prec@1 75.78 (76.05) Prec@5 94.53 (91.35) + train[2018-10-21-07:01:20] Epoch: [173][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.113 (2.910) Prec@1 70.31 (76.07) Prec@5 90.62 (91.30) + train[2018-10-21-07:03:05] Epoch: [173][1000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.607 (2.907) Prec@1 82.81 (76.17) Prec@5 93.75 (91.33) + train[2018-10-21-07:04:50] Epoch: [173][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.854 (2.901) Prec@1 76.56 (76.29) Prec@5 94.53 (91.40) + train[2018-10-21-07:06:35] Epoch: [173][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.954 (2.906) Prec@1 75.78 (76.18) Prec@5 87.50 (91.32) + train[2018-10-21-07:08:21] Epoch: [173][1600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.176 (2.905) Prec@1 74.22 (76.20) Prec@5 89.84 (91.35) + train[2018-10-21-07:10:06] Epoch: [173][1800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.771 (2.908) Prec@1 77.34 (76.11) Prec@5 94.53 (91.31) + train[2018-10-21-07:11:52] Epoch: [173][2000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.093 (2.908) Prec@1 67.97 (76.10) Prec@5 88.28 (91.30) + train[2018-10-21-07:13:37] Epoch: [173][2200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.739 (2.906) Prec@1 79.69 (76.11) Prec@5 92.97 (91.30) + train[2018-10-21-07:15:23] Epoch: [173][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.907 (2.906) Prec@1 74.22 (76.10) Prec@5 90.62 (91.31) + train[2018-10-21-07:17:10] Epoch: [173][2600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.125 (2.906) Prec@1 66.41 (76.04) Prec@5 88.28 (91.31) + train[2018-10-21-07:18:55] Epoch: [173][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.682 (2.905) Prec@1 80.47 (76.05) Prec@5 95.31 (91.33) + train[2018-10-21-07:20:39] Epoch: [173][3000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.873 (2.906) Prec@1 78.91 (76.00) Prec@5 89.84 (91.31) + train[2018-10-21-07:22:25] Epoch: [173][3200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.719 (2.907) Prec@1 75.78 (76.00) Prec@5 93.75 (91.30) + train[2018-10-21-07:24:10] Epoch: [173][3400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.938 (2.907) Prec@1 77.34 (75.99) Prec@5 91.41 (91.29) + train[2018-10-21-07:25:55] Epoch: [173][3600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.729 (2.907) Prec@1 79.69 (75.98) Prec@5 93.75 (91.29) + train[2018-10-21-07:27:40] Epoch: [173][3800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.925 (2.907) Prec@1 78.12 (75.98) Prec@5 91.41 (91.30) + train[2018-10-21-07:29:25] Epoch: [173][4000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.798 (2.907) Prec@1 75.78 (75.95) Prec@5 92.97 (91.30) + train[2018-10-21-07:31:11] Epoch: [173][4200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.654 (2.908) Prec@1 79.69 (75.93) Prec@5 94.53 (91.31) + train[2018-10-21-07:32:56] Epoch: [173][4400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.044 (2.908) Prec@1 71.09 (75.92) Prec@5 89.84 (91.31) + train[2018-10-21-07:34:42] Epoch: [173][4600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.815 (2.908) Prec@1 80.47 (75.92) Prec@5 91.41 (91.31) + train[2018-10-21-07:36:27] Epoch: [173][4800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.927 (2.908) Prec@1 73.44 (75.91) Prec@5 92.97 (91.31) + train[2018-10-21-07:38:12] Epoch: [173][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.289 (2.909) Prec@1 67.19 (75.90) Prec@5 83.59 (91.30) + train[2018-10-21-07:39:58] Epoch: [173][5200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.553 (2.908) Prec@1 83.59 (75.92) Prec@5 92.97 (91.31) + train[2018-10-21-07:41:42] Epoch: [173][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.025 (2.908) Prec@1 73.44 (75.91) Prec@5 89.84 (91.30) + train[2018-10-21-07:43:27] Epoch: [173][5600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.077 (2.908) Prec@1 74.22 (75.90) Prec@5 89.84 (91.30) + train[2018-10-21-07:45:11] Epoch: [173][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.705 (2.908) Prec@1 84.38 (75.90) Prec@5 90.62 (91.30) + train[2018-10-21-07:46:56] Epoch: [173][6000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.992 (2.909) Prec@1 73.44 (75.89) Prec@5 89.84 (91.29) + train[2018-10-21-07:48:42] Epoch: [173][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.827 (2.909) Prec@1 74.22 (75.88) Prec@5 96.09 (91.29) + train[2018-10-21-07:50:27] Epoch: [173][6400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.673 (2.909) Prec@1 80.47 (75.88) Prec@5 93.75 (91.29) + train[2018-10-21-07:52:11] Epoch: [173][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.961 (2.909) Prec@1 73.44 (75.87) Prec@5 91.41 (91.29) + train[2018-10-21-07:53:57] Epoch: [173][6800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.850 (2.909) Prec@1 78.12 (75.86) Prec@5 91.41 (91.28) + train[2018-10-21-07:55:44] Epoch: [173][7000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.297 (2.910) Prec@1 73.44 (75.86) Prec@5 85.94 (91.27) + train[2018-10-21-07:57:30] Epoch: [173][7200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.044 (2.911) Prec@1 71.88 (75.84) Prec@5 90.62 (91.27) + train[2018-10-21-07:59:18] Epoch: [173][7400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.739 (2.911) Prec@1 78.12 (75.83) Prec@5 91.41 (91.27) + train[2018-10-21-08:01:04] Epoch: [173][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.986 (2.911) Prec@1 77.34 (75.82) Prec@5 89.84 (91.26) + train[2018-10-21-08:02:49] Epoch: [173][7800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.148 (2.911) Prec@1 73.44 (75.82) Prec@5 88.28 (91.26) + train[2018-10-21-08:04:34] Epoch: [173][8000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.022 (2.912) Prec@1 71.88 (75.81) Prec@5 92.19 (91.25) + train[2018-10-21-08:06:21] Epoch: [173][8200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.745 (2.912) Prec@1 77.34 (75.81) Prec@5 92.97 (91.26) + train[2018-10-21-08:08:08] Epoch: [173][8400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.129 (2.912) Prec@1 70.31 (75.82) Prec@5 86.72 (91.26) + train[2018-10-21-08:09:55] Epoch: [173][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.667 (2.911) Prec@1 78.12 (75.83) Prec@5 92.97 (91.27) + train[2018-10-21-08:11:41] Epoch: [173][8800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.726 (2.911) Prec@1 79.69 (75.83) Prec@5 93.75 (91.26) + train[2018-10-21-08:13:26] Epoch: [173][9000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.724 (2.911) Prec@1 79.69 (75.83) Prec@5 95.31 (91.26) + train[2018-10-21-08:15:12] Epoch: [173][9200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.900 (2.911) Prec@1 80.47 (75.83) Prec@5 92.19 (91.26) + train[2018-10-21-08:16:56] Epoch: [173][9400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.857 (2.911) Prec@1 74.22 (75.83) Prec@5 90.62 (91.26) + train[2018-10-21-08:18:41] Epoch: [173][9600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.975 (2.911) Prec@1 74.22 (75.83) Prec@5 90.62 (91.26) + train[2018-10-21-08:20:26] Epoch: [173][9800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.874 (2.911) Prec@1 78.91 (75.83) Prec@5 89.84 (91.26) + train[2018-10-21-08:22:11] Epoch: [173][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.936 (2.911) Prec@1 74.22 (75.84) Prec@5 89.84 (91.26) + train[2018-10-21-08:22:15] Epoch: [173][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.858 (2.911) Prec@1 60.00 (75.84) Prec@5 73.33 (91.26) +[2018-10-21-08:22:15] **train** Prec@1 75.84 Prec@5 91.26 Error@1 24.16 Error@5 8.74 Loss:2.911 + test [2018-10-21-08:22:19] Epoch: [173][000/391] Time 4.03 (4.03) Data 3.89 (3.89) Loss 0.516 (0.516) Prec@1 93.75 (93.75) Prec@5 99.22 (99.22) + test [2018-10-21-08:22:45] Epoch: [173][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.205 (0.994) Prec@1 68.75 (77.25) Prec@5 91.41 (93.55) + test [2018-10-21-08:23:10] Epoch: [173][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.179 (1.161) Prec@1 45.00 (73.65) Prec@5 83.75 (91.37) +[2018-10-21-08:23:10] **test** Prec@1 73.65 Prec@5 91.37 Error@1 26.35 Error@5 8.63 Loss:1.161 +----> Best Accuracy : Acc@1=73.71, Acc@5=91.30, Error@1=26.29, Error@5=8.70 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-21-08:23:11] [Epoch=174/250] [Need: 112:39:21] LR=0.0005 ~ 0.0005, Batch=128 + train[2018-10-21-08:23:15] Epoch: [174][000/10010] Time 4.36 (4.36) Data 3.72 (3.72) Loss 2.883 (2.883) Prec@1 70.31 (70.31) Prec@5 91.41 (91.41) + train[2018-10-21-08:25:02] Epoch: [174][200/10010] Time 0.52 (0.55) Data 0.00 (0.02) Loss 2.896 (2.909) Prec@1 78.91 (75.96) Prec@5 89.84 (91.17) + train[2018-10-21-08:26:47] Epoch: [174][400/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 2.969 (2.907) Prec@1 74.22 (75.91) Prec@5 89.06 (91.28) + train[2018-10-21-08:28:32] Epoch: [174][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.958 (2.906) Prec@1 71.88 (75.99) Prec@5 91.41 (91.30) + train[2018-10-21-08:30:17] Epoch: [174][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.917 (2.904) Prec@1 78.12 (76.06) Prec@5 88.28 (91.34) + train[2018-10-21-08:32:01] Epoch: [174][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.094 (2.906) Prec@1 72.66 (75.99) Prec@5 89.06 (91.33) + train[2018-10-21-08:33:46] Epoch: [174][1200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.900 (2.908) Prec@1 73.44 (75.98) Prec@5 93.75 (91.31) + train[2018-10-21-08:35:31] Epoch: [174][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.976 (2.910) Prec@1 76.56 (75.95) Prec@5 90.62 (91.32) + train[2018-10-21-08:37:16] Epoch: [174][1600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.042 (2.907) Prec@1 71.88 (76.00) Prec@5 89.84 (91.36) + train[2018-10-21-08:39:00] Epoch: [174][1800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.900 (2.906) Prec@1 75.00 (76.05) Prec@5 89.84 (91.36) + train[2018-10-21-08:40:46] Epoch: [174][2000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.798 (2.907) Prec@1 77.34 (76.03) Prec@5 92.19 (91.36) + train[2018-10-21-08:42:32] Epoch: [174][2200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.800 (2.905) Prec@1 78.91 (76.06) Prec@5 92.97 (91.35) + train[2018-10-21-08:44:17] Epoch: [174][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.951 (2.904) Prec@1 75.78 (76.04) Prec@5 89.06 (91.36) + train[2018-10-21-08:46:02] Epoch: [174][2600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.261 (2.905) Prec@1 75.78 (76.05) Prec@5 87.50 (91.35) + train[2018-10-21-08:47:47] Epoch: [174][2800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.791 (2.906) Prec@1 75.78 (76.04) Prec@5 92.19 (91.35) + train[2018-10-21-08:49:32] Epoch: [174][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.154 (2.906) Prec@1 71.88 (76.02) Prec@5 92.19 (91.32) + train[2018-10-21-08:51:17] Epoch: [174][3200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.557 (2.907) Prec@1 82.03 (76.01) Prec@5 94.53 (91.33) + train[2018-10-21-08:53:02] Epoch: [174][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.743 (2.906) Prec@1 80.47 (76.01) Prec@5 91.41 (91.35) + train[2018-10-21-08:54:47] Epoch: [174][3600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.845 (2.906) Prec@1 78.12 (75.99) Prec@5 91.41 (91.36) + train[2018-10-21-08:56:33] Epoch: [174][3800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.856 (2.905) Prec@1 82.03 (76.01) Prec@5 91.41 (91.36) + train[2018-10-21-08:58:18] Epoch: [174][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.891 (2.906) Prec@1 77.34 (75.99) Prec@5 92.19 (91.35) + train[2018-10-21-09:00:04] Epoch: [174][4200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.911 (2.907) Prec@1 76.56 (75.98) Prec@5 92.19 (91.34) + train[2018-10-21-09:01:49] Epoch: [174][4400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.116 (2.907) Prec@1 75.78 (75.98) Prec@5 89.06 (91.34) + train[2018-10-21-09:03:34] Epoch: [174][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.866 (2.907) Prec@1 76.56 (75.96) Prec@5 92.97 (91.34) + train[2018-10-21-09:05:18] Epoch: [174][4800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.996 (2.907) Prec@1 80.47 (75.96) Prec@5 91.41 (91.34) + train[2018-10-21-09:07:03] Epoch: [174][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.830 (2.907) Prec@1 75.00 (75.97) Prec@5 93.75 (91.34) + train[2018-10-21-09:08:47] Epoch: [174][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.863 (2.908) Prec@1 75.78 (75.95) Prec@5 91.41 (91.33) + train[2018-10-21-09:10:32] Epoch: [174][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.957 (2.908) Prec@1 73.44 (75.95) Prec@5 91.41 (91.33) + train[2018-10-21-09:12:16] Epoch: [174][5600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.016 (2.908) Prec@1 75.78 (75.94) Prec@5 89.84 (91.33) + train[2018-10-21-09:14:01] Epoch: [174][5800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.600 (2.908) Prec@1 82.03 (75.94) Prec@5 94.53 (91.32) + train[2018-10-21-09:15:46] Epoch: [174][6000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.707 (2.908) Prec@1 79.69 (75.94) Prec@5 91.41 (91.31) + train[2018-10-21-09:17:31] Epoch: [174][6200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.842 (2.908) Prec@1 80.47 (75.93) Prec@5 92.19 (91.31) + train[2018-10-21-09:19:15] Epoch: [174][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.891 (2.909) Prec@1 77.34 (75.92) Prec@5 91.41 (91.30) + train[2018-10-21-09:21:00] Epoch: [174][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.005 (2.910) Prec@1 75.00 (75.92) Prec@5 90.62 (91.29) + train[2018-10-21-09:22:44] Epoch: [174][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.788 (2.910) Prec@1 78.91 (75.91) Prec@5 94.53 (91.29) + train[2018-10-21-09:24:28] Epoch: [174][7000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.094 (2.910) Prec@1 71.88 (75.92) Prec@5 91.41 (91.30) + train[2018-10-21-09:26:13] Epoch: [174][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.062 (2.909) Prec@1 71.88 (75.91) Prec@5 87.50 (91.30) + train[2018-10-21-09:27:57] Epoch: [174][7400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.781 (2.910) Prec@1 79.69 (75.90) Prec@5 90.62 (91.29) + train[2018-10-21-09:29:42] Epoch: [174][7600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.645 (2.910) Prec@1 80.47 (75.90) Prec@5 94.53 (91.29) + train[2018-10-21-09:31:27] Epoch: [174][7800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.130 (2.910) Prec@1 72.66 (75.91) Prec@5 89.06 (91.30) + train[2018-10-21-09:33:12] Epoch: [174][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.033 (2.910) Prec@1 74.22 (75.91) Prec@5 88.28 (91.30) + train[2018-10-21-09:34:57] Epoch: [174][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.953 (2.910) Prec@1 71.09 (75.90) Prec@5 89.84 (91.29) + train[2018-10-21-09:36:41] Epoch: [174][8400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.248 (2.911) Prec@1 71.09 (75.89) Prec@5 88.28 (91.29) + train[2018-10-21-09:38:26] Epoch: [174][8600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.068 (2.911) Prec@1 71.88 (75.88) Prec@5 90.62 (91.29) + train[2018-10-21-09:40:11] Epoch: [174][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.735 (2.911) Prec@1 77.34 (75.88) Prec@5 92.97 (91.29) + train[2018-10-21-09:41:55] Epoch: [174][9000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.980 (2.911) Prec@1 72.66 (75.88) Prec@5 90.62 (91.30) + train[2018-10-21-09:43:39] Epoch: [174][9200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.818 (2.911) Prec@1 76.56 (75.88) Prec@5 93.75 (91.29) + train[2018-10-21-09:45:24] Epoch: [174][9400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.170 (2.911) Prec@1 69.53 (75.88) Prec@5 87.50 (91.29) + train[2018-10-21-09:47:09] Epoch: [174][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.758 (2.911) Prec@1 81.25 (75.88) Prec@5 91.41 (91.29) + train[2018-10-21-09:48:53] Epoch: [174][9800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.914 (2.911) Prec@1 71.88 (75.89) Prec@5 90.62 (91.29) + train[2018-10-21-09:50:38] Epoch: [174][10000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.122 (2.911) Prec@1 67.97 (75.89) Prec@5 92.19 (91.29) + train[2018-10-21-09:50:42] Epoch: [174][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 3.357 (2.911) Prec@1 66.67 (75.89) Prec@5 93.33 (91.29) +[2018-10-21-09:50:42] **train** Prec@1 75.89 Prec@5 91.29 Error@1 24.11 Error@5 8.71 Loss:2.911 + test [2018-10-21-09:50:46] Epoch: [174][000/391] Time 4.05 (4.05) Data 3.91 (3.91) Loss 0.538 (0.538) Prec@1 93.75 (93.75) Prec@5 99.22 (99.22) + test [2018-10-21-09:51:13] Epoch: [174][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.167 (1.001) Prec@1 68.75 (77.30) Prec@5 92.19 (93.49) + test [2018-10-21-09:51:37] Epoch: [174][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.100 (1.166) Prec@1 48.75 (73.65) Prec@5 81.25 (91.35) +[2018-10-21-09:51:37] **test** Prec@1 73.65 Prec@5 91.35 Error@1 26.35 Error@5 8.65 Loss:1.166 +----> Best Accuracy : Acc@1=73.71, Acc@5=91.30, Error@1=26.29, Error@5=8.70 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-21-09:51:37] [Epoch=175/250] [Need: 110:33:36] LR=0.0005 ~ 0.0005, Batch=128 + train[2018-10-21-09:51:42] Epoch: [175][000/10010] Time 4.91 (4.91) Data 4.32 (4.32) Loss 3.054 (3.054) Prec@1 75.78 (75.78) Prec@5 90.62 (90.62) + train[2018-10-21-09:53:27] Epoch: [175][200/10010] Time 0.54 (0.55) Data 0.00 (0.02) Loss 3.008 (2.916) Prec@1 77.34 (76.19) Prec@5 85.94 (90.96) + train[2018-10-21-09:55:12] Epoch: [175][400/10010] Time 0.53 (0.54) Data 0.00 (0.01) Loss 2.670 (2.908) Prec@1 79.69 (76.02) Prec@5 94.53 (91.18) + train[2018-10-21-09:56:57] Epoch: [175][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 2.907 (2.903) Prec@1 78.12 (76.14) Prec@5 90.62 (91.26) + train[2018-10-21-09:58:42] Epoch: [175][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.310 (2.903) Prec@1 69.53 (76.17) Prec@5 86.72 (91.27) + train[2018-10-21-10:00:26] Epoch: [175][1000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.795 (2.901) Prec@1 77.34 (76.15) Prec@5 90.62 (91.35) + train[2018-10-21-10:02:11] Epoch: [175][1200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.987 (2.902) Prec@1 78.12 (76.11) Prec@5 91.41 (91.33) + train[2018-10-21-10:03:56] Epoch: [175][1400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.812 (2.902) Prec@1 76.56 (76.08) Prec@5 91.41 (91.35) + train[2018-10-21-10:05:41] Epoch: [175][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.957 (2.902) Prec@1 73.44 (76.09) Prec@5 90.62 (91.34) + train[2018-10-21-10:07:25] Epoch: [175][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.947 (2.901) Prec@1 73.44 (76.10) Prec@5 89.84 (91.35) + train[2018-10-21-10:09:10] Epoch: [175][2000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.775 (2.903) Prec@1 79.69 (76.04) Prec@5 91.41 (91.33) + train[2018-10-21-10:10:54] Epoch: [175][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.076 (2.902) Prec@1 74.22 (76.03) Prec@5 87.50 (91.36) + train[2018-10-21-10:12:39] Epoch: [175][2400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.957 (2.901) Prec@1 75.78 (76.07) Prec@5 88.28 (91.38) + train[2018-10-21-10:14:24] Epoch: [175][2600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.756 (2.901) Prec@1 78.91 (76.06) Prec@5 91.41 (91.36) + train[2018-10-21-10:16:09] Epoch: [175][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.628 (2.900) Prec@1 78.91 (76.06) Prec@5 95.31 (91.38) + train[2018-10-21-10:17:54] Epoch: [175][3000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.862 (2.901) Prec@1 76.56 (76.04) Prec@5 90.62 (91.36) + train[2018-10-21-10:19:39] Epoch: [175][3200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.990 (2.902) Prec@1 77.34 (76.04) Prec@5 89.84 (91.34) + train[2018-10-21-10:21:24] Epoch: [175][3400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.516 (2.901) Prec@1 85.94 (76.05) Prec@5 94.53 (91.35) + train[2018-10-21-10:23:08] Epoch: [175][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.814 (2.902) Prec@1 75.00 (76.04) Prec@5 90.62 (91.33) + train[2018-10-21-10:24:53] Epoch: [175][3800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.713 (2.903) Prec@1 80.47 (76.04) Prec@5 92.19 (91.33) + train[2018-10-21-10:26:37] Epoch: [175][4000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.960 (2.903) Prec@1 72.66 (76.04) Prec@5 87.50 (91.32) + train[2018-10-21-10:28:22] Epoch: [175][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.119 (2.903) Prec@1 71.09 (76.02) Prec@5 87.50 (91.32) + train[2018-10-21-10:30:06] Epoch: [175][4400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.123 (2.903) Prec@1 71.88 (76.03) Prec@5 89.06 (91.31) + train[2018-10-21-10:31:51] Epoch: [175][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.638 (2.904) Prec@1 80.47 (76.01) Prec@5 96.09 (91.30) + train[2018-10-21-10:33:36] Epoch: [175][4800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.769 (2.904) Prec@1 76.56 (76.02) Prec@5 94.53 (91.30) + train[2018-10-21-10:35:21] Epoch: [175][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.980 (2.903) Prec@1 74.22 (76.04) Prec@5 90.62 (91.30) + train[2018-10-21-10:37:06] Epoch: [175][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.042 (2.904) Prec@1 71.09 (76.04) Prec@5 91.41 (91.30) + train[2018-10-21-10:38:50] Epoch: [175][5400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.740 (2.904) Prec@1 80.47 (76.03) Prec@5 94.53 (91.31) + train[2018-10-21-10:40:34] Epoch: [175][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.123 (2.904) Prec@1 72.66 (76.03) Prec@5 89.84 (91.30) + train[2018-10-21-10:42:18] Epoch: [175][5800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.599 (2.904) Prec@1 82.03 (76.03) Prec@5 93.75 (91.31) + train[2018-10-21-10:44:03] Epoch: [175][6000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.090 (2.905) Prec@1 71.88 (76.02) Prec@5 87.50 (91.30) + train[2018-10-21-10:45:48] Epoch: [175][6200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.039 (2.905) Prec@1 77.34 (76.01) Prec@5 90.62 (91.31) + train[2018-10-21-10:47:32] Epoch: [175][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.970 (2.904) Prec@1 72.66 (76.02) Prec@5 91.41 (91.32) + train[2018-10-21-10:49:18] Epoch: [175][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.871 (2.904) Prec@1 75.78 (76.02) Prec@5 90.62 (91.32) + train[2018-10-21-10:51:02] Epoch: [175][6800/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 2.916 (2.905) Prec@1 75.00 (76.01) Prec@5 89.84 (91.32) + train[2018-10-21-10:52:47] Epoch: [175][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.802 (2.905) Prec@1 78.12 (76.02) Prec@5 92.19 (91.33) + train[2018-10-21-10:54:32] Epoch: [175][7200/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.184 (2.905) Prec@1 69.53 (76.00) Prec@5 88.28 (91.32) + train[2018-10-21-10:56:16] Epoch: [175][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.971 (2.905) Prec@1 74.22 (76.00) Prec@5 89.06 (91.31) + train[2018-10-21-10:58:01] Epoch: [175][7600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.469 (2.905) Prec@1 84.38 (76.01) Prec@5 95.31 (91.31) + train[2018-10-21-10:59:46] Epoch: [175][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.327 (2.905) Prec@1 69.53 (76.01) Prec@5 85.16 (91.32) + train[2018-10-21-11:01:30] Epoch: [175][8000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 2.585 (2.905) Prec@1 88.28 (76.01) Prec@5 94.53 (91.32) + train[2018-10-21-11:03:15] Epoch: [175][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.996 (2.905) Prec@1 74.22 (76.00) Prec@5 87.50 (91.31) + train[2018-10-21-11:05:00] Epoch: [175][8400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.686 (2.905) Prec@1 81.25 (76.00) Prec@5 91.41 (91.32) + train[2018-10-21-11:06:45] Epoch: [175][8600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.175 (2.905) Prec@1 68.75 (75.99) Prec@5 89.06 (91.32) + train[2018-10-21-11:08:29] Epoch: [175][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.735 (2.905) Prec@1 78.91 (75.98) Prec@5 92.19 (91.32) + train[2018-10-21-11:10:14] Epoch: [175][9000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.558 (2.905) Prec@1 82.81 (75.98) Prec@5 95.31 (91.32) + train[2018-10-21-11:11:58] Epoch: [175][9200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.859 (2.905) Prec@1 72.66 (75.98) Prec@5 91.41 (91.31) + train[2018-10-21-11:13:43] Epoch: [175][9400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 2.741 (2.906) Prec@1 75.00 (75.97) Prec@5 95.31 (91.31) + train[2018-10-21-11:15:28] Epoch: [175][9600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.739 (2.906) Prec@1 82.03 (75.97) Prec@5 93.75 (91.31) + train[2018-10-21-11:17:13] Epoch: [175][9800/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 2.777 (2.905) Prec@1 77.34 (75.98) Prec@5 92.19 (91.32) + train[2018-10-21-11:18:57] Epoch: [175][10000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.281 (2.906) Prec@1 71.09 (75.97) Prec@5 86.72 (91.31) + train[2018-10-21-11:19:01] Epoch: [175][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 3.965 (2.906) Prec@1 60.00 (75.97) Prec@5 80.00 (91.31) +[2018-10-21-11:19:01] **train** Prec@1 75.97 Prec@5 91.31 Error@1 24.03 Error@5 8.69 Loss:2.906 + test [2018-10-21-11:19:05] Epoch: [175][000/391] Time 3.78 (3.78) Data 3.65 (3.65) Loss 0.568 (0.568) Prec@1 91.41 (91.41) Prec@5 98.44 (98.44) + test [2018-10-21-11:19:31] Epoch: [175][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.184 (1.013) Prec@1 68.75 (77.35) Prec@5 92.97 (93.56) + test [2018-10-21-11:19:56] Epoch: [175][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.178 (1.179) Prec@1 45.00 (73.71) Prec@5 81.25 (91.40) +[2018-10-21-11:19:56] **test** Prec@1 73.71 Prec@5 91.40 Error@1 26.29 Error@5 8.60 Loss:1.179 +----> Best Accuracy : Acc@1=73.71, Acc@5=91.30, Error@1=26.29, Error@5=8.70 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-21-11:19:57] [Epoch=176/250] [Need: 108:55:47] LR=0.0005 ~ 0.0005, Batch=128 + train[2018-10-21-11:20:01] Epoch: [176][000/10010] Time 4.06 (4.06) Data 3.49 (3.49) Loss 2.809 (2.809) Prec@1 82.03 (82.03) Prec@5 92.97 (92.97) + train[2018-10-21-11:21:46] Epoch: [176][200/10010] Time 0.56 (0.54) Data 0.00 (0.02) Loss 3.113 (2.898) Prec@1 72.66 (76.16) Prec@5 85.94 (91.36) + train[2018-10-21-11:23:31] Epoch: [176][400/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.717 (2.889) Prec@1 84.38 (76.17) Prec@5 93.75 (91.61) + train[2018-10-21-11:25:16] Epoch: [176][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 2.767 (2.886) Prec@1 78.91 (76.18) Prec@5 92.97 (91.65) + train[2018-10-21-11:27:00] Epoch: [176][800/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.044 (2.892) Prec@1 71.88 (76.09) Prec@5 89.06 (91.56) + train[2018-10-21-11:28:45] Epoch: [176][1000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.354 (2.894) Prec@1 75.78 (76.11) Prec@5 84.38 (91.54) + train[2018-10-21-11:30:30] Epoch: [176][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.793 (2.895) Prec@1 75.78 (76.09) Prec@5 91.41 (91.50) + train[2018-10-21-11:32:15] Epoch: [176][1400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.564 (2.896) Prec@1 78.12 (76.07) Prec@5 97.66 (91.49) + train[2018-10-21-11:33:59] Epoch: [176][1600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.714 (2.897) Prec@1 79.69 (76.04) Prec@5 94.53 (91.49) + train[2018-10-21-11:35:44] Epoch: [176][1800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.588 (2.898) Prec@1 82.81 (75.98) Prec@5 96.09 (91.50) + train[2018-10-21-11:37:29] Epoch: [176][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.733 (2.899) Prec@1 78.12 (75.97) Prec@5 93.75 (91.48) + train[2018-10-21-11:39:14] Epoch: [176][2200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.902 (2.901) Prec@1 76.56 (75.94) Prec@5 92.19 (91.46) + train[2018-10-21-11:40:59] Epoch: [176][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.650 (2.902) Prec@1 82.03 (75.95) Prec@5 92.19 (91.41) + train[2018-10-21-11:42:44] Epoch: [176][2600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.674 (2.904) Prec@1 80.47 (75.94) Prec@5 93.75 (91.40) + train[2018-10-21-11:44:29] Epoch: [176][2800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.936 (2.905) Prec@1 75.00 (75.90) Prec@5 90.62 (91.40) + train[2018-10-21-11:46:14] Epoch: [176][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.793 (2.904) Prec@1 80.47 (75.91) Prec@5 93.75 (91.39) + train[2018-10-21-11:48:01] Epoch: [176][3200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.070 (2.904) Prec@1 74.22 (75.91) Prec@5 89.84 (91.40) + train[2018-10-21-11:49:48] Epoch: [176][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.697 (2.904) Prec@1 78.91 (75.91) Prec@5 95.31 (91.39) + train[2018-10-21-11:51:34] Epoch: [176][3600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.899 (2.904) Prec@1 71.88 (75.92) Prec@5 92.19 (91.39) + train[2018-10-21-11:53:20] Epoch: [176][3800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.232 (2.903) Prec@1 65.62 (75.93) Prec@5 88.28 (91.40) + train[2018-10-21-11:55:04] Epoch: [176][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.520 (2.903) Prec@1 82.03 (75.94) Prec@5 95.31 (91.40) + train[2018-10-21-11:56:49] Epoch: [176][4200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.009 (2.903) Prec@1 81.25 (75.97) Prec@5 89.84 (91.40) + train[2018-10-21-11:58:34] Epoch: [176][4400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.012 (2.903) Prec@1 70.31 (75.96) Prec@5 91.41 (91.39) + train[2018-10-21-12:00:19] Epoch: [176][4600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.054 (2.903) Prec@1 73.44 (75.95) Prec@5 91.41 (91.40) + train[2018-10-21-12:02:05] Epoch: [176][4800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.107 (2.902) Prec@1 69.53 (75.99) Prec@5 87.50 (91.41) + train[2018-10-21-12:03:50] Epoch: [176][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.759 (2.902) Prec@1 79.69 (75.99) Prec@5 91.41 (91.42) + train[2018-10-21-12:05:35] Epoch: [176][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.722 (2.902) Prec@1 79.69 (75.99) Prec@5 93.75 (91.41) + train[2018-10-21-12:07:21] Epoch: [176][5400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.906 (2.903) Prec@1 77.34 (75.97) Prec@5 88.28 (91.41) + train[2018-10-21-12:09:06] Epoch: [176][5600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.697 (2.903) Prec@1 82.03 (75.97) Prec@5 92.97 (91.41) + train[2018-10-21-12:10:51] Epoch: [176][5800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.833 (2.904) Prec@1 77.34 (75.98) Prec@5 92.19 (91.41) + train[2018-10-21-12:12:36] Epoch: [176][6000/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.923 (2.904) Prec@1 75.78 (75.98) Prec@5 92.97 (91.40) + train[2018-10-21-12:14:21] Epoch: [176][6200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.904 (2.906) Prec@1 79.69 (75.95) Prec@5 89.06 (91.38) + train[2018-10-21-12:16:07] Epoch: [176][6400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.999 (2.905) Prec@1 71.09 (75.96) Prec@5 92.97 (91.38) + train[2018-10-21-12:17:52] Epoch: [176][6600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.817 (2.905) Prec@1 80.47 (75.95) Prec@5 90.62 (91.37) + train[2018-10-21-12:19:37] Epoch: [176][6800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.055 (2.906) Prec@1 73.44 (75.96) Prec@5 89.84 (91.37) + train[2018-10-21-12:21:24] Epoch: [176][7000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.071 (2.905) Prec@1 73.44 (75.97) Prec@5 88.28 (91.37) + train[2018-10-21-12:23:09] Epoch: [176][7200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.864 (2.905) Prec@1 77.34 (75.97) Prec@5 90.62 (91.36) + train[2018-10-21-12:24:54] Epoch: [176][7400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.854 (2.906) Prec@1 75.78 (75.96) Prec@5 92.19 (91.36) + train[2018-10-21-12:26:39] Epoch: [176][7600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.963 (2.905) Prec@1 71.88 (75.96) Prec@5 92.19 (91.36) + train[2018-10-21-12:28:23] Epoch: [176][7800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.798 (2.906) Prec@1 78.12 (75.95) Prec@5 93.75 (91.36) + train[2018-10-21-12:30:09] Epoch: [176][8000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.775 (2.905) Prec@1 76.56 (75.95) Prec@5 92.97 (91.36) + train[2018-10-21-12:31:53] Epoch: [176][8200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.722 (2.906) Prec@1 78.91 (75.95) Prec@5 96.09 (91.36) + train[2018-10-21-12:33:39] Epoch: [176][8400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.908 (2.905) Prec@1 77.34 (75.96) Prec@5 92.19 (91.36) + train[2018-10-21-12:35:23] Epoch: [176][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.805 (2.905) Prec@1 76.56 (75.95) Prec@5 92.97 (91.36) + train[2018-10-21-12:37:08] Epoch: [176][8800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.853 (2.905) Prec@1 75.78 (75.96) Prec@5 90.62 (91.37) + train[2018-10-21-12:38:53] Epoch: [176][9000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.904 (2.905) Prec@1 73.44 (75.96) Prec@5 92.19 (91.37) + train[2018-10-21-12:40:38] Epoch: [176][9200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.913 (2.906) Prec@1 79.69 (75.94) Prec@5 93.75 (91.36) + train[2018-10-21-12:42:23] Epoch: [176][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.962 (2.906) Prec@1 75.00 (75.94) Prec@5 92.19 (91.35) + train[2018-10-21-12:44:07] Epoch: [176][9600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.280 (2.906) Prec@1 72.66 (75.94) Prec@5 85.94 (91.35) + train[2018-10-21-12:45:53] Epoch: [176][9800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.575 (2.906) Prec@1 82.81 (75.95) Prec@5 93.75 (91.35) + train[2018-10-21-12:47:38] Epoch: [176][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.829 (2.906) Prec@1 76.56 (75.95) Prec@5 92.19 (91.35) + train[2018-10-21-12:47:42] Epoch: [176][10009/10010] Time 0.17 (0.53) Data 0.00 (0.00) Loss 4.533 (2.906) Prec@1 53.33 (75.95) Prec@5 66.67 (91.35) +[2018-10-21-12:47:42] **train** Prec@1 75.95 Prec@5 91.35 Error@1 24.05 Error@5 8.65 Loss:2.906 + test [2018-10-21-12:47:46] Epoch: [176][000/391] Time 3.93 (3.93) Data 3.79 (3.79) Loss 0.515 (0.515) Prec@1 92.19 (92.19) Prec@5 99.22 (99.22) + test [2018-10-21-12:48:12] Epoch: [176][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.120 (0.992) Prec@1 69.53 (77.36) Prec@5 92.97 (93.69) + test [2018-10-21-12:48:37] Epoch: [176][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.180 (1.163) Prec@1 47.50 (73.70) Prec@5 80.00 (91.35) +[2018-10-21-12:48:37] **test** Prec@1 73.70 Prec@5 91.35 Error@1 26.30 Error@5 8.65 Loss:1.163 +----> Best Accuracy : Acc@1=73.71, Acc@5=91.30, Error@1=26.29, Error@5=8.70 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-21-12:48:37] [Epoch=177/250] [Need: 107:53:00] LR=0.0005 ~ 0.0005, Batch=128 + train[2018-10-21-12:48:42] Epoch: [177][000/10010] Time 4.69 (4.69) Data 4.09 (4.09) Loss 2.575 (2.575) Prec@1 83.59 (83.59) Prec@5 96.09 (96.09) + train[2018-10-21-12:50:26] Epoch: [177][200/10010] Time 0.52 (0.54) Data 0.00 (0.02) Loss 2.928 (2.899) Prec@1 74.22 (76.26) Prec@5 88.28 (91.27) + train[2018-10-21-12:52:11] Epoch: [177][400/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.047 (2.901) Prec@1 70.31 (76.13) Prec@5 90.62 (91.30) + train[2018-10-21-12:53:56] Epoch: [177][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 3.036 (2.897) Prec@1 73.44 (76.03) Prec@5 90.62 (91.38) + train[2018-10-21-12:55:40] Epoch: [177][800/10010] Time 0.57 (0.53) Data 0.00 (0.01) Loss 2.768 (2.898) Prec@1 79.69 (76.05) Prec@5 94.53 (91.31) + train[2018-10-21-12:57:25] Epoch: [177][1000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.020 (2.897) Prec@1 74.22 (76.05) Prec@5 85.16 (91.34) + train[2018-10-21-12:59:09] Epoch: [177][1200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.651 (2.893) Prec@1 79.69 (76.13) Prec@5 92.97 (91.40) + train[2018-10-21-13:00:53] Epoch: [177][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.725 (2.895) Prec@1 81.25 (76.07) Prec@5 91.41 (91.39) + train[2018-10-21-13:02:38] Epoch: [177][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.947 (2.895) Prec@1 72.66 (76.10) Prec@5 89.84 (91.40) + train[2018-10-21-13:04:23] Epoch: [177][1800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.184 (2.897) Prec@1 73.44 (76.05) Prec@5 89.06 (91.37) + train[2018-10-21-13:06:07] Epoch: [177][2000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.848 (2.896) Prec@1 74.22 (76.11) Prec@5 93.75 (91.38) + train[2018-10-21-13:07:52] Epoch: [177][2200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.895 (2.897) Prec@1 75.78 (76.10) Prec@5 89.84 (91.38) + train[2018-10-21-13:09:37] Epoch: [177][2400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.762 (2.896) Prec@1 77.34 (76.13) Prec@5 93.75 (91.41) + train[2018-10-21-13:11:22] Epoch: [177][2600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.803 (2.899) Prec@1 76.56 (76.08) Prec@5 92.97 (91.37) + train[2018-10-21-13:13:06] Epoch: [177][2800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.755 (2.900) Prec@1 79.69 (76.09) Prec@5 91.41 (91.37) + train[2018-10-21-13:14:51] Epoch: [177][3000/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 2.756 (2.900) Prec@1 79.69 (76.10) Prec@5 92.97 (91.37) + train[2018-10-21-13:16:36] Epoch: [177][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.734 (2.900) Prec@1 80.47 (76.08) Prec@5 92.97 (91.35) + train[2018-10-21-13:18:20] Epoch: [177][3400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.780 (2.902) Prec@1 81.25 (76.06) Prec@5 92.19 (91.34) + train[2018-10-21-13:20:04] Epoch: [177][3600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.037 (2.903) Prec@1 77.34 (76.03) Prec@5 89.06 (91.33) + train[2018-10-21-13:21:49] Epoch: [177][3800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.010 (2.902) Prec@1 76.56 (76.05) Prec@5 92.19 (91.35) + train[2018-10-21-13:23:33] Epoch: [177][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.906 (2.902) Prec@1 74.22 (76.05) Prec@5 90.62 (91.35) + train[2018-10-21-13:25:19] Epoch: [177][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.648 (2.902) Prec@1 79.69 (76.04) Prec@5 93.75 (91.35) + train[2018-10-21-13:27:03] Epoch: [177][4400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.179 (2.902) Prec@1 76.56 (76.04) Prec@5 89.06 (91.35) + train[2018-10-21-13:28:47] Epoch: [177][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.874 (2.902) Prec@1 73.44 (76.04) Prec@5 93.75 (91.35) + train[2018-10-21-13:30:32] Epoch: [177][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.833 (2.903) Prec@1 78.91 (76.01) Prec@5 90.62 (91.34) + train[2018-10-21-13:32:17] Epoch: [177][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.827 (2.903) Prec@1 75.78 (76.01) Prec@5 91.41 (91.34) + train[2018-10-21-13:34:02] Epoch: [177][5200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.762 (2.903) Prec@1 74.22 (76.01) Prec@5 92.97 (91.34) + train[2018-10-21-13:35:47] Epoch: [177][5400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.802 (2.903) Prec@1 79.69 (76.01) Prec@5 91.41 (91.34) + train[2018-10-21-13:37:32] Epoch: [177][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.947 (2.903) Prec@1 75.00 (76.01) Prec@5 90.62 (91.34) + train[2018-10-21-13:39:17] Epoch: [177][5800/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 2.836 (2.903) Prec@1 78.91 (76.01) Prec@5 90.62 (91.34) + train[2018-10-21-13:41:02] Epoch: [177][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.030 (2.903) Prec@1 77.34 (76.00) Prec@5 90.62 (91.34) + train[2018-10-21-13:42:47] Epoch: [177][6200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.076 (2.903) Prec@1 71.88 (76.00) Prec@5 89.84 (91.34) + train[2018-10-21-13:44:32] Epoch: [177][6400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.730 (2.904) Prec@1 80.47 (76.00) Prec@5 93.75 (91.33) + train[2018-10-21-13:46:17] Epoch: [177][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.183 (2.904) Prec@1 78.12 (76.00) Prec@5 87.50 (91.33) + train[2018-10-21-13:48:01] Epoch: [177][6800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.868 (2.904) Prec@1 75.78 (76.01) Prec@5 91.41 (91.34) + train[2018-10-21-13:49:45] Epoch: [177][7000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.038 (2.904) Prec@1 73.44 (76.00) Prec@5 86.72 (91.34) + train[2018-10-21-13:51:29] Epoch: [177][7200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.167 (2.904) Prec@1 72.66 (76.00) Prec@5 89.06 (91.34) + train[2018-10-21-13:53:13] Epoch: [177][7400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.824 (2.904) Prec@1 75.78 (76.00) Prec@5 92.97 (91.34) + train[2018-10-21-13:54:58] Epoch: [177][7600/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 2.802 (2.905) Prec@1 77.34 (76.00) Prec@5 93.75 (91.34) + train[2018-10-21-13:56:42] Epoch: [177][7800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.079 (2.905) Prec@1 72.66 (75.99) Prec@5 89.06 (91.33) + train[2018-10-21-13:58:27] Epoch: [177][8000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.997 (2.905) Prec@1 69.53 (76.00) Prec@5 88.28 (91.34) + train[2018-10-21-14:00:11] Epoch: [177][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.929 (2.904) Prec@1 76.56 (76.00) Prec@5 89.06 (91.34) + train[2018-10-21-14:01:57] Epoch: [177][8400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.000 (2.905) Prec@1 68.75 (76.00) Prec@5 90.62 (91.33) + train[2018-10-21-14:03:42] Epoch: [177][8600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.825 (2.905) Prec@1 79.69 (75.99) Prec@5 91.41 (91.33) + train[2018-10-21-14:05:26] Epoch: [177][8800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.063 (2.905) Prec@1 70.31 (75.99) Prec@5 93.75 (91.33) + train[2018-10-21-14:07:10] Epoch: [177][9000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.846 (2.906) Prec@1 78.91 (75.99) Prec@5 92.97 (91.32) + train[2018-10-21-14:08:55] Epoch: [177][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.313 (2.906) Prec@1 71.88 (75.98) Prec@5 84.38 (91.33) + train[2018-10-21-14:10:41] Epoch: [177][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.068 (2.906) Prec@1 75.00 (75.99) Prec@5 89.84 (91.33) + train[2018-10-21-14:12:26] Epoch: [177][9600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.200 (2.906) Prec@1 74.22 (75.98) Prec@5 84.38 (91.33) + train[2018-10-21-14:14:11] Epoch: [177][9800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.930 (2.906) Prec@1 75.00 (75.99) Prec@5 89.84 (91.33) + train[2018-10-21-14:15:55] Epoch: [177][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.773 (2.905) Prec@1 78.12 (75.99) Prec@5 95.31 (91.33) + train[2018-10-21-14:16:00] Epoch: [177][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 3.825 (2.905) Prec@1 66.67 (75.99) Prec@5 93.33 (91.33) +[2018-10-21-14:16:00] **train** Prec@1 75.99 Prec@5 91.33 Error@1 24.01 Error@5 8.67 Loss:2.905 + test [2018-10-21-14:16:03] Epoch: [177][000/391] Time 3.69 (3.69) Data 3.55 (3.55) Loss 0.570 (0.570) Prec@1 91.41 (91.41) Prec@5 99.22 (99.22) + test [2018-10-21-14:16:30] Epoch: [177][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.241 (1.006) Prec@1 65.62 (77.35) Prec@5 92.19 (93.66) + test [2018-10-21-14:16:55] Epoch: [177][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.125 (1.177) Prec@1 47.50 (73.64) Prec@5 80.00 (91.38) +[2018-10-21-14:16:55] **test** Prec@1 73.64 Prec@5 91.38 Error@1 26.36 Error@5 8.62 Loss:1.177 +----> Best Accuracy : Acc@1=73.71, Acc@5=91.30, Error@1=26.29, Error@5=8.70 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-21-14:16:55] [Epoch=178/250] [Need: 105:57:39] LR=0.0004 ~ 0.0004, Batch=128 + train[2018-10-21-14:17:00] Epoch: [178][000/10010] Time 5.13 (5.13) Data 4.53 (4.53) Loss 2.746 (2.746) Prec@1 77.34 (77.34) Prec@5 92.97 (92.97) + train[2018-10-21-14:18:44] Epoch: [178][200/10010] Time 0.51 (0.54) Data 0.00 (0.02) Loss 2.907 (2.886) Prec@1 76.56 (76.24) Prec@5 92.19 (91.55) + train[2018-10-21-14:20:29] Epoch: [178][400/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.047 (2.894) Prec@1 70.31 (76.13) Prec@5 88.28 (91.49) + train[2018-10-21-14:22:14] Epoch: [178][600/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.635 (2.892) Prec@1 79.69 (76.17) Prec@5 96.09 (91.43) + train[2018-10-21-14:23:59] Epoch: [178][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.856 (2.893) Prec@1 80.47 (76.15) Prec@5 92.97 (91.47) + train[2018-10-21-14:25:43] Epoch: [178][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.457 (2.893) Prec@1 83.59 (76.23) Prec@5 96.88 (91.44) + train[2018-10-21-14:27:28] Epoch: [178][1200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.418 (2.890) Prec@1 85.94 (76.29) Prec@5 96.09 (91.46) + train[2018-10-21-14:29:13] Epoch: [178][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.979 (2.893) Prec@1 73.44 (76.21) Prec@5 91.41 (91.44) + train[2018-10-21-14:30:58] Epoch: [178][1600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.940 (2.893) Prec@1 80.47 (76.20) Prec@5 92.97 (91.45) + train[2018-10-21-14:32:43] Epoch: [178][1800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.883 (2.894) Prec@1 77.34 (76.15) Prec@5 92.19 (91.43) + train[2018-10-21-14:34:28] Epoch: [178][2000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.644 (2.893) Prec@1 76.56 (76.19) Prec@5 96.09 (91.44) + train[2018-10-21-14:36:13] Epoch: [178][2200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.629 (2.895) Prec@1 75.78 (76.16) Prec@5 94.53 (91.41) + train[2018-10-21-14:37:59] Epoch: [178][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.625 (2.894) Prec@1 82.03 (76.17) Prec@5 93.75 (91.40) + train[2018-10-21-14:39:43] Epoch: [178][2600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.798 (2.894) Prec@1 79.69 (76.18) Prec@5 90.62 (91.39) + train[2018-10-21-14:41:28] Epoch: [178][2800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.167 (2.896) Prec@1 68.75 (76.14) Prec@5 87.50 (91.39) + train[2018-10-21-14:43:13] Epoch: [178][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.253 (2.895) Prec@1 71.88 (76.15) Prec@5 87.50 (91.41) + train[2018-10-21-14:44:57] Epoch: [178][3200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.916 (2.895) Prec@1 78.91 (76.13) Prec@5 91.41 (91.40) + train[2018-10-21-14:46:42] Epoch: [178][3400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.839 (2.896) Prec@1 75.78 (76.10) Prec@5 92.97 (91.40) + train[2018-10-21-14:48:27] Epoch: [178][3600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.909 (2.896) Prec@1 73.44 (76.11) Prec@5 89.06 (91.40) + train[2018-10-21-14:50:12] Epoch: [178][3800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.875 (2.895) Prec@1 76.56 (76.12) Prec@5 92.19 (91.41) + train[2018-10-21-14:51:57] Epoch: [178][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.776 (2.896) Prec@1 82.81 (76.12) Prec@5 91.41 (91.40) + train[2018-10-21-14:53:42] Epoch: [178][4200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.796 (2.896) Prec@1 77.34 (76.13) Prec@5 90.62 (91.39) + train[2018-10-21-14:55:27] Epoch: [178][4400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.991 (2.897) Prec@1 76.56 (76.12) Prec@5 89.84 (91.39) + train[2018-10-21-14:57:12] Epoch: [178][4600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.820 (2.897) Prec@1 77.34 (76.11) Prec@5 93.75 (91.39) + train[2018-10-21-14:58:56] Epoch: [178][4800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.990 (2.897) Prec@1 75.00 (76.11) Prec@5 89.06 (91.40) + train[2018-10-21-15:00:41] Epoch: [178][5000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.627 (2.898) Prec@1 78.91 (76.10) Prec@5 96.09 (91.38) + train[2018-10-21-15:02:26] Epoch: [178][5200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.970 (2.898) Prec@1 76.56 (76.10) Prec@5 90.62 (91.39) + train[2018-10-21-15:04:12] Epoch: [178][5400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.292 (2.898) Prec@1 74.22 (76.10) Prec@5 89.06 (91.38) + train[2018-10-21-15:05:56] Epoch: [178][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.941 (2.898) Prec@1 75.78 (76.10) Prec@5 90.62 (91.39) + train[2018-10-21-15:07:41] Epoch: [178][5800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.784 (2.898) Prec@1 80.47 (76.10) Prec@5 89.84 (91.39) + train[2018-10-21-15:09:26] Epoch: [178][6000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.867 (2.898) Prec@1 74.22 (76.09) Prec@5 90.62 (91.39) + train[2018-10-21-15:11:11] Epoch: [178][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.981 (2.899) Prec@1 78.12 (76.08) Prec@5 88.28 (91.39) + train[2018-10-21-15:12:55] Epoch: [178][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.905 (2.899) Prec@1 76.56 (76.08) Prec@5 92.19 (91.38) + train[2018-10-21-15:14:41] Epoch: [178][6600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.735 (2.900) Prec@1 82.03 (76.05) Prec@5 91.41 (91.37) + train[2018-10-21-15:16:25] Epoch: [178][6800/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 2.996 (2.901) Prec@1 75.00 (76.04) Prec@5 92.97 (91.37) + train[2018-10-21-15:18:10] Epoch: [178][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.777 (2.901) Prec@1 78.91 (76.04) Prec@5 95.31 (91.37) + train[2018-10-21-15:19:55] Epoch: [178][7200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.785 (2.901) Prec@1 77.34 (76.04) Prec@5 92.97 (91.36) + train[2018-10-21-15:21:40] Epoch: [178][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.937 (2.901) Prec@1 80.47 (76.04) Prec@5 91.41 (91.36) + train[2018-10-21-15:23:26] Epoch: [178][7600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.803 (2.901) Prec@1 80.47 (76.04) Prec@5 90.62 (91.36) + train[2018-10-21-15:25:11] Epoch: [178][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.872 (2.901) Prec@1 73.44 (76.04) Prec@5 91.41 (91.36) + train[2018-10-21-15:26:55] Epoch: [178][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.615 (2.902) Prec@1 80.47 (76.03) Prec@5 94.53 (91.36) + train[2018-10-21-15:28:40] Epoch: [178][8200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.759 (2.902) Prec@1 78.91 (76.03) Prec@5 93.75 (91.36) + train[2018-10-21-15:30:24] Epoch: [178][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.842 (2.902) Prec@1 73.44 (76.02) Prec@5 92.19 (91.35) + train[2018-10-21-15:32:09] Epoch: [178][8600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.842 (2.902) Prec@1 76.56 (76.01) Prec@5 94.53 (91.35) + train[2018-10-21-15:33:53] Epoch: [178][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.966 (2.902) Prec@1 73.44 (76.02) Prec@5 91.41 (91.35) + train[2018-10-21-15:35:38] Epoch: [178][9000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.918 (2.902) Prec@1 74.22 (76.02) Prec@5 89.84 (91.35) + train[2018-10-21-15:37:23] Epoch: [178][9200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.651 (2.903) Prec@1 82.03 (76.01) Prec@5 94.53 (91.34) + train[2018-10-21-15:39:08] Epoch: [178][9400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.734 (2.903) Prec@1 81.25 (76.01) Prec@5 93.75 (91.34) + train[2018-10-21-15:40:53] Epoch: [178][9600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.842 (2.903) Prec@1 78.91 (76.02) Prec@5 90.62 (91.34) + train[2018-10-21-15:42:38] Epoch: [178][9800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.047 (2.903) Prec@1 72.66 (76.02) Prec@5 88.28 (91.34) + train[2018-10-21-15:44:23] Epoch: [178][10000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.075 (2.903) Prec@1 71.88 (76.01) Prec@5 89.84 (91.34) + train[2018-10-21-15:44:28] Epoch: [178][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 3.465 (2.903) Prec@1 66.67 (76.01) Prec@5 80.00 (91.34) +[2018-10-21-15:44:28] **train** Prec@1 76.01 Prec@5 91.34 Error@1 23.99 Error@5 8.66 Loss:2.903 + test [2018-10-21-15:44:32] Epoch: [178][000/391] Time 3.89 (3.89) Data 3.76 (3.76) Loss 0.569 (0.569) Prec@1 92.19 (92.19) Prec@5 99.22 (99.22) + test [2018-10-21-15:44:58] Epoch: [178][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.198 (0.997) Prec@1 66.41 (77.25) Prec@5 91.41 (93.69) + test [2018-10-21-15:45:23] Epoch: [178][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.057 (1.167) Prec@1 48.75 (73.65) Prec@5 85.00 (91.44) +[2018-10-21-15:45:23] **test** Prec@1 73.65 Prec@5 91.44 Error@1 26.35 Error@5 8.56 Loss:1.167 +----> Best Accuracy : Acc@1=73.71, Acc@5=91.30, Error@1=26.29, Error@5=8.70 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-21-15:45:23] [Epoch=179/250] [Need: 104:41:19] LR=0.0004 ~ 0.0004, Batch=128 + train[2018-10-21-15:45:28] Epoch: [179][000/10010] Time 4.93 (4.93) Data 4.34 (4.34) Loss 2.918 (2.918) Prec@1 78.91 (78.91) Prec@5 92.19 (92.19) + train[2018-10-21-15:47:12] Epoch: [179][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 2.795 (2.900) Prec@1 76.56 (76.27) Prec@5 92.97 (91.43) + train[2018-10-21-15:48:57] Epoch: [179][400/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 2.585 (2.906) Prec@1 81.25 (75.93) Prec@5 95.31 (91.43) + train[2018-10-21-15:50:41] Epoch: [179][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 2.777 (2.907) Prec@1 75.78 (75.93) Prec@5 93.75 (91.36) + train[2018-10-21-15:52:26] Epoch: [179][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.865 (2.907) Prec@1 80.47 (76.00) Prec@5 90.62 (91.30) + train[2018-10-21-15:54:11] Epoch: [179][1000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.328 (2.905) Prec@1 65.62 (76.02) Prec@5 90.62 (91.33) + train[2018-10-21-15:55:56] Epoch: [179][1200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.042 (2.906) Prec@1 74.22 (76.02) Prec@5 89.06 (91.29) + train[2018-10-21-15:57:40] Epoch: [179][1400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.075 (2.904) Prec@1 71.09 (76.05) Prec@5 89.06 (91.34) + train[2018-10-21-15:59:25] Epoch: [179][1600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.690 (2.903) Prec@1 80.47 (76.03) Prec@5 92.97 (91.34) + train[2018-10-21-16:01:09] Epoch: [179][1800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.837 (2.900) Prec@1 75.00 (76.05) Prec@5 92.97 (91.37) + train[2018-10-21-16:02:54] Epoch: [179][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.091 (2.901) Prec@1 71.09 (76.06) Prec@5 89.06 (91.34) + train[2018-10-21-16:04:39] Epoch: [179][2200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.065 (2.901) Prec@1 71.88 (76.07) Prec@5 89.06 (91.32) + train[2018-10-21-16:06:23] Epoch: [179][2400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.291 (2.901) Prec@1 66.41 (76.03) Prec@5 87.50 (91.33) + train[2018-10-21-16:08:09] Epoch: [179][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.908 (2.900) Prec@1 71.88 (76.05) Prec@5 92.19 (91.36) + train[2018-10-21-16:09:54] Epoch: [179][2800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.019 (2.901) Prec@1 70.31 (76.03) Prec@5 89.84 (91.35) + train[2018-10-21-16:11:38] Epoch: [179][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.803 (2.902) Prec@1 74.22 (76.02) Prec@5 92.97 (91.35) + train[2018-10-21-16:13:23] Epoch: [179][3200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.896 (2.903) Prec@1 77.34 (76.00) Prec@5 87.50 (91.34) + train[2018-10-21-16:15:08] Epoch: [179][3400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.822 (2.901) Prec@1 77.34 (76.04) Prec@5 92.19 (91.36) + train[2018-10-21-16:16:53] Epoch: [179][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.790 (2.901) Prec@1 73.44 (76.05) Prec@5 94.53 (91.37) + train[2018-10-21-16:18:37] Epoch: [179][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.914 (2.900) Prec@1 75.00 (76.05) Prec@5 92.19 (91.37) + train[2018-10-21-16:20:21] Epoch: [179][4000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.424 (2.900) Prec@1 70.31 (76.08) Prec@5 82.81 (91.38) + train[2018-10-21-16:22:05] Epoch: [179][4200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.076 (2.900) Prec@1 74.22 (76.08) Prec@5 89.06 (91.38) + train[2018-10-21-16:23:50] Epoch: [179][4400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.836 (2.901) Prec@1 78.91 (76.05) Prec@5 92.97 (91.37) + train[2018-10-21-16:25:34] Epoch: [179][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.711 (2.901) Prec@1 75.00 (76.04) Prec@5 94.53 (91.37) + train[2018-10-21-16:27:20] Epoch: [179][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.585 (2.901) Prec@1 79.69 (76.04) Prec@5 96.88 (91.37) + train[2018-10-21-16:29:05] Epoch: [179][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.112 (2.900) Prec@1 69.53 (76.05) Prec@5 86.72 (91.37) + train[2018-10-21-16:30:49] Epoch: [179][5200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.759 (2.900) Prec@1 80.47 (76.05) Prec@5 91.41 (91.36) + train[2018-10-21-16:32:34] Epoch: [179][5400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 2.770 (2.900) Prec@1 79.69 (76.04) Prec@5 89.84 (91.36) + train[2018-10-21-16:34:18] Epoch: [179][5600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.995 (2.900) Prec@1 77.34 (76.04) Prec@5 89.06 (91.37) + train[2018-10-21-16:36:03] Epoch: [179][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.937 (2.899) Prec@1 78.91 (76.04) Prec@5 91.41 (91.37) + train[2018-10-21-16:37:48] Epoch: [179][6000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.027 (2.899) Prec@1 74.22 (76.04) Prec@5 89.06 (91.37) + train[2018-10-21-16:39:33] Epoch: [179][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.622 (2.900) Prec@1 82.03 (76.03) Prec@5 92.97 (91.36) + train[2018-10-21-16:41:18] Epoch: [179][6400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.977 (2.900) Prec@1 70.31 (76.02) Prec@5 90.62 (91.36) + train[2018-10-21-16:43:03] Epoch: [179][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.860 (2.900) Prec@1 78.91 (76.03) Prec@5 91.41 (91.36) + train[2018-10-21-16:44:48] Epoch: [179][6800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 3.278 (2.900) Prec@1 65.62 (76.03) Prec@5 88.28 (91.36) + train[2018-10-21-16:46:33] Epoch: [179][7000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.690 (2.900) Prec@1 82.03 (76.04) Prec@5 92.97 (91.36) + train[2018-10-21-16:48:17] Epoch: [179][7200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.583 (2.899) Prec@1 77.34 (76.05) Prec@5 96.88 (91.36) + train[2018-10-21-16:50:02] Epoch: [179][7400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.305 (2.899) Prec@1 71.09 (76.05) Prec@5 87.50 (91.37) + train[2018-10-21-16:51:47] Epoch: [179][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.884 (2.899) Prec@1 76.56 (76.05) Prec@5 91.41 (91.36) + train[2018-10-21-16:53:32] Epoch: [179][7800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.831 (2.899) Prec@1 76.56 (76.04) Prec@5 92.97 (91.36) + train[2018-10-21-16:55:16] Epoch: [179][8000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.869 (2.899) Prec@1 74.22 (76.04) Prec@5 92.19 (91.36) + train[2018-10-21-16:57:01] Epoch: [179][8200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.868 (2.899) Prec@1 71.88 (76.04) Prec@5 91.41 (91.36) + train[2018-10-21-16:58:45] Epoch: [179][8400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.901 (2.900) Prec@1 74.22 (76.04) Prec@5 91.41 (91.36) + train[2018-10-21-17:00:30] Epoch: [179][8600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.960 (2.900) Prec@1 70.31 (76.04) Prec@5 92.19 (91.36) + train[2018-10-21-17:02:15] Epoch: [179][8800/10010] Time 0.49 (0.52) Data 0.00 (0.00) Loss 2.715 (2.899) Prec@1 81.25 (76.05) Prec@5 92.97 (91.36) + train[2018-10-21-17:03:59] Epoch: [179][9000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.852 (2.899) Prec@1 75.78 (76.04) Prec@5 92.97 (91.36) + train[2018-10-21-17:05:43] Epoch: [179][9200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.817 (2.899) Prec@1 72.66 (76.04) Prec@5 91.41 (91.36) + train[2018-10-21-17:07:28] Epoch: [179][9400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.678 (2.899) Prec@1 82.03 (76.04) Prec@5 94.53 (91.36) + train[2018-10-21-17:09:12] Epoch: [179][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.649 (2.900) Prec@1 78.12 (76.04) Prec@5 92.97 (91.36) + train[2018-10-21-17:10:57] Epoch: [179][9800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.979 (2.900) Prec@1 74.22 (76.03) Prec@5 87.50 (91.35) + train[2018-10-21-17:12:42] Epoch: [179][10000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.140 (2.900) Prec@1 74.22 (76.02) Prec@5 88.28 (91.35) + train[2018-10-21-17:12:46] Epoch: [179][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 2.686 (2.900) Prec@1 86.67 (76.03) Prec@5 86.67 (91.35) +[2018-10-21-17:12:46] **train** Prec@1 76.03 Prec@5 91.35 Error@1 23.97 Error@5 8.65 Loss:2.900 + test [2018-10-21-17:12:50] Epoch: [179][000/391] Time 4.05 (4.05) Data 3.91 (3.91) Loss 0.559 (0.559) Prec@1 91.41 (91.41) Prec@5 99.22 (99.22) + test [2018-10-21-17:13:16] Epoch: [179][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.140 (0.979) Prec@1 67.97 (77.41) Prec@5 91.41 (93.52) + test [2018-10-21-17:13:41] Epoch: [179][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.118 (1.146) Prec@1 45.00 (73.76) Prec@5 85.00 (91.31) +[2018-10-21-17:13:41] **test** Prec@1 73.76 Prec@5 91.31 Error@1 26.24 Error@5 8.69 Loss:1.146 +----> Best Accuracy : Acc@1=73.76, Acc@5=91.31, Error@1=26.24, Error@5=8.69 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-21-17:13:41] [Epoch=180/250] [Need: 103:00:42] LR=0.0004 ~ 0.0004, Batch=128 + train[2018-10-21-17:13:46] Epoch: [180][000/10010] Time 5.10 (5.10) Data 4.43 (4.43) Loss 2.648 (2.648) Prec@1 81.25 (81.25) Prec@5 94.53 (94.53) + train[2018-10-21-17:15:31] Epoch: [180][200/10010] Time 0.55 (0.55) Data 0.00 (0.02) Loss 2.939 (2.907) Prec@1 75.78 (76.11) Prec@5 89.06 (91.28) + train[2018-10-21-17:17:15] Epoch: [180][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.767 (2.908) Prec@1 78.91 (75.96) Prec@5 96.09 (91.25) + train[2018-10-21-17:19:01] Epoch: [180][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.217 (2.908) Prec@1 68.75 (75.99) Prec@5 89.06 (91.25) + train[2018-10-21-17:20:44] Epoch: [180][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.860 (2.901) Prec@1 76.56 (76.10) Prec@5 93.75 (91.36) + train[2018-10-21-17:22:29] Epoch: [180][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.067 (2.894) Prec@1 70.31 (76.18) Prec@5 89.84 (91.45) + train[2018-10-21-17:24:14] Epoch: [180][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.744 (2.893) Prec@1 77.34 (76.23) Prec@5 93.75 (91.44) + train[2018-10-21-17:25:58] Epoch: [180][1400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.989 (2.892) Prec@1 71.88 (76.27) Prec@5 89.06 (91.44) + train[2018-10-21-17:27:42] Epoch: [180][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.926 (2.892) Prec@1 78.91 (76.26) Prec@5 90.62 (91.45) + train[2018-10-21-17:29:27] Epoch: [180][1800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.897 (2.892) Prec@1 75.78 (76.28) Prec@5 90.62 (91.45) + train[2018-10-21-17:31:12] Epoch: [180][2000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.072 (2.893) Prec@1 75.78 (76.26) Prec@5 86.72 (91.44) + train[2018-10-21-17:32:57] Epoch: [180][2200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.868 (2.894) Prec@1 78.91 (76.25) Prec@5 93.75 (91.44) + train[2018-10-21-17:34:42] Epoch: [180][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.239 (2.894) Prec@1 71.88 (76.24) Prec@5 87.50 (91.44) + train[2018-10-21-17:36:27] Epoch: [180][2600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.858 (2.894) Prec@1 75.00 (76.26) Prec@5 93.75 (91.44) + train[2018-10-21-17:38:12] Epoch: [180][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.196 (2.894) Prec@1 63.28 (76.24) Prec@5 88.28 (91.44) + train[2018-10-21-17:39:57] Epoch: [180][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.747 (2.896) Prec@1 76.56 (76.20) Prec@5 95.31 (91.42) + train[2018-10-21-17:41:42] Epoch: [180][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.091 (2.895) Prec@1 73.44 (76.19) Prec@5 88.28 (91.42) + train[2018-10-21-17:43:26] Epoch: [180][3400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.888 (2.895) Prec@1 75.00 (76.19) Prec@5 87.50 (91.42) + train[2018-10-21-17:45:11] Epoch: [180][3600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.882 (2.896) Prec@1 76.56 (76.17) Prec@5 88.28 (91.41) + train[2018-10-21-17:46:56] Epoch: [180][3800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.715 (2.896) Prec@1 82.81 (76.18) Prec@5 93.75 (91.41) + train[2018-10-21-17:48:41] Epoch: [180][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.815 (2.896) Prec@1 78.91 (76.18) Prec@5 92.19 (91.41) + train[2018-10-21-17:50:26] Epoch: [180][4200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.301 (2.896) Prec@1 64.84 (76.17) Prec@5 82.81 (91.41) + train[2018-10-21-17:52:11] Epoch: [180][4400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.905 (2.896) Prec@1 76.56 (76.16) Prec@5 91.41 (91.41) + train[2018-10-21-17:53:56] Epoch: [180][4600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.088 (2.896) Prec@1 71.09 (76.17) Prec@5 89.06 (91.42) + train[2018-10-21-17:55:41] Epoch: [180][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.960 (2.896) Prec@1 76.56 (76.15) Prec@5 91.41 (91.41) + train[2018-10-21-17:57:25] Epoch: [180][5000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.947 (2.897) Prec@1 75.00 (76.14) Prec@5 91.41 (91.40) + train[2018-10-21-17:59:10] Epoch: [180][5200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.795 (2.897) Prec@1 78.91 (76.15) Prec@5 92.19 (91.40) + train[2018-10-21-18:00:56] Epoch: [180][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.596 (2.897) Prec@1 82.81 (76.15) Prec@5 96.88 (91.41) + train[2018-10-21-18:02:41] Epoch: [180][5600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.671 (2.897) Prec@1 78.91 (76.16) Prec@5 96.09 (91.41) + train[2018-10-21-18:04:25] Epoch: [180][5800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.761 (2.897) Prec@1 79.69 (76.15) Prec@5 91.41 (91.41) + train[2018-10-21-18:06:11] Epoch: [180][6000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.023 (2.897) Prec@1 71.09 (76.15) Prec@5 89.84 (91.40) + train[2018-10-21-18:07:56] Epoch: [180][6200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.083 (2.897) Prec@1 71.88 (76.14) Prec@5 88.28 (91.40) + train[2018-10-21-18:09:40] Epoch: [180][6400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.740 (2.897) Prec@1 80.47 (76.14) Prec@5 93.75 (91.40) + train[2018-10-21-18:11:25] Epoch: [180][6600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.152 (2.897) Prec@1 75.00 (76.14) Prec@5 89.06 (91.40) + train[2018-10-21-18:13:10] Epoch: [180][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.104 (2.897) Prec@1 74.22 (76.14) Prec@5 89.84 (91.40) + train[2018-10-21-18:14:56] Epoch: [180][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.710 (2.897) Prec@1 81.25 (76.15) Prec@5 92.97 (91.40) + train[2018-10-21-18:16:42] Epoch: [180][7200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.041 (2.897) Prec@1 67.19 (76.13) Prec@5 90.62 (91.40) + train[2018-10-21-18:18:28] Epoch: [180][7400/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.702 (2.898) Prec@1 80.47 (76.12) Prec@5 96.09 (91.39) + train[2018-10-21-18:20:15] Epoch: [180][7600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.890 (2.898) Prec@1 78.91 (76.12) Prec@5 89.84 (91.38) + train[2018-10-21-18:22:01] Epoch: [180][7800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.514 (2.899) Prec@1 84.38 (76.11) Prec@5 92.97 (91.38) + train[2018-10-21-18:23:45] Epoch: [180][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.740 (2.899) Prec@1 81.25 (76.11) Prec@5 92.19 (91.38) + train[2018-10-21-18:25:30] Epoch: [180][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.347 (2.900) Prec@1 71.88 (76.10) Prec@5 88.28 (91.38) + train[2018-10-21-18:27:14] Epoch: [180][8400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.782 (2.899) Prec@1 76.56 (76.10) Prec@5 91.41 (91.38) + train[2018-10-21-18:28:58] Epoch: [180][8600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.199 (2.900) Prec@1 68.75 (76.09) Prec@5 87.50 (91.38) + train[2018-10-21-18:30:43] Epoch: [180][8800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.873 (2.900) Prec@1 78.12 (76.08) Prec@5 90.62 (91.38) + train[2018-10-21-18:32:28] Epoch: [180][9000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.022 (2.900) Prec@1 75.00 (76.09) Prec@5 89.84 (91.38) + train[2018-10-21-18:34:12] Epoch: [180][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.008 (2.900) Prec@1 71.88 (76.09) Prec@5 89.84 (91.38) + train[2018-10-21-18:35:57] Epoch: [180][9400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.854 (2.901) Prec@1 78.91 (76.08) Prec@5 91.41 (91.37) + train[2018-10-21-18:37:42] Epoch: [180][9600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.937 (2.901) Prec@1 78.12 (76.07) Prec@5 92.19 (91.37) + train[2018-10-21-18:39:27] Epoch: [180][9800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.991 (2.901) Prec@1 75.00 (76.07) Prec@5 88.28 (91.37) + train[2018-10-21-18:41:11] Epoch: [180][10000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.785 (2.901) Prec@1 79.69 (76.07) Prec@5 93.75 (91.37) + train[2018-10-21-18:41:15] Epoch: [180][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 2.787 (2.901) Prec@1 86.67 (76.07) Prec@5 86.67 (91.37) +[2018-10-21-18:41:15] **train** Prec@1 76.07 Prec@5 91.37 Error@1 23.93 Error@5 8.63 Loss:2.901 + test [2018-10-21-18:41:19] Epoch: [180][000/391] Time 4.08 (4.08) Data 3.95 (3.95) Loss 0.560 (0.560) Prec@1 91.41 (91.41) Prec@5 98.44 (98.44) + test [2018-10-21-18:41:45] Epoch: [180][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.175 (0.996) Prec@1 67.97 (77.37) Prec@5 92.97 (93.57) + test [2018-10-21-18:42:09] Epoch: [180][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.088 (1.165) Prec@1 47.50 (73.68) Prec@5 85.00 (91.37) +[2018-10-21-18:42:09] **test** Prec@1 73.68 Prec@5 91.37 Error@1 26.32 Error@5 8.63 Loss:1.165 +----> Best Accuracy : Acc@1=73.76, Acc@5=91.31, Error@1=26.24, Error@5=8.69 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-21-18:42:10] [Epoch=181/250] [Need: 101:44:56] LR=0.0004 ~ 0.0004, Batch=128 + train[2018-10-21-18:42:14] Epoch: [181][000/10010] Time 4.27 (4.27) Data 3.66 (3.66) Loss 2.956 (2.956) Prec@1 77.34 (77.34) Prec@5 92.19 (92.19) + train[2018-10-21-18:43:58] Epoch: [181][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 2.857 (2.869) Prec@1 74.22 (76.53) Prec@5 92.97 (91.54) + train[2018-10-21-18:45:43] Epoch: [181][400/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.998 (2.879) Prec@1 74.22 (76.46) Prec@5 89.06 (91.50) + train[2018-10-21-18:47:28] Epoch: [181][600/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 2.907 (2.876) Prec@1 75.00 (76.54) Prec@5 88.28 (91.58) + train[2018-10-21-18:49:12] Epoch: [181][800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.646 (2.882) Prec@1 79.69 (76.50) Prec@5 94.53 (91.53) + train[2018-10-21-18:50:57] Epoch: [181][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.667 (2.886) Prec@1 80.47 (76.43) Prec@5 93.75 (91.46) + train[2018-10-21-18:52:42] Epoch: [181][1200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.073 (2.886) Prec@1 73.44 (76.42) Prec@5 89.06 (91.48) + train[2018-10-21-18:54:28] Epoch: [181][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.581 (2.888) Prec@1 79.69 (76.36) Prec@5 93.75 (91.43) + train[2018-10-21-18:56:13] Epoch: [181][1600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.819 (2.889) Prec@1 78.12 (76.33) Prec@5 93.75 (91.44) + train[2018-10-21-18:57:58] Epoch: [181][1800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.043 (2.890) Prec@1 75.00 (76.31) Prec@5 89.06 (91.45) + train[2018-10-21-18:59:43] Epoch: [181][2000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.012 (2.890) Prec@1 69.53 (76.31) Prec@5 90.62 (91.44) + train[2018-10-21-19:01:28] Epoch: [181][2200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.857 (2.891) Prec@1 78.91 (76.28) Prec@5 92.19 (91.44) + train[2018-10-21-19:03:13] Epoch: [181][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.852 (2.891) Prec@1 74.22 (76.29) Prec@5 93.75 (91.44) + train[2018-10-21-19:04:57] Epoch: [181][2600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.116 (2.891) Prec@1 71.88 (76.29) Prec@5 89.84 (91.43) + train[2018-10-21-19:06:42] Epoch: [181][2800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.912 (2.891) Prec@1 66.41 (76.27) Prec@5 92.97 (91.44) + train[2018-10-21-19:08:27] Epoch: [181][3000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.704 (2.892) Prec@1 76.56 (76.27) Prec@5 93.75 (91.43) + train[2018-10-21-19:10:12] Epoch: [181][3200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.227 (2.893) Prec@1 71.88 (76.24) Prec@5 87.50 (91.43) + train[2018-10-21-19:11:57] Epoch: [181][3400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.827 (2.894) Prec@1 78.12 (76.22) Prec@5 91.41 (91.42) + train[2018-10-21-19:13:42] Epoch: [181][3600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.831 (2.894) Prec@1 78.12 (76.22) Prec@5 90.62 (91.42) + train[2018-10-21-19:15:27] Epoch: [181][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.877 (2.894) Prec@1 75.00 (76.20) Prec@5 92.19 (91.43) + train[2018-10-21-19:17:12] Epoch: [181][4000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.097 (2.895) Prec@1 74.22 (76.19) Prec@5 87.50 (91.43) + train[2018-10-21-19:18:56] Epoch: [181][4200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.910 (2.895) Prec@1 75.00 (76.20) Prec@5 89.84 (91.42) + train[2018-10-21-19:20:41] Epoch: [181][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.981 (2.895) Prec@1 73.44 (76.19) Prec@5 90.62 (91.43) + train[2018-10-21-19:22:27] Epoch: [181][4600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.003 (2.895) Prec@1 74.22 (76.19) Prec@5 90.62 (91.42) + train[2018-10-21-19:24:11] Epoch: [181][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.915 (2.895) Prec@1 73.44 (76.19) Prec@5 93.75 (91.42) + train[2018-10-21-19:25:56] Epoch: [181][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.870 (2.894) Prec@1 76.56 (76.20) Prec@5 92.97 (91.43) + train[2018-10-21-19:27:40] Epoch: [181][5200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.004 (2.894) Prec@1 75.78 (76.20) Prec@5 89.06 (91.43) + train[2018-10-21-19:29:25] Epoch: [181][5400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.155 (2.893) Prec@1 71.09 (76.21) Prec@5 86.72 (91.45) + train[2018-10-21-19:31:10] Epoch: [181][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.080 (2.894) Prec@1 71.88 (76.21) Prec@5 87.50 (91.44) + train[2018-10-21-19:32:55] Epoch: [181][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.660 (2.894) Prec@1 77.34 (76.20) Prec@5 92.97 (91.44) + train[2018-10-21-19:34:40] Epoch: [181][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.905 (2.895) Prec@1 71.88 (76.19) Prec@5 93.75 (91.44) + train[2018-10-21-19:36:25] Epoch: [181][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.792 (2.895) Prec@1 77.34 (76.18) Prec@5 92.97 (91.43) + train[2018-10-21-19:38:10] Epoch: [181][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.527 (2.896) Prec@1 80.47 (76.18) Prec@5 96.09 (91.42) + train[2018-10-21-19:39:55] Epoch: [181][6600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.876 (2.896) Prec@1 73.44 (76.17) Prec@5 89.06 (91.42) + train[2018-10-21-19:41:40] Epoch: [181][6800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.797 (2.896) Prec@1 77.34 (76.16) Prec@5 92.97 (91.42) + train[2018-10-21-19:43:24] Epoch: [181][7000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.610 (2.897) Prec@1 83.59 (76.14) Prec@5 95.31 (91.40) + train[2018-10-21-19:45:09] Epoch: [181][7200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.088 (2.897) Prec@1 71.09 (76.12) Prec@5 88.28 (91.40) + train[2018-10-21-19:46:54] Epoch: [181][7400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.826 (2.897) Prec@1 75.78 (76.12) Prec@5 92.19 (91.39) + train[2018-10-21-19:48:39] Epoch: [181][7600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.227 (2.898) Prec@1 71.88 (76.12) Prec@5 84.38 (91.38) + train[2018-10-21-19:50:24] Epoch: [181][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.073 (2.897) Prec@1 75.00 (76.12) Prec@5 91.41 (91.39) + train[2018-10-21-19:52:09] Epoch: [181][8000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.828 (2.897) Prec@1 77.34 (76.13) Prec@5 91.41 (91.40) + train[2018-10-21-19:53:54] Epoch: [181][8200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.890 (2.897) Prec@1 75.78 (76.13) Prec@5 91.41 (91.40) + train[2018-10-21-19:55:38] Epoch: [181][8400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.667 (2.897) Prec@1 81.25 (76.12) Prec@5 92.97 (91.40) + train[2018-10-21-19:57:23] Epoch: [181][8600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.019 (2.897) Prec@1 68.75 (76.12) Prec@5 89.06 (91.41) + train[2018-10-21-19:59:07] Epoch: [181][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.648 (2.897) Prec@1 78.91 (76.11) Prec@5 94.53 (91.41) + train[2018-10-21-20:00:52] Epoch: [181][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.623 (2.897) Prec@1 80.47 (76.11) Prec@5 94.53 (91.41) + train[2018-10-21-20:02:36] Epoch: [181][9200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.155 (2.897) Prec@1 71.88 (76.11) Prec@5 85.94 (91.40) + train[2018-10-21-20:04:21] Epoch: [181][9400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 2.880 (2.897) Prec@1 77.34 (76.11) Prec@5 92.19 (91.41) + train[2018-10-21-20:06:06] Epoch: [181][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.685 (2.898) Prec@1 85.16 (76.11) Prec@5 93.75 (91.41) + train[2018-10-21-20:07:51] Epoch: [181][9800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.573 (2.898) Prec@1 79.69 (76.10) Prec@5 92.19 (91.40) + train[2018-10-21-20:09:36] Epoch: [181][10000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.005 (2.898) Prec@1 75.78 (76.11) Prec@5 89.06 (91.40) + train[2018-10-21-20:09:40] Epoch: [181][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 2.842 (2.898) Prec@1 73.33 (76.11) Prec@5 93.33 (91.40) +[2018-10-21-20:09:40] **train** Prec@1 76.11 Prec@5 91.40 Error@1 23.89 Error@5 8.60 Loss:2.898 + test [2018-10-21-20:09:44] Epoch: [181][000/391] Time 3.79 (3.79) Data 3.66 (3.66) Loss 0.563 (0.563) Prec@1 90.62 (90.62) Prec@5 99.22 (99.22) + test [2018-10-21-20:10:10] Epoch: [181][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.112 (1.004) Prec@1 72.66 (77.32) Prec@5 92.19 (93.64) + test [2018-10-21-20:10:35] Epoch: [181][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.116 (1.171) Prec@1 46.25 (73.78) Prec@5 83.75 (91.39) +[2018-10-21-20:10:35] **test** Prec@1 73.78 Prec@5 91.39 Error@1 26.22 Error@5 8.61 Loss:1.171 +----> Best Accuracy : Acc@1=73.78, Acc@5=91.39, Error@1=26.22, Error@5=8.61 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-21-20:10:35] [Epoch=182/250] [Need: 100:13:13] LR=0.0004 ~ 0.0004, Batch=128 + train[2018-10-21-20:10:40] Epoch: [182][000/10010] Time 4.95 (4.95) Data 4.38 (4.38) Loss 2.831 (2.831) Prec@1 78.91 (78.91) Prec@5 89.84 (89.84) + train[2018-10-21-20:12:26] Epoch: [182][200/10010] Time 0.55 (0.55) Data 0.00 (0.02) Loss 2.986 (2.878) Prec@1 76.56 (76.60) Prec@5 90.62 (91.85) + train[2018-10-21-20:14:11] Epoch: [182][400/10010] Time 0.54 (0.54) Data 0.00 (0.01) Loss 2.677 (2.885) Prec@1 83.59 (76.44) Prec@5 91.41 (91.59) + train[2018-10-21-20:15:55] Epoch: [182][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.767 (2.892) Prec@1 78.12 (76.32) Prec@5 91.41 (91.47) + train[2018-10-21-20:17:40] Epoch: [182][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.760 (2.892) Prec@1 76.56 (76.33) Prec@5 93.75 (91.48) + train[2018-10-21-20:19:24] Epoch: [182][1000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.022 (2.894) Prec@1 71.09 (76.26) Prec@5 91.41 (91.45) + train[2018-10-21-20:21:09] Epoch: [182][1200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.517 (2.899) Prec@1 84.38 (76.14) Prec@5 95.31 (91.39) + train[2018-10-21-20:22:55] Epoch: [182][1400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.847 (2.898) Prec@1 71.09 (76.14) Prec@5 90.62 (91.41) + train[2018-10-21-20:24:40] Epoch: [182][1600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.994 (2.899) Prec@1 74.22 (76.11) Prec@5 88.28 (91.38) + train[2018-10-21-20:26:24] Epoch: [182][1800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.779 (2.898) Prec@1 77.34 (76.12) Prec@5 94.53 (91.37) + train[2018-10-21-20:28:09] Epoch: [182][2000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.952 (2.898) Prec@1 78.12 (76.11) Prec@5 92.19 (91.38) + train[2018-10-21-20:29:54] Epoch: [182][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.000 (2.895) Prec@1 74.22 (76.15) Prec@5 90.62 (91.40) + train[2018-10-21-20:31:38] Epoch: [182][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.016 (2.896) Prec@1 73.44 (76.15) Prec@5 89.84 (91.40) + train[2018-10-21-20:33:24] Epoch: [182][2600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.050 (2.896) Prec@1 72.66 (76.13) Prec@5 88.28 (91.40) + train[2018-10-21-20:35:10] Epoch: [182][2800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.943 (2.897) Prec@1 75.78 (76.14) Prec@5 92.19 (91.39) + train[2018-10-21-20:36:55] Epoch: [182][3000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.789 (2.897) Prec@1 80.47 (76.12) Prec@5 92.19 (91.39) + train[2018-10-21-20:38:39] Epoch: [182][3200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.929 (2.896) Prec@1 75.00 (76.13) Prec@5 90.62 (91.39) + train[2018-10-21-20:40:24] Epoch: [182][3400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.239 (2.897) Prec@1 72.66 (76.13) Prec@5 88.28 (91.38) + train[2018-10-21-20:42:08] Epoch: [182][3600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.690 (2.897) Prec@1 81.25 (76.11) Prec@5 94.53 (91.38) + train[2018-10-21-20:43:52] Epoch: [182][3800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.922 (2.896) Prec@1 78.91 (76.13) Prec@5 89.84 (91.40) + train[2018-10-21-20:45:37] Epoch: [182][4000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.049 (2.896) Prec@1 73.44 (76.13) Prec@5 85.94 (91.40) + train[2018-10-21-20:47:22] Epoch: [182][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.763 (2.896) Prec@1 78.12 (76.12) Prec@5 94.53 (91.39) + train[2018-10-21-20:49:07] Epoch: [182][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.885 (2.896) Prec@1 76.56 (76.14) Prec@5 90.62 (91.40) + train[2018-10-21-20:50:52] Epoch: [182][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.800 (2.896) Prec@1 80.47 (76.13) Prec@5 92.97 (91.40) + train[2018-10-21-20:52:36] Epoch: [182][4800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.106 (2.896) Prec@1 71.88 (76.14) Prec@5 88.28 (91.40) + train[2018-10-21-20:54:22] Epoch: [182][5000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.639 (2.895) Prec@1 81.25 (76.16) Prec@5 95.31 (91.41) + train[2018-10-21-20:56:06] Epoch: [182][5200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.165 (2.895) Prec@1 71.09 (76.15) Prec@5 88.28 (91.40) + train[2018-10-21-20:57:52] Epoch: [182][5400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.501 (2.896) Prec@1 80.47 (76.14) Prec@5 95.31 (91.41) + train[2018-10-21-20:59:37] Epoch: [182][5600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.209 (2.896) Prec@1 70.31 (76.14) Prec@5 89.84 (91.40) + train[2018-10-21-21:01:22] Epoch: [182][5800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.762 (2.896) Prec@1 72.66 (76.14) Prec@5 94.53 (91.41) + train[2018-10-21-21:03:07] Epoch: [182][6000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.781 (2.896) Prec@1 78.12 (76.13) Prec@5 92.97 (91.41) + train[2018-10-21-21:04:51] Epoch: [182][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.985 (2.896) Prec@1 78.12 (76.14) Prec@5 91.41 (91.41) + train[2018-10-21-21:06:36] Epoch: [182][6400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.682 (2.896) Prec@1 82.81 (76.14) Prec@5 92.19 (91.41) + train[2018-10-21-21:08:21] Epoch: [182][6600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.838 (2.896) Prec@1 80.47 (76.14) Prec@5 90.62 (91.40) + train[2018-10-21-21:10:07] Epoch: [182][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.909 (2.896) Prec@1 78.91 (76.14) Prec@5 88.28 (91.41) + train[2018-10-21-21:11:51] Epoch: [182][7000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.896 (2.896) Prec@1 77.34 (76.14) Prec@5 90.62 (91.41) + train[2018-10-21-21:13:36] Epoch: [182][7200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.483 (2.896) Prec@1 83.59 (76.14) Prec@5 96.09 (91.40) + train[2018-10-21-21:15:20] Epoch: [182][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.926 (2.896) Prec@1 77.34 (76.14) Prec@5 91.41 (91.41) + train[2018-10-21-21:17:05] Epoch: [182][7600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.904 (2.896) Prec@1 75.00 (76.14) Prec@5 92.19 (91.41) + train[2018-10-21-21:18:50] Epoch: [182][7800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.996 (2.896) Prec@1 75.78 (76.14) Prec@5 90.62 (91.42) + train[2018-10-21-21:20:35] Epoch: [182][8000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.790 (2.896) Prec@1 78.12 (76.14) Prec@5 93.75 (91.42) + train[2018-10-21-21:22:19] Epoch: [182][8200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.443 (2.896) Prec@1 82.81 (76.15) Prec@5 95.31 (91.42) + train[2018-10-21-21:24:04] Epoch: [182][8400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.755 (2.896) Prec@1 78.12 (76.14) Prec@5 93.75 (91.42) + train[2018-10-21-21:25:50] Epoch: [182][8600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.136 (2.896) Prec@1 72.66 (76.14) Prec@5 89.84 (91.42) + train[2018-10-21-21:27:34] Epoch: [182][8800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.854 (2.896) Prec@1 75.78 (76.14) Prec@5 92.97 (91.42) + train[2018-10-21-21:29:19] Epoch: [182][9000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.926 (2.896) Prec@1 75.00 (76.15) Prec@5 94.53 (91.42) + train[2018-10-21-21:31:04] Epoch: [182][9200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.779 (2.895) Prec@1 75.00 (76.15) Prec@5 95.31 (91.42) + train[2018-10-21-21:32:49] Epoch: [182][9400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.839 (2.896) Prec@1 76.56 (76.15) Prec@5 93.75 (91.42) + train[2018-10-21-21:34:33] Epoch: [182][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.055 (2.896) Prec@1 75.00 (76.15) Prec@5 89.84 (91.42) + train[2018-10-21-21:36:19] Epoch: [182][9800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.765 (2.896) Prec@1 74.22 (76.14) Prec@5 94.53 (91.43) + train[2018-10-21-21:38:04] Epoch: [182][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.700 (2.896) Prec@1 79.69 (76.14) Prec@5 95.31 (91.42) + train[2018-10-21-21:38:08] Epoch: [182][10009/10010] Time 0.21 (0.52) Data 0.00 (0.00) Loss 4.998 (2.896) Prec@1 46.67 (76.14) Prec@5 66.67 (91.42) +[2018-10-21-21:38:08] **train** Prec@1 76.14 Prec@5 91.42 Error@1 23.86 Error@5 8.58 Loss:2.896 + test [2018-10-21-21:38:12] Epoch: [182][000/391] Time 4.12 (4.12) Data 3.98 (3.98) Loss 0.526 (0.526) Prec@1 92.97 (92.97) Prec@5 98.44 (98.44) + test [2018-10-21-21:38:38] Epoch: [182][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.153 (1.004) Prec@1 66.41 (77.34) Prec@5 94.53 (93.52) + test [2018-10-21-21:39:03] Epoch: [182][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.190 (1.170) Prec@1 48.75 (73.77) Prec@5 82.50 (91.35) +[2018-10-21-21:39:03] **test** Prec@1 73.77 Prec@5 91.35 Error@1 26.23 Error@5 8.65 Loss:1.170 +----> Best Accuracy : Acc@1=73.78, Acc@5=91.39, Error@1=26.22, Error@5=8.61 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-21-21:39:03] [Epoch=183/250] [Need: 98:46:53] LR=0.0004 ~ 0.0004, Batch=128 + train[2018-10-21-21:39:08] Epoch: [183][000/10010] Time 5.06 (5.06) Data 4.47 (4.47) Loss 3.017 (3.017) Prec@1 75.00 (75.00) Prec@5 92.19 (92.19) + train[2018-10-21-21:40:52] Epoch: [183][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 3.043 (2.896) Prec@1 71.88 (76.39) Prec@5 91.41 (91.58) + train[2018-10-21-21:42:36] Epoch: [183][400/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 2.959 (2.903) Prec@1 72.66 (76.20) Prec@5 92.97 (91.32) + train[2018-10-21-21:44:20] Epoch: [183][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.237 (2.896) Prec@1 73.44 (76.29) Prec@5 85.16 (91.38) + train[2018-10-21-21:46:06] Epoch: [183][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 2.980 (2.894) Prec@1 75.78 (76.28) Prec@5 92.97 (91.43) + train[2018-10-21-21:47:50] Epoch: [183][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.032 (2.891) Prec@1 73.44 (76.31) Prec@5 90.62 (91.46) + train[2018-10-21-21:49:35] Epoch: [183][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.049 (2.888) Prec@1 77.34 (76.38) Prec@5 90.62 (91.49) + train[2018-10-21-21:51:20] Epoch: [183][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.173 (2.890) Prec@1 75.00 (76.32) Prec@5 85.94 (91.47) + train[2018-10-21-21:53:05] Epoch: [183][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.869 (2.889) Prec@1 78.12 (76.35) Prec@5 91.41 (91.50) + train[2018-10-21-21:54:50] Epoch: [183][1800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.224 (2.890) Prec@1 75.78 (76.33) Prec@5 88.28 (91.49) + train[2018-10-21-21:56:35] Epoch: [183][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.882 (2.889) Prec@1 75.78 (76.36) Prec@5 91.41 (91.50) + train[2018-10-21-21:58:20] Epoch: [183][2200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.656 (2.888) Prec@1 78.12 (76.35) Prec@5 95.31 (91.51) + train[2018-10-21-22:00:05] Epoch: [183][2400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.520 (2.889) Prec@1 82.81 (76.34) Prec@5 96.88 (91.51) + train[2018-10-21-22:01:50] Epoch: [183][2600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.317 (2.888) Prec@1 71.09 (76.36) Prec@5 85.16 (91.52) + train[2018-10-21-22:03:34] Epoch: [183][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.810 (2.888) Prec@1 79.69 (76.34) Prec@5 92.19 (91.53) + train[2018-10-21-22:05:20] Epoch: [183][3000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.810 (2.889) Prec@1 78.12 (76.32) Prec@5 90.62 (91.52) + train[2018-10-21-22:07:05] Epoch: [183][3200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.029 (2.889) Prec@1 75.00 (76.31) Prec@5 89.06 (91.51) + train[2018-10-21-22:08:49] Epoch: [183][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.020 (2.889) Prec@1 76.56 (76.31) Prec@5 92.19 (91.51) + train[2018-10-21-22:10:33] Epoch: [183][3600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.007 (2.890) Prec@1 75.78 (76.30) Prec@5 86.72 (91.49) + train[2018-10-21-22:12:18] Epoch: [183][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.768 (2.889) Prec@1 81.25 (76.32) Prec@5 94.53 (91.50) + train[2018-10-21-22:14:03] Epoch: [183][4000/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 2.627 (2.890) Prec@1 82.81 (76.30) Prec@5 93.75 (91.49) + train[2018-10-21-22:15:47] Epoch: [183][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.804 (2.891) Prec@1 80.47 (76.28) Prec@5 92.97 (91.49) + train[2018-10-21-22:17:32] Epoch: [183][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.940 (2.891) Prec@1 77.34 (76.28) Prec@5 90.62 (91.49) + train[2018-10-21-22:19:17] Epoch: [183][4600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.886 (2.891) Prec@1 77.34 (76.27) Prec@5 89.84 (91.49) + train[2018-10-21-22:21:02] Epoch: [183][4800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.883 (2.891) Prec@1 75.78 (76.25) Prec@5 91.41 (91.48) + train[2018-10-21-22:22:47] Epoch: [183][5000/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 2.822 (2.891) Prec@1 78.12 (76.25) Prec@5 91.41 (91.49) + train[2018-10-21-22:24:32] Epoch: [183][5200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.646 (2.891) Prec@1 79.69 (76.24) Prec@5 93.75 (91.48) + train[2018-10-21-22:26:16] Epoch: [183][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.795 (2.892) Prec@1 82.03 (76.22) Prec@5 93.75 (91.47) + train[2018-10-21-22:28:01] Epoch: [183][5600/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 2.983 (2.892) Prec@1 77.34 (76.23) Prec@5 85.94 (91.47) + train[2018-10-21-22:29:45] Epoch: [183][5800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.776 (2.892) Prec@1 78.12 (76.23) Prec@5 92.19 (91.47) + train[2018-10-21-22:31:29] Epoch: [183][6000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.860 (2.892) Prec@1 78.12 (76.23) Prec@5 92.97 (91.47) + train[2018-10-21-22:33:14] Epoch: [183][6200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.486 (2.892) Prec@1 83.59 (76.24) Prec@5 96.88 (91.47) + train[2018-10-21-22:34:59] Epoch: [183][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.533 (2.892) Prec@1 82.81 (76.25) Prec@5 95.31 (91.47) + train[2018-10-21-22:36:44] Epoch: [183][6600/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 3.114 (2.892) Prec@1 75.00 (76.25) Prec@5 87.50 (91.46) + train[2018-10-21-22:38:28] Epoch: [183][6800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.789 (2.892) Prec@1 78.12 (76.24) Prec@5 92.97 (91.46) + train[2018-10-21-22:40:13] Epoch: [183][7000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.024 (2.892) Prec@1 69.53 (76.23) Prec@5 92.19 (91.46) + train[2018-10-21-22:41:58] Epoch: [183][7200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.278 (2.892) Prec@1 71.09 (76.23) Prec@5 88.28 (91.46) + train[2018-10-21-22:43:43] Epoch: [183][7400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.809 (2.892) Prec@1 75.78 (76.23) Prec@5 93.75 (91.46) + train[2018-10-21-22:45:29] Epoch: [183][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.923 (2.892) Prec@1 74.22 (76.22) Prec@5 92.97 (91.46) + train[2018-10-21-22:47:14] Epoch: [183][7800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.018 (2.893) Prec@1 78.12 (76.22) Prec@5 88.28 (91.46) + train[2018-10-21-22:48:59] Epoch: [183][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.890 (2.893) Prec@1 73.44 (76.21) Prec@5 92.97 (91.46) + train[2018-10-21-22:50:43] Epoch: [183][8200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.981 (2.893) Prec@1 80.47 (76.19) Prec@5 90.62 (91.45) + train[2018-10-21-22:52:28] Epoch: [183][8400/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.951 (2.893) Prec@1 77.34 (76.19) Prec@5 90.62 (91.46) + train[2018-10-21-22:54:13] Epoch: [183][8600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.917 (2.894) Prec@1 75.00 (76.19) Prec@5 92.19 (91.45) + train[2018-10-21-22:55:57] Epoch: [183][8800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.923 (2.893) Prec@1 74.22 (76.19) Prec@5 89.06 (91.45) + train[2018-10-21-22:57:42] Epoch: [183][9000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.797 (2.894) Prec@1 78.12 (76.19) Prec@5 92.19 (91.45) + train[2018-10-21-22:59:27] Epoch: [183][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.715 (2.894) Prec@1 79.69 (76.19) Prec@5 92.19 (91.45) + train[2018-10-21-23:01:11] Epoch: [183][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.873 (2.894) Prec@1 78.91 (76.18) Prec@5 94.53 (91.44) + train[2018-10-21-23:02:56] Epoch: [183][9600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.938 (2.894) Prec@1 74.22 (76.18) Prec@5 93.75 (91.44) + train[2018-10-21-23:04:41] Epoch: [183][9800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.942 (2.894) Prec@1 72.66 (76.18) Prec@5 92.19 (91.44) + train[2018-10-21-23:06:26] Epoch: [183][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.033 (2.894) Prec@1 69.53 (76.18) Prec@5 92.19 (91.45) + train[2018-10-21-23:06:30] Epoch: [183][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 2.825 (2.894) Prec@1 80.00 (76.18) Prec@5 93.33 (91.44) +[2018-10-21-23:06:30] **train** Prec@1 76.18 Prec@5 91.44 Error@1 23.82 Error@5 8.56 Loss:2.894 + test [2018-10-21-23:06:34] Epoch: [183][000/391] Time 4.12 (4.12) Data 3.99 (3.99) Loss 0.544 (0.544) Prec@1 92.19 (92.19) Prec@5 99.22 (99.22) + test [2018-10-21-23:07:01] Epoch: [183][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.218 (0.992) Prec@1 68.75 (77.35) Prec@5 91.41 (93.63) + test [2018-10-21-23:07:26] Epoch: [183][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.153 (1.163) Prec@1 46.25 (73.79) Prec@5 82.50 (91.49) +[2018-10-21-23:07:26] **test** Prec@1 73.79 Prec@5 91.49 Error@1 26.21 Error@5 8.51 Loss:1.163 +----> Best Accuracy : Acc@1=73.79, Acc@5=91.49, Error@1=26.21, Error@5=8.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-21-23:07:26] [Epoch=184/250] [Need: 97:13:39] LR=0.0004 ~ 0.0004, Batch=128 + train[2018-10-21-23:07:32] Epoch: [184][000/10010] Time 5.26 (5.26) Data 4.67 (4.67) Loss 2.960 (2.960) Prec@1 72.66 (72.66) Prec@5 91.41 (91.41) + train[2018-10-21-23:09:17] Epoch: [184][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 2.919 (2.874) Prec@1 75.78 (76.71) Prec@5 93.75 (91.65) + train[2018-10-21-23:11:01] Epoch: [184][400/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 2.687 (2.878) Prec@1 82.81 (76.69) Prec@5 93.75 (91.57) + train[2018-10-21-23:12:45] Epoch: [184][600/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.748 (2.872) Prec@1 78.91 (76.71) Prec@5 91.41 (91.65) + train[2018-10-21-23:14:30] Epoch: [184][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.825 (2.877) Prec@1 75.00 (76.63) Prec@5 95.31 (91.65) + train[2018-10-21-23:16:14] Epoch: [184][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.724 (2.876) Prec@1 78.91 (76.60) Prec@5 94.53 (91.66) + train[2018-10-21-23:17:59] Epoch: [184][1200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.831 (2.876) Prec@1 74.22 (76.54) Prec@5 92.97 (91.67) + train[2018-10-21-23:19:44] Epoch: [184][1400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.928 (2.879) Prec@1 75.78 (76.52) Prec@5 91.41 (91.61) + train[2018-10-21-23:21:30] Epoch: [184][1600/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.963 (2.881) Prec@1 73.44 (76.54) Prec@5 87.50 (91.60) + train[2018-10-21-23:23:15] Epoch: [184][1800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.969 (2.883) Prec@1 75.00 (76.50) Prec@5 89.84 (91.60) + train[2018-10-21-23:25:00] Epoch: [184][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.837 (2.883) Prec@1 80.47 (76.47) Prec@5 92.19 (91.60) + train[2018-10-21-23:26:45] Epoch: [184][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.514 (2.883) Prec@1 82.03 (76.47) Prec@5 95.31 (91.58) + train[2018-10-21-23:28:29] Epoch: [184][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.591 (2.883) Prec@1 82.81 (76.47) Prec@5 93.75 (91.58) + train[2018-10-21-23:30:14] Epoch: [184][2600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.971 (2.884) Prec@1 73.44 (76.45) Prec@5 91.41 (91.57) + train[2018-10-21-23:32:00] Epoch: [184][2800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.812 (2.885) Prec@1 75.00 (76.43) Prec@5 92.19 (91.55) + train[2018-10-21-23:33:44] Epoch: [184][3000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.807 (2.885) Prec@1 78.91 (76.44) Prec@5 91.41 (91.56) + train[2018-10-21-23:35:29] Epoch: [184][3200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.016 (2.884) Prec@1 73.44 (76.46) Prec@5 90.62 (91.56) + train[2018-10-21-23:37:14] Epoch: [184][3400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.707 (2.884) Prec@1 81.25 (76.46) Prec@5 92.19 (91.56) + train[2018-10-21-23:38:59] Epoch: [184][3600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.950 (2.883) Prec@1 79.69 (76.48) Prec@5 90.62 (91.56) + train[2018-10-21-23:40:44] Epoch: [184][3800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.865 (2.882) Prec@1 80.47 (76.50) Prec@5 92.19 (91.57) + train[2018-10-21-23:42:29] Epoch: [184][4000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.948 (2.882) Prec@1 74.22 (76.49) Prec@5 90.62 (91.57) + train[2018-10-21-23:44:14] Epoch: [184][4200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.979 (2.883) Prec@1 73.44 (76.45) Prec@5 91.41 (91.57) + train[2018-10-21-23:45:59] Epoch: [184][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.749 (2.884) Prec@1 78.12 (76.45) Prec@5 92.19 (91.56) + train[2018-10-21-23:47:44] Epoch: [184][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.976 (2.883) Prec@1 79.69 (76.45) Prec@5 89.06 (91.56) + train[2018-10-21-23:49:30] Epoch: [184][4800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.909 (2.885) Prec@1 71.09 (76.42) Prec@5 90.62 (91.54) + train[2018-10-21-23:51:15] Epoch: [184][5000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.898 (2.885) Prec@1 76.56 (76.42) Prec@5 92.97 (91.54) + train[2018-10-21-23:52:59] Epoch: [184][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.840 (2.885) Prec@1 80.47 (76.41) Prec@5 89.84 (91.53) + train[2018-10-21-23:54:44] Epoch: [184][5400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.066 (2.885) Prec@1 73.44 (76.40) Prec@5 89.84 (91.54) + train[2018-10-21-23:56:28] Epoch: [184][5600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.894 (2.885) Prec@1 80.47 (76.40) Prec@5 92.19 (91.55) + train[2018-10-21-23:58:13] Epoch: [184][5800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.877 (2.885) Prec@1 76.56 (76.38) Prec@5 89.06 (91.53) + train[2018-10-21-23:59:57] Epoch: [184][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.667 (2.886) Prec@1 78.91 (76.37) Prec@5 93.75 (91.53) + train[2018-10-22-00:01:43] Epoch: [184][6200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.820 (2.886) Prec@1 74.22 (76.36) Prec@5 93.75 (91.52) + train[2018-10-22-00:03:27] Epoch: [184][6400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.144 (2.887) Prec@1 73.44 (76.36) Prec@5 89.84 (91.52) + train[2018-10-22-00:05:12] Epoch: [184][6600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.791 (2.887) Prec@1 77.34 (76.36) Prec@5 89.84 (91.53) + train[2018-10-22-00:06:56] Epoch: [184][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.886 (2.887) Prec@1 81.25 (76.36) Prec@5 89.84 (91.52) + train[2018-10-22-00:08:41] Epoch: [184][7000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.760 (2.888) Prec@1 80.47 (76.34) Prec@5 92.97 (91.52) + train[2018-10-22-00:10:26] Epoch: [184][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.186 (2.889) Prec@1 68.75 (76.34) Prec@5 89.84 (91.52) + train[2018-10-22-00:12:10] Epoch: [184][7400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.895 (2.889) Prec@1 75.00 (76.33) Prec@5 89.06 (91.52) + train[2018-10-22-00:13:55] Epoch: [184][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.847 (2.889) Prec@1 78.12 (76.33) Prec@5 92.97 (91.52) + train[2018-10-22-00:15:39] Epoch: [184][7800/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 2.944 (2.889) Prec@1 75.00 (76.32) Prec@5 89.84 (91.51) + train[2018-10-22-00:17:25] Epoch: [184][8000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.870 (2.889) Prec@1 80.47 (76.33) Prec@5 93.75 (91.51) + train[2018-10-22-00:19:10] Epoch: [184][8200/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.915 (2.889) Prec@1 78.91 (76.33) Prec@5 91.41 (91.51) + train[2018-10-22-00:20:55] Epoch: [184][8400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.935 (2.889) Prec@1 78.91 (76.32) Prec@5 89.06 (91.51) + train[2018-10-22-00:22:39] Epoch: [184][8600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.997 (2.889) Prec@1 74.22 (76.33) Prec@5 90.62 (91.52) + train[2018-10-22-00:24:24] Epoch: [184][8800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.028 (2.889) Prec@1 75.00 (76.32) Prec@5 89.84 (91.51) + train[2018-10-22-00:26:08] Epoch: [184][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.033 (2.890) Prec@1 75.00 (76.31) Prec@5 91.41 (91.51) + train[2018-10-22-00:27:53] Epoch: [184][9200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.869 (2.890) Prec@1 78.91 (76.30) Prec@5 89.06 (91.50) + train[2018-10-22-00:29:39] Epoch: [184][9400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.944 (2.890) Prec@1 74.22 (76.29) Prec@5 91.41 (91.50) + train[2018-10-22-00:31:24] Epoch: [184][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.767 (2.890) Prec@1 74.22 (76.29) Prec@5 92.19 (91.49) + train[2018-10-22-00:33:08] Epoch: [184][9800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.794 (2.890) Prec@1 78.12 (76.29) Prec@5 92.19 (91.49) + train[2018-10-22-00:34:54] Epoch: [184][10000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.637 (2.891) Prec@1 78.91 (76.28) Prec@5 95.31 (91.49) + train[2018-10-22-00:34:58] Epoch: [184][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 2.798 (2.891) Prec@1 73.33 (76.28) Prec@5 93.33 (91.49) +[2018-10-22-00:34:58] **train** Prec@1 76.28 Prec@5 91.49 Error@1 23.72 Error@5 8.51 Loss:2.891 + test [2018-10-22-00:35:02] Epoch: [184][000/391] Time 3.66 (3.66) Data 3.53 (3.53) Loss 0.549 (0.549) Prec@1 92.19 (92.19) Prec@5 99.22 (99.22) + test [2018-10-22-00:35:28] Epoch: [184][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.183 (0.982) Prec@1 66.41 (77.32) Prec@5 92.19 (93.65) + test [2018-10-22-00:35:53] Epoch: [184][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.103 (1.152) Prec@1 46.25 (73.79) Prec@5 83.75 (91.40) +[2018-10-22-00:35:53] **test** Prec@1 73.79 Prec@5 91.40 Error@1 26.21 Error@5 8.60 Loss:1.152 +----> Best Accuracy : Acc@1=73.79, Acc@5=91.40, Error@1=26.21, Error@5=8.60 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-22-00:35:53] [Epoch=185/250] [Need: 95:48:44] LR=0.0004 ~ 0.0004, Batch=128 + train[2018-10-22-00:35:58] Epoch: [185][000/10010] Time 5.22 (5.22) Data 4.65 (4.65) Loss 2.776 (2.776) Prec@1 74.22 (74.22) Prec@5 93.75 (93.75) + train[2018-10-22-00:37:42] Epoch: [185][200/10010] Time 0.52 (0.55) Data 0.00 (0.02) Loss 2.768 (2.903) Prec@1 74.22 (76.23) Prec@5 92.97 (91.31) + train[2018-10-22-00:39:27] Epoch: [185][400/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.192 (2.895) Prec@1 69.53 (76.29) Prec@5 87.50 (91.46) + train[2018-10-22-00:41:11] Epoch: [185][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.139 (2.898) Prec@1 76.56 (76.23) Prec@5 87.50 (91.48) + train[2018-10-22-00:42:55] Epoch: [185][800/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 2.799 (2.896) Prec@1 78.91 (76.22) Prec@5 92.19 (91.51) + train[2018-10-22-00:44:40] Epoch: [185][1000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.937 (2.895) Prec@1 72.66 (76.28) Prec@5 93.75 (91.54) + train[2018-10-22-00:46:25] Epoch: [185][1200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.942 (2.896) Prec@1 75.78 (76.21) Prec@5 89.06 (91.49) + train[2018-10-22-00:48:09] Epoch: [185][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.682 (2.897) Prec@1 80.47 (76.21) Prec@5 93.75 (91.43) + train[2018-10-22-00:49:53] Epoch: [185][1600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.992 (2.894) Prec@1 72.66 (76.26) Prec@5 89.84 (91.48) + train[2018-10-22-00:51:39] Epoch: [185][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.136 (2.893) Prec@1 77.34 (76.29) Prec@5 89.06 (91.47) + train[2018-10-22-00:53:23] Epoch: [185][2000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.001 (2.893) Prec@1 76.56 (76.29) Prec@5 89.84 (91.49) + train[2018-10-22-00:55:08] Epoch: [185][2200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.041 (2.892) Prec@1 74.22 (76.29) Prec@5 88.28 (91.52) + train[2018-10-22-00:56:53] Epoch: [185][2400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.711 (2.892) Prec@1 81.25 (76.31) Prec@5 90.62 (91.51) + train[2018-10-22-00:58:38] Epoch: [185][2600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.861 (2.893) Prec@1 78.91 (76.32) Prec@5 92.19 (91.50) + train[2018-10-22-01:00:23] Epoch: [185][2800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.881 (2.892) Prec@1 75.78 (76.33) Prec@5 90.62 (91.51) + train[2018-10-22-01:02:08] Epoch: [185][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.711 (2.892) Prec@1 78.91 (76.33) Prec@5 93.75 (91.49) + train[2018-10-22-01:03:52] Epoch: [185][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.034 (2.893) Prec@1 73.44 (76.31) Prec@5 89.84 (91.48) + train[2018-10-22-01:05:37] Epoch: [185][3400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.119 (2.893) Prec@1 75.00 (76.31) Prec@5 86.72 (91.48) + train[2018-10-22-01:07:21] Epoch: [185][3600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.117 (2.892) Prec@1 67.19 (76.32) Prec@5 91.41 (91.49) + train[2018-10-22-01:09:06] Epoch: [185][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.904 (2.892) Prec@1 75.00 (76.32) Prec@5 92.19 (91.49) + train[2018-10-22-01:10:50] Epoch: [185][4000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.944 (2.892) Prec@1 75.78 (76.33) Prec@5 90.62 (91.50) + train[2018-10-22-01:12:35] Epoch: [185][4200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.052 (2.891) Prec@1 71.09 (76.34) Prec@5 92.19 (91.49) + train[2018-10-22-01:14:19] Epoch: [185][4400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.943 (2.892) Prec@1 71.88 (76.34) Prec@5 89.84 (91.49) + train[2018-10-22-01:16:04] Epoch: [185][4600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.935 (2.890) Prec@1 78.12 (76.36) Prec@5 89.84 (91.51) + train[2018-10-22-01:17:49] Epoch: [185][4800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.886 (2.891) Prec@1 78.12 (76.34) Prec@5 93.75 (91.51) + train[2018-10-22-01:19:33] Epoch: [185][5000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.576 (2.891) Prec@1 83.59 (76.34) Prec@5 94.53 (91.51) + train[2018-10-22-01:21:18] Epoch: [185][5200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.843 (2.891) Prec@1 79.69 (76.32) Prec@5 90.62 (91.51) + train[2018-10-22-01:23:02] Epoch: [185][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.847 (2.892) Prec@1 79.69 (76.30) Prec@5 92.97 (91.51) + train[2018-10-22-01:24:47] Epoch: [185][5600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.842 (2.891) Prec@1 77.34 (76.31) Prec@5 91.41 (91.50) + train[2018-10-22-01:26:32] Epoch: [185][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.051 (2.891) Prec@1 74.22 (76.32) Prec@5 91.41 (91.50) + train[2018-10-22-01:28:17] Epoch: [185][6000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.070 (2.892) Prec@1 69.53 (76.31) Prec@5 90.62 (91.50) + train[2018-10-22-01:30:02] Epoch: [185][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.777 (2.892) Prec@1 74.22 (76.31) Prec@5 91.41 (91.50) + train[2018-10-22-01:31:47] Epoch: [185][6400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.183 (2.892) Prec@1 69.53 (76.30) Prec@5 87.50 (91.50) + train[2018-10-22-01:33:32] Epoch: [185][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.796 (2.892) Prec@1 78.12 (76.30) Prec@5 90.62 (91.50) + train[2018-10-22-01:35:17] Epoch: [185][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.785 (2.893) Prec@1 76.56 (76.30) Prec@5 92.19 (91.49) + train[2018-10-22-01:37:02] Epoch: [185][7000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.696 (2.893) Prec@1 81.25 (76.29) Prec@5 92.97 (91.49) + train[2018-10-22-01:38:48] Epoch: [185][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.022 (2.893) Prec@1 71.88 (76.28) Prec@5 91.41 (91.49) + train[2018-10-22-01:40:35] Epoch: [185][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.634 (2.893) Prec@1 84.38 (76.28) Prec@5 94.53 (91.49) + train[2018-10-22-01:42:21] Epoch: [185][7600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.696 (2.893) Prec@1 78.12 (76.27) Prec@5 92.19 (91.47) + train[2018-10-22-01:44:07] Epoch: [185][7800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.728 (2.894) Prec@1 82.81 (76.27) Prec@5 92.19 (91.47) + train[2018-10-22-01:45:51] Epoch: [185][8000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.880 (2.894) Prec@1 78.12 (76.27) Prec@5 92.97 (91.47) + train[2018-10-22-01:47:36] Epoch: [185][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.730 (2.893) Prec@1 80.47 (76.27) Prec@5 91.41 (91.47) + train[2018-10-22-01:49:21] Epoch: [185][8400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.079 (2.894) Prec@1 73.44 (76.26) Prec@5 89.06 (91.47) + train[2018-10-22-01:51:05] Epoch: [185][8600/10010] Time 0.58 (0.52) Data 0.00 (0.00) Loss 2.907 (2.893) Prec@1 75.78 (76.26) Prec@5 91.41 (91.48) + train[2018-10-22-01:52:51] Epoch: [185][8800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.783 (2.893) Prec@1 78.12 (76.28) Prec@5 94.53 (91.49) + train[2018-10-22-01:54:35] Epoch: [185][9000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.031 (2.893) Prec@1 72.66 (76.27) Prec@5 89.84 (91.48) + train[2018-10-22-01:56:20] Epoch: [185][9200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.083 (2.893) Prec@1 74.22 (76.26) Prec@5 89.84 (91.48) + train[2018-10-22-01:58:04] Epoch: [185][9400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.662 (2.894) Prec@1 77.34 (76.26) Prec@5 92.97 (91.47) + train[2018-10-22-01:59:49] Epoch: [185][9600/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.072 (2.894) Prec@1 71.88 (76.26) Prec@5 91.41 (91.47) + train[2018-10-22-02:01:34] Epoch: [185][9800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.547 (2.894) Prec@1 82.81 (76.25) Prec@5 94.53 (91.47) + train[2018-10-22-02:03:19] Epoch: [185][10000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.960 (2.894) Prec@1 73.44 (76.25) Prec@5 92.19 (91.47) + train[2018-10-22-02:03:23] Epoch: [185][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 3.646 (2.894) Prec@1 53.33 (76.25) Prec@5 93.33 (91.47) +[2018-10-22-02:03:23] **train** Prec@1 76.25 Prec@5 91.47 Error@1 23.75 Error@5 8.53 Loss:2.894 + test [2018-10-22-02:03:27] Epoch: [185][000/391] Time 3.93 (3.93) Data 3.79 (3.79) Loss 0.564 (0.564) Prec@1 89.06 (89.06) Prec@5 99.22 (99.22) + test [2018-10-22-02:03:53] Epoch: [185][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.259 (0.995) Prec@1 66.41 (77.27) Prec@5 90.62 (93.68) + test [2018-10-22-02:04:18] Epoch: [185][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.141 (1.165) Prec@1 47.50 (73.68) Prec@5 81.25 (91.41) +[2018-10-22-02:04:18] **test** Prec@1 73.68 Prec@5 91.41 Error@1 26.32 Error@5 8.59 Loss:1.165 +----> Best Accuracy : Acc@1=73.79, Acc@5=91.40, Error@1=26.21, Error@5=8.60 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-22-02:04:18] [Epoch=186/250] [Need: 94:19:10] LR=0.0003 ~ 0.0003, Batch=128 + train[2018-10-22-02:04:23] Epoch: [186][000/10010] Time 4.60 (4.60) Data 3.98 (3.98) Loss 2.863 (2.863) Prec@1 78.91 (78.91) Prec@5 92.97 (92.97) + train[2018-10-22-02:06:07] Epoch: [186][200/10010] Time 0.51 (0.54) Data 0.00 (0.02) Loss 2.534 (2.864) Prec@1 84.38 (76.70) Prec@5 96.09 (91.86) + train[2018-10-22-02:07:52] Epoch: [186][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.883 (2.880) Prec@1 79.69 (76.62) Prec@5 92.97 (91.62) + train[2018-10-22-02:09:36] Epoch: [186][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.183 (2.885) Prec@1 69.53 (76.52) Prec@5 85.94 (91.45) + train[2018-10-22-02:11:21] Epoch: [186][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.871 (2.882) Prec@1 74.22 (76.56) Prec@5 90.62 (91.47) + train[2018-10-22-02:13:07] Epoch: [186][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.076 (2.880) Prec@1 75.78 (76.53) Prec@5 89.84 (91.55) + train[2018-10-22-02:14:51] Epoch: [186][1200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.621 (2.882) Prec@1 78.12 (76.46) Prec@5 94.53 (91.57) + train[2018-10-22-02:16:35] Epoch: [186][1400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.056 (2.882) Prec@1 71.88 (76.45) Prec@5 87.50 (91.57) + train[2018-10-22-02:18:19] Epoch: [186][1600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.854 (2.885) Prec@1 75.78 (76.43) Prec@5 92.97 (91.54) + train[2018-10-22-02:20:04] Epoch: [186][1800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.088 (2.884) Prec@1 75.00 (76.38) Prec@5 89.06 (91.56) + train[2018-10-22-02:21:49] Epoch: [186][2000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.671 (2.886) Prec@1 77.34 (76.35) Prec@5 95.31 (91.54) + train[2018-10-22-02:23:34] Epoch: [186][2200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.102 (2.887) Prec@1 74.22 (76.35) Prec@5 85.94 (91.54) + train[2018-10-22-02:25:19] Epoch: [186][2400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.258 (2.887) Prec@1 70.31 (76.35) Prec@5 86.72 (91.54) + train[2018-10-22-02:27:04] Epoch: [186][2600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.758 (2.888) Prec@1 80.47 (76.35) Prec@5 92.19 (91.54) + train[2018-10-22-02:28:49] Epoch: [186][2800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.766 (2.888) Prec@1 75.78 (76.33) Prec@5 94.53 (91.54) + train[2018-10-22-02:30:33] Epoch: [186][3000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.738 (2.887) Prec@1 78.12 (76.34) Prec@5 94.53 (91.55) + train[2018-10-22-02:32:18] Epoch: [186][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.937 (2.887) Prec@1 73.44 (76.36) Prec@5 92.19 (91.54) + train[2018-10-22-02:34:03] Epoch: [186][3400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.071 (2.888) Prec@1 75.00 (76.33) Prec@5 89.06 (91.52) + train[2018-10-22-02:35:48] Epoch: [186][3600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.998 (2.888) Prec@1 73.44 (76.33) Prec@5 94.53 (91.51) + train[2018-10-22-02:37:33] Epoch: [186][3800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.959 (2.888) Prec@1 72.66 (76.34) Prec@5 91.41 (91.51) + train[2018-10-22-02:39:17] Epoch: [186][4000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.903 (2.889) Prec@1 76.56 (76.32) Prec@5 90.62 (91.50) + train[2018-10-22-02:41:02] Epoch: [186][4200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.036 (2.889) Prec@1 75.00 (76.32) Prec@5 89.06 (91.49) + train[2018-10-22-02:42:47] Epoch: [186][4400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.918 (2.889) Prec@1 79.69 (76.31) Prec@5 89.06 (91.48) + train[2018-10-22-02:44:31] Epoch: [186][4600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.960 (2.890) Prec@1 68.75 (76.31) Prec@5 89.06 (91.48) + train[2018-10-22-02:46:16] Epoch: [186][4800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.642 (2.890) Prec@1 77.34 (76.30) Prec@5 92.97 (91.47) + train[2018-10-22-02:48:01] Epoch: [186][5000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.011 (2.891) Prec@1 78.12 (76.27) Prec@5 89.06 (91.46) + train[2018-10-22-02:49:46] Epoch: [186][5200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.536 (2.891) Prec@1 82.03 (76.27) Prec@5 92.97 (91.45) + train[2018-10-22-02:51:31] Epoch: [186][5400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.174 (2.891) Prec@1 72.66 (76.28) Prec@5 88.28 (91.45) + train[2018-10-22-02:53:16] Epoch: [186][5600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.616 (2.892) Prec@1 84.38 (76.28) Prec@5 95.31 (91.45) + train[2018-10-22-02:55:01] Epoch: [186][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.996 (2.891) Prec@1 70.31 (76.28) Prec@5 89.06 (91.45) + train[2018-10-22-02:56:46] Epoch: [186][6000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.673 (2.891) Prec@1 79.69 (76.30) Prec@5 92.97 (91.46) + train[2018-10-22-02:58:31] Epoch: [186][6200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.166 (2.891) Prec@1 67.97 (76.30) Prec@5 88.28 (91.45) + train[2018-10-22-03:00:15] Epoch: [186][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.921 (2.890) Prec@1 76.56 (76.30) Prec@5 93.75 (91.46) + train[2018-10-22-03:02:00] Epoch: [186][6600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.559 (2.891) Prec@1 84.38 (76.28) Prec@5 97.66 (91.46) + train[2018-10-22-03:03:45] Epoch: [186][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.764 (2.891) Prec@1 81.25 (76.28) Prec@5 92.19 (91.46) + train[2018-10-22-03:05:29] Epoch: [186][7000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.803 (2.891) Prec@1 72.66 (76.27) Prec@5 93.75 (91.46) + train[2018-10-22-03:07:14] Epoch: [186][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.957 (2.892) Prec@1 79.69 (76.27) Prec@5 92.19 (91.46) + train[2018-10-22-03:08:58] Epoch: [186][7400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 2.634 (2.892) Prec@1 78.12 (76.26) Prec@5 94.53 (91.45) + train[2018-10-22-03:10:43] Epoch: [186][7600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.911 (2.892) Prec@1 76.56 (76.26) Prec@5 86.72 (91.45) + train[2018-10-22-03:12:28] Epoch: [186][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.745 (2.892) Prec@1 77.34 (76.27) Prec@5 96.09 (91.45) + train[2018-10-22-03:14:13] Epoch: [186][8000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.803 (2.892) Prec@1 75.78 (76.26) Prec@5 90.62 (91.45) + train[2018-10-22-03:15:58] Epoch: [186][8200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.978 (2.892) Prec@1 74.22 (76.26) Prec@5 90.62 (91.45) + train[2018-10-22-03:17:43] Epoch: [186][8400/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 3.091 (2.893) Prec@1 68.75 (76.25) Prec@5 87.50 (91.45) + train[2018-10-22-03:19:27] Epoch: [186][8600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.972 (2.893) Prec@1 74.22 (76.25) Prec@5 90.62 (91.45) + train[2018-10-22-03:21:12] Epoch: [186][8800/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.942 (2.893) Prec@1 77.34 (76.25) Prec@5 91.41 (91.44) + train[2018-10-22-03:22:57] Epoch: [186][9000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.771 (2.893) Prec@1 76.56 (76.24) Prec@5 91.41 (91.44) + train[2018-10-22-03:24:42] Epoch: [186][9200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.056 (2.894) Prec@1 75.78 (76.24) Prec@5 88.28 (91.44) + train[2018-10-22-03:26:26] Epoch: [186][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.859 (2.893) Prec@1 74.22 (76.25) Prec@5 93.75 (91.45) + train[2018-10-22-03:28:11] Epoch: [186][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.863 (2.894) Prec@1 77.34 (76.24) Prec@5 91.41 (91.43) + train[2018-10-22-03:29:56] Epoch: [186][9800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.869 (2.894) Prec@1 74.22 (76.25) Prec@5 93.75 (91.44) + train[2018-10-22-03:31:40] Epoch: [186][10000/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.981 (2.893) Prec@1 76.56 (76.25) Prec@5 92.19 (91.45) + train[2018-10-22-03:31:45] Epoch: [186][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 3.337 (2.893) Prec@1 66.67 (76.25) Prec@5 100.00 (91.45) +[2018-10-22-03:31:45] **train** Prec@1 76.25 Prec@5 91.45 Error@1 23.75 Error@5 8.55 Loss:2.893 + test [2018-10-22-03:31:49] Epoch: [186][000/391] Time 4.08 (4.08) Data 3.94 (3.94) Loss 0.491 (0.491) Prec@1 93.75 (93.75) Prec@5 99.22 (99.22) + test [2018-10-22-03:32:15] Epoch: [186][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.178 (0.986) Prec@1 69.53 (77.48) Prec@5 92.97 (93.74) + test [2018-10-22-03:32:39] Epoch: [186][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.009 (1.156) Prec@1 46.25 (73.82) Prec@5 83.75 (91.48) +[2018-10-22-03:32:39] **test** Prec@1 73.82 Prec@5 91.48 Error@1 26.18 Error@5 8.52 Loss:1.156 +----> Best Accuracy : Acc@1=73.82, Acc@5=91.48, Error@1=26.18, Error@5=8.52 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-22-03:32:40] [Epoch=187/250] [Need: 92:46:19] LR=0.0003 ~ 0.0003, Batch=128 + train[2018-10-22-03:32:44] Epoch: [187][000/10010] Time 4.47 (4.47) Data 3.86 (3.86) Loss 2.806 (2.806) Prec@1 80.47 (80.47) Prec@5 92.19 (92.19) + train[2018-10-22-03:34:29] Epoch: [187][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 2.797 (2.863) Prec@1 81.25 (76.75) Prec@5 90.62 (91.63) + train[2018-10-22-03:36:14] Epoch: [187][400/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 2.653 (2.875) Prec@1 79.69 (76.62) Prec@5 96.09 (91.67) + train[2018-10-22-03:37:58] Epoch: [187][600/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.888 (2.882) Prec@1 76.56 (76.46) Prec@5 93.75 (91.55) + train[2018-10-22-03:39:43] Epoch: [187][800/10010] Time 0.57 (0.53) Data 0.00 (0.01) Loss 2.802 (2.884) Prec@1 75.78 (76.47) Prec@5 92.19 (91.53) + train[2018-10-22-03:41:27] Epoch: [187][1000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.070 (2.884) Prec@1 70.31 (76.43) Prec@5 88.28 (91.52) + train[2018-10-22-03:43:12] Epoch: [187][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.783 (2.881) Prec@1 78.12 (76.48) Prec@5 92.19 (91.55) + train[2018-10-22-03:44:57] Epoch: [187][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.926 (2.882) Prec@1 73.44 (76.44) Prec@5 90.62 (91.54) + train[2018-10-22-03:46:42] Epoch: [187][1600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.930 (2.887) Prec@1 75.00 (76.35) Prec@5 90.62 (91.51) + train[2018-10-22-03:48:26] Epoch: [187][1800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.894 (2.885) Prec@1 77.34 (76.36) Prec@5 89.84 (91.52) + train[2018-10-22-03:50:11] Epoch: [187][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.892 (2.885) Prec@1 71.88 (76.35) Prec@5 92.97 (91.53) + train[2018-10-22-03:51:56] Epoch: [187][2200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.968 (2.886) Prec@1 78.12 (76.35) Prec@5 91.41 (91.51) + train[2018-10-22-03:53:40] Epoch: [187][2400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.767 (2.887) Prec@1 77.34 (76.34) Prec@5 92.97 (91.50) + train[2018-10-22-03:55:25] Epoch: [187][2600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.007 (2.888) Prec@1 75.00 (76.34) Prec@5 90.62 (91.51) + train[2018-10-22-03:57:10] Epoch: [187][2800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.895 (2.888) Prec@1 74.22 (76.34) Prec@5 92.19 (91.50) + train[2018-10-22-03:58:55] Epoch: [187][3000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.861 (2.888) Prec@1 77.34 (76.34) Prec@5 91.41 (91.49) + train[2018-10-22-04:00:39] Epoch: [187][3200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.877 (2.887) Prec@1 82.03 (76.36) Prec@5 91.41 (91.51) + train[2018-10-22-04:02:23] Epoch: [187][3400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.033 (2.886) Prec@1 73.44 (76.36) Prec@5 89.84 (91.53) + train[2018-10-22-04:04:08] Epoch: [187][3600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.532 (2.887) Prec@1 80.47 (76.35) Prec@5 94.53 (91.52) + train[2018-10-22-04:05:53] Epoch: [187][3800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.574 (2.887) Prec@1 82.81 (76.34) Prec@5 94.53 (91.52) + train[2018-10-22-04:07:38] Epoch: [187][4000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.020 (2.888) Prec@1 70.31 (76.33) Prec@5 87.50 (91.51) + train[2018-10-22-04:09:23] Epoch: [187][4200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.805 (2.888) Prec@1 75.00 (76.34) Prec@5 93.75 (91.51) + train[2018-10-22-04:11:07] Epoch: [187][4400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.776 (2.888) Prec@1 77.34 (76.35) Prec@5 92.97 (91.50) + train[2018-10-22-04:12:51] Epoch: [187][4600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.921 (2.888) Prec@1 72.66 (76.34) Prec@5 89.84 (91.50) + train[2018-10-22-04:14:36] Epoch: [187][4800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.913 (2.888) Prec@1 75.00 (76.34) Prec@5 93.75 (91.51) + train[2018-10-22-04:16:20] Epoch: [187][5000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.892 (2.889) Prec@1 78.12 (76.33) Prec@5 92.19 (91.50) + train[2018-10-22-04:18:04] Epoch: [187][5200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.621 (2.889) Prec@1 82.03 (76.31) Prec@5 93.75 (91.49) + train[2018-10-22-04:19:49] Epoch: [187][5400/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.848 (2.890) Prec@1 79.69 (76.29) Prec@5 91.41 (91.49) + train[2018-10-22-04:21:34] Epoch: [187][5600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.686 (2.890) Prec@1 82.81 (76.30) Prec@5 94.53 (91.49) + train[2018-10-22-04:23:19] Epoch: [187][5800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.702 (2.889) Prec@1 81.25 (76.30) Prec@5 95.31 (91.49) + train[2018-10-22-04:25:03] Epoch: [187][6000/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 2.822 (2.889) Prec@1 78.91 (76.32) Prec@5 92.97 (91.51) + train[2018-10-22-04:26:47] Epoch: [187][6200/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.122 (2.889) Prec@1 70.31 (76.31) Prec@5 89.06 (91.51) + train[2018-10-22-04:28:32] Epoch: [187][6400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.899 (2.889) Prec@1 78.12 (76.31) Prec@5 90.62 (91.51) + train[2018-10-22-04:30:17] Epoch: [187][6600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.974 (2.889) Prec@1 75.78 (76.30) Prec@5 91.41 (91.50) + train[2018-10-22-04:32:01] Epoch: [187][6800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.182 (2.889) Prec@1 74.22 (76.29) Prec@5 86.72 (91.49) + train[2018-10-22-04:33:45] Epoch: [187][7000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.979 (2.889) Prec@1 75.00 (76.29) Prec@5 89.84 (91.50) + train[2018-10-22-04:35:30] Epoch: [187][7200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.711 (2.889) Prec@1 79.69 (76.31) Prec@5 95.31 (91.50) + train[2018-10-22-04:37:15] Epoch: [187][7400/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.879 (2.889) Prec@1 78.91 (76.30) Prec@5 91.41 (91.50) + train[2018-10-22-04:39:00] Epoch: [187][7600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.064 (2.889) Prec@1 72.66 (76.30) Prec@5 90.62 (91.50) + train[2018-10-22-04:40:45] Epoch: [187][7800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.910 (2.890) Prec@1 73.44 (76.29) Prec@5 92.19 (91.49) + train[2018-10-22-04:42:30] Epoch: [187][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.109 (2.889) Prec@1 68.75 (76.30) Prec@5 89.06 (91.50) + train[2018-10-22-04:44:14] Epoch: [187][8200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.990 (2.889) Prec@1 75.00 (76.29) Prec@5 92.97 (91.49) + train[2018-10-22-04:45:58] Epoch: [187][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.933 (2.890) Prec@1 77.34 (76.29) Prec@5 89.84 (91.49) + train[2018-10-22-04:47:42] Epoch: [187][8600/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.750 (2.890) Prec@1 80.47 (76.29) Prec@5 94.53 (91.49) + train[2018-10-22-04:49:27] Epoch: [187][8800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.857 (2.889) Prec@1 81.25 (76.29) Prec@5 93.75 (91.49) + train[2018-10-22-04:51:12] Epoch: [187][9000/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 3.059 (2.889) Prec@1 71.09 (76.29) Prec@5 86.72 (91.49) + train[2018-10-22-04:52:56] Epoch: [187][9200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.857 (2.890) Prec@1 75.00 (76.28) Prec@5 92.19 (91.49) + train[2018-10-22-04:54:40] Epoch: [187][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.053 (2.889) Prec@1 75.00 (76.30) Prec@5 91.41 (91.49) + train[2018-10-22-04:56:24] Epoch: [187][9600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.892 (2.890) Prec@1 75.00 (76.28) Prec@5 92.19 (91.48) + train[2018-10-22-04:58:09] Epoch: [187][9800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.793 (2.890) Prec@1 80.47 (76.28) Prec@5 93.75 (91.48) + train[2018-10-22-04:59:55] Epoch: [187][10000/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.842 (2.890) Prec@1 76.56 (76.29) Prec@5 94.53 (91.48) + train[2018-10-22-04:59:59] Epoch: [187][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 3.954 (2.890) Prec@1 66.67 (76.28) Prec@5 80.00 (91.48) +[2018-10-22-04:59:59] **train** Prec@1 76.28 Prec@5 91.48 Error@1 23.72 Error@5 8.52 Loss:2.890 + test [2018-10-22-05:00:04] Epoch: [187][000/391] Time 4.09 (4.09) Data 3.96 (3.96) Loss 0.536 (0.536) Prec@1 93.75 (93.75) Prec@5 99.22 (99.22) + test [2018-10-22-05:00:29] Epoch: [187][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.140 (0.990) Prec@1 71.09 (77.39) Prec@5 92.97 (93.70) + test [2018-10-22-05:00:54] Epoch: [187][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.159 (1.160) Prec@1 46.25 (73.79) Prec@5 83.75 (91.44) +[2018-10-22-05:00:54] **test** Prec@1 73.79 Prec@5 91.44 Error@1 26.21 Error@5 8.56 Loss:1.160 +----> Best Accuracy : Acc@1=73.82, Acc@5=91.48, Error@1=26.18, Error@5=8.52 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-22-05:00:55] [Epoch=188/250] [Need: 91:11:22] LR=0.0003 ~ 0.0003, Batch=128 + train[2018-10-22-05:00:59] Epoch: [188][000/10010] Time 4.46 (4.46) Data 3.87 (3.87) Loss 3.139 (3.139) Prec@1 69.53 (69.53) Prec@5 89.84 (89.84) + train[2018-10-22-05:02:45] Epoch: [188][200/10010] Time 0.52 (0.55) Data 0.00 (0.02) Loss 2.812 (2.899) Prec@1 76.56 (76.22) Prec@5 91.41 (91.53) + train[2018-10-22-05:04:30] Epoch: [188][400/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.954 (2.889) Prec@1 70.31 (76.34) Prec@5 92.97 (91.53) + train[2018-10-22-05:06:14] Epoch: [188][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.397 (2.881) Prec@1 86.72 (76.49) Prec@5 97.66 (91.64) + train[2018-10-22-05:07:59] Epoch: [188][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.914 (2.878) Prec@1 75.78 (76.64) Prec@5 92.19 (91.68) + train[2018-10-22-05:09:45] Epoch: [188][1000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.152 (2.884) Prec@1 71.09 (76.53) Prec@5 85.94 (91.56) + train[2018-10-22-05:11:30] Epoch: [188][1200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.229 (2.884) Prec@1 69.53 (76.50) Prec@5 86.72 (91.59) + train[2018-10-22-05:13:15] Epoch: [188][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.042 (2.881) Prec@1 73.44 (76.54) Prec@5 91.41 (91.61) + train[2018-10-22-05:15:00] Epoch: [188][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.583 (2.880) Prec@1 83.59 (76.58) Prec@5 94.53 (91.59) + train[2018-10-22-05:16:45] Epoch: [188][1800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.922 (2.880) Prec@1 75.78 (76.56) Prec@5 91.41 (91.60) + train[2018-10-22-05:18:30] Epoch: [188][2000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.901 (2.881) Prec@1 73.44 (76.53) Prec@5 92.19 (91.59) + train[2018-10-22-05:20:16] Epoch: [188][2200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.002 (2.882) Prec@1 75.00 (76.52) Prec@5 90.62 (91.58) + train[2018-10-22-05:22:01] Epoch: [188][2400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.372 (2.881) Prec@1 71.09 (76.55) Prec@5 85.16 (91.59) + train[2018-10-22-05:23:46] Epoch: [188][2600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.964 (2.882) Prec@1 77.34 (76.54) Prec@5 87.50 (91.58) + train[2018-10-22-05:25:31] Epoch: [188][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.853 (2.882) Prec@1 77.34 (76.53) Prec@5 91.41 (91.57) + train[2018-10-22-05:27:16] Epoch: [188][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.014 (2.883) Prec@1 73.44 (76.52) Prec@5 89.84 (91.56) + train[2018-10-22-05:29:01] Epoch: [188][3200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.938 (2.883) Prec@1 75.78 (76.53) Prec@5 89.84 (91.55) + train[2018-10-22-05:30:46] Epoch: [188][3400/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.808 (2.883) Prec@1 77.34 (76.53) Prec@5 93.75 (91.56) + train[2018-10-22-05:32:31] Epoch: [188][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.753 (2.883) Prec@1 77.34 (76.51) Prec@5 95.31 (91.56) + train[2018-10-22-05:34:16] Epoch: [188][3800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.722 (2.884) Prec@1 79.69 (76.49) Prec@5 93.75 (91.56) + train[2018-10-22-05:36:01] Epoch: [188][4000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.764 (2.884) Prec@1 74.22 (76.48) Prec@5 92.97 (91.55) + train[2018-10-22-05:37:46] Epoch: [188][4200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.775 (2.884) Prec@1 77.34 (76.46) Prec@5 92.19 (91.54) + train[2018-10-22-05:39:30] Epoch: [188][4400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.989 (2.884) Prec@1 73.44 (76.47) Prec@5 92.97 (91.53) + train[2018-10-22-05:41:15] Epoch: [188][4600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.844 (2.884) Prec@1 78.12 (76.47) Prec@5 92.97 (91.54) + train[2018-10-22-05:42:59] Epoch: [188][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.784 (2.885) Prec@1 80.47 (76.45) Prec@5 91.41 (91.52) + train[2018-10-22-05:44:44] Epoch: [188][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.815 (2.885) Prec@1 78.12 (76.44) Prec@5 92.19 (91.52) + train[2018-10-22-05:46:29] Epoch: [188][5200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.750 (2.886) Prec@1 76.56 (76.43) Prec@5 92.97 (91.52) + train[2018-10-22-05:48:14] Epoch: [188][5400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.720 (2.886) Prec@1 77.34 (76.42) Prec@5 92.97 (91.52) + train[2018-10-22-05:49:59] Epoch: [188][5600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.125 (2.886) Prec@1 75.00 (76.41) Prec@5 86.72 (91.51) + train[2018-10-22-05:51:43] Epoch: [188][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.844 (2.886) Prec@1 72.66 (76.41) Prec@5 93.75 (91.51) + train[2018-10-22-05:53:28] Epoch: [188][6000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.902 (2.886) Prec@1 76.56 (76.41) Prec@5 91.41 (91.51) + train[2018-10-22-05:55:12] Epoch: [188][6200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.990 (2.887) Prec@1 74.22 (76.39) Prec@5 87.50 (91.50) + train[2018-10-22-05:56:57] Epoch: [188][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.102 (2.887) Prec@1 71.09 (76.38) Prec@5 90.62 (91.50) + train[2018-10-22-05:58:42] Epoch: [188][6600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.857 (2.887) Prec@1 75.00 (76.37) Prec@5 91.41 (91.49) + train[2018-10-22-06:00:27] Epoch: [188][6800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.084 (2.888) Prec@1 75.00 (76.36) Prec@5 90.62 (91.49) + train[2018-10-22-06:02:12] Epoch: [188][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.034 (2.888) Prec@1 70.31 (76.36) Prec@5 89.84 (91.49) + train[2018-10-22-06:03:56] Epoch: [188][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.424 (2.888) Prec@1 71.09 (76.37) Prec@5 89.06 (91.49) + train[2018-10-22-06:05:40] Epoch: [188][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.695 (2.888) Prec@1 75.00 (76.36) Prec@5 95.31 (91.49) + train[2018-10-22-06:07:25] Epoch: [188][7600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.104 (2.888) Prec@1 75.00 (76.37) Prec@5 88.28 (91.49) + train[2018-10-22-06:09:09] Epoch: [188][7800/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.830 (2.888) Prec@1 75.00 (76.36) Prec@5 91.41 (91.49) + train[2018-10-22-06:10:54] Epoch: [188][8000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.166 (2.888) Prec@1 73.44 (76.36) Prec@5 85.94 (91.50) + train[2018-10-22-06:12:39] Epoch: [188][8200/10010] Time 0.57 (0.52) Data 0.00 (0.00) Loss 2.615 (2.888) Prec@1 76.56 (76.36) Prec@5 95.31 (91.50) + train[2018-10-22-06:14:24] Epoch: [188][8400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.167 (2.888) Prec@1 75.00 (76.35) Prec@5 85.16 (91.49) + train[2018-10-22-06:16:09] Epoch: [188][8600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.028 (2.888) Prec@1 76.56 (76.36) Prec@5 89.06 (91.49) + train[2018-10-22-06:17:54] Epoch: [188][8800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.836 (2.889) Prec@1 75.78 (76.34) Prec@5 91.41 (91.49) + train[2018-10-22-06:19:39] Epoch: [188][9000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.357 (2.888) Prec@1 71.88 (76.34) Prec@5 89.84 (91.49) + train[2018-10-22-06:21:25] Epoch: [188][9200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.079 (2.889) Prec@1 75.78 (76.34) Prec@5 88.28 (91.49) + train[2018-10-22-06:23:09] Epoch: [188][9400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.836 (2.889) Prec@1 75.78 (76.34) Prec@5 92.97 (91.49) + train[2018-10-22-06:24:54] Epoch: [188][9600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.823 (2.888) Prec@1 77.34 (76.35) Prec@5 92.97 (91.49) + train[2018-10-22-06:26:39] Epoch: [188][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.939 (2.888) Prec@1 75.00 (76.34) Prec@5 91.41 (91.49) + train[2018-10-22-06:28:24] Epoch: [188][10000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.799 (2.889) Prec@1 78.12 (76.34) Prec@5 91.41 (91.49) + train[2018-10-22-06:28:28] Epoch: [188][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 3.075 (2.888) Prec@1 73.33 (76.34) Prec@5 86.67 (91.49) +[2018-10-22-06:28:28] **train** Prec@1 76.34 Prec@5 91.49 Error@1 23.66 Error@5 8.51 Loss:2.888 + test [2018-10-22-06:28:32] Epoch: [188][000/391] Time 3.94 (3.94) Data 3.81 (3.81) Loss 0.572 (0.572) Prec@1 89.84 (89.84) Prec@5 99.22 (99.22) + test [2018-10-22-06:28:58] Epoch: [188][200/391] Time 0.12 (0.15) Data 0.00 (0.02) Loss 1.183 (0.988) Prec@1 69.53 (77.39) Prec@5 92.97 (93.66) + test [2018-10-22-06:29:23] Epoch: [188][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.112 (1.155) Prec@1 47.50 (73.79) Prec@5 82.50 (91.43) +[2018-10-22-06:29:23] **test** Prec@1 73.79 Prec@5 91.43 Error@1 26.21 Error@5 8.57 Loss:1.155 +----> Best Accuracy : Acc@1=73.82, Acc@5=91.48, Error@1=26.18, Error@5=8.52 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-22-06:29:23] [Epoch=189/250] [Need: 89:56:50] LR=0.0003 ~ 0.0003, Batch=128 + train[2018-10-22-06:29:27] Epoch: [189][000/10010] Time 4.29 (4.29) Data 3.65 (3.65) Loss 2.963 (2.963) Prec@1 75.00 (75.00) Prec@5 89.84 (89.84) + train[2018-10-22-06:31:13] Epoch: [189][200/10010] Time 0.53 (0.55) Data 0.00 (0.02) Loss 2.584 (2.882) Prec@1 79.69 (76.67) Prec@5 96.09 (91.48) + train[2018-10-22-06:32:58] Epoch: [189][400/10010] Time 0.54 (0.54) Data 0.00 (0.01) Loss 2.894 (2.888) Prec@1 77.34 (76.47) Prec@5 92.19 (91.36) + train[2018-10-22-06:34:43] Epoch: [189][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.659 (2.885) Prec@1 78.91 (76.55) Prec@5 94.53 (91.38) + train[2018-10-22-06:36:28] Epoch: [189][800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.010 (2.887) Prec@1 76.56 (76.52) Prec@5 92.19 (91.38) + train[2018-10-22-06:38:13] Epoch: [189][1000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.790 (2.886) Prec@1 77.34 (76.54) Prec@5 91.41 (91.40) + train[2018-10-22-06:39:57] Epoch: [189][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.874 (2.889) Prec@1 76.56 (76.47) Prec@5 92.19 (91.38) + train[2018-10-22-06:41:42] Epoch: [189][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.268 (2.889) Prec@1 70.31 (76.45) Prec@5 85.94 (91.43) + train[2018-10-22-06:43:26] Epoch: [189][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.870 (2.889) Prec@1 76.56 (76.47) Prec@5 91.41 (91.43) + train[2018-10-22-06:45:11] Epoch: [189][1800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.923 (2.889) Prec@1 72.66 (76.44) Prec@5 91.41 (91.43) + train[2018-10-22-06:46:56] Epoch: [189][2000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.571 (2.887) Prec@1 85.16 (76.49) Prec@5 94.53 (91.46) + train[2018-10-22-06:48:41] Epoch: [189][2200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.859 (2.886) Prec@1 76.56 (76.48) Prec@5 92.97 (91.47) + train[2018-10-22-06:50:26] Epoch: [189][2400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.204 (2.886) Prec@1 69.53 (76.44) Prec@5 85.94 (91.45) + train[2018-10-22-06:52:11] Epoch: [189][2600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.672 (2.887) Prec@1 78.91 (76.43) Prec@5 92.97 (91.46) + train[2018-10-22-06:53:57] Epoch: [189][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.029 (2.887) Prec@1 71.09 (76.41) Prec@5 90.62 (91.48) + train[2018-10-22-06:55:42] Epoch: [189][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.862 (2.886) Prec@1 74.22 (76.41) Prec@5 91.41 (91.50) + train[2018-10-22-06:57:27] Epoch: [189][3200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.898 (2.886) Prec@1 77.34 (76.42) Prec@5 91.41 (91.50) + train[2018-10-22-06:59:12] Epoch: [189][3400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.717 (2.886) Prec@1 79.69 (76.42) Prec@5 94.53 (91.51) + train[2018-10-22-07:00:57] Epoch: [189][3600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.780 (2.886) Prec@1 78.91 (76.41) Prec@5 91.41 (91.52) + train[2018-10-22-07:02:42] Epoch: [189][3800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.042 (2.886) Prec@1 73.44 (76.39) Prec@5 91.41 (91.51) + train[2018-10-22-07:04:26] Epoch: [189][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.869 (2.886) Prec@1 71.88 (76.41) Prec@5 92.97 (91.52) + train[2018-10-22-07:06:11] Epoch: [189][4200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.571 (2.886) Prec@1 82.81 (76.41) Prec@5 96.09 (91.52) + train[2018-10-22-07:07:55] Epoch: [189][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.027 (2.886) Prec@1 72.66 (76.40) Prec@5 90.62 (91.52) + train[2018-10-22-07:09:41] Epoch: [189][4600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.658 (2.886) Prec@1 82.03 (76.40) Prec@5 93.75 (91.53) + train[2018-10-22-07:11:25] Epoch: [189][4800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.005 (2.885) Prec@1 78.91 (76.40) Prec@5 89.84 (91.54) + train[2018-10-22-07:13:10] Epoch: [189][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.758 (2.885) Prec@1 78.12 (76.40) Prec@5 93.75 (91.54) + train[2018-10-22-07:14:55] Epoch: [189][5200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.896 (2.885) Prec@1 78.12 (76.41) Prec@5 92.97 (91.53) + train[2018-10-22-07:16:40] Epoch: [189][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.148 (2.885) Prec@1 73.44 (76.40) Prec@5 89.06 (91.53) + train[2018-10-22-07:18:24] Epoch: [189][5600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.787 (2.885) Prec@1 78.91 (76.42) Prec@5 92.97 (91.53) + train[2018-10-22-07:20:10] Epoch: [189][5800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.109 (2.885) Prec@1 73.44 (76.41) Prec@5 91.41 (91.52) + train[2018-10-22-07:21:55] Epoch: [189][6000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.884 (2.885) Prec@1 76.56 (76.41) Prec@5 91.41 (91.52) + train[2018-10-22-07:23:40] Epoch: [189][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.899 (2.886) Prec@1 78.91 (76.40) Prec@5 92.19 (91.52) + train[2018-10-22-07:25:25] Epoch: [189][6400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.762 (2.886) Prec@1 77.34 (76.40) Prec@5 93.75 (91.52) + train[2018-10-22-07:27:09] Epoch: [189][6600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.864 (2.886) Prec@1 72.66 (76.40) Prec@5 89.84 (91.53) + train[2018-10-22-07:28:54] Epoch: [189][6800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.030 (2.885) Prec@1 72.66 (76.39) Prec@5 88.28 (91.53) + train[2018-10-22-07:30:39] Epoch: [189][7000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.050 (2.886) Prec@1 75.78 (76.39) Prec@5 90.62 (91.52) + train[2018-10-22-07:32:24] Epoch: [189][7200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.600 (2.886) Prec@1 82.81 (76.40) Prec@5 94.53 (91.52) + train[2018-10-22-07:34:08] Epoch: [189][7400/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.784 (2.885) Prec@1 82.03 (76.40) Prec@5 89.84 (91.52) + train[2018-10-22-07:35:54] Epoch: [189][7600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.863 (2.886) Prec@1 78.12 (76.40) Prec@5 90.62 (91.52) + train[2018-10-22-07:37:38] Epoch: [189][7800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.245 (2.886) Prec@1 70.31 (76.39) Prec@5 88.28 (91.51) + train[2018-10-22-07:39:22] Epoch: [189][8000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.172 (2.886) Prec@1 71.09 (76.39) Prec@5 89.84 (91.52) + train[2018-10-22-07:41:07] Epoch: [189][8200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.953 (2.886) Prec@1 70.31 (76.37) Prec@5 92.97 (91.51) + train[2018-10-22-07:42:52] Epoch: [189][8400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.325 (2.887) Prec@1 67.97 (76.37) Prec@5 85.94 (91.51) + train[2018-10-22-07:44:36] Epoch: [189][8600/10010] Time 0.54 (0.52) Data 0.00 (0.00) Loss 2.718 (2.887) Prec@1 81.25 (76.36) Prec@5 93.75 (91.51) + train[2018-10-22-07:46:21] Epoch: [189][8800/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 3.185 (2.887) Prec@1 69.53 (76.36) Prec@5 89.84 (91.51) + train[2018-10-22-07:48:06] Epoch: [189][9000/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.628 (2.887) Prec@1 80.47 (76.36) Prec@5 95.31 (91.50) + train[2018-10-22-07:49:50] Epoch: [189][9200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.108 (2.887) Prec@1 74.22 (76.36) Prec@5 88.28 (91.50) + train[2018-10-22-07:51:35] Epoch: [189][9400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.016 (2.887) Prec@1 75.00 (76.35) Prec@5 87.50 (91.50) + train[2018-10-22-07:53:20] Epoch: [189][9600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.830 (2.887) Prec@1 71.09 (76.35) Prec@5 92.19 (91.49) + train[2018-10-22-07:55:05] Epoch: [189][9800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.177 (2.887) Prec@1 71.09 (76.35) Prec@5 89.06 (91.49) + train[2018-10-22-07:56:51] Epoch: [189][10000/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.756 (2.888) Prec@1 75.78 (76.33) Prec@5 95.31 (91.49) + train[2018-10-22-07:56:55] Epoch: [189][10009/10010] Time 0.20 (0.52) Data 0.00 (0.00) Loss 3.046 (2.888) Prec@1 73.33 (76.33) Prec@5 93.33 (91.49) +[2018-10-22-07:56:55] **train** Prec@1 76.33 Prec@5 91.49 Error@1 23.67 Error@5 8.51 Loss:2.888 + test [2018-10-22-07:56:59] Epoch: [189][000/391] Time 3.87 (3.87) Data 3.74 (3.74) Loss 0.537 (0.537) Prec@1 92.97 (92.97) Prec@5 98.44 (98.44) + test [2018-10-22-07:57:25] Epoch: [189][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.149 (0.989) Prec@1 68.75 (77.55) Prec@5 92.97 (93.74) + test [2018-10-22-07:57:50] Epoch: [189][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.051 (1.157) Prec@1 43.75 (73.92) Prec@5 85.00 (91.51) +[2018-10-22-07:57:50] **test** Prec@1 73.92 Prec@5 91.51 Error@1 26.08 Error@5 8.49 Loss:1.157 +----> Best Accuracy : Acc@1=73.92, Acc@5=91.51, Error@1=26.08, Error@5=8.49 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-22-07:57:50] [Epoch=190/250] [Need: 88:27:21] LR=0.0003 ~ 0.0003, Batch=128 + train[2018-10-22-07:57:55] Epoch: [190][000/10010] Time 4.83 (4.83) Data 4.20 (4.20) Loss 2.795 (2.795) Prec@1 80.47 (80.47) Prec@5 90.62 (90.62) + train[2018-10-22-07:59:39] Epoch: [190][200/10010] Time 0.55 (0.54) Data 0.00 (0.02) Loss 3.153 (2.875) Prec@1 71.88 (76.72) Prec@5 90.62 (91.72) + train[2018-10-22-08:01:24] Epoch: [190][400/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 2.866 (2.886) Prec@1 77.34 (76.52) Prec@5 92.97 (91.54) + train[2018-10-22-08:03:09] Epoch: [190][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.995 (2.894) Prec@1 75.00 (76.32) Prec@5 89.84 (91.48) + train[2018-10-22-08:04:53] Epoch: [190][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 3.030 (2.893) Prec@1 71.88 (76.32) Prec@5 89.06 (91.51) + train[2018-10-22-08:06:38] Epoch: [190][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.011 (2.893) Prec@1 75.00 (76.35) Prec@5 92.19 (91.50) + train[2018-10-22-08:08:23] Epoch: [190][1200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.846 (2.887) Prec@1 76.56 (76.43) Prec@5 90.62 (91.56) + train[2018-10-22-08:10:08] Epoch: [190][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.935 (2.888) Prec@1 73.44 (76.41) Prec@5 91.41 (91.53) + train[2018-10-22-08:11:53] Epoch: [190][1600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.012 (2.887) Prec@1 72.66 (76.40) Prec@5 88.28 (91.53) + train[2018-10-22-08:13:38] Epoch: [190][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.755 (2.885) Prec@1 76.56 (76.42) Prec@5 93.75 (91.54) + train[2018-10-22-08:15:22] Epoch: [190][2000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.662 (2.886) Prec@1 81.25 (76.41) Prec@5 93.75 (91.55) + train[2018-10-22-08:17:07] Epoch: [190][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.907 (2.885) Prec@1 75.00 (76.42) Prec@5 91.41 (91.58) + train[2018-10-22-08:18:52] Epoch: [190][2400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.538 (2.885) Prec@1 79.69 (76.41) Prec@5 96.88 (91.56) + train[2018-10-22-08:20:37] Epoch: [190][2600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.675 (2.885) Prec@1 81.25 (76.39) Prec@5 91.41 (91.54) + train[2018-10-22-08:22:22] Epoch: [190][2800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.779 (2.884) Prec@1 75.78 (76.43) Prec@5 93.75 (91.55) + train[2018-10-22-08:24:06] Epoch: [190][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.027 (2.884) Prec@1 77.34 (76.41) Prec@5 93.75 (91.54) + train[2018-10-22-08:25:50] Epoch: [190][3200/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.702 (2.885) Prec@1 78.12 (76.39) Prec@5 93.75 (91.53) + train[2018-10-22-08:27:37] Epoch: [190][3400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.842 (2.885) Prec@1 77.34 (76.38) Prec@5 91.41 (91.54) + train[2018-10-22-08:29:22] Epoch: [190][3600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.660 (2.885) Prec@1 77.34 (76.40) Prec@5 93.75 (91.53) + train[2018-10-22-08:31:07] Epoch: [190][3800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.676 (2.885) Prec@1 78.12 (76.40) Prec@5 93.75 (91.54) + train[2018-10-22-08:32:52] Epoch: [190][4000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.822 (2.886) Prec@1 73.44 (76.40) Prec@5 92.19 (91.54) + train[2018-10-22-08:34:36] Epoch: [190][4200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.904 (2.886) Prec@1 74.22 (76.39) Prec@5 91.41 (91.53) + train[2018-10-22-08:36:20] Epoch: [190][4400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.896 (2.885) Prec@1 75.78 (76.41) Prec@5 91.41 (91.53) + train[2018-10-22-08:38:05] Epoch: [190][4600/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.846 (2.885) Prec@1 75.00 (76.41) Prec@5 93.75 (91.54) + train[2018-10-22-08:39:50] Epoch: [190][4800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.721 (2.885) Prec@1 81.25 (76.41) Prec@5 95.31 (91.54) + train[2018-10-22-08:41:35] Epoch: [190][5000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.724 (2.885) Prec@1 78.91 (76.40) Prec@5 94.53 (91.54) + train[2018-10-22-08:43:20] Epoch: [190][5200/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 2.825 (2.884) Prec@1 81.25 (76.41) Prec@5 92.97 (91.55) + train[2018-10-22-08:45:05] Epoch: [190][5400/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.887 (2.884) Prec@1 72.66 (76.39) Prec@5 93.75 (91.55) + train[2018-10-22-08:46:49] Epoch: [190][5600/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.989 (2.885) Prec@1 75.00 (76.39) Prec@5 90.62 (91.54) + train[2018-10-22-08:48:34] Epoch: [190][5800/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.662 (2.884) Prec@1 80.47 (76.40) Prec@5 92.97 (91.54) + train[2018-10-22-08:50:20] Epoch: [190][6000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 3.006 (2.884) Prec@1 75.00 (76.40) Prec@5 90.62 (91.54) + train[2018-10-22-08:52:04] Epoch: [190][6200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 3.204 (2.884) Prec@1 70.31 (76.39) Prec@5 86.72 (91.54) + train[2018-10-22-08:53:49] Epoch: [190][6400/10010] Time 0.56 (0.52) Data 0.00 (0.00) Loss 2.577 (2.884) Prec@1 80.47 (76.38) Prec@5 95.31 (91.54) + train[2018-10-22-08:55:33] Epoch: [190][6600/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 3.119 (2.885) Prec@1 72.66 (76.37) Prec@5 90.62 (91.54) + train[2018-10-22-08:57:18] Epoch: [190][6800/10010] Time 0.55 (0.52) Data 0.00 (0.00) Loss 3.086 (2.885) Prec@1 77.34 (76.37) Prec@5 88.28 (91.54) + train[2018-10-22-08:59:03] Epoch: [190][7000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.841 (2.885) Prec@1 77.34 (76.37) Prec@5 91.41 (91.54) + train[2018-10-22-09:00:48] Epoch: [190][7200/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.780 (2.885) Prec@1 78.91 (76.37) Prec@5 89.84 (91.54) + train[2018-10-22-09:02:35] Epoch: [190][7400/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.705 (2.884) Prec@1 78.12 (76.38) Prec@5 94.53 (91.54) + train[2018-10-22-09:04:19] Epoch: [190][7600/10010] Time 0.53 (0.52) Data 0.00 (0.00) Loss 2.879 (2.885) Prec@1 80.47 (76.37) Prec@5 91.41 (91.55) + train[2018-10-22-09:06:05] Epoch: [190][7800/10010] Time 0.50 (0.52) Data 0.00 (0.00) Loss 2.834 (2.885) Prec@1 76.56 (76.37) Prec@5 90.62 (91.54) + train[2018-10-22-09:07:50] Epoch: [190][8000/10010] Time 0.52 (0.52) Data 0.00 (0.00) Loss 2.625 (2.885) Prec@1 81.25 (76.35) Prec@5 94.53 (91.53) + train[2018-10-22-09:09:36] Epoch: [190][8200/10010] Time 0.51 (0.52) Data 0.00 (0.00) Loss 2.810 (2.885) Prec@1 78.91 (76.36) Prec@5 92.97 (91.54) + train[2018-10-22-09:11:22] Epoch: [190][8400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.827 (2.885) Prec@1 75.00 (76.36) Prec@5 92.97 (91.54) + train[2018-10-22-09:13:09] Epoch: [190][8600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.056 (2.886) Prec@1 76.56 (76.35) Prec@5 92.19 (91.54) + train[2018-10-22-09:14:55] Epoch: [190][8800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.038 (2.886) Prec@1 70.31 (76.34) Prec@5 90.62 (91.53) + train[2018-10-22-09:16:41] Epoch: [190][9000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.933 (2.886) Prec@1 73.44 (76.34) Prec@5 89.84 (91.54) + train[2018-10-22-09:18:27] Epoch: [190][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.187 (2.886) Prec@1 70.31 (76.35) Prec@5 90.62 (91.54) + train[2018-10-22-09:20:12] Epoch: [190][9400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.684 (2.886) Prec@1 81.25 (76.35) Prec@5 93.75 (91.54) + train[2018-10-22-09:21:58] Epoch: [190][9600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.034 (2.886) Prec@1 73.44 (76.35) Prec@5 86.72 (91.53) + train[2018-10-22-09:23:44] Epoch: [190][9800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.781 (2.886) Prec@1 81.25 (76.34) Prec@5 92.19 (91.53) + train[2018-10-22-09:25:29] Epoch: [190][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.606 (2.886) Prec@1 82.03 (76.34) Prec@5 94.53 (91.53) + train[2018-10-22-09:25:34] Epoch: [190][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 2.623 (2.886) Prec@1 86.67 (76.34) Prec@5 93.33 (91.53) +[2018-10-22-09:25:34] **train** Prec@1 76.34 Prec@5 91.53 Error@1 23.66 Error@5 8.47 Loss:2.886 + test [2018-10-22-09:25:38] Epoch: [190][000/391] Time 4.10 (4.10) Data 3.97 (3.97) Loss 0.539 (0.539) Prec@1 92.19 (92.19) Prec@5 99.22 (99.22) + test [2018-10-22-09:26:04] Epoch: [190][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.174 (0.981) Prec@1 65.62 (77.29) Prec@5 91.41 (93.56) + test [2018-10-22-09:26:28] Epoch: [190][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.123 (1.151) Prec@1 42.50 (73.68) Prec@5 82.50 (91.35) +[2018-10-22-09:26:28] **test** Prec@1 73.68 Prec@5 91.35 Error@1 26.32 Error@5 8.65 Loss:1.151 +----> Best Accuracy : Acc@1=73.92, Acc@5=91.51, Error@1=26.08, Error@5=8.49 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-22-09:26:28] [Epoch=191/250] [Need: 87:09:35] LR=0.0003 ~ 0.0003, Batch=128 + train[2018-10-22-09:26:33] Epoch: [191][000/10010] Time 4.84 (4.84) Data 4.20 (4.20) Loss 3.062 (3.062) Prec@1 72.66 (72.66) Prec@5 89.06 (89.06) + train[2018-10-22-09:28:18] Epoch: [191][200/10010] Time 0.50 (0.54) Data 0.00 (0.02) Loss 2.676 (2.880) Prec@1 82.81 (76.64) Prec@5 92.19 (91.54) + train[2018-10-22-09:30:03] Epoch: [191][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.954 (2.895) Prec@1 71.09 (76.28) Prec@5 91.41 (91.54) + train[2018-10-22-09:31:48] Epoch: [191][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 2.705 (2.898) Prec@1 76.56 (76.29) Prec@5 95.31 (91.45) + train[2018-10-22-09:33:32] Epoch: [191][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.816 (2.893) Prec@1 79.69 (76.35) Prec@5 89.84 (91.47) + train[2018-10-22-09:35:17] Epoch: [191][1000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.945 (2.891) Prec@1 75.78 (76.37) Prec@5 91.41 (91.47) + train[2018-10-22-09:37:02] Epoch: [191][1200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.902 (2.891) Prec@1 73.44 (76.39) Prec@5 90.62 (91.44) + train[2018-10-22-09:38:47] Epoch: [191][1400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.979 (2.889) Prec@1 75.78 (76.38) Prec@5 89.06 (91.49) + train[2018-10-22-09:40:32] Epoch: [191][1600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.002 (2.888) Prec@1 75.00 (76.43) Prec@5 89.84 (91.47) + train[2018-10-22-09:42:18] Epoch: [191][1800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.945 (2.887) Prec@1 70.31 (76.45) Prec@5 91.41 (91.50) + train[2018-10-22-09:44:03] Epoch: [191][2000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.955 (2.887) Prec@1 72.66 (76.46) Prec@5 89.06 (91.48) + train[2018-10-22-09:45:48] Epoch: [191][2200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.898 (2.887) Prec@1 74.22 (76.49) Prec@5 89.84 (91.48) + train[2018-10-22-09:47:34] Epoch: [191][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.136 (2.888) Prec@1 72.66 (76.45) Prec@5 88.28 (91.47) + train[2018-10-22-09:49:19] Epoch: [191][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.798 (2.888) Prec@1 78.12 (76.45) Prec@5 90.62 (91.48) + train[2018-10-22-09:51:04] Epoch: [191][2800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.849 (2.888) Prec@1 77.34 (76.47) Prec@5 92.19 (91.48) + train[2018-10-22-09:52:49] Epoch: [191][3000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.717 (2.887) Prec@1 78.12 (76.48) Prec@5 93.75 (91.50) + train[2018-10-22-09:54:34] Epoch: [191][3200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.744 (2.886) Prec@1 77.34 (76.47) Prec@5 92.97 (91.50) + train[2018-10-22-09:56:19] Epoch: [191][3400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.860 (2.886) Prec@1 75.78 (76.47) Prec@5 93.75 (91.51) + train[2018-10-22-09:58:03] Epoch: [191][3600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.557 (2.886) Prec@1 82.03 (76.47) Prec@5 94.53 (91.50) + train[2018-10-22-09:59:49] Epoch: [191][3800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.842 (2.886) Prec@1 76.56 (76.45) Prec@5 95.31 (91.50) + train[2018-10-22-10:01:33] Epoch: [191][4000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.068 (2.886) Prec@1 73.44 (76.46) Prec@5 89.06 (91.51) + train[2018-10-22-10:03:18] Epoch: [191][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.071 (2.886) Prec@1 71.09 (76.45) Prec@5 89.06 (91.51) + train[2018-10-22-10:05:04] Epoch: [191][4400/10010] Time 0.62 (0.53) Data 0.00 (0.00) Loss 3.022 (2.886) Prec@1 70.31 (76.44) Prec@5 89.84 (91.51) + train[2018-10-22-10:06:50] Epoch: [191][4600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.490 (2.886) Prec@1 83.59 (76.45) Prec@5 94.53 (91.51) + train[2018-10-22-10:08:36] Epoch: [191][4800/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.568 (2.885) Prec@1 78.91 (76.45) Prec@5 94.53 (91.51) + train[2018-10-22-10:10:21] Epoch: [191][5000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.211 (2.885) Prec@1 68.75 (76.46) Prec@5 89.84 (91.51) + train[2018-10-22-10:12:07] Epoch: [191][5200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.929 (2.885) Prec@1 78.91 (76.47) Prec@5 92.19 (91.51) + train[2018-10-22-10:13:51] Epoch: [191][5400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.968 (2.885) Prec@1 75.00 (76.45) Prec@5 89.84 (91.52) + train[2018-10-22-10:15:36] Epoch: [191][5600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.977 (2.886) Prec@1 75.78 (76.44) Prec@5 90.62 (91.51) + train[2018-10-22-10:17:21] Epoch: [191][5800/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.886 (2.886) Prec@1 75.00 (76.45) Prec@5 92.97 (91.52) + train[2018-10-22-10:19:06] Epoch: [191][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.935 (2.885) Prec@1 71.88 (76.45) Prec@5 92.97 (91.53) + train[2018-10-22-10:20:51] Epoch: [191][6200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.967 (2.885) Prec@1 75.78 (76.46) Prec@5 93.75 (91.54) + train[2018-10-22-10:22:36] Epoch: [191][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.181 (2.885) Prec@1 75.00 (76.47) Prec@5 89.06 (91.54) + train[2018-10-22-10:24:22] Epoch: [191][6600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.103 (2.885) Prec@1 69.53 (76.47) Prec@5 90.62 (91.54) + train[2018-10-22-10:26:07] Epoch: [191][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.031 (2.885) Prec@1 77.34 (76.47) Prec@5 89.06 (91.54) + train[2018-10-22-10:27:52] Epoch: [191][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.957 (2.885) Prec@1 75.78 (76.47) Prec@5 88.28 (91.54) + train[2018-10-22-10:29:37] Epoch: [191][7200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.816 (2.885) Prec@1 79.69 (76.46) Prec@5 94.53 (91.54) + train[2018-10-22-10:31:22] Epoch: [191][7400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.944 (2.885) Prec@1 71.09 (76.46) Prec@5 90.62 (91.54) + train[2018-10-22-10:33:07] Epoch: [191][7600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.761 (2.885) Prec@1 80.47 (76.47) Prec@5 90.62 (91.54) + train[2018-10-22-10:34:52] Epoch: [191][7800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.597 (2.884) Prec@1 84.38 (76.47) Prec@5 92.97 (91.55) + train[2018-10-22-10:36:38] Epoch: [191][8000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.679 (2.885) Prec@1 81.25 (76.46) Prec@5 95.31 (91.55) + train[2018-10-22-10:38:23] Epoch: [191][8200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.998 (2.885) Prec@1 75.78 (76.46) Prec@5 89.06 (91.55) + train[2018-10-22-10:40:09] Epoch: [191][8400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.959 (2.885) Prec@1 75.78 (76.46) Prec@5 90.62 (91.55) + train[2018-10-22-10:41:55] Epoch: [191][8600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.924 (2.885) Prec@1 72.66 (76.46) Prec@5 92.97 (91.56) + train[2018-10-22-10:43:41] Epoch: [191][8800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.893 (2.884) Prec@1 82.81 (76.47) Prec@5 92.97 (91.55) + train[2018-10-22-10:45:26] Epoch: [191][9000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.816 (2.884) Prec@1 76.56 (76.47) Prec@5 88.28 (91.55) + train[2018-10-22-10:47:10] Epoch: [191][9200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.906 (2.884) Prec@1 70.31 (76.47) Prec@5 92.97 (91.55) + train[2018-10-22-10:48:55] Epoch: [191][9400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.704 (2.885) Prec@1 80.47 (76.46) Prec@5 92.19 (91.55) + train[2018-10-22-10:50:40] Epoch: [191][9600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.854 (2.885) Prec@1 80.47 (76.46) Prec@5 92.97 (91.55) + train[2018-10-22-10:52:25] Epoch: [191][9800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.889 (2.885) Prec@1 75.78 (76.47) Prec@5 89.84 (91.55) + train[2018-10-22-10:54:10] Epoch: [191][10000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.667 (2.884) Prec@1 78.12 (76.47) Prec@5 92.97 (91.55) + train[2018-10-22-10:54:14] Epoch: [191][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 4.959 (2.884) Prec@1 46.67 (76.47) Prec@5 80.00 (91.55) +[2018-10-22-10:54:14] **train** Prec@1 76.47 Prec@5 91.55 Error@1 23.53 Error@5 8.45 Loss:2.884 + test [2018-10-22-10:54:18] Epoch: [191][000/391] Time 4.20 (4.20) Data 4.06 (4.06) Loss 0.540 (0.540) Prec@1 92.19 (92.19) Prec@5 99.22 (99.22) + test [2018-10-22-10:54:45] Epoch: [191][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.177 (0.999) Prec@1 66.41 (77.27) Prec@5 91.41 (93.65) + test [2018-10-22-10:55:10] Epoch: [191][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.142 (1.168) Prec@1 43.75 (73.70) Prec@5 82.50 (91.43) +[2018-10-22-10:55:10] **test** Prec@1 73.70 Prec@5 91.43 Error@1 26.30 Error@5 8.57 Loss:1.168 +----> Best Accuracy : Acc@1=73.92, Acc@5=91.51, Error@1=26.08, Error@5=8.49 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-22-10:55:10] [Epoch=192/250] [Need: 85:44:02] LR=0.0003 ~ 0.0003, Batch=128 + train[2018-10-22-10:55:15] Epoch: [192][000/10010] Time 5.37 (5.37) Data 4.78 (4.78) Loss 2.788 (2.788) Prec@1 78.12 (78.12) Prec@5 89.84 (89.84) + train[2018-10-22-10:57:00] Epoch: [192][200/10010] Time 0.55 (0.55) Data 0.00 (0.02) Loss 2.991 (2.895) Prec@1 75.00 (75.98) Prec@5 86.72 (91.34) + train[2018-10-22-10:58:45] Epoch: [192][400/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.695 (2.884) Prec@1 79.69 (76.23) Prec@5 92.97 (91.51) + train[2018-10-22-11:00:30] Epoch: [192][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.841 (2.881) Prec@1 72.66 (76.31) Prec@5 93.75 (91.56) + train[2018-10-22-11:02:14] Epoch: [192][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.761 (2.879) Prec@1 79.69 (76.35) Prec@5 92.19 (91.60) + train[2018-10-22-11:03:59] Epoch: [192][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.850 (2.879) Prec@1 79.69 (76.45) Prec@5 92.19 (91.62) + train[2018-10-22-11:05:44] Epoch: [192][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.863 (2.879) Prec@1 76.56 (76.49) Prec@5 92.19 (91.60) + train[2018-10-22-11:07:29] Epoch: [192][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.765 (2.876) Prec@1 75.00 (76.53) Prec@5 92.97 (91.63) + train[2018-10-22-11:09:13] Epoch: [192][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.989 (2.876) Prec@1 78.91 (76.56) Prec@5 88.28 (91.64) + train[2018-10-22-11:10:58] Epoch: [192][1800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.683 (2.877) Prec@1 81.25 (76.55) Prec@5 94.53 (91.63) + train[2018-10-22-11:12:42] Epoch: [192][2000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.764 (2.877) Prec@1 78.91 (76.56) Prec@5 90.62 (91.63) + train[2018-10-22-11:14:27] Epoch: [192][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.821 (2.878) Prec@1 80.47 (76.55) Prec@5 93.75 (91.61) + train[2018-10-22-11:16:12] Epoch: [192][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.914 (2.877) Prec@1 74.22 (76.58) Prec@5 91.41 (91.64) + train[2018-10-22-11:17:57] Epoch: [192][2600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.888 (2.879) Prec@1 76.56 (76.54) Prec@5 92.19 (91.62) + train[2018-10-22-11:19:41] Epoch: [192][2800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.815 (2.880) Prec@1 75.78 (76.52) Prec@5 94.53 (91.61) + train[2018-10-22-11:21:25] Epoch: [192][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.690 (2.880) Prec@1 78.91 (76.51) Prec@5 97.66 (91.61) + train[2018-10-22-11:23:11] Epoch: [192][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.964 (2.880) Prec@1 74.22 (76.52) Prec@5 87.50 (91.61) + train[2018-10-22-11:24:57] Epoch: [192][3400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.700 (2.881) Prec@1 79.69 (76.49) Prec@5 94.53 (91.62) + train[2018-10-22-11:26:43] Epoch: [192][3600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.784 (2.881) Prec@1 80.47 (76.50) Prec@5 92.97 (91.61) + train[2018-10-22-11:28:27] Epoch: [192][3800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.013 (2.881) Prec@1 75.78 (76.48) Prec@5 91.41 (91.60) + train[2018-10-22-11:30:12] Epoch: [192][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.223 (2.882) Prec@1 70.31 (76.48) Prec@5 87.50 (91.60) + train[2018-10-22-11:31:57] Epoch: [192][4200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.727 (2.882) Prec@1 77.34 (76.48) Prec@5 95.31 (91.59) + train[2018-10-22-11:33:43] Epoch: [192][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.181 (2.883) Prec@1 74.22 (76.44) Prec@5 90.62 (91.58) + train[2018-10-22-11:35:29] Epoch: [192][4600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.991 (2.884) Prec@1 78.91 (76.42) Prec@5 88.28 (91.57) + train[2018-10-22-11:37:15] Epoch: [192][4800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.898 (2.884) Prec@1 78.12 (76.42) Prec@5 91.41 (91.57) + train[2018-10-22-11:39:00] Epoch: [192][5000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.546 (2.883) Prec@1 86.72 (76.43) Prec@5 93.75 (91.58) + train[2018-10-22-11:40:45] Epoch: [192][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.804 (2.883) Prec@1 74.22 (76.44) Prec@5 93.75 (91.57) + train[2018-10-22-11:42:30] Epoch: [192][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.728 (2.883) Prec@1 79.69 (76.43) Prec@5 92.97 (91.58) + train[2018-10-22-11:44:16] Epoch: [192][5600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.683 (2.884) Prec@1 84.38 (76.43) Prec@5 93.75 (91.57) + train[2018-10-22-11:46:03] Epoch: [192][5800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.039 (2.883) Prec@1 72.66 (76.44) Prec@5 88.28 (91.58) + train[2018-10-22-11:47:50] Epoch: [192][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.079 (2.883) Prec@1 72.66 (76.44) Prec@5 90.62 (91.58) + train[2018-10-22-11:49:35] Epoch: [192][6200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.970 (2.884) Prec@1 74.22 (76.43) Prec@5 92.19 (91.57) + train[2018-10-22-11:51:19] Epoch: [192][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.812 (2.884) Prec@1 77.34 (76.44) Prec@5 92.19 (91.57) + train[2018-10-22-11:53:05] Epoch: [192][6600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.947 (2.884) Prec@1 72.66 (76.43) Prec@5 92.97 (91.57) + train[2018-10-22-11:54:53] Epoch: [192][6800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.770 (2.884) Prec@1 76.56 (76.44) Prec@5 91.41 (91.57) + train[2018-10-22-11:56:40] Epoch: [192][7000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.973 (2.884) Prec@1 72.66 (76.43) Prec@5 89.84 (91.56) + train[2018-10-22-11:58:27] Epoch: [192][7200/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.782 (2.884) Prec@1 77.34 (76.43) Prec@5 90.62 (91.56) + train[2018-10-22-12:00:14] Epoch: [192][7400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.889 (2.884) Prec@1 76.56 (76.43) Prec@5 90.62 (91.56) + train[2018-10-22-12:02:01] Epoch: [192][7600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.080 (2.884) Prec@1 71.09 (76.43) Prec@5 90.62 (91.55) + train[2018-10-22-12:03:49] Epoch: [192][7800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.916 (2.884) Prec@1 81.25 (76.43) Prec@5 88.28 (91.55) + train[2018-10-22-12:05:37] Epoch: [192][8000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.883 (2.883) Prec@1 76.56 (76.44) Prec@5 92.19 (91.56) + train[2018-10-22-12:07:25] Epoch: [192][8200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.734 (2.883) Prec@1 78.12 (76.43) Prec@5 92.19 (91.56) + train[2018-10-22-12:09:12] Epoch: [192][8400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.831 (2.883) Prec@1 75.78 (76.43) Prec@5 91.41 (91.56) + train[2018-10-22-12:10:59] Epoch: [192][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.640 (2.883) Prec@1 80.47 (76.43) Prec@5 92.97 (91.56) + train[2018-10-22-12:12:46] Epoch: [192][8800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.962 (2.883) Prec@1 73.44 (76.43) Prec@5 90.62 (91.56) + train[2018-10-22-12:14:33] Epoch: [192][9000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.258 (2.883) Prec@1 69.53 (76.43) Prec@5 88.28 (91.57) + train[2018-10-22-12:16:20] Epoch: [192][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.842 (2.882) Prec@1 78.91 (76.43) Prec@5 93.75 (91.57) + train[2018-10-22-12:18:07] Epoch: [192][9400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.810 (2.882) Prec@1 79.69 (76.43) Prec@5 91.41 (91.57) + train[2018-10-22-12:19:54] Epoch: [192][9600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.159 (2.883) Prec@1 76.56 (76.43) Prec@5 87.50 (91.56) + train[2018-10-22-12:21:42] Epoch: [192][9800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.900 (2.883) Prec@1 76.56 (76.42) Prec@5 90.62 (91.56) + train[2018-10-22-12:23:28] Epoch: [192][10000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.676 (2.883) Prec@1 78.91 (76.42) Prec@5 93.75 (91.55) + train[2018-10-22-12:23:33] Epoch: [192][10009/10010] Time 0.14 (0.53) Data 0.00 (0.00) Loss 3.430 (2.883) Prec@1 73.33 (76.42) Prec@5 80.00 (91.55) +[2018-10-22-12:23:33] **train** Prec@1 76.42 Prec@5 91.55 Error@1 23.58 Error@5 8.45 Loss:2.883 + test [2018-10-22-12:23:37] Epoch: [192][000/391] Time 3.90 (3.90) Data 3.76 (3.76) Loss 0.563 (0.563) Prec@1 92.19 (92.19) Prec@5 99.22 (99.22) + test [2018-10-22-12:24:03] Epoch: [192][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.245 (0.995) Prec@1 63.28 (77.35) Prec@5 92.19 (93.67) + test [2018-10-22-12:24:29] Epoch: [192][390/391] Time 0.09 (0.14) Data 0.00 (0.02) Loss 2.140 (1.166) Prec@1 47.50 (73.64) Prec@5 82.50 (91.41) +[2018-10-22-12:24:29] **test** Prec@1 73.64 Prec@5 91.41 Error@1 26.36 Error@5 8.59 Loss:1.166 +----> Best Accuracy : Acc@1=73.92, Acc@5=91.51, Error@1=26.08, Error@5=8.49 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-22-12:24:30] [Epoch=193/250] [Need: 84:51:41] LR=0.0003 ~ 0.0003, Batch=128 + train[2018-10-22-12:24:35] Epoch: [193][000/10010] Time 5.47 (5.47) Data 4.89 (4.89) Loss 2.940 (2.940) Prec@1 74.22 (74.22) Prec@5 92.19 (92.19) + train[2018-10-22-12:26:21] Epoch: [193][200/10010] Time 0.53 (0.55) Data 0.00 (0.02) Loss 2.816 (2.897) Prec@1 78.91 (76.31) Prec@5 93.75 (91.22) + train[2018-10-22-12:28:06] Epoch: [193][400/10010] Time 0.53 (0.54) Data 0.00 (0.01) Loss 2.547 (2.889) Prec@1 84.38 (76.39) Prec@5 96.09 (91.32) + train[2018-10-22-12:29:50] Epoch: [193][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 2.977 (2.886) Prec@1 76.56 (76.38) Prec@5 88.28 (91.47) + train[2018-10-22-12:31:35] Epoch: [193][800/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 2.950 (2.881) Prec@1 75.78 (76.47) Prec@5 90.62 (91.54) + train[2018-10-22-12:33:20] Epoch: [193][1000/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.001 (2.884) Prec@1 73.44 (76.45) Prec@5 89.84 (91.54) + train[2018-10-22-12:35:06] Epoch: [193][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.002 (2.883) Prec@1 72.66 (76.46) Prec@5 90.62 (91.55) + train[2018-10-22-12:36:51] Epoch: [193][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.595 (2.881) Prec@1 78.12 (76.49) Prec@5 94.53 (91.58) + train[2018-10-22-12:38:35] Epoch: [193][1600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.720 (2.880) Prec@1 77.34 (76.51) Prec@5 92.97 (91.60) + train[2018-10-22-12:40:20] Epoch: [193][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.792 (2.880) Prec@1 77.34 (76.53) Prec@5 92.97 (91.58) + train[2018-10-22-12:42:05] Epoch: [193][2000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.934 (2.880) Prec@1 75.78 (76.53) Prec@5 91.41 (91.59) + train[2018-10-22-12:43:49] Epoch: [193][2200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.981 (2.881) Prec@1 72.66 (76.52) Prec@5 92.19 (91.58) + train[2018-10-22-12:45:35] Epoch: [193][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.931 (2.882) Prec@1 75.00 (76.50) Prec@5 91.41 (91.58) + train[2018-10-22-12:47:21] Epoch: [193][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.900 (2.882) Prec@1 73.44 (76.47) Prec@5 94.53 (91.58) + train[2018-10-22-12:49:05] Epoch: [193][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.928 (2.883) Prec@1 71.09 (76.46) Prec@5 90.62 (91.57) + train[2018-10-22-12:50:50] Epoch: [193][3000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.633 (2.883) Prec@1 78.12 (76.44) Prec@5 94.53 (91.57) + train[2018-10-22-12:52:35] Epoch: [193][3200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.907 (2.885) Prec@1 77.34 (76.39) Prec@5 91.41 (91.56) + train[2018-10-22-12:54:20] Epoch: [193][3400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.978 (2.884) Prec@1 72.66 (76.40) Prec@5 89.06 (91.57) + train[2018-10-22-12:56:07] Epoch: [193][3600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.867 (2.883) Prec@1 77.34 (76.42) Prec@5 92.19 (91.57) + train[2018-10-22-12:57:53] Epoch: [193][3800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.748 (2.883) Prec@1 80.47 (76.43) Prec@5 92.19 (91.57) + train[2018-10-22-12:59:37] Epoch: [193][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.035 (2.884) Prec@1 74.22 (76.43) Prec@5 88.28 (91.56) + train[2018-10-22-13:01:21] Epoch: [193][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.494 (2.884) Prec@1 79.69 (76.42) Prec@5 96.09 (91.55) + train[2018-10-22-13:03:05] Epoch: [193][4400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.872 (2.885) Prec@1 75.00 (76.41) Prec@5 91.41 (91.54) + train[2018-10-22-13:04:50] Epoch: [193][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.829 (2.885) Prec@1 78.12 (76.42) Prec@5 91.41 (91.53) + train[2018-10-22-13:06:35] Epoch: [193][4800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.042 (2.885) Prec@1 71.09 (76.43) Prec@5 90.62 (91.54) + train[2018-10-22-13:08:19] Epoch: [193][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.872 (2.884) Prec@1 77.34 (76.44) Prec@5 89.84 (91.54) + train[2018-10-22-13:10:04] Epoch: [193][5200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.877 (2.884) Prec@1 78.91 (76.44) Prec@5 92.19 (91.54) + train[2018-10-22-13:11:48] Epoch: [193][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.753 (2.884) Prec@1 82.03 (76.46) Prec@5 93.75 (91.54) + train[2018-10-22-13:13:33] Epoch: [193][5600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.865 (2.883) Prec@1 75.78 (76.46) Prec@5 90.62 (91.55) + train[2018-10-22-13:15:18] Epoch: [193][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.650 (2.884) Prec@1 82.03 (76.45) Prec@5 95.31 (91.54) + train[2018-10-22-13:17:05] Epoch: [193][6000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.566 (2.883) Prec@1 79.69 (76.47) Prec@5 97.66 (91.55) + train[2018-10-22-13:18:52] Epoch: [193][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.850 (2.883) Prec@1 75.00 (76.47) Prec@5 92.97 (91.54) + train[2018-10-22-13:20:40] Epoch: [193][6400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.914 (2.883) Prec@1 71.09 (76.46) Prec@5 89.06 (91.54) + train[2018-10-22-13:22:24] Epoch: [193][6600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.872 (2.884) Prec@1 79.69 (76.46) Prec@5 92.19 (91.54) + train[2018-10-22-13:24:10] Epoch: [193][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.925 (2.884) Prec@1 72.66 (76.46) Prec@5 92.19 (91.54) + train[2018-10-22-13:25:55] Epoch: [193][7000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.645 (2.884) Prec@1 82.81 (76.46) Prec@5 91.41 (91.54) + train[2018-10-22-13:27:40] Epoch: [193][7200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.352 (2.884) Prec@1 85.16 (76.47) Prec@5 96.88 (91.54) + train[2018-10-22-13:29:24] Epoch: [193][7400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.834 (2.884) Prec@1 78.91 (76.46) Prec@5 91.41 (91.54) + train[2018-10-22-13:31:10] Epoch: [193][7600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.788 (2.884) Prec@1 78.91 (76.45) Prec@5 93.75 (91.54) + train[2018-10-22-13:32:55] Epoch: [193][7800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.958 (2.884) Prec@1 77.34 (76.45) Prec@5 89.06 (91.54) + train[2018-10-22-13:34:39] Epoch: [193][8000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.845 (2.884) Prec@1 76.56 (76.46) Prec@5 92.19 (91.54) + train[2018-10-22-13:36:25] Epoch: [193][8200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.948 (2.884) Prec@1 78.12 (76.45) Prec@5 90.62 (91.54) + train[2018-10-22-13:38:12] Epoch: [193][8400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.868 (2.884) Prec@1 76.56 (76.46) Prec@5 91.41 (91.53) + train[2018-10-22-13:39:58] Epoch: [193][8600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.151 (2.884) Prec@1 71.88 (76.45) Prec@5 89.06 (91.53) + train[2018-10-22-13:41:45] Epoch: [193][8800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.873 (2.884) Prec@1 81.25 (76.44) Prec@5 93.75 (91.53) + train[2018-10-22-13:43:32] Epoch: [193][9000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.737 (2.885) Prec@1 80.47 (76.44) Prec@5 92.97 (91.53) + train[2018-10-22-13:45:19] Epoch: [193][9200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.008 (2.884) Prec@1 72.66 (76.44) Prec@5 91.41 (91.53) + train[2018-10-22-13:47:06] Epoch: [193][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.775 (2.885) Prec@1 78.91 (76.43) Prec@5 91.41 (91.52) + train[2018-10-22-13:48:51] Epoch: [193][9600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.759 (2.885) Prec@1 80.47 (76.43) Prec@5 94.53 (91.53) + train[2018-10-22-13:50:37] Epoch: [193][9800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.433 (2.885) Prec@1 67.19 (76.41) Prec@5 82.03 (91.52) + train[2018-10-22-13:52:24] Epoch: [193][10000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.045 (2.885) Prec@1 72.66 (76.41) Prec@5 88.28 (91.52) + train[2018-10-22-13:52:29] Epoch: [193][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 4.409 (2.885) Prec@1 66.67 (76.41) Prec@5 66.67 (91.52) +[2018-10-22-13:52:29] **train** Prec@1 76.41 Prec@5 91.52 Error@1 23.59 Error@5 8.48 Loss:2.885 + test [2018-10-22-13:52:33] Epoch: [193][000/391] Time 4.04 (4.04) Data 3.90 (3.90) Loss 0.531 (0.531) Prec@1 92.19 (92.19) Prec@5 99.22 (99.22) + test [2018-10-22-13:52:59] Epoch: [193][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.248 (0.995) Prec@1 64.06 (77.40) Prec@5 90.62 (93.61) + test [2018-10-22-13:53:24] Epoch: [193][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.159 (1.162) Prec@1 48.75 (73.80) Prec@5 85.00 (91.44) +[2018-10-22-13:53:24] **test** Prec@1 73.80 Prec@5 91.44 Error@1 26.20 Error@5 8.56 Loss:1.162 +----> Best Accuracy : Acc@1=73.92, Acc@5=91.51, Error@1=26.08, Error@5=8.49 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-22-13:53:24] [Epoch=194/250] [Need: 82:59:07] LR=0.0003 ~ 0.0003, Batch=128 + train[2018-10-22-13:53:29] Epoch: [194][000/10010] Time 5.05 (5.05) Data 4.48 (4.48) Loss 2.976 (2.976) Prec@1 75.00 (75.00) Prec@5 88.28 (88.28) + train[2018-10-22-13:55:15] Epoch: [194][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 2.964 (2.857) Prec@1 72.66 (77.05) Prec@5 92.97 (92.01) + train[2018-10-22-13:57:00] Epoch: [194][400/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.654 (2.877) Prec@1 81.25 (76.69) Prec@5 92.97 (91.78) + train[2018-10-22-13:58:44] Epoch: [194][600/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.861 (2.877) Prec@1 75.00 (76.67) Prec@5 91.41 (91.72) + train[2018-10-22-14:00:28] Epoch: [194][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.762 (2.876) Prec@1 78.12 (76.66) Prec@5 93.75 (91.71) + train[2018-10-22-14:02:14] Epoch: [194][1000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.560 (2.878) Prec@1 79.69 (76.59) Prec@5 96.09 (91.68) + train[2018-10-22-14:03:59] Epoch: [194][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.926 (2.877) Prec@1 73.44 (76.62) Prec@5 95.31 (91.69) + train[2018-10-22-14:05:45] Epoch: [194][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.668 (2.876) Prec@1 80.47 (76.60) Prec@5 92.97 (91.67) + train[2018-10-22-14:07:30] Epoch: [194][1600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.594 (2.875) Prec@1 83.59 (76.60) Prec@5 94.53 (91.68) + train[2018-10-22-14:09:16] Epoch: [194][1800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.922 (2.878) Prec@1 78.12 (76.56) Prec@5 90.62 (91.67) + train[2018-10-22-14:11:02] Epoch: [194][2000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.164 (2.875) Prec@1 71.09 (76.61) Prec@5 89.06 (91.69) + train[2018-10-22-14:12:47] Epoch: [194][2200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.820 (2.876) Prec@1 76.56 (76.60) Prec@5 91.41 (91.67) + train[2018-10-22-14:14:32] Epoch: [194][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.969 (2.877) Prec@1 75.78 (76.59) Prec@5 92.19 (91.66) + train[2018-10-22-14:16:17] Epoch: [194][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.558 (2.877) Prec@1 82.03 (76.59) Prec@5 95.31 (91.66) + train[2018-10-22-14:18:03] Epoch: [194][2800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.628 (2.877) Prec@1 81.25 (76.60) Prec@5 94.53 (91.65) + train[2018-10-22-14:19:48] Epoch: [194][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.681 (2.878) Prec@1 78.91 (76.58) Prec@5 96.09 (91.65) + train[2018-10-22-14:21:33] Epoch: [194][3200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.086 (2.878) Prec@1 73.44 (76.59) Prec@5 89.06 (91.65) + train[2018-10-22-14:23:18] Epoch: [194][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.646 (2.879) Prec@1 80.47 (76.54) Prec@5 94.53 (91.65) + train[2018-10-22-14:25:03] Epoch: [194][3600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.122 (2.880) Prec@1 76.56 (76.52) Prec@5 85.94 (91.63) + train[2018-10-22-14:26:47] Epoch: [194][3800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.808 (2.880) Prec@1 75.78 (76.52) Prec@5 90.62 (91.63) + train[2018-10-22-14:28:32] Epoch: [194][4000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.982 (2.879) Prec@1 75.78 (76.54) Prec@5 89.84 (91.64) + train[2018-10-22-14:30:17] Epoch: [194][4200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.961 (2.878) Prec@1 71.09 (76.54) Prec@5 92.97 (91.65) + train[2018-10-22-14:32:03] Epoch: [194][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.897 (2.879) Prec@1 72.66 (76.53) Prec@5 94.53 (91.65) + train[2018-10-22-14:33:49] Epoch: [194][4600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.996 (2.878) Prec@1 77.34 (76.55) Prec@5 90.62 (91.66) + train[2018-10-22-14:35:34] Epoch: [194][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.828 (2.879) Prec@1 75.78 (76.54) Prec@5 93.75 (91.65) + train[2018-10-22-14:37:19] Epoch: [194][5000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.701 (2.878) Prec@1 76.56 (76.56) Prec@5 93.75 (91.65) + train[2018-10-22-14:39:04] Epoch: [194][5200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.111 (2.878) Prec@1 74.22 (76.56) Prec@5 89.84 (91.65) + train[2018-10-22-14:40:49] Epoch: [194][5400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.532 (2.878) Prec@1 67.19 (76.56) Prec@5 83.59 (91.65) + train[2018-10-22-14:42:34] Epoch: [194][5600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.878 (2.878) Prec@1 76.56 (76.56) Prec@5 91.41 (91.65) + train[2018-10-22-14:44:19] Epoch: [194][5800/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.014 (2.879) Prec@1 74.22 (76.55) Prec@5 89.06 (91.64) + train[2018-10-22-14:46:05] Epoch: [194][6000/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.890 (2.878) Prec@1 74.22 (76.55) Prec@5 90.62 (91.64) + train[2018-10-22-14:47:50] Epoch: [194][6200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.639 (2.878) Prec@1 82.03 (76.55) Prec@5 93.75 (91.64) + train[2018-10-22-14:49:35] Epoch: [194][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.766 (2.878) Prec@1 78.12 (76.55) Prec@5 94.53 (91.64) + train[2018-10-22-14:51:19] Epoch: [194][6600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.702 (2.878) Prec@1 77.34 (76.56) Prec@5 92.19 (91.63) + train[2018-10-22-14:53:03] Epoch: [194][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.949 (2.879) Prec@1 80.47 (76.55) Prec@5 90.62 (91.62) + train[2018-10-22-14:54:50] Epoch: [194][7000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.945 (2.879) Prec@1 75.00 (76.55) Prec@5 90.62 (91.62) + train[2018-10-22-14:56:37] Epoch: [194][7200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.721 (2.879) Prec@1 79.69 (76.54) Prec@5 93.75 (91.61) + train[2018-10-22-14:58:23] Epoch: [194][7400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.668 (2.879) Prec@1 81.25 (76.54) Prec@5 95.31 (91.62) + train[2018-10-22-15:00:10] Epoch: [194][7600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.667 (2.879) Prec@1 81.25 (76.54) Prec@5 92.97 (91.62) + train[2018-10-22-15:01:57] Epoch: [194][7800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.027 (2.879) Prec@1 73.44 (76.53) Prec@5 90.62 (91.61) + train[2018-10-22-15:03:43] Epoch: [194][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.893 (2.879) Prec@1 74.22 (76.52) Prec@5 92.97 (91.62) + train[2018-10-22-15:05:31] Epoch: [194][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.027 (2.879) Prec@1 70.31 (76.52) Prec@5 92.97 (91.62) + train[2018-10-22-15:07:16] Epoch: [194][8400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.833 (2.879) Prec@1 75.78 (76.53) Prec@5 92.97 (91.62) + train[2018-10-22-15:09:04] Epoch: [194][8600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.358 (2.879) Prec@1 68.75 (76.52) Prec@5 84.38 (91.62) + train[2018-10-22-15:10:51] Epoch: [194][8800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.868 (2.879) Prec@1 78.12 (76.52) Prec@5 91.41 (91.61) + train[2018-10-22-15:12:38] Epoch: [194][9000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.161 (2.879) Prec@1 74.22 (76.52) Prec@5 86.72 (91.61) + train[2018-10-22-15:14:25] Epoch: [194][9200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.017 (2.879) Prec@1 68.75 (76.51) Prec@5 91.41 (91.61) + train[2018-10-22-15:16:11] Epoch: [194][9400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.002 (2.879) Prec@1 71.09 (76.52) Prec@5 89.06 (91.61) + train[2018-10-22-15:17:57] Epoch: [194][9600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.723 (2.879) Prec@1 79.69 (76.52) Prec@5 92.97 (91.61) + train[2018-10-22-15:19:43] Epoch: [194][9800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.884 (2.880) Prec@1 73.44 (76.52) Prec@5 92.97 (91.61) + train[2018-10-22-15:21:28] Epoch: [194][10000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.968 (2.879) Prec@1 79.69 (76.52) Prec@5 90.62 (91.61) + train[2018-10-22-15:21:32] Epoch: [194][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 3.405 (2.879) Prec@1 60.00 (76.52) Prec@5 86.67 (91.61) +[2018-10-22-15:21:32] **train** Prec@1 76.52 Prec@5 91.61 Error@1 23.48 Error@5 8.39 Loss:2.879 + test [2018-10-22-15:21:37] Epoch: [194][000/391] Time 4.02 (4.02) Data 3.89 (3.89) Loss 0.530 (0.530) Prec@1 92.19 (92.19) Prec@5 99.22 (99.22) + test [2018-10-22-15:22:03] Epoch: [194][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.196 (0.986) Prec@1 66.41 (77.34) Prec@5 91.41 (93.58) + test [2018-10-22-15:22:28] Epoch: [194][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.166 (1.154) Prec@1 48.75 (73.75) Prec@5 82.50 (91.37) +[2018-10-22-15:22:28] **test** Prec@1 73.75 Prec@5 91.37 Error@1 26.25 Error@5 8.63 Loss:1.154 +----> Best Accuracy : Acc@1=73.92, Acc@5=91.51, Error@1=26.08, Error@5=8.49 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-22-15:22:28] [Epoch=195/250] [Need: 81:38:17] LR=0.0003 ~ 0.0003, Batch=128 + train[2018-10-22-15:22:33] Epoch: [195][000/10010] Time 4.67 (4.67) Data 4.08 (4.08) Loss 2.956 (2.956) Prec@1 75.78 (75.78) Prec@5 87.50 (87.50) + train[2018-10-22-15:24:17] Epoch: [195][200/10010] Time 0.51 (0.54) Data 0.00 (0.02) Loss 2.705 (2.851) Prec@1 80.47 (77.34) Prec@5 93.75 (91.81) + train[2018-10-22-15:26:02] Epoch: [195][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.014 (2.863) Prec@1 75.00 (76.93) Prec@5 88.28 (91.76) + train[2018-10-22-15:27:46] Epoch: [195][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.262 (2.872) Prec@1 69.53 (76.79) Prec@5 84.38 (91.65) + train[2018-10-22-15:29:30] Epoch: [195][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.902 (2.877) Prec@1 74.22 (76.66) Prec@5 93.75 (91.57) + train[2018-10-22-15:31:16] Epoch: [195][1000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.865 (2.877) Prec@1 74.22 (76.61) Prec@5 92.19 (91.57) + train[2018-10-22-15:33:00] Epoch: [195][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.773 (2.879) Prec@1 78.91 (76.56) Prec@5 92.19 (91.54) + train[2018-10-22-15:34:46] Epoch: [195][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.929 (2.879) Prec@1 76.56 (76.60) Prec@5 89.06 (91.57) + train[2018-10-22-15:36:31] Epoch: [195][1600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.942 (2.881) Prec@1 75.00 (76.55) Prec@5 90.62 (91.56) + train[2018-10-22-15:38:15] Epoch: [195][1800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.614 (2.881) Prec@1 77.34 (76.56) Prec@5 92.97 (91.54) + train[2018-10-22-15:39:59] Epoch: [195][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.640 (2.881) Prec@1 78.91 (76.57) Prec@5 94.53 (91.54) + train[2018-10-22-15:41:45] Epoch: [195][2200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.886 (2.882) Prec@1 73.44 (76.55) Prec@5 92.97 (91.52) + train[2018-10-22-15:43:31] Epoch: [195][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.912 (2.881) Prec@1 73.44 (76.56) Prec@5 94.53 (91.54) + train[2018-10-22-15:45:16] Epoch: [195][2600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.002 (2.882) Prec@1 75.00 (76.55) Prec@5 89.84 (91.52) + train[2018-10-22-15:47:01] Epoch: [195][2800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.981 (2.881) Prec@1 75.00 (76.55) Prec@5 89.06 (91.54) + train[2018-10-22-15:48:47] Epoch: [195][3000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.958 (2.881) Prec@1 75.78 (76.55) Prec@5 89.84 (91.55) + train[2018-10-22-15:50:32] Epoch: [195][3200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.960 (2.881) Prec@1 75.00 (76.56) Prec@5 90.62 (91.55) + train[2018-10-22-15:52:17] Epoch: [195][3400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.805 (2.881) Prec@1 76.56 (76.57) Prec@5 92.19 (91.56) + train[2018-10-22-15:54:01] Epoch: [195][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.901 (2.881) Prec@1 75.00 (76.57) Prec@5 90.62 (91.56) + train[2018-10-22-15:55:48] Epoch: [195][3800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.648 (2.881) Prec@1 82.03 (76.55) Prec@5 93.75 (91.56) + train[2018-10-22-15:57:35] Epoch: [195][4000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.614 (2.881) Prec@1 82.03 (76.54) Prec@5 93.75 (91.55) + train[2018-10-22-15:59:22] Epoch: [195][4200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.708 (2.881) Prec@1 78.91 (76.54) Prec@5 92.97 (91.55) + train[2018-10-22-16:01:09] Epoch: [195][4400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.960 (2.881) Prec@1 74.22 (76.53) Prec@5 93.75 (91.56) + train[2018-10-22-16:02:55] Epoch: [195][4600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.108 (2.880) Prec@1 71.09 (76.55) Prec@5 88.28 (91.57) + train[2018-10-22-16:04:41] Epoch: [195][4800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.856 (2.880) Prec@1 75.00 (76.55) Prec@5 92.97 (91.58) + train[2018-10-22-16:06:27] Epoch: [195][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.775 (2.879) Prec@1 79.69 (76.55) Prec@5 90.62 (91.58) + train[2018-10-22-16:08:13] Epoch: [195][5200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.086 (2.880) Prec@1 70.31 (76.53) Prec@5 88.28 (91.58) + train[2018-10-22-16:09:59] Epoch: [195][5400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.144 (2.880) Prec@1 70.31 (76.54) Prec@5 88.28 (91.58) + train[2018-10-22-16:11:47] Epoch: [195][5600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.661 (2.879) Prec@1 80.47 (76.54) Prec@5 93.75 (91.58) + train[2018-10-22-16:13:35] Epoch: [195][5800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.989 (2.879) Prec@1 73.44 (76.54) Prec@5 92.19 (91.59) + train[2018-10-22-16:15:21] Epoch: [195][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.769 (2.880) Prec@1 78.12 (76.54) Prec@5 94.53 (91.59) + train[2018-10-22-16:17:09] Epoch: [195][6200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.042 (2.879) Prec@1 67.97 (76.54) Prec@5 90.62 (91.59) + train[2018-10-22-16:18:56] Epoch: [195][6400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.141 (2.880) Prec@1 75.78 (76.52) Prec@5 87.50 (91.59) + train[2018-10-22-16:20:44] Epoch: [195][6600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.633 (2.880) Prec@1 82.81 (76.52) Prec@5 95.31 (91.60) + train[2018-10-22-16:22:31] Epoch: [195][6800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.691 (2.880) Prec@1 78.12 (76.52) Prec@5 91.41 (91.59) + train[2018-10-22-16:24:19] Epoch: [195][7000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.852 (2.880) Prec@1 75.00 (76.52) Prec@5 93.75 (91.59) + train[2018-10-22-16:26:05] Epoch: [195][7200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.147 (2.880) Prec@1 72.66 (76.52) Prec@5 88.28 (91.58) + train[2018-10-22-16:27:52] Epoch: [195][7400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.673 (2.880) Prec@1 82.03 (76.51) Prec@5 92.19 (91.58) + train[2018-10-22-16:29:38] Epoch: [195][7600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.900 (2.881) Prec@1 78.91 (76.50) Prec@5 91.41 (91.57) + train[2018-10-22-16:31:25] Epoch: [195][7800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.642 (2.881) Prec@1 78.91 (76.50) Prec@5 92.97 (91.57) + train[2018-10-22-16:33:13] Epoch: [195][8000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.987 (2.881) Prec@1 74.22 (76.49) Prec@5 89.84 (91.57) + train[2018-10-22-16:35:00] Epoch: [195][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.605 (2.881) Prec@1 82.03 (76.49) Prec@5 93.75 (91.57) + train[2018-10-22-16:36:47] Epoch: [195][8400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.835 (2.881) Prec@1 75.00 (76.48) Prec@5 91.41 (91.56) + train[2018-10-22-16:38:34] Epoch: [195][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.022 (2.881) Prec@1 74.22 (76.48) Prec@5 87.50 (91.56) + train[2018-10-22-16:40:20] Epoch: [195][8800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.992 (2.881) Prec@1 70.31 (76.48) Prec@5 89.84 (91.56) + train[2018-10-22-16:42:07] Epoch: [195][9000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.917 (2.881) Prec@1 77.34 (76.49) Prec@5 90.62 (91.56) + train[2018-10-22-16:43:54] Epoch: [195][9200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.453 (2.881) Prec@1 87.50 (76.49) Prec@5 92.97 (91.57) + train[2018-10-22-16:45:41] Epoch: [195][9400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.997 (2.881) Prec@1 74.22 (76.48) Prec@5 89.84 (91.56) + train[2018-10-22-16:47:27] Epoch: [195][9600/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.757 (2.881) Prec@1 82.81 (76.47) Prec@5 92.19 (91.56) + train[2018-10-22-16:49:13] Epoch: [195][9800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.782 (2.881) Prec@1 79.69 (76.47) Prec@5 92.97 (91.56) + train[2018-10-22-16:50:58] Epoch: [195][10000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.449 (2.882) Prec@1 86.72 (76.47) Prec@5 95.31 (91.55) + train[2018-10-22-16:51:02] Epoch: [195][10009/10010] Time 0.14 (0.53) Data 0.00 (0.00) Loss 2.862 (2.882) Prec@1 73.33 (76.47) Prec@5 93.33 (91.55) +[2018-10-22-16:51:02] **train** Prec@1 76.47 Prec@5 91.55 Error@1 23.53 Error@5 8.45 Loss:2.882 + test [2018-10-22-16:51:06] Epoch: [195][000/391] Time 4.15 (4.15) Data 4.01 (4.01) Loss 0.566 (0.566) Prec@1 92.97 (92.97) Prec@5 99.22 (99.22) + test [2018-10-22-16:51:32] Epoch: [195][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.151 (0.987) Prec@1 70.31 (77.43) Prec@5 92.97 (93.74) + test [2018-10-22-16:51:57] Epoch: [195][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.146 (1.154) Prec@1 45.00 (73.85) Prec@5 82.50 (91.45) +[2018-10-22-16:51:57] **test** Prec@1 73.85 Prec@5 91.45 Error@1 26.15 Error@5 8.55 Loss:1.154 +----> Best Accuracy : Acc@1=73.92, Acc@5=91.51, Error@1=26.08, Error@5=8.49 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-22-16:51:58] [Epoch=196/250] [Need: 80:32:42] LR=0.0003 ~ 0.0003, Batch=128 + train[2018-10-22-16:52:03] Epoch: [196][000/10010] Time 5.37 (5.37) Data 4.76 (4.76) Loss 3.010 (3.010) Prec@1 74.22 (74.22) Prec@5 91.41 (91.41) + train[2018-10-22-16:53:48] Epoch: [196][200/10010] Time 0.54 (0.55) Data 0.00 (0.02) Loss 2.945 (2.911) Prec@1 70.31 (75.73) Prec@5 91.41 (91.32) + train[2018-10-22-16:55:34] Epoch: [196][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.910 (2.893) Prec@1 73.44 (76.03) Prec@5 90.62 (91.53) + train[2018-10-22-16:57:19] Epoch: [196][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.776 (2.887) Prec@1 77.34 (76.20) Prec@5 96.09 (91.63) + train[2018-10-22-16:59:06] Epoch: [196][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.904 (2.887) Prec@1 76.56 (76.20) Prec@5 91.41 (91.64) + train[2018-10-22-17:00:51] Epoch: [196][1000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.825 (2.886) Prec@1 76.56 (76.22) Prec@5 92.97 (91.62) + train[2018-10-22-17:02:36] Epoch: [196][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.519 (2.883) Prec@1 82.03 (76.30) Prec@5 96.09 (91.67) + train[2018-10-22-17:04:22] Epoch: [196][1400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.650 (2.881) Prec@1 80.47 (76.35) Prec@5 95.31 (91.68) + train[2018-10-22-17:06:08] Epoch: [196][1600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.058 (2.881) Prec@1 72.66 (76.39) Prec@5 89.06 (91.66) + train[2018-10-22-17:07:53] Epoch: [196][1800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.974 (2.881) Prec@1 75.78 (76.40) Prec@5 88.28 (91.65) + train[2018-10-22-17:09:37] Epoch: [196][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.635 (2.881) Prec@1 81.25 (76.41) Prec@5 92.97 (91.62) + train[2018-10-22-17:11:22] Epoch: [196][2200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.682 (2.879) Prec@1 83.59 (76.48) Prec@5 92.97 (91.64) + train[2018-10-22-17:13:08] Epoch: [196][2400/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.052 (2.879) Prec@1 72.66 (76.51) Prec@5 88.28 (91.64) + train[2018-10-22-17:14:55] Epoch: [196][2600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.860 (2.877) Prec@1 75.78 (76.55) Prec@5 91.41 (91.65) + train[2018-10-22-17:16:42] Epoch: [196][2800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.238 (2.876) Prec@1 71.88 (76.56) Prec@5 85.94 (91.66) + train[2018-10-22-17:18:27] Epoch: [196][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.704 (2.877) Prec@1 79.69 (76.53) Prec@5 94.53 (91.64) + train[2018-10-22-17:20:13] Epoch: [196][3200/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.648 (2.877) Prec@1 82.81 (76.51) Prec@5 93.75 (91.64) + train[2018-10-22-17:21:59] Epoch: [196][3400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.805 (2.876) Prec@1 82.03 (76.52) Prec@5 91.41 (91.64) + train[2018-10-22-17:23:44] Epoch: [196][3600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.702 (2.875) Prec@1 80.47 (76.53) Prec@5 92.19 (91.65) + train[2018-10-22-17:25:31] Epoch: [196][3800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.237 (2.876) Prec@1 71.88 (76.55) Prec@5 86.72 (91.63) + train[2018-10-22-17:27:17] Epoch: [196][4000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.590 (2.876) Prec@1 81.25 (76.55) Prec@5 94.53 (91.63) + train[2018-10-22-17:29:06] Epoch: [196][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.878 (2.876) Prec@1 78.91 (76.57) Prec@5 94.53 (91.64) + train[2018-10-22-17:30:54] Epoch: [196][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.909 (2.876) Prec@1 76.56 (76.56) Prec@5 94.53 (91.63) + train[2018-10-22-17:32:40] Epoch: [196][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.256 (2.876) Prec@1 69.53 (76.56) Prec@5 86.72 (91.62) + train[2018-10-22-17:34:25] Epoch: [196][4800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.088 (2.877) Prec@1 73.44 (76.57) Prec@5 89.06 (91.61) + train[2018-10-22-17:36:10] Epoch: [196][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.990 (2.876) Prec@1 76.56 (76.57) Prec@5 90.62 (91.63) + train[2018-10-22-17:37:55] Epoch: [196][5200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.150 (2.876) Prec@1 70.31 (76.59) Prec@5 87.50 (91.62) + train[2018-10-22-17:39:42] Epoch: [196][5400/10010] Time 0.69 (0.53) Data 0.00 (0.00) Loss 2.638 (2.876) Prec@1 78.12 (76.58) Prec@5 96.09 (91.62) + train[2018-10-22-17:41:27] Epoch: [196][5600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.697 (2.876) Prec@1 81.25 (76.57) Prec@5 89.84 (91.62) + train[2018-10-22-17:43:13] Epoch: [196][5800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.785 (2.876) Prec@1 81.25 (76.57) Prec@5 92.97 (91.62) + train[2018-10-22-17:44:58] Epoch: [196][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.021 (2.877) Prec@1 75.78 (76.58) Prec@5 90.62 (91.61) + train[2018-10-22-17:46:44] Epoch: [196][6200/10010] Time 0.66 (0.53) Data 0.00 (0.00) Loss 2.895 (2.877) Prec@1 77.34 (76.56) Prec@5 91.41 (91.60) + train[2018-10-22-17:48:28] Epoch: [196][6400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.902 (2.877) Prec@1 75.00 (76.57) Prec@5 89.84 (91.61) + train[2018-10-22-17:50:12] Epoch: [196][6600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.072 (2.878) Prec@1 69.53 (76.55) Prec@5 89.84 (91.59) + train[2018-10-22-17:51:58] Epoch: [196][6800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.842 (2.879) Prec@1 75.00 (76.53) Prec@5 91.41 (91.58) + train[2018-10-22-17:53:46] Epoch: [196][7000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.055 (2.879) Prec@1 72.66 (76.54) Prec@5 89.06 (91.58) + train[2018-10-22-17:55:32] Epoch: [196][7200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.925 (2.880) Prec@1 78.12 (76.52) Prec@5 92.19 (91.58) + train[2018-10-22-17:57:17] Epoch: [196][7400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.701 (2.879) Prec@1 82.81 (76.53) Prec@5 93.75 (91.59) + train[2018-10-22-17:59:01] Epoch: [196][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.042 (2.879) Prec@1 75.00 (76.53) Prec@5 85.94 (91.59) + train[2018-10-22-18:00:46] Epoch: [196][7800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.780 (2.879) Prec@1 77.34 (76.52) Prec@5 90.62 (91.59) + train[2018-10-22-18:02:33] Epoch: [196][8000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.018 (2.880) Prec@1 75.00 (76.52) Prec@5 89.06 (91.58) + train[2018-10-22-18:04:20] Epoch: [196][8200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.973 (2.880) Prec@1 74.22 (76.51) Prec@5 90.62 (91.57) + train[2018-10-22-18:06:06] Epoch: [196][8400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.027 (2.880) Prec@1 76.56 (76.51) Prec@5 89.84 (91.57) + train[2018-10-22-18:07:52] Epoch: [196][8600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.016 (2.881) Prec@1 77.34 (76.51) Prec@5 88.28 (91.57) + train[2018-10-22-18:09:36] Epoch: [196][8800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.001 (2.881) Prec@1 77.34 (76.51) Prec@5 87.50 (91.57) + train[2018-10-22-18:11:22] Epoch: [196][9000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.872 (2.881) Prec@1 71.88 (76.52) Prec@5 92.97 (91.57) + train[2018-10-22-18:13:06] Epoch: [196][9200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.842 (2.880) Prec@1 76.56 (76.52) Prec@5 91.41 (91.57) + train[2018-10-22-18:14:52] Epoch: [196][9400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.688 (2.880) Prec@1 78.91 (76.52) Prec@5 93.75 (91.57) + train[2018-10-22-18:16:37] Epoch: [196][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.905 (2.880) Prec@1 78.12 (76.52) Prec@5 89.84 (91.58) + train[2018-10-22-18:18:22] Epoch: [196][9800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.766 (2.880) Prec@1 77.34 (76.52) Prec@5 92.19 (91.57) + train[2018-10-22-18:20:06] Epoch: [196][10000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.749 (2.880) Prec@1 76.56 (76.52) Prec@5 92.19 (91.57) + train[2018-10-22-18:20:10] Epoch: [196][10009/10010] Time 0.14 (0.53) Data 0.00 (0.00) Loss 3.405 (2.880) Prec@1 60.00 (76.52) Prec@5 86.67 (91.57) +[2018-10-22-18:20:10] **train** Prec@1 76.52 Prec@5 91.57 Error@1 23.48 Error@5 8.43 Loss:2.880 + test [2018-10-22-18:20:14] Epoch: [196][000/391] Time 4.13 (4.13) Data 3.99 (3.99) Loss 0.493 (0.493) Prec@1 93.75 (93.75) Prec@5 98.44 (98.44) + test [2018-10-22-18:20:41] Epoch: [196][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.163 (0.989) Prec@1 68.75 (77.48) Prec@5 92.19 (93.61) + test [2018-10-22-18:21:05] Epoch: [196][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.095 (1.158) Prec@1 48.75 (73.82) Prec@5 82.50 (91.35) +[2018-10-22-18:21:05] **test** Prec@1 73.82 Prec@5 91.35 Error@1 26.18 Error@5 8.65 Loss:1.158 +----> Best Accuracy : Acc@1=73.92, Acc@5=91.51, Error@1=26.08, Error@5=8.49 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-22-18:21:05] [Epoch=197/250] [Need: 78:43:54] LR=0.0002 ~ 0.0002, Batch=128 + train[2018-10-22-18:21:10] Epoch: [197][000/10010] Time 4.79 (4.79) Data 4.13 (4.13) Loss 2.822 (2.822) Prec@1 74.22 (74.22) Prec@5 92.19 (92.19) + train[2018-10-22-18:22:56] Epoch: [197][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 2.652 (2.871) Prec@1 80.47 (76.62) Prec@5 93.75 (91.60) + train[2018-10-22-18:24:40] Epoch: [197][400/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 2.819 (2.888) Prec@1 75.78 (76.32) Prec@5 92.19 (91.45) + train[2018-10-22-18:26:25] Epoch: [197][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.857 (2.891) Prec@1 75.78 (76.24) Prec@5 90.62 (91.45) + train[2018-10-22-18:28:10] Epoch: [197][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.942 (2.887) Prec@1 76.56 (76.35) Prec@5 90.62 (91.46) + train[2018-10-22-18:29:55] Epoch: [197][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.898 (2.882) Prec@1 75.78 (76.45) Prec@5 91.41 (91.52) + train[2018-10-22-18:31:40] Epoch: [197][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.803 (2.880) Prec@1 78.91 (76.57) Prec@5 94.53 (91.53) + train[2018-10-22-18:33:24] Epoch: [197][1400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.704 (2.879) Prec@1 80.47 (76.57) Prec@5 93.75 (91.53) + train[2018-10-22-18:35:09] Epoch: [197][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.784 (2.878) Prec@1 75.78 (76.58) Prec@5 92.19 (91.54) + train[2018-10-22-18:36:54] Epoch: [197][1800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.611 (2.879) Prec@1 82.81 (76.56) Prec@5 92.97 (91.54) + train[2018-10-22-18:38:39] Epoch: [197][2000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.094 (2.879) Prec@1 71.09 (76.53) Prec@5 91.41 (91.55) + train[2018-10-22-18:40:24] Epoch: [197][2200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.854 (2.879) Prec@1 78.12 (76.54) Prec@5 92.97 (91.56) + train[2018-10-22-18:42:09] Epoch: [197][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.083 (2.878) Prec@1 71.09 (76.56) Prec@5 88.28 (91.57) + train[2018-10-22-18:43:55] Epoch: [197][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.896 (2.878) Prec@1 79.69 (76.58) Prec@5 91.41 (91.57) + train[2018-10-22-18:45:39] Epoch: [197][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.151 (2.879) Prec@1 71.88 (76.55) Prec@5 86.72 (91.56) + train[2018-10-22-18:47:27] Epoch: [197][3000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.978 (2.879) Prec@1 74.22 (76.54) Prec@5 89.06 (91.57) + train[2018-10-22-18:49:13] Epoch: [197][3200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.879 (2.879) Prec@1 72.66 (76.53) Prec@5 92.97 (91.57) + train[2018-10-22-18:50:59] Epoch: [197][3400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.718 (2.880) Prec@1 82.03 (76.52) Prec@5 94.53 (91.56) + train[2018-10-22-18:52:44] Epoch: [197][3600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.767 (2.880) Prec@1 77.34 (76.53) Prec@5 91.41 (91.55) + train[2018-10-22-18:54:31] Epoch: [197][3800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.821 (2.879) Prec@1 72.66 (76.53) Prec@5 91.41 (91.55) + train[2018-10-22-18:56:16] Epoch: [197][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.784 (2.878) Prec@1 82.81 (76.55) Prec@5 93.75 (91.57) + train[2018-10-22-18:58:00] Epoch: [197][4200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.991 (2.878) Prec@1 77.34 (76.55) Prec@5 88.28 (91.57) + train[2018-10-22-18:59:45] Epoch: [197][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.057 (2.879) Prec@1 74.22 (76.54) Prec@5 88.28 (91.57) + train[2018-10-22-19:01:30] Epoch: [197][4600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.975 (2.879) Prec@1 75.78 (76.53) Prec@5 92.97 (91.57) + train[2018-10-22-19:03:16] Epoch: [197][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.026 (2.880) Prec@1 74.22 (76.52) Prec@5 91.41 (91.56) + train[2018-10-22-19:05:00] Epoch: [197][5000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.817 (2.880) Prec@1 80.47 (76.51) Prec@5 89.06 (91.56) + train[2018-10-22-19:06:44] Epoch: [197][5200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.146 (2.881) Prec@1 77.34 (76.49) Prec@5 88.28 (91.56) + train[2018-10-22-19:08:31] Epoch: [197][5400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.976 (2.881) Prec@1 72.66 (76.50) Prec@5 90.62 (91.56) + train[2018-10-22-19:10:17] Epoch: [197][5600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.832 (2.881) Prec@1 78.12 (76.48) Prec@5 93.75 (91.56) + train[2018-10-22-19:12:02] Epoch: [197][5800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.825 (2.881) Prec@1 76.56 (76.48) Prec@5 92.19 (91.56) + train[2018-10-22-19:13:49] Epoch: [197][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.870 (2.882) Prec@1 78.91 (76.47) Prec@5 93.75 (91.56) + train[2018-10-22-19:15:36] Epoch: [197][6200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.801 (2.882) Prec@1 80.47 (76.46) Prec@5 92.19 (91.55) + train[2018-10-22-19:17:24] Epoch: [197][6400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.952 (2.882) Prec@1 77.34 (76.46) Prec@5 88.28 (91.55) + train[2018-10-22-19:19:10] Epoch: [197][6600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.664 (2.882) Prec@1 79.69 (76.47) Prec@5 92.19 (91.56) + train[2018-10-22-19:20:56] Epoch: [197][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.671 (2.882) Prec@1 79.69 (76.46) Prec@5 93.75 (91.56) + train[2018-10-22-19:22:41] Epoch: [197][7000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.820 (2.882) Prec@1 77.34 (76.46) Prec@5 93.75 (91.57) + train[2018-10-22-19:24:25] Epoch: [197][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.847 (2.881) Prec@1 70.31 (76.47) Prec@5 92.19 (91.56) + train[2018-10-22-19:26:10] Epoch: [197][7400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.866 (2.881) Prec@1 76.56 (76.49) Prec@5 91.41 (91.57) + train[2018-10-22-19:27:55] Epoch: [197][7600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.951 (2.881) Prec@1 74.22 (76.48) Prec@5 89.84 (91.56) + train[2018-10-22-19:29:40] Epoch: [197][7800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.880 (2.881) Prec@1 78.12 (76.47) Prec@5 92.19 (91.56) + train[2018-10-22-19:31:26] Epoch: [197][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.037 (2.882) Prec@1 75.78 (76.46) Prec@5 91.41 (91.56) + train[2018-10-22-19:33:10] Epoch: [197][8200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.785 (2.881) Prec@1 78.12 (76.48) Prec@5 94.53 (91.57) + train[2018-10-22-19:34:55] Epoch: [197][8400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.706 (2.881) Prec@1 80.47 (76.49) Prec@5 92.19 (91.57) + train[2018-10-22-19:36:41] Epoch: [197][8600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.988 (2.882) Prec@1 75.00 (76.48) Prec@5 90.62 (91.56) + train[2018-10-22-19:38:26] Epoch: [197][8800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.394 (2.882) Prec@1 68.75 (76.48) Prec@5 86.72 (91.57) + train[2018-10-22-19:40:11] Epoch: [197][9000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.598 (2.881) Prec@1 78.91 (76.49) Prec@5 96.09 (91.57) + train[2018-10-22-19:41:56] Epoch: [197][9200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.926 (2.881) Prec@1 74.22 (76.48) Prec@5 90.62 (91.57) + train[2018-10-22-19:43:41] Epoch: [197][9400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.138 (2.881) Prec@1 71.88 (76.49) Prec@5 90.62 (91.57) + train[2018-10-22-19:45:27] Epoch: [197][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.866 (2.881) Prec@1 80.47 (76.49) Prec@5 93.75 (91.58) + train[2018-10-22-19:47:14] Epoch: [197][9800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.748 (2.880) Prec@1 78.12 (76.50) Prec@5 92.97 (91.58) + train[2018-10-22-19:49:01] Epoch: [197][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.726 (2.880) Prec@1 78.12 (76.50) Prec@5 96.09 (91.59) + train[2018-10-22-19:49:06] Epoch: [197][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 4.371 (2.880) Prec@1 40.00 (76.50) Prec@5 73.33 (91.58) +[2018-10-22-19:49:06] **train** Prec@1 76.50 Prec@5 91.58 Error@1 23.50 Error@5 8.42 Loss:2.880 + test [2018-10-22-19:49:10] Epoch: [197][000/391] Time 4.32 (4.32) Data 4.19 (4.19) Loss 0.528 (0.528) Prec@1 92.97 (92.97) Prec@5 99.22 (99.22) + test [2018-10-22-19:49:37] Epoch: [197][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.255 (0.993) Prec@1 67.19 (77.49) Prec@5 92.19 (93.67) + test [2018-10-22-19:50:01] Epoch: [197][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.073 (1.163) Prec@1 48.75 (73.87) Prec@5 85.00 (91.41) +[2018-10-22-19:50:01] **test** Prec@1 73.87 Prec@5 91.41 Error@1 26.13 Error@5 8.59 Loss:1.163 +----> Best Accuracy : Acc@1=73.92, Acc@5=91.51, Error@1=26.08, Error@5=8.49 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-22-19:50:02] [Epoch=198/250] [Need: 77:04:38] LR=0.0002 ~ 0.0002, Batch=128 + train[2018-10-22-19:50:06] Epoch: [198][000/10010] Time 4.83 (4.83) Data 4.23 (4.23) Loss 2.884 (2.884) Prec@1 78.12 (78.12) Prec@5 89.06 (89.06) + train[2018-10-22-19:51:52] Epoch: [198][200/10010] Time 0.58 (0.55) Data 0.00 (0.02) Loss 2.948 (2.901) Prec@1 74.22 (75.96) Prec@5 92.19 (91.35) + train[2018-10-22-19:53:37] Epoch: [198][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.894 (2.897) Prec@1 77.34 (76.17) Prec@5 92.19 (91.39) + train[2018-10-22-19:55:23] Epoch: [198][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.615 (2.891) Prec@1 80.47 (76.40) Prec@5 92.97 (91.48) + train[2018-10-22-19:57:08] Epoch: [198][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.971 (2.891) Prec@1 77.34 (76.37) Prec@5 87.50 (91.45) + train[2018-10-22-19:58:53] Epoch: [198][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.266 (2.887) Prec@1 72.66 (76.43) Prec@5 87.50 (91.51) + train[2018-10-22-20:00:39] Epoch: [198][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.683 (2.884) Prec@1 83.59 (76.50) Prec@5 94.53 (91.51) + train[2018-10-22-20:02:24] Epoch: [198][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.874 (2.882) Prec@1 78.91 (76.54) Prec@5 90.62 (91.54) + train[2018-10-22-20:04:09] Epoch: [198][1600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.999 (2.882) Prec@1 75.78 (76.52) Prec@5 90.62 (91.54) + train[2018-10-22-20:05:54] Epoch: [198][1800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.979 (2.881) Prec@1 78.12 (76.53) Prec@5 87.50 (91.53) + train[2018-10-22-20:07:38] Epoch: [198][2000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.860 (2.882) Prec@1 80.47 (76.50) Prec@5 90.62 (91.52) + train[2018-10-22-20:09:23] Epoch: [198][2200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.827 (2.881) Prec@1 81.25 (76.51) Prec@5 90.62 (91.53) + train[2018-10-22-20:11:08] Epoch: [198][2400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.648 (2.880) Prec@1 79.69 (76.53) Prec@5 94.53 (91.57) + train[2018-10-22-20:12:52] Epoch: [198][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.957 (2.881) Prec@1 74.22 (76.50) Prec@5 90.62 (91.57) + train[2018-10-22-20:14:37] Epoch: [198][2800/10010] Time 0.62 (0.53) Data 0.00 (0.00) Loss 2.680 (2.878) Prec@1 78.91 (76.55) Prec@5 94.53 (91.61) + train[2018-10-22-20:16:23] Epoch: [198][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.881 (2.878) Prec@1 75.00 (76.54) Prec@5 92.97 (91.61) + train[2018-10-22-20:18:08] Epoch: [198][3200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.518 (2.878) Prec@1 85.94 (76.54) Prec@5 94.53 (91.62) + train[2018-10-22-20:19:54] Epoch: [198][3400/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.858 (2.879) Prec@1 72.66 (76.51) Prec@5 92.97 (91.61) + train[2018-10-22-20:21:40] Epoch: [198][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.769 (2.879) Prec@1 77.34 (76.53) Prec@5 93.75 (91.61) + train[2018-10-22-20:23:26] Epoch: [198][3800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.992 (2.880) Prec@1 77.34 (76.52) Prec@5 88.28 (91.59) + train[2018-10-22-20:25:11] Epoch: [198][4000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.947 (2.880) Prec@1 77.34 (76.50) Prec@5 90.62 (91.57) + train[2018-10-22-20:26:56] Epoch: [198][4200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.836 (2.881) Prec@1 78.91 (76.48) Prec@5 91.41 (91.56) + train[2018-10-22-20:28:41] Epoch: [198][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.667 (2.882) Prec@1 84.38 (76.48) Prec@5 92.19 (91.56) + train[2018-10-22-20:30:27] Epoch: [198][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.917 (2.882) Prec@1 74.22 (76.47) Prec@5 93.75 (91.55) + train[2018-10-22-20:32:12] Epoch: [198][4800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.077 (2.882) Prec@1 74.22 (76.46) Prec@5 87.50 (91.55) + train[2018-10-22-20:33:57] Epoch: [198][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.865 (2.882) Prec@1 78.91 (76.47) Prec@5 89.06 (91.56) + train[2018-10-22-20:35:42] Epoch: [198][5200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.078 (2.882) Prec@1 71.09 (76.47) Prec@5 92.97 (91.56) + train[2018-10-22-20:37:28] Epoch: [198][5400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.850 (2.882) Prec@1 77.34 (76.49) Prec@5 89.06 (91.57) + train[2018-10-22-20:39:15] Epoch: [198][5600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.901 (2.881) Prec@1 75.00 (76.49) Prec@5 92.97 (91.58) + train[2018-10-22-20:41:02] Epoch: [198][5800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.569 (2.881) Prec@1 85.16 (76.50) Prec@5 95.31 (91.58) + train[2018-10-22-20:42:47] Epoch: [198][6000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.830 (2.881) Prec@1 79.69 (76.49) Prec@5 92.97 (91.57) + train[2018-10-22-20:44:32] Epoch: [198][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.029 (2.881) Prec@1 72.66 (76.49) Prec@5 91.41 (91.58) + train[2018-10-22-20:46:17] Epoch: [198][6400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.989 (2.881) Prec@1 77.34 (76.50) Prec@5 90.62 (91.58) + train[2018-10-22-20:48:02] Epoch: [198][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.888 (2.880) Prec@1 77.34 (76.50) Prec@5 89.06 (91.58) + train[2018-10-22-20:49:49] Epoch: [198][6800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.045 (2.880) Prec@1 76.56 (76.51) Prec@5 89.06 (91.58) + train[2018-10-22-20:51:35] Epoch: [198][7000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.149 (2.880) Prec@1 71.88 (76.52) Prec@5 85.94 (91.58) + train[2018-10-22-20:53:19] Epoch: [198][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.036 (2.880) Prec@1 75.78 (76.52) Prec@5 88.28 (91.59) + train[2018-10-22-20:55:05] Epoch: [198][7400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.990 (2.880) Prec@1 75.00 (76.52) Prec@5 88.28 (91.58) + train[2018-10-22-20:56:51] Epoch: [198][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.822 (2.880) Prec@1 75.78 (76.53) Prec@5 91.41 (91.59) + train[2018-10-22-20:58:37] Epoch: [198][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.818 (2.880) Prec@1 78.12 (76.53) Prec@5 93.75 (91.58) + train[2018-10-22-21:00:23] Epoch: [198][8000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.032 (2.880) Prec@1 71.88 (76.52) Prec@5 89.06 (91.58) + train[2018-10-22-21:02:08] Epoch: [198][8200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.020 (2.881) Prec@1 72.66 (76.51) Prec@5 89.84 (91.57) + train[2018-10-22-21:03:52] Epoch: [198][8400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.647 (2.881) Prec@1 81.25 (76.50) Prec@5 95.31 (91.57) + train[2018-10-22-21:05:37] Epoch: [198][8600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.007 (2.881) Prec@1 73.44 (76.50) Prec@5 85.16 (91.57) + train[2018-10-22-21:07:22] Epoch: [198][8800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.858 (2.881) Prec@1 74.22 (76.50) Prec@5 92.19 (91.57) + train[2018-10-22-21:09:08] Epoch: [198][9000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.892 (2.880) Prec@1 73.44 (76.51) Prec@5 95.31 (91.58) + train[2018-10-22-21:10:51] Epoch: [198][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.891 (2.881) Prec@1 74.22 (76.50) Prec@5 90.62 (91.57) + train[2018-10-22-21:12:36] Epoch: [198][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.046 (2.881) Prec@1 73.44 (76.50) Prec@5 89.06 (91.57) + train[2018-10-22-21:14:20] Epoch: [198][9600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.652 (2.881) Prec@1 78.91 (76.49) Prec@5 93.75 (91.57) + train[2018-10-22-21:16:05] Epoch: [198][9800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.656 (2.881) Prec@1 77.34 (76.50) Prec@5 91.41 (91.57) + train[2018-10-22-21:17:50] Epoch: [198][10000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.807 (2.882) Prec@1 76.56 (76.49) Prec@5 91.41 (91.56) + train[2018-10-22-21:17:54] Epoch: [198][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 2.679 (2.882) Prec@1 73.33 (76.49) Prec@5 93.33 (91.56) +[2018-10-22-21:17:54] **train** Prec@1 76.49 Prec@5 91.56 Error@1 23.51 Error@5 8.44 Loss:2.882 + test [2018-10-22-21:17:58] Epoch: [198][000/391] Time 4.05 (4.05) Data 3.91 (3.91) Loss 0.514 (0.514) Prec@1 92.97 (92.97) Prec@5 99.22 (99.22) + test [2018-10-22-21:18:25] Epoch: [198][200/391] Time 0.14 (0.15) Data 0.01 (0.02) Loss 1.140 (0.980) Prec@1 71.09 (77.39) Prec@5 92.19 (93.73) + test [2018-10-22-21:18:50] Epoch: [198][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.038 (1.148) Prec@1 48.75 (73.77) Prec@5 83.75 (91.50) +[2018-10-22-21:18:50] **test** Prec@1 73.77 Prec@5 91.50 Error@1 26.23 Error@5 8.50 Loss:1.148 +----> Best Accuracy : Acc@1=73.92, Acc@5=91.51, Error@1=26.08, Error@5=8.49 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-22-21:18:50] [Epoch=199/250] [Need: 75:28:56] LR=0.0002 ~ 0.0002, Batch=128 + train[2018-10-22-21:18:54] Epoch: [199][000/10010] Time 4.44 (4.44) Data 3.80 (3.80) Loss 3.294 (3.294) Prec@1 71.09 (71.09) Prec@5 82.81 (82.81) + train[2018-10-22-21:20:40] Epoch: [199][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 2.934 (2.869) Prec@1 74.22 (76.67) Prec@5 90.62 (91.71) + train[2018-10-22-21:22:25] Epoch: [199][400/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 3.083 (2.878) Prec@1 71.09 (76.55) Prec@5 89.84 (91.54) + train[2018-10-22-21:24:09] Epoch: [199][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 2.594 (2.872) Prec@1 85.16 (76.69) Prec@5 94.53 (91.58) + train[2018-10-22-21:25:54] Epoch: [199][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.947 (2.872) Prec@1 72.66 (76.68) Prec@5 91.41 (91.58) + train[2018-10-22-21:27:38] Epoch: [199][1000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.086 (2.874) Prec@1 72.66 (76.61) Prec@5 92.19 (91.58) + train[2018-10-22-21:29:22] Epoch: [199][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.829 (2.874) Prec@1 78.91 (76.55) Prec@5 90.62 (91.57) + train[2018-10-22-21:31:07] Epoch: [199][1400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.773 (2.873) Prec@1 79.69 (76.58) Prec@5 93.75 (91.60) + train[2018-10-22-21:32:53] Epoch: [199][1600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.596 (2.872) Prec@1 79.69 (76.60) Prec@5 93.75 (91.62) + train[2018-10-22-21:34:38] Epoch: [199][1800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.850 (2.872) Prec@1 80.47 (76.63) Prec@5 92.97 (91.63) + train[2018-10-22-21:36:23] Epoch: [199][2000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.782 (2.872) Prec@1 76.56 (76.60) Prec@5 92.19 (91.66) + train[2018-10-22-21:38:07] Epoch: [199][2200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.014 (2.872) Prec@1 79.69 (76.61) Prec@5 89.06 (91.67) + train[2018-10-22-21:39:53] Epoch: [199][2400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.863 (2.871) Prec@1 74.22 (76.64) Prec@5 92.19 (91.68) + train[2018-10-22-21:41:39] Epoch: [199][2600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.878 (2.871) Prec@1 74.22 (76.64) Prec@5 91.41 (91.68) + train[2018-10-22-21:43:24] Epoch: [199][2800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.034 (2.872) Prec@1 77.34 (76.63) Prec@5 87.50 (91.68) + train[2018-10-22-21:45:09] Epoch: [199][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.175 (2.873) Prec@1 74.22 (76.61) Prec@5 89.84 (91.66) + train[2018-10-22-21:46:54] Epoch: [199][3200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.084 (2.872) Prec@1 74.22 (76.61) Prec@5 89.06 (91.68) + train[2018-10-22-21:48:40] Epoch: [199][3400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.912 (2.873) Prec@1 77.34 (76.61) Prec@5 88.28 (91.66) + train[2018-10-22-21:50:24] Epoch: [199][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.908 (2.873) Prec@1 75.78 (76.61) Prec@5 92.97 (91.68) + train[2018-10-22-21:52:10] Epoch: [199][3800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.885 (2.874) Prec@1 75.00 (76.59) Prec@5 92.97 (91.68) + train[2018-10-22-21:53:55] Epoch: [199][4000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.866 (2.874) Prec@1 81.25 (76.60) Prec@5 92.19 (91.68) + train[2018-10-22-21:55:41] Epoch: [199][4200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.806 (2.874) Prec@1 78.12 (76.60) Prec@5 89.06 (91.68) + train[2018-10-22-21:57:26] Epoch: [199][4400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.981 (2.874) Prec@1 75.00 (76.60) Prec@5 91.41 (91.67) + train[2018-10-22-21:59:11] Epoch: [199][4600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.048 (2.874) Prec@1 74.22 (76.60) Prec@5 89.84 (91.67) + train[2018-10-22-22:00:57] Epoch: [199][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.731 (2.875) Prec@1 78.91 (76.59) Prec@5 93.75 (91.66) + train[2018-10-22-22:02:43] Epoch: [199][5000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.890 (2.874) Prec@1 75.00 (76.59) Prec@5 90.62 (91.66) + train[2018-10-22-22:04:27] Epoch: [199][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.854 (2.875) Prec@1 76.56 (76.60) Prec@5 94.53 (91.65) + train[2018-10-22-22:06:13] Epoch: [199][5400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.020 (2.874) Prec@1 75.00 (76.59) Prec@5 89.06 (91.65) + train[2018-10-22-22:07:57] Epoch: [199][5600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.713 (2.875) Prec@1 81.25 (76.59) Prec@5 92.19 (91.65) + train[2018-10-22-22:09:43] Epoch: [199][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.673 (2.875) Prec@1 80.47 (76.58) Prec@5 92.97 (91.65) + train[2018-10-22-22:11:28] Epoch: [199][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.772 (2.875) Prec@1 78.91 (76.58) Prec@5 91.41 (91.65) + train[2018-10-22-22:13:14] Epoch: [199][6200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.983 (2.875) Prec@1 74.22 (76.58) Prec@5 91.41 (91.65) + train[2018-10-22-22:15:00] Epoch: [199][6400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.829 (2.875) Prec@1 78.91 (76.58) Prec@5 92.19 (91.65) + train[2018-10-22-22:16:45] Epoch: [199][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.858 (2.875) Prec@1 78.91 (76.59) Prec@5 92.19 (91.66) + train[2018-10-22-22:18:30] Epoch: [199][6800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.902 (2.875) Prec@1 77.34 (76.59) Prec@5 92.97 (91.66) + train[2018-10-22-22:20:15] Epoch: [199][7000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.952 (2.875) Prec@1 76.56 (76.58) Prec@5 89.84 (91.66) + train[2018-10-22-22:21:59] Epoch: [199][7200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.827 (2.875) Prec@1 77.34 (76.58) Prec@5 92.97 (91.66) + train[2018-10-22-22:23:44] Epoch: [199][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.829 (2.876) Prec@1 78.91 (76.58) Prec@5 91.41 (91.65) + train[2018-10-22-22:25:28] Epoch: [199][7600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.974 (2.876) Prec@1 75.78 (76.57) Prec@5 89.06 (91.64) + train[2018-10-22-22:27:14] Epoch: [199][7800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.870 (2.876) Prec@1 73.44 (76.57) Prec@5 91.41 (91.64) + train[2018-10-22-22:29:00] Epoch: [199][8000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.724 (2.876) Prec@1 84.38 (76.57) Prec@5 92.97 (91.65) + train[2018-10-22-22:30:46] Epoch: [199][8200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.057 (2.876) Prec@1 76.56 (76.57) Prec@5 90.62 (91.64) + train[2018-10-22-22:32:32] Epoch: [199][8400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.601 (2.876) Prec@1 82.81 (76.57) Prec@5 93.75 (91.65) + train[2018-10-22-22:34:19] Epoch: [199][8600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.649 (2.876) Prec@1 81.25 (76.57) Prec@5 94.53 (91.64) + train[2018-10-22-22:36:04] Epoch: [199][8800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.737 (2.876) Prec@1 78.91 (76.56) Prec@5 90.62 (91.64) + train[2018-10-22-22:37:49] Epoch: [199][9000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.790 (2.877) Prec@1 77.34 (76.55) Prec@5 94.53 (91.64) + train[2018-10-22-22:39:33] Epoch: [199][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.760 (2.877) Prec@1 75.00 (76.55) Prec@5 92.97 (91.63) + train[2018-10-22-22:41:18] Epoch: [199][9400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.028 (2.877) Prec@1 75.78 (76.55) Prec@5 89.84 (91.63) + train[2018-10-22-22:43:04] Epoch: [199][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.111 (2.878) Prec@1 75.00 (76.54) Prec@5 89.84 (91.63) + train[2018-10-22-22:44:48] Epoch: [199][9800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.694 (2.878) Prec@1 75.00 (76.54) Prec@5 95.31 (91.63) + train[2018-10-22-22:46:33] Epoch: [199][10000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.916 (2.877) Prec@1 69.53 (76.54) Prec@5 92.19 (91.63) + train[2018-10-22-22:46:37] Epoch: [199][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 3.645 (2.877) Prec@1 66.67 (76.54) Prec@5 73.33 (91.63) +[2018-10-22-22:46:37] **train** Prec@1 76.54 Prec@5 91.63 Error@1 23.46 Error@5 8.37 Loss:2.877 + test [2018-10-22-22:46:41] Epoch: [199][000/391] Time 4.05 (4.05) Data 3.91 (3.91) Loss 0.547 (0.547) Prec@1 92.97 (92.97) Prec@5 99.22 (99.22) + test [2018-10-22-22:47:07] Epoch: [199][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.113 (0.989) Prec@1 71.09 (77.41) Prec@5 92.97 (93.66) + test [2018-10-22-22:47:33] Epoch: [199][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.121 (1.161) Prec@1 47.50 (73.78) Prec@5 82.50 (91.44) +[2018-10-22-22:47:33] **test** Prec@1 73.78 Prec@5 91.44 Error@1 26.22 Error@5 8.56 Loss:1.161 +----> Best Accuracy : Acc@1=73.92, Acc@5=91.51, Error@1=26.08, Error@5=8.49 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-22-22:47:33] [Epoch=200/250] [Need: 73:55:48] LR=0.0002 ~ 0.0002, Batch=128 + train[2018-10-22-22:47:38] Epoch: [200][000/10010] Time 4.97 (4.97) Data 4.30 (4.30) Loss 2.844 (2.844) Prec@1 72.66 (72.66) Prec@5 94.53 (94.53) + train[2018-10-22-22:49:22] Epoch: [200][200/10010] Time 0.55 (0.55) Data 0.00 (0.02) Loss 2.854 (2.876) Prec@1 76.56 (76.65) Prec@5 90.62 (91.56) + train[2018-10-22-22:51:08] Epoch: [200][400/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.708 (2.879) Prec@1 78.91 (76.53) Prec@5 94.53 (91.60) + train[2018-10-22-22:52:52] Epoch: [200][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.191 (2.877) Prec@1 68.75 (76.58) Prec@5 88.28 (91.66) + train[2018-10-22-22:54:37] Epoch: [200][800/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 2.797 (2.881) Prec@1 78.12 (76.55) Prec@5 93.75 (91.62) + train[2018-10-22-22:56:22] Epoch: [200][1000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.763 (2.878) Prec@1 79.69 (76.62) Prec@5 95.31 (91.66) + train[2018-10-22-22:58:07] Epoch: [200][1200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.928 (2.877) Prec@1 73.44 (76.60) Prec@5 90.62 (91.68) + train[2018-10-22-22:59:52] Epoch: [200][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.098 (2.874) Prec@1 71.09 (76.63) Prec@5 87.50 (91.71) + train[2018-10-22-23:01:37] Epoch: [200][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.862 (2.876) Prec@1 76.56 (76.59) Prec@5 90.62 (91.68) + train[2018-10-22-23:03:21] Epoch: [200][1800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.229 (2.874) Prec@1 67.97 (76.63) Prec@5 85.94 (91.69) + train[2018-10-22-23:05:06] Epoch: [200][2000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.044 (2.873) Prec@1 67.19 (76.65) Prec@5 92.19 (91.70) + train[2018-10-22-23:06:51] Epoch: [200][2200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.747 (2.873) Prec@1 79.69 (76.64) Prec@5 96.09 (91.71) + train[2018-10-22-23:08:36] Epoch: [200][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.711 (2.874) Prec@1 74.22 (76.63) Prec@5 96.09 (91.70) + train[2018-10-22-23:10:22] Epoch: [200][2600/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 2.723 (2.873) Prec@1 78.12 (76.62) Prec@5 92.19 (91.70) + train[2018-10-22-23:12:07] Epoch: [200][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.816 (2.872) Prec@1 79.69 (76.63) Prec@5 91.41 (91.69) + train[2018-10-22-23:13:52] Epoch: [200][3000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.039 (2.872) Prec@1 71.88 (76.63) Prec@5 91.41 (91.70) + train[2018-10-22-23:15:37] Epoch: [200][3200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.860 (2.873) Prec@1 76.56 (76.61) Prec@5 91.41 (91.69) + train[2018-10-22-23:17:22] Epoch: [200][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.935 (2.873) Prec@1 77.34 (76.62) Prec@5 90.62 (91.69) + train[2018-10-22-23:19:07] Epoch: [200][3600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.959 (2.873) Prec@1 75.78 (76.62) Prec@5 90.62 (91.67) + train[2018-10-22-23:20:52] Epoch: [200][3800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.770 (2.875) Prec@1 78.12 (76.60) Prec@5 92.19 (91.65) + train[2018-10-22-23:22:37] Epoch: [200][4000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.781 (2.873) Prec@1 80.47 (76.62) Prec@5 89.84 (91.67) + train[2018-10-22-23:24:22] Epoch: [200][4200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.660 (2.873) Prec@1 80.47 (76.61) Prec@5 91.41 (91.67) + train[2018-10-22-23:26:08] Epoch: [200][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.608 (2.873) Prec@1 84.38 (76.61) Prec@5 95.31 (91.67) + train[2018-10-22-23:27:53] Epoch: [200][4600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.149 (2.874) Prec@1 71.88 (76.60) Prec@5 86.72 (91.67) + train[2018-10-22-23:29:38] Epoch: [200][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.720 (2.875) Prec@1 78.12 (76.56) Prec@5 94.53 (91.66) + train[2018-10-22-23:31:23] Epoch: [200][5000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.846 (2.875) Prec@1 79.69 (76.57) Prec@5 94.53 (91.65) + train[2018-10-22-23:33:09] Epoch: [200][5200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.144 (2.875) Prec@1 70.31 (76.56) Prec@5 89.84 (91.65) + train[2018-10-22-23:34:53] Epoch: [200][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.076 (2.875) Prec@1 72.66 (76.56) Prec@5 89.06 (91.65) + train[2018-10-22-23:36:38] Epoch: [200][5600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.212 (2.875) Prec@1 71.88 (76.56) Prec@5 86.72 (91.65) + train[2018-10-22-23:38:24] Epoch: [200][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.967 (2.875) Prec@1 75.00 (76.56) Prec@5 92.19 (91.65) + train[2018-10-22-23:40:09] Epoch: [200][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.906 (2.875) Prec@1 71.09 (76.56) Prec@5 90.62 (91.64) + train[2018-10-22-23:41:53] Epoch: [200][6200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.219 (2.876) Prec@1 72.66 (76.55) Prec@5 86.72 (91.64) + train[2018-10-22-23:43:38] Epoch: [200][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.582 (2.876) Prec@1 79.69 (76.55) Prec@5 96.09 (91.64) + train[2018-10-22-23:45:23] Epoch: [200][6600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.942 (2.876) Prec@1 77.34 (76.56) Prec@5 88.28 (91.64) + train[2018-10-22-23:47:08] Epoch: [200][6800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.971 (2.876) Prec@1 74.22 (76.57) Prec@5 89.06 (91.64) + train[2018-10-22-23:48:52] Epoch: [200][7000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.782 (2.876) Prec@1 76.56 (76.56) Prec@5 92.97 (91.64) + train[2018-10-22-23:50:37] Epoch: [200][7200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.238 (2.877) Prec@1 72.66 (76.56) Prec@5 88.28 (91.63) + train[2018-10-22-23:52:23] Epoch: [200][7400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.292 (2.877) Prec@1 71.09 (76.56) Prec@5 84.38 (91.63) + train[2018-10-22-23:54:08] Epoch: [200][7600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.137 (2.877) Prec@1 76.56 (76.56) Prec@5 87.50 (91.62) + train[2018-10-22-23:55:53] Epoch: [200][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.922 (2.877) Prec@1 75.78 (76.56) Prec@5 92.19 (91.62) + train[2018-10-22-23:57:38] Epoch: [200][8000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.861 (2.877) Prec@1 76.56 (76.56) Prec@5 89.84 (91.63) + train[2018-10-22-23:59:23] Epoch: [200][8200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.883 (2.877) Prec@1 77.34 (76.56) Prec@5 92.97 (91.63) + train[2018-10-23-00:01:08] Epoch: [200][8400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.949 (2.876) Prec@1 78.91 (76.57) Prec@5 89.84 (91.63) + train[2018-10-23-00:02:52] Epoch: [200][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.237 (2.877) Prec@1 69.53 (76.55) Prec@5 86.72 (91.62) + train[2018-10-23-00:04:37] Epoch: [200][8800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.893 (2.877) Prec@1 77.34 (76.54) Prec@5 91.41 (91.62) + train[2018-10-23-00:06:22] Epoch: [200][9000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.668 (2.877) Prec@1 80.47 (76.54) Prec@5 95.31 (91.62) + train[2018-10-23-00:08:08] Epoch: [200][9200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.867 (2.877) Prec@1 79.69 (76.54) Prec@5 90.62 (91.62) + train[2018-10-23-00:09:53] Epoch: [200][9400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.762 (2.877) Prec@1 80.47 (76.55) Prec@5 93.75 (91.62) + train[2018-10-23-00:11:38] Epoch: [200][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.679 (2.877) Prec@1 79.69 (76.55) Prec@5 96.09 (91.62) + train[2018-10-23-00:13:23] Epoch: [200][9800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.802 (2.878) Prec@1 78.12 (76.55) Prec@5 90.62 (91.62) + train[2018-10-23-00:15:09] Epoch: [200][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.063 (2.877) Prec@1 72.66 (76.55) Prec@5 90.62 (91.62) + train[2018-10-23-00:15:13] Epoch: [200][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 3.997 (2.877) Prec@1 53.33 (76.55) Prec@5 80.00 (91.62) +[2018-10-23-00:15:13] **train** Prec@1 76.55 Prec@5 91.62 Error@1 23.45 Error@5 8.38 Loss:2.877 + test [2018-10-23-00:15:17] Epoch: [200][000/391] Time 3.94 (3.94) Data 3.80 (3.80) Loss 0.551 (0.551) Prec@1 92.97 (92.97) Prec@5 98.44 (98.44) + test [2018-10-23-00:15:43] Epoch: [200][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.164 (0.993) Prec@1 69.53 (77.37) Prec@5 91.41 (93.67) + test [2018-10-23-00:16:08] Epoch: [200][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.124 (1.159) Prec@1 46.25 (73.76) Prec@5 82.50 (91.44) +[2018-10-23-00:16:08] **test** Prec@1 73.76 Prec@5 91.44 Error@1 26.24 Error@5 8.56 Loss:1.159 +----> Best Accuracy : Acc@1=73.92, Acc@5=91.51, Error@1=26.08, Error@5=8.49 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-23-00:16:08] [Epoch=201/250] [Need: 72:20:38] LR=0.0002 ~ 0.0002, Batch=128 + train[2018-10-23-00:16:12] Epoch: [201][000/10010] Time 4.59 (4.59) Data 3.97 (3.97) Loss 3.255 (3.255) Prec@1 69.53 (69.53) Prec@5 87.50 (87.50) + train[2018-10-23-00:17:58] Epoch: [201][200/10010] Time 0.54 (0.55) Data 0.00 (0.02) Loss 2.826 (2.867) Prec@1 75.00 (76.88) Prec@5 92.19 (91.69) + train[2018-10-23-00:19:42] Epoch: [201][400/10010] Time 0.53 (0.54) Data 0.00 (0.01) Loss 3.036 (2.860) Prec@1 74.22 (76.98) Prec@5 89.06 (91.79) + train[2018-10-23-00:21:27] Epoch: [201][600/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.004 (2.867) Prec@1 78.91 (76.92) Prec@5 90.62 (91.68) + train[2018-10-23-00:23:11] Epoch: [201][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.752 (2.872) Prec@1 78.12 (76.76) Prec@5 91.41 (91.64) + train[2018-10-23-00:24:56] Epoch: [201][1000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.011 (2.875) Prec@1 75.00 (76.73) Prec@5 89.84 (91.65) + train[2018-10-23-00:26:40] Epoch: [201][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.104 (2.875) Prec@1 74.22 (76.71) Prec@5 89.84 (91.64) + train[2018-10-23-00:28:26] Epoch: [201][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.075 (2.878) Prec@1 71.09 (76.60) Prec@5 86.72 (91.60) + train[2018-10-23-00:30:10] Epoch: [201][1600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.185 (2.876) Prec@1 69.53 (76.66) Prec@5 88.28 (91.63) + train[2018-10-23-00:31:55] Epoch: [201][1800/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.793 (2.874) Prec@1 78.12 (76.67) Prec@5 92.97 (91.66) + train[2018-10-23-00:33:40] Epoch: [201][2000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.933 (2.874) Prec@1 70.31 (76.63) Prec@5 92.19 (91.67) + train[2018-10-23-00:35:25] Epoch: [201][2200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.671 (2.876) Prec@1 78.91 (76.61) Prec@5 93.75 (91.66) + train[2018-10-23-00:37:10] Epoch: [201][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.034 (2.876) Prec@1 72.66 (76.60) Prec@5 88.28 (91.64) + train[2018-10-23-00:38:54] Epoch: [201][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.783 (2.876) Prec@1 78.12 (76.62) Prec@5 94.53 (91.63) + train[2018-10-23-00:40:40] Epoch: [201][2800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.854 (2.876) Prec@1 78.12 (76.62) Prec@5 90.62 (91.63) + train[2018-10-23-00:42:25] Epoch: [201][3000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.621 (2.877) Prec@1 82.81 (76.60) Prec@5 96.09 (91.61) + train[2018-10-23-00:44:10] Epoch: [201][3200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.756 (2.877) Prec@1 76.56 (76.62) Prec@5 96.88 (91.62) + train[2018-10-23-00:45:56] Epoch: [201][3400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.071 (2.876) Prec@1 71.88 (76.62) Prec@5 87.50 (91.62) + train[2018-10-23-00:47:41] Epoch: [201][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.730 (2.877) Prec@1 78.91 (76.60) Prec@5 92.19 (91.62) + train[2018-10-23-00:49:26] Epoch: [201][3800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.010 (2.877) Prec@1 73.44 (76.59) Prec@5 88.28 (91.62) + train[2018-10-23-00:51:11] Epoch: [201][4000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.790 (2.877) Prec@1 78.12 (76.58) Prec@5 90.62 (91.63) + train[2018-10-23-00:52:57] Epoch: [201][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.824 (2.876) Prec@1 82.03 (76.58) Prec@5 91.41 (91.62) + train[2018-10-23-00:54:42] Epoch: [201][4400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.829 (2.877) Prec@1 76.56 (76.58) Prec@5 91.41 (91.62) + train[2018-10-23-00:56:27] Epoch: [201][4600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.771 (2.878) Prec@1 76.56 (76.57) Prec@5 94.53 (91.61) + train[2018-10-23-00:58:12] Epoch: [201][4800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.858 (2.878) Prec@1 79.69 (76.55) Prec@5 92.97 (91.61) + train[2018-10-23-00:59:57] Epoch: [201][5000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.807 (2.878) Prec@1 78.12 (76.55) Prec@5 91.41 (91.61) + train[2018-10-23-01:01:42] Epoch: [201][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.336 (2.878) Prec@1 66.41 (76.56) Prec@5 85.94 (91.61) + train[2018-10-23-01:03:27] Epoch: [201][5400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.795 (2.877) Prec@1 75.78 (76.55) Prec@5 94.53 (91.62) + train[2018-10-23-01:05:12] Epoch: [201][5600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.694 (2.878) Prec@1 78.91 (76.55) Prec@5 96.09 (91.62) + train[2018-10-23-01:06:57] Epoch: [201][5800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.890 (2.878) Prec@1 77.34 (76.55) Prec@5 89.84 (91.61) + train[2018-10-23-01:08:42] Epoch: [201][6000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.748 (2.878) Prec@1 75.78 (76.54) Prec@5 92.97 (91.61) + train[2018-10-23-01:10:27] Epoch: [201][6200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.848 (2.878) Prec@1 78.12 (76.54) Prec@5 92.19 (91.61) + train[2018-10-23-01:12:12] Epoch: [201][6400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.874 (2.879) Prec@1 78.12 (76.53) Prec@5 92.97 (91.60) + train[2018-10-23-01:13:57] Epoch: [201][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.702 (2.879) Prec@1 79.69 (76.53) Prec@5 94.53 (91.59) + train[2018-10-23-01:15:42] Epoch: [201][6800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.675 (2.879) Prec@1 79.69 (76.53) Prec@5 96.09 (91.58) + train[2018-10-23-01:17:27] Epoch: [201][7000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.035 (2.879) Prec@1 70.31 (76.53) Prec@5 89.06 (91.59) + train[2018-10-23-01:19:11] Epoch: [201][7200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.924 (2.878) Prec@1 72.66 (76.53) Prec@5 91.41 (91.58) + train[2018-10-23-01:20:56] Epoch: [201][7400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.266 (2.879) Prec@1 70.31 (76.52) Prec@5 88.28 (91.58) + train[2018-10-23-01:22:41] Epoch: [201][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.974 (2.878) Prec@1 72.66 (76.53) Prec@5 89.84 (91.60) + train[2018-10-23-01:24:26] Epoch: [201][7800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.922 (2.878) Prec@1 74.22 (76.52) Prec@5 93.75 (91.60) + train[2018-10-23-01:26:10] Epoch: [201][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.837 (2.879) Prec@1 78.91 (76.51) Prec@5 92.19 (91.59) + train[2018-10-23-01:27:56] Epoch: [201][8200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.783 (2.879) Prec@1 75.00 (76.51) Prec@5 92.97 (91.59) + train[2018-10-23-01:29:42] Epoch: [201][8400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.907 (2.878) Prec@1 75.00 (76.52) Prec@5 93.75 (91.60) + train[2018-10-23-01:31:26] Epoch: [201][8600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.197 (2.879) Prec@1 66.41 (76.51) Prec@5 89.84 (91.59) + train[2018-10-23-01:33:12] Epoch: [201][8800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.791 (2.879) Prec@1 78.91 (76.51) Prec@5 92.19 (91.59) + train[2018-10-23-01:34:56] Epoch: [201][9000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.849 (2.878) Prec@1 73.44 (76.52) Prec@5 94.53 (91.59) + train[2018-10-23-01:36:42] Epoch: [201][9200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.099 (2.878) Prec@1 71.88 (76.52) Prec@5 89.06 (91.59) + train[2018-10-23-01:38:26] Epoch: [201][9400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.245 (2.879) Prec@1 74.22 (76.52) Prec@5 88.28 (91.59) + train[2018-10-23-01:40:12] Epoch: [201][9600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.657 (2.879) Prec@1 78.91 (76.53) Prec@5 96.09 (91.59) + train[2018-10-23-01:41:58] Epoch: [201][9800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.775 (2.879) Prec@1 79.69 (76.53) Prec@5 91.41 (91.59) + train[2018-10-23-01:43:43] Epoch: [201][10000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.160 (2.878) Prec@1 74.22 (76.53) Prec@5 89.84 (91.59) + train[2018-10-23-01:43:47] Epoch: [201][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 3.534 (2.878) Prec@1 73.33 (76.53) Prec@5 93.33 (91.59) +[2018-10-23-01:43:47] **train** Prec@1 76.53 Prec@5 91.59 Error@1 23.47 Error@5 8.41 Loss:2.878 + test [2018-10-23-01:43:52] Epoch: [201][000/391] Time 4.03 (4.03) Data 3.90 (3.90) Loss 0.538 (0.538) Prec@1 92.97 (92.97) Prec@5 99.22 (99.22) + test [2018-10-23-01:44:18] Epoch: [201][200/391] Time 0.14 (0.15) Data 0.00 (0.02) Loss 1.179 (1.000) Prec@1 69.53 (77.40) Prec@5 92.19 (93.67) + test [2018-10-23-01:44:42] Epoch: [201][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.129 (1.167) Prec@1 48.75 (73.84) Prec@5 81.25 (91.39) +[2018-10-23-01:44:42] **test** Prec@1 73.84 Prec@5 91.39 Error@1 26.16 Error@5 8.61 Loss:1.167 +----> Best Accuracy : Acc@1=73.92, Acc@5=91.51, Error@1=26.08, Error@5=8.49 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-23-01:44:42] [Epoch=202/250] [Need: 70:51:44] LR=0.0002 ~ 0.0002, Batch=128 + train[2018-10-23-01:44:47] Epoch: [202][000/10010] Time 4.81 (4.81) Data 4.12 (4.12) Loss 2.880 (2.880) Prec@1 77.34 (77.34) Prec@5 90.62 (90.62) + train[2018-10-23-01:46:32] Epoch: [202][200/10010] Time 0.53 (0.54) Data 0.00 (0.02) Loss 2.911 (2.880) Prec@1 72.66 (76.34) Prec@5 92.97 (91.61) + train[2018-10-23-01:48:16] Epoch: [202][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.045 (2.871) Prec@1 74.22 (76.47) Prec@5 88.28 (91.65) + train[2018-10-23-01:50:01] Epoch: [202][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.990 (2.870) Prec@1 76.56 (76.62) Prec@5 88.28 (91.62) + train[2018-10-23-01:51:46] Epoch: [202][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.621 (2.866) Prec@1 75.78 (76.74) Prec@5 97.66 (91.67) + train[2018-10-23-01:53:31] Epoch: [202][1000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.511 (2.865) Prec@1 83.59 (76.75) Prec@5 95.31 (91.64) + train[2018-10-23-01:55:16] Epoch: [202][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.078 (2.865) Prec@1 76.56 (76.74) Prec@5 89.84 (91.66) + train[2018-10-23-01:57:02] Epoch: [202][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.792 (2.864) Prec@1 75.78 (76.75) Prec@5 91.41 (91.69) + train[2018-10-23-01:58:46] Epoch: [202][1600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.281 (2.866) Prec@1 71.88 (76.70) Prec@5 84.38 (91.69) + train[2018-10-23-02:00:31] Epoch: [202][1800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.972 (2.868) Prec@1 78.91 (76.69) Prec@5 90.62 (91.67) + train[2018-10-23-02:02:15] Epoch: [202][2000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.902 (2.867) Prec@1 77.34 (76.69) Prec@5 92.97 (91.69) + train[2018-10-23-02:03:59] Epoch: [202][2200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.848 (2.868) Prec@1 82.03 (76.67) Prec@5 92.97 (91.68) + train[2018-10-23-02:05:45] Epoch: [202][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.613 (2.870) Prec@1 79.69 (76.62) Prec@5 95.31 (91.67) + train[2018-10-23-02:07:30] Epoch: [202][2600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.796 (2.868) Prec@1 76.56 (76.66) Prec@5 92.97 (91.69) + train[2018-10-23-02:09:15] Epoch: [202][2800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.886 (2.869) Prec@1 77.34 (76.66) Prec@5 90.62 (91.68) + train[2018-10-23-02:11:00] Epoch: [202][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.832 (2.870) Prec@1 78.91 (76.65) Prec@5 91.41 (91.68) + train[2018-10-23-02:12:46] Epoch: [202][3200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.907 (2.871) Prec@1 76.56 (76.62) Prec@5 90.62 (91.68) + train[2018-10-23-02:14:31] Epoch: [202][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.239 (2.871) Prec@1 74.22 (76.61) Prec@5 86.72 (91.69) + train[2018-10-23-02:16:16] Epoch: [202][3600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.747 (2.871) Prec@1 79.69 (76.61) Prec@5 92.19 (91.69) + train[2018-10-23-02:18:02] Epoch: [202][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.787 (2.871) Prec@1 78.91 (76.62) Prec@5 91.41 (91.68) + train[2018-10-23-02:19:47] Epoch: [202][4000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.817 (2.872) Prec@1 80.47 (76.60) Prec@5 90.62 (91.67) + train[2018-10-23-02:21:32] Epoch: [202][4200/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.959 (2.873) Prec@1 74.22 (76.59) Prec@5 89.06 (91.68) + train[2018-10-23-02:23:17] Epoch: [202][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.727 (2.872) Prec@1 80.47 (76.60) Prec@5 93.75 (91.68) + train[2018-10-23-02:25:02] Epoch: [202][4600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.621 (2.873) Prec@1 82.81 (76.60) Prec@5 94.53 (91.67) + train[2018-10-23-02:26:47] Epoch: [202][4800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.669 (2.873) Prec@1 79.69 (76.60) Prec@5 92.97 (91.67) + train[2018-10-23-02:28:32] Epoch: [202][5000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.821 (2.874) Prec@1 78.91 (76.59) Prec@5 92.19 (91.65) + train[2018-10-23-02:30:16] Epoch: [202][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.602 (2.874) Prec@1 82.03 (76.59) Prec@5 94.53 (91.65) + train[2018-10-23-02:32:01] Epoch: [202][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.144 (2.875) Prec@1 71.09 (76.59) Prec@5 87.50 (91.65) + train[2018-10-23-02:33:47] Epoch: [202][5600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.752 (2.874) Prec@1 79.69 (76.60) Prec@5 93.75 (91.65) + train[2018-10-23-02:35:31] Epoch: [202][5800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.718 (2.874) Prec@1 78.91 (76.61) Prec@5 93.75 (91.65) + train[2018-10-23-02:37:16] Epoch: [202][6000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.871 (2.873) Prec@1 74.22 (76.63) Prec@5 93.75 (91.66) + train[2018-10-23-02:39:01] Epoch: [202][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.829 (2.873) Prec@1 75.78 (76.63) Prec@5 89.84 (91.66) + train[2018-10-23-02:40:46] Epoch: [202][6400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.064 (2.873) Prec@1 75.00 (76.63) Prec@5 88.28 (91.66) + train[2018-10-23-02:42:32] Epoch: [202][6600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.499 (2.873) Prec@1 83.59 (76.63) Prec@5 98.44 (91.66) + train[2018-10-23-02:44:17] Epoch: [202][6800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.777 (2.874) Prec@1 81.25 (76.61) Prec@5 92.19 (91.65) + train[2018-10-23-02:46:01] Epoch: [202][7000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.890 (2.874) Prec@1 75.78 (76.60) Prec@5 89.06 (91.65) + train[2018-10-23-02:47:46] Epoch: [202][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.702 (2.876) Prec@1 76.56 (76.59) Prec@5 94.53 (91.64) + train[2018-10-23-02:49:31] Epoch: [202][7400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.116 (2.875) Prec@1 70.31 (76.59) Prec@5 91.41 (91.65) + train[2018-10-23-02:51:17] Epoch: [202][7600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.595 (2.876) Prec@1 80.47 (76.59) Prec@5 95.31 (91.64) + train[2018-10-23-02:53:04] Epoch: [202][7800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.968 (2.875) Prec@1 76.56 (76.60) Prec@5 91.41 (91.65) + train[2018-10-23-02:54:51] Epoch: [202][8000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.810 (2.875) Prec@1 76.56 (76.60) Prec@5 90.62 (91.64) + train[2018-10-23-02:56:38] Epoch: [202][8200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.941 (2.876) Prec@1 75.78 (76.59) Prec@5 91.41 (91.64) + train[2018-10-23-02:58:25] Epoch: [202][8400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.982 (2.876) Prec@1 76.56 (76.59) Prec@5 88.28 (91.63) + train[2018-10-23-03:00:11] Epoch: [202][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.970 (2.876) Prec@1 76.56 (76.59) Prec@5 89.84 (91.63) + train[2018-10-23-03:01:58] Epoch: [202][8800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.911 (2.876) Prec@1 71.88 (76.60) Prec@5 93.75 (91.63) + train[2018-10-23-03:03:45] Epoch: [202][9000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.848 (2.876) Prec@1 80.47 (76.60) Prec@5 91.41 (91.63) + train[2018-10-23-03:05:32] Epoch: [202][9200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.728 (2.876) Prec@1 80.47 (76.61) Prec@5 92.97 (91.63) + train[2018-10-23-03:07:19] Epoch: [202][9400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.918 (2.876) Prec@1 74.22 (76.60) Prec@5 92.19 (91.63) + train[2018-10-23-03:09:06] Epoch: [202][9600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.057 (2.876) Prec@1 67.19 (76.59) Prec@5 93.75 (91.63) + train[2018-10-23-03:10:52] Epoch: [202][9800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.399 (2.876) Prec@1 87.50 (76.59) Prec@5 95.31 (91.62) + train[2018-10-23-03:12:39] Epoch: [202][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.884 (2.876) Prec@1 74.22 (76.59) Prec@5 93.75 (91.63) + train[2018-10-23-03:12:43] Epoch: [202][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.096 (2.876) Prec@1 86.67 (76.59) Prec@5 86.67 (91.63) +[2018-10-23-03:12:43] **train** Prec@1 76.59 Prec@5 91.63 Error@1 23.41 Error@5 8.37 Loss:2.876 + test [2018-10-23-03:12:47] Epoch: [202][000/391] Time 4.09 (4.09) Data 3.95 (3.95) Loss 0.570 (0.570) Prec@1 92.97 (92.97) Prec@5 98.44 (98.44) + test [2018-10-23-03:13:13] Epoch: [202][200/391] Time 0.13 (0.15) Data 0.00 (0.02) Loss 1.173 (0.994) Prec@1 68.75 (77.62) Prec@5 91.41 (93.62) + test [2018-10-23-03:13:38] Epoch: [202][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.097 (1.163) Prec@1 52.50 (73.91) Prec@5 82.50 (91.42) +[2018-10-23-03:13:38] **test** Prec@1 73.91 Prec@5 91.42 Error@1 26.09 Error@5 8.58 Loss:1.163 +----> Best Accuracy : Acc@1=73.92, Acc@5=91.51, Error@1=26.08, Error@5=8.49 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-23-03:13:38] [Epoch=203/250] [Need: 69:39:46] LR=0.0002 ~ 0.0002, Batch=128 + train[2018-10-23-03:13:43] Epoch: [203][000/10010] Time 5.03 (5.03) Data 4.42 (4.42) Loss 2.561 (2.561) Prec@1 77.34 (77.34) Prec@5 95.31 (95.31) + train[2018-10-23-03:15:29] Epoch: [203][200/10010] Time 0.52 (0.55) Data 0.00 (0.02) Loss 3.006 (2.856) Prec@1 73.44 (76.99) Prec@5 90.62 (92.01) + train[2018-10-23-03:17:14] Epoch: [203][400/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.916 (2.853) Prec@1 75.78 (76.97) Prec@5 91.41 (91.99) + train[2018-10-23-03:18:58] Epoch: [203][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.762 (2.860) Prec@1 81.25 (76.91) Prec@5 90.62 (91.91) + train[2018-10-23-03:20:44] Epoch: [203][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.700 (2.861) Prec@1 78.12 (76.82) Prec@5 94.53 (91.92) + train[2018-10-23-03:22:30] Epoch: [203][1000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.093 (2.863) Prec@1 71.88 (76.75) Prec@5 89.84 (91.88) + train[2018-10-23-03:24:16] Epoch: [203][1200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.013 (2.866) Prec@1 77.34 (76.72) Prec@5 89.84 (91.85) + train[2018-10-23-03:26:02] Epoch: [203][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.026 (2.868) Prec@1 73.44 (76.69) Prec@5 91.41 (91.79) + train[2018-10-23-03:27:48] Epoch: [203][1600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.982 (2.867) Prec@1 75.78 (76.71) Prec@5 88.28 (91.80) + train[2018-10-23-03:29:34] Epoch: [203][1800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.000 (2.868) Prec@1 72.66 (76.71) Prec@5 89.84 (91.77) + train[2018-10-23-03:31:19] Epoch: [203][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.890 (2.868) Prec@1 72.66 (76.71) Prec@5 94.53 (91.78) + train[2018-10-23-03:33:05] Epoch: [203][2200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.788 (2.868) Prec@1 71.88 (76.70) Prec@5 92.97 (91.76) + train[2018-10-23-03:34:50] Epoch: [203][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.544 (2.869) Prec@1 81.25 (76.66) Prec@5 96.09 (91.74) + train[2018-10-23-03:36:36] Epoch: [203][2600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.809 (2.869) Prec@1 78.12 (76.68) Prec@5 92.19 (91.73) + train[2018-10-23-03:38:23] Epoch: [203][2800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.612 (2.870) Prec@1 82.81 (76.65) Prec@5 92.97 (91.72) + train[2018-10-23-03:40:08] Epoch: [203][3000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.024 (2.870) Prec@1 73.44 (76.66) Prec@5 87.50 (91.71) + train[2018-10-23-03:41:55] Epoch: [203][3200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.080 (2.870) Prec@1 72.66 (76.66) Prec@5 88.28 (91.72) + train[2018-10-23-03:43:40] Epoch: [203][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.979 (2.871) Prec@1 71.09 (76.67) Prec@5 92.97 (91.71) + train[2018-10-23-03:45:27] Epoch: [203][3600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.958 (2.871) Prec@1 73.44 (76.66) Prec@5 89.84 (91.71) + train[2018-10-23-03:47:13] Epoch: [203][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.014 (2.871) Prec@1 75.00 (76.66) Prec@5 90.62 (91.71) + train[2018-10-23-03:48:58] Epoch: [203][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.850 (2.870) Prec@1 78.12 (76.67) Prec@5 90.62 (91.71) + train[2018-10-23-03:50:44] Epoch: [203][4200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.593 (2.871) Prec@1 80.47 (76.67) Prec@5 94.53 (91.71) + train[2018-10-23-03:52:31] Epoch: [203][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.986 (2.871) Prec@1 72.66 (76.67) Prec@5 87.50 (91.71) + train[2018-10-23-03:54:16] Epoch: [203][4600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.767 (2.871) Prec@1 78.91 (76.65) Prec@5 92.97 (91.70) + train[2018-10-23-03:56:01] Epoch: [203][4800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.531 (2.871) Prec@1 76.56 (76.66) Prec@5 96.88 (91.70) + train[2018-10-23-03:57:48] Epoch: [203][5000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.646 (2.871) Prec@1 80.47 (76.67) Prec@5 92.97 (91.71) + train[2018-10-23-03:59:33] Epoch: [203][5200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.900 (2.871) Prec@1 76.56 (76.67) Prec@5 90.62 (91.70) + train[2018-10-23-04:01:20] Epoch: [203][5400/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.829 (2.872) Prec@1 76.56 (76.68) Prec@5 92.97 (91.70) + train[2018-10-23-04:03:06] Epoch: [203][5600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.782 (2.871) Prec@1 78.91 (76.68) Prec@5 90.62 (91.70) + train[2018-10-23-04:04:52] Epoch: [203][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.924 (2.872) Prec@1 76.56 (76.66) Prec@5 89.06 (91.69) + train[2018-10-23-04:06:38] Epoch: [203][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.955 (2.872) Prec@1 72.66 (76.67) Prec@5 91.41 (91.69) + train[2018-10-23-04:08:25] Epoch: [203][6200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.759 (2.872) Prec@1 80.47 (76.67) Prec@5 92.97 (91.68) + train[2018-10-23-04:10:10] Epoch: [203][6400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.852 (2.872) Prec@1 78.12 (76.67) Prec@5 91.41 (91.68) + train[2018-10-23-04:11:56] Epoch: [203][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.526 (2.873) Prec@1 82.81 (76.66) Prec@5 92.97 (91.67) + train[2018-10-23-04:13:42] Epoch: [203][6800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.557 (2.873) Prec@1 82.81 (76.65) Prec@5 93.75 (91.67) + train[2018-10-23-04:15:28] Epoch: [203][7000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.804 (2.873) Prec@1 74.22 (76.65) Prec@5 92.19 (91.66) + train[2018-10-23-04:17:13] Epoch: [203][7200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.760 (2.874) Prec@1 74.22 (76.64) Prec@5 92.19 (91.66) + train[2018-10-23-04:19:00] Epoch: [203][7400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.909 (2.874) Prec@1 75.78 (76.64) Prec@5 90.62 (91.65) + train[2018-10-23-04:20:46] Epoch: [203][7600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.928 (2.875) Prec@1 78.12 (76.62) Prec@5 91.41 (91.65) + train[2018-10-23-04:22:32] Epoch: [203][7800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.461 (2.874) Prec@1 81.25 (76.63) Prec@5 96.88 (91.65) + train[2018-10-23-04:24:18] Epoch: [203][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.937 (2.874) Prec@1 75.00 (76.64) Prec@5 89.06 (91.65) + train[2018-10-23-04:26:03] Epoch: [203][8200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.061 (2.874) Prec@1 72.66 (76.63) Prec@5 89.84 (91.65) + train[2018-10-23-04:27:49] Epoch: [203][8400/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 3.127 (2.875) Prec@1 72.66 (76.63) Prec@5 89.84 (91.65) + train[2018-10-23-04:29:35] Epoch: [203][8600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.746 (2.875) Prec@1 81.25 (76.61) Prec@5 92.97 (91.64) + train[2018-10-23-04:31:21] Epoch: [203][8800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.140 (2.875) Prec@1 71.88 (76.62) Prec@5 89.84 (91.64) + train[2018-10-23-04:33:07] Epoch: [203][9000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.895 (2.875) Prec@1 74.22 (76.61) Prec@5 89.84 (91.64) + train[2018-10-23-04:34:53] Epoch: [203][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.954 (2.875) Prec@1 75.00 (76.62) Prec@5 89.06 (91.64) + train[2018-10-23-04:36:40] Epoch: [203][9400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.202 (2.875) Prec@1 71.88 (76.63) Prec@5 86.72 (91.64) + train[2018-10-23-04:38:26] Epoch: [203][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.774 (2.875) Prec@1 75.78 (76.62) Prec@5 95.31 (91.65) + train[2018-10-23-04:40:11] Epoch: [203][9800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.652 (2.875) Prec@1 78.91 (76.62) Prec@5 94.53 (91.65) + train[2018-10-23-04:41:57] Epoch: [203][10000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.837 (2.875) Prec@1 78.91 (76.62) Prec@5 92.97 (91.65) + train[2018-10-23-04:42:01] Epoch: [203][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 3.619 (2.875) Prec@1 53.33 (76.62) Prec@5 93.33 (91.65) +[2018-10-23-04:42:01] **train** Prec@1 76.62 Prec@5 91.65 Error@1 23.38 Error@5 8.35 Loss:2.875 + test [2018-10-23-04:42:05] Epoch: [203][000/391] Time 4.38 (4.38) Data 4.25 (4.25) Loss 0.527 (0.527) Prec@1 92.97 (92.97) Prec@5 98.44 (98.44) + test [2018-10-23-04:42:32] Epoch: [203][200/391] Time 0.13 (0.16) Data 0.00 (0.02) Loss 1.207 (1.003) Prec@1 67.97 (77.33) Prec@5 90.62 (93.66) + test [2018-10-23-04:42:58] Epoch: [203][390/391] Time 0.08 (0.14) Data 0.00 (0.01) Loss 2.142 (1.173) Prec@1 47.50 (73.73) Prec@5 82.50 (91.39) +[2018-10-23-04:42:58] **test** Prec@1 73.73 Prec@5 91.39 Error@1 26.27 Error@5 8.61 Loss:1.173 +----> Best Accuracy : Acc@1=73.92, Acc@5=91.51, Error@1=26.08, Error@5=8.49 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-23-04:42:58] [Epoch=204/250] [Need: 68:28:56] LR=0.0002 ~ 0.0002, Batch=128 + train[2018-10-23-04:43:03] Epoch: [204][000/10010] Time 4.81 (4.81) Data 4.09 (4.09) Loss 2.739 (2.739) Prec@1 78.12 (78.12) Prec@5 93.75 (93.75) + train[2018-10-23-04:44:48] Epoch: [204][200/10010] Time 0.55 (0.55) Data 0.00 (0.02) Loss 2.847 (2.865) Prec@1 78.91 (77.00) Prec@5 92.19 (91.78) + train[2018-10-23-04:46:34] Epoch: [204][400/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.734 (2.866) Prec@1 83.59 (76.99) Prec@5 94.53 (91.77) + train[2018-10-23-04:48:19] Epoch: [204][600/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 2.996 (2.869) Prec@1 76.56 (76.81) Prec@5 89.84 (91.72) + train[2018-10-23-04:50:05] Epoch: [204][800/10010] Time 0.56 (0.53) Data 0.00 (0.01) Loss 2.513 (2.870) Prec@1 85.94 (76.78) Prec@5 92.97 (91.68) + train[2018-10-23-04:51:51] Epoch: [204][1000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.012 (2.871) Prec@1 76.56 (76.81) Prec@5 89.84 (91.72) + train[2018-10-23-04:53:37] Epoch: [204][1200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.996 (2.871) Prec@1 77.34 (76.77) Prec@5 88.28 (91.74) + train[2018-10-23-04:55:22] Epoch: [204][1400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.870 (2.873) Prec@1 75.78 (76.72) Prec@5 91.41 (91.72) + train[2018-10-23-04:57:08] Epoch: [204][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.784 (2.870) Prec@1 78.91 (76.73) Prec@5 93.75 (91.76) + train[2018-10-23-04:58:53] Epoch: [204][1800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.925 (2.870) Prec@1 75.00 (76.73) Prec@5 92.97 (91.74) + train[2018-10-23-05:00:40] Epoch: [204][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.974 (2.872) Prec@1 73.44 (76.72) Prec@5 90.62 (91.71) + train[2018-10-23-05:02:26] Epoch: [204][2200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.739 (2.872) Prec@1 77.34 (76.70) Prec@5 95.31 (91.70) + train[2018-10-23-05:04:11] Epoch: [204][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.671 (2.872) Prec@1 78.91 (76.71) Prec@5 94.53 (91.71) + train[2018-10-23-05:05:58] Epoch: [204][2600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.041 (2.874) Prec@1 78.91 (76.67) Prec@5 89.06 (91.67) + train[2018-10-23-05:07:44] Epoch: [204][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.864 (2.874) Prec@1 79.69 (76.69) Prec@5 91.41 (91.66) + train[2018-10-23-05:09:30] Epoch: [204][3000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.023 (2.874) Prec@1 75.00 (76.68) Prec@5 90.62 (91.65) + train[2018-10-23-05:11:16] Epoch: [204][3200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.756 (2.874) Prec@1 71.09 (76.66) Prec@5 93.75 (91.66) + train[2018-10-23-05:13:02] Epoch: [204][3400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.958 (2.874) Prec@1 75.78 (76.65) Prec@5 91.41 (91.65) + train[2018-10-23-05:14:47] Epoch: [204][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.957 (2.875) Prec@1 75.78 (76.64) Prec@5 89.06 (91.65) + train[2018-10-23-05:16:33] Epoch: [204][3800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.642 (2.876) Prec@1 80.47 (76.63) Prec@5 92.97 (91.64) + train[2018-10-23-05:18:19] Epoch: [204][4000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.858 (2.876) Prec@1 77.34 (76.62) Prec@5 93.75 (91.64) + train[2018-10-23-05:20:06] Epoch: [204][4200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.697 (2.876) Prec@1 81.25 (76.62) Prec@5 95.31 (91.63) + train[2018-10-23-05:21:51] Epoch: [204][4400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.913 (2.876) Prec@1 76.56 (76.61) Prec@5 92.97 (91.63) + train[2018-10-23-05:23:38] Epoch: [204][4600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.896 (2.877) Prec@1 77.34 (76.61) Prec@5 88.28 (91.62) + train[2018-10-23-05:25:23] Epoch: [204][4800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.631 (2.876) Prec@1 83.59 (76.62) Prec@5 95.31 (91.63) + train[2018-10-23-05:27:10] Epoch: [204][5000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.213 (2.875) Prec@1 74.22 (76.62) Prec@5 88.28 (91.63) + train[2018-10-23-05:28:55] Epoch: [204][5200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.640 (2.875) Prec@1 82.03 (76.64) Prec@5 92.19 (91.64) + train[2018-10-23-05:30:41] Epoch: [204][5400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.759 (2.874) Prec@1 81.25 (76.64) Prec@5 91.41 (91.64) + train[2018-10-23-05:32:28] Epoch: [204][5600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.660 (2.874) Prec@1 84.38 (76.65) Prec@5 92.19 (91.65) + train[2018-10-23-05:34:14] Epoch: [204][5800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.860 (2.873) Prec@1 78.12 (76.65) Prec@5 89.84 (91.66) + train[2018-10-23-05:36:03] Epoch: [204][6000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.868 (2.873) Prec@1 76.56 (76.66) Prec@5 91.41 (91.66) + train[2018-10-23-05:37:48] Epoch: [204][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.026 (2.873) Prec@1 75.78 (76.66) Prec@5 89.84 (91.66) + train[2018-10-23-05:39:34] Epoch: [204][6400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.663 (2.873) Prec@1 80.47 (76.66) Prec@5 93.75 (91.66) + train[2018-10-23-05:41:19] Epoch: [204][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.761 (2.874) Prec@1 78.91 (76.66) Prec@5 92.19 (91.65) + train[2018-10-23-05:43:07] Epoch: [204][6800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.856 (2.873) Prec@1 76.56 (76.67) Prec@5 92.19 (91.64) + train[2018-10-23-05:44:55] Epoch: [204][7000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.043 (2.873) Prec@1 74.22 (76.67) Prec@5 89.84 (91.64) + train[2018-10-23-05:46:40] Epoch: [204][7200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.748 (2.873) Prec@1 81.25 (76.67) Prec@5 94.53 (91.65) + train[2018-10-23-05:48:27] Epoch: [204][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.890 (2.874) Prec@1 72.66 (76.66) Prec@5 92.97 (91.65) + train[2018-10-23-05:50:13] Epoch: [204][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.204 (2.874) Prec@1 67.97 (76.66) Prec@5 90.62 (91.65) + train[2018-10-23-05:51:59] Epoch: [204][7800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.816 (2.874) Prec@1 76.56 (76.66) Prec@5 92.19 (91.65) + train[2018-10-23-05:53:44] Epoch: [204][8000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.933 (2.874) Prec@1 79.69 (76.66) Prec@5 89.06 (91.65) + train[2018-10-23-05:55:31] Epoch: [204][8200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.559 (2.874) Prec@1 84.38 (76.66) Prec@5 92.97 (91.65) + train[2018-10-23-05:57:17] Epoch: [204][8400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.823 (2.873) Prec@1 73.44 (76.66) Prec@5 89.84 (91.66) + train[2018-10-23-05:59:03] Epoch: [204][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.706 (2.873) Prec@1 83.59 (76.66) Prec@5 92.19 (91.66) + train[2018-10-23-06:00:48] Epoch: [204][8800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.831 (2.873) Prec@1 80.47 (76.66) Prec@5 92.19 (91.65) + train[2018-10-23-06:02:33] Epoch: [204][9000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.875 (2.873) Prec@1 81.25 (76.66) Prec@5 91.41 (91.65) + train[2018-10-23-06:04:18] Epoch: [204][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.164 (2.873) Prec@1 69.53 (76.66) Prec@5 87.50 (91.65) + train[2018-10-23-06:06:03] Epoch: [204][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.962 (2.874) Prec@1 75.00 (76.66) Prec@5 89.84 (91.65) + train[2018-10-23-06:07:49] Epoch: [204][9600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.730 (2.873) Prec@1 78.12 (76.66) Prec@5 92.97 (91.65) + train[2018-10-23-06:09:36] Epoch: [204][9800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.612 (2.873) Prec@1 81.25 (76.66) Prec@5 94.53 (91.65) + train[2018-10-23-06:11:24] Epoch: [204][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.688 (2.874) Prec@1 79.69 (76.65) Prec@5 93.75 (91.65) + train[2018-10-23-06:11:28] Epoch: [204][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 2.958 (2.873) Prec@1 80.00 (76.65) Prec@5 100.00 (91.65) +[2018-10-23-06:11:28] **train** Prec@1 76.65 Prec@5 91.65 Error@1 23.35 Error@5 8.35 Loss:2.873 + test [2018-10-23-06:11:32] Epoch: [204][000/391] Time 3.71 (3.71) Data 3.57 (3.57) Loss 0.520 (0.520) Prec@1 93.75 (93.75) Prec@5 98.44 (98.44) + test [2018-10-23-06:12:00] Epoch: [204][200/391] Time 0.14 (0.16) Data 0.00 (0.02) Loss 1.180 (0.987) Prec@1 70.31 (77.48) Prec@5 91.41 (93.66) + test [2018-10-23-06:12:25] Epoch: [204][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.135 (1.156) Prec@1 46.25 (73.82) Prec@5 82.50 (91.42) +[2018-10-23-06:12:25] **test** Prec@1 73.82 Prec@5 91.42 Error@1 26.18 Error@5 8.58 Loss:1.156 +----> Best Accuracy : Acc@1=73.92, Acc@5=91.51, Error@1=26.08, Error@5=8.49 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-23-06:12:26] [Epoch=205/250] [Need: 67:05:47] LR=0.0002 ~ 0.0002, Batch=128 + train[2018-10-23-06:12:32] Epoch: [205][000/10010] Time 6.04 (6.04) Data 5.49 (5.49) Loss 2.716 (2.716) Prec@1 82.03 (82.03) Prec@5 94.53 (94.53) + train[2018-10-23-06:14:17] Epoch: [205][200/10010] Time 0.51 (0.55) Data 0.00 (0.03) Loss 3.017 (2.865) Prec@1 72.66 (77.09) Prec@5 87.50 (91.57) + train[2018-10-23-06:16:02] Epoch: [205][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.840 (2.873) Prec@1 77.34 (76.66) Prec@5 92.97 (91.69) + train[2018-10-23-06:17:48] Epoch: [205][600/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.549 (2.878) Prec@1 81.25 (76.55) Prec@5 95.31 (91.67) + train[2018-10-23-06:19:33] Epoch: [205][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.607 (2.875) Prec@1 84.38 (76.59) Prec@5 96.09 (91.68) + train[2018-10-23-06:21:18] Epoch: [205][1000/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.845 (2.875) Prec@1 73.44 (76.61) Prec@5 91.41 (91.65) + train[2018-10-23-06:23:03] Epoch: [205][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.946 (2.874) Prec@1 76.56 (76.64) Prec@5 91.41 (91.68) + train[2018-10-23-06:24:49] Epoch: [205][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.805 (2.876) Prec@1 78.12 (76.60) Prec@5 93.75 (91.66) + train[2018-10-23-06:26:35] Epoch: [205][1600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.795 (2.878) Prec@1 78.12 (76.55) Prec@5 93.75 (91.63) + train[2018-10-23-06:28:22] Epoch: [205][1800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.006 (2.878) Prec@1 71.88 (76.54) Prec@5 91.41 (91.65) + train[2018-10-23-06:30:08] Epoch: [205][2000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.968 (2.877) Prec@1 73.44 (76.56) Prec@5 90.62 (91.64) + train[2018-10-23-06:31:54] Epoch: [205][2200/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.722 (2.877) Prec@1 75.78 (76.57) Prec@5 92.19 (91.60) + train[2018-10-23-06:33:39] Epoch: [205][2400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.947 (2.877) Prec@1 75.00 (76.57) Prec@5 89.84 (91.61) + train[2018-10-23-06:35:24] Epoch: [205][2600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.195 (2.877) Prec@1 71.88 (76.60) Prec@5 89.84 (91.60) + train[2018-10-23-06:37:10] Epoch: [205][2800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.593 (2.877) Prec@1 85.94 (76.62) Prec@5 95.31 (91.60) + train[2018-10-23-06:38:55] Epoch: [205][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.811 (2.875) Prec@1 80.47 (76.66) Prec@5 93.75 (91.61) + train[2018-10-23-06:40:40] Epoch: [205][3200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.685 (2.874) Prec@1 80.47 (76.67) Prec@5 94.53 (91.62) + train[2018-10-23-06:42:25] Epoch: [205][3400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.708 (2.874) Prec@1 80.47 (76.69) Prec@5 94.53 (91.61) + train[2018-10-23-06:44:10] Epoch: [205][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.869 (2.873) Prec@1 76.56 (76.70) Prec@5 92.19 (91.63) + train[2018-10-23-06:45:55] Epoch: [205][3800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.018 (2.873) Prec@1 71.09 (76.69) Prec@5 86.72 (91.63) + train[2018-10-23-06:47:40] Epoch: [205][4000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.870 (2.873) Prec@1 75.00 (76.70) Prec@5 93.75 (91.64) + train[2018-10-23-06:49:25] Epoch: [205][4200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.434 (2.873) Prec@1 82.81 (76.70) Prec@5 96.88 (91.64) + train[2018-10-23-06:51:11] Epoch: [205][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.527 (2.872) Prec@1 82.81 (76.71) Prec@5 93.75 (91.64) + train[2018-10-23-06:52:58] Epoch: [205][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.878 (2.873) Prec@1 74.22 (76.71) Prec@5 91.41 (91.64) + train[2018-10-23-06:54:43] Epoch: [205][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.983 (2.873) Prec@1 72.66 (76.72) Prec@5 91.41 (91.64) + train[2018-10-23-06:56:28] Epoch: [205][5000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.090 (2.873) Prec@1 75.00 (76.70) Prec@5 88.28 (91.63) + train[2018-10-23-06:58:14] Epoch: [205][5200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.065 (2.874) Prec@1 75.78 (76.70) Prec@5 90.62 (91.63) + train[2018-10-23-07:00:00] Epoch: [205][5400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.980 (2.873) Prec@1 74.22 (76.70) Prec@5 91.41 (91.63) + train[2018-10-23-07:01:45] Epoch: [205][5600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.843 (2.872) Prec@1 79.69 (76.71) Prec@5 89.84 (91.64) + train[2018-10-23-07:03:32] Epoch: [205][5800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.820 (2.873) Prec@1 83.59 (76.70) Prec@5 89.84 (91.64) + train[2018-10-23-07:05:17] Epoch: [205][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.782 (2.873) Prec@1 75.78 (76.70) Prec@5 92.97 (91.66) + train[2018-10-23-07:07:03] Epoch: [205][6200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.177 (2.873) Prec@1 71.88 (76.71) Prec@5 86.72 (91.65) + train[2018-10-23-07:08:49] Epoch: [205][6400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.538 (2.872) Prec@1 81.25 (76.73) Prec@5 94.53 (91.66) + train[2018-10-23-07:10:34] Epoch: [205][6600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.814 (2.872) Prec@1 79.69 (76.73) Prec@5 91.41 (91.65) + train[2018-10-23-07:12:21] Epoch: [205][6800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.790 (2.872) Prec@1 78.91 (76.72) Prec@5 92.19 (91.64) + train[2018-10-23-07:14:06] Epoch: [205][7000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.567 (2.872) Prec@1 82.03 (76.72) Prec@5 94.53 (91.64) + train[2018-10-23-07:15:52] Epoch: [205][7200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.907 (2.873) Prec@1 74.22 (76.71) Prec@5 91.41 (91.64) + train[2018-10-23-07:17:41] Epoch: [205][7400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.934 (2.873) Prec@1 79.69 (76.70) Prec@5 88.28 (91.64) + train[2018-10-23-07:19:26] Epoch: [205][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.888 (2.874) Prec@1 74.22 (76.69) Prec@5 94.53 (91.63) + train[2018-10-23-07:21:12] Epoch: [205][7800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.855 (2.874) Prec@1 81.25 (76.70) Prec@5 88.28 (91.64) + train[2018-10-23-07:22:58] Epoch: [205][8000/10010] Time 0.61 (0.53) Data 0.00 (0.00) Loss 2.988 (2.874) Prec@1 71.09 (76.69) Prec@5 89.84 (91.63) + train[2018-10-23-07:24:45] Epoch: [205][8200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.848 (2.874) Prec@1 78.91 (76.68) Prec@5 92.97 (91.64) + train[2018-10-23-07:26:32] Epoch: [205][8400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.702 (2.874) Prec@1 80.47 (76.68) Prec@5 89.84 (91.63) + train[2018-10-23-07:28:20] Epoch: [205][8600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.823 (2.874) Prec@1 74.22 (76.68) Prec@5 96.09 (91.64) + train[2018-10-23-07:30:09] Epoch: [205][8800/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.976 (2.874) Prec@1 75.78 (76.68) Prec@5 90.62 (91.64) + train[2018-10-23-07:31:57] Epoch: [205][9000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.217 (2.874) Prec@1 70.31 (76.69) Prec@5 87.50 (91.64) + train[2018-10-23-07:33:46] Epoch: [205][9200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.926 (2.874) Prec@1 76.56 (76.68) Prec@5 89.84 (91.64) + train[2018-10-23-07:35:35] Epoch: [205][9400/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.658 (2.874) Prec@1 78.91 (76.68) Prec@5 93.75 (91.64) + train[2018-10-23-07:37:22] Epoch: [205][9600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.973 (2.874) Prec@1 72.66 (76.67) Prec@5 90.62 (91.64) + train[2018-10-23-07:39:08] Epoch: [205][9800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.945 (2.874) Prec@1 69.53 (76.67) Prec@5 91.41 (91.64) + train[2018-10-23-07:40:54] Epoch: [205][10000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.288 (2.874) Prec@1 64.84 (76.66) Prec@5 87.50 (91.63) + train[2018-10-23-07:40:58] Epoch: [205][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.019 (2.874) Prec@1 66.67 (76.66) Prec@5 100.00 (91.63) +[2018-10-23-07:40:58] **train** Prec@1 76.66 Prec@5 91.63 Error@1 23.34 Error@5 8.37 Loss:2.874 + test [2018-10-23-07:41:02] Epoch: [205][000/391] Time 3.87 (3.87) Data 3.74 (3.74) Loss 0.543 (0.543) Prec@1 94.53 (94.53) Prec@5 98.44 (98.44) + test [2018-10-23-07:41:30] Epoch: [205][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.169 (0.991) Prec@1 69.53 (77.44) Prec@5 92.97 (93.62) + test [2018-10-23-07:41:55] Epoch: [205][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.141 (1.161) Prec@1 48.75 (73.77) Prec@5 82.50 (91.39) +[2018-10-23-07:41:55] **test** Prec@1 73.77 Prec@5 91.39 Error@1 26.23 Error@5 8.61 Loss:1.161 +----> Best Accuracy : Acc@1=73.92, Acc@5=91.51, Error@1=26.08, Error@5=8.49 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-23-07:41:55] [Epoch=206/250] [Need: 65:37:37] LR=0.0002 ~ 0.0002, Batch=128 + train[2018-10-23-07:42:00] Epoch: [206][000/10010] Time 4.84 (4.84) Data 4.14 (4.14) Loss 2.851 (2.851) Prec@1 73.44 (73.44) Prec@5 93.75 (93.75) + train[2018-10-23-07:43:46] Epoch: [206][200/10010] Time 0.53 (0.55) Data 0.00 (0.02) Loss 2.641 (2.880) Prec@1 85.94 (76.69) Prec@5 93.75 (91.32) + train[2018-10-23-07:45:33] Epoch: [206][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.818 (2.876) Prec@1 75.78 (76.77) Prec@5 92.97 (91.41) + train[2018-10-23-07:47:21] Epoch: [206][600/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.964 (2.871) Prec@1 70.31 (76.81) Prec@5 88.28 (91.60) + train[2018-10-23-07:49:07] Epoch: [206][800/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.921 (2.867) Prec@1 74.22 (76.84) Prec@5 89.84 (91.67) + train[2018-10-23-07:50:52] Epoch: [206][1000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.932 (2.865) Prec@1 78.12 (76.83) Prec@5 89.06 (91.70) + train[2018-10-23-07:52:38] Epoch: [206][1200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 3.118 (2.866) Prec@1 75.00 (76.79) Prec@5 85.16 (91.71) + train[2018-10-23-07:54:25] Epoch: [206][1400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.957 (2.865) Prec@1 75.78 (76.81) Prec@5 89.06 (91.71) + train[2018-10-23-07:56:11] Epoch: [206][1600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.054 (2.867) Prec@1 71.88 (76.78) Prec@5 89.06 (91.69) + train[2018-10-23-07:57:57] Epoch: [206][1800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.942 (2.870) Prec@1 79.69 (76.72) Prec@5 91.41 (91.66) + train[2018-10-23-07:59:44] Epoch: [206][2000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.958 (2.869) Prec@1 75.78 (76.72) Prec@5 90.62 (91.67) + train[2018-10-23-08:01:31] Epoch: [206][2200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.797 (2.868) Prec@1 79.69 (76.73) Prec@5 92.19 (91.69) + train[2018-10-23-08:03:17] Epoch: [206][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.124 (2.868) Prec@1 73.44 (76.74) Prec@5 91.41 (91.70) + train[2018-10-23-08:05:03] Epoch: [206][2600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.933 (2.870) Prec@1 77.34 (76.71) Prec@5 91.41 (91.68) + train[2018-10-23-08:06:52] Epoch: [206][2800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.998 (2.870) Prec@1 73.44 (76.71) Prec@5 90.62 (91.66) + train[2018-10-23-08:08:38] Epoch: [206][3000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.593 (2.870) Prec@1 79.69 (76.69) Prec@5 95.31 (91.65) + train[2018-10-23-08:10:27] Epoch: [206][3200/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.805 (2.869) Prec@1 77.34 (76.71) Prec@5 91.41 (91.67) + train[2018-10-23-08:12:12] Epoch: [206][3400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.802 (2.869) Prec@1 78.91 (76.71) Prec@5 92.97 (91.67) + train[2018-10-23-08:13:59] Epoch: [206][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.683 (2.870) Prec@1 82.03 (76.69) Prec@5 96.09 (91.66) + train[2018-10-23-08:15:46] Epoch: [206][3800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.627 (2.871) Prec@1 79.69 (76.69) Prec@5 96.88 (91.67) + train[2018-10-23-08:17:34] Epoch: [206][4000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.120 (2.871) Prec@1 69.53 (76.69) Prec@5 85.94 (91.67) + train[2018-10-23-08:19:21] Epoch: [206][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.789 (2.871) Prec@1 78.12 (76.68) Prec@5 95.31 (91.66) + train[2018-10-23-08:21:08] Epoch: [206][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.908 (2.872) Prec@1 75.78 (76.68) Prec@5 92.19 (91.66) + train[2018-10-23-08:22:55] Epoch: [206][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.084 (2.872) Prec@1 73.44 (76.67) Prec@5 90.62 (91.66) + train[2018-10-23-08:24:41] Epoch: [206][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.968 (2.873) Prec@1 72.66 (76.66) Prec@5 92.19 (91.66) + train[2018-10-23-08:26:28] Epoch: [206][5000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.134 (2.872) Prec@1 72.66 (76.67) Prec@5 89.84 (91.67) + train[2018-10-23-08:28:16] Epoch: [206][5200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.948 (2.872) Prec@1 70.31 (76.67) Prec@5 91.41 (91.66) + train[2018-10-23-08:30:02] Epoch: [206][5400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.806 (2.872) Prec@1 75.00 (76.67) Prec@5 91.41 (91.66) + train[2018-10-23-08:31:48] Epoch: [206][5600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.836 (2.871) Prec@1 75.78 (76.68) Prec@5 93.75 (91.67) + train[2018-10-23-08:33:35] Epoch: [206][5800/10010] Time 0.61 (0.53) Data 0.00 (0.00) Loss 2.899 (2.872) Prec@1 71.88 (76.67) Prec@5 93.75 (91.67) + train[2018-10-23-08:35:22] Epoch: [206][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.939 (2.871) Prec@1 77.34 (76.69) Prec@5 91.41 (91.68) + train[2018-10-23-08:37:07] Epoch: [206][6200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.857 (2.871) Prec@1 80.47 (76.68) Prec@5 92.19 (91.68) + train[2018-10-23-08:38:54] Epoch: [206][6400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.927 (2.872) Prec@1 78.91 (76.67) Prec@5 90.62 (91.67) + train[2018-10-23-08:40:42] Epoch: [206][6600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.961 (2.872) Prec@1 75.00 (76.67) Prec@5 89.84 (91.67) + train[2018-10-23-08:42:28] Epoch: [206][6800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.898 (2.872) Prec@1 78.12 (76.67) Prec@5 93.75 (91.68) + train[2018-10-23-08:44:15] Epoch: [206][7000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.661 (2.872) Prec@1 82.81 (76.66) Prec@5 94.53 (91.68) + train[2018-10-23-08:46:03] Epoch: [206][7200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.788 (2.872) Prec@1 77.34 (76.67) Prec@5 90.62 (91.68) + train[2018-10-23-08:47:50] Epoch: [206][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.834 (2.872) Prec@1 74.22 (76.66) Prec@5 95.31 (91.68) + train[2018-10-23-08:49:37] Epoch: [206][7600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.958 (2.872) Prec@1 75.00 (76.66) Prec@5 92.19 (91.68) + train[2018-10-23-08:51:23] Epoch: [206][7800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.230 (2.872) Prec@1 70.31 (76.66) Prec@5 89.84 (91.68) + train[2018-10-23-08:53:09] Epoch: [206][8000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.013 (2.872) Prec@1 73.44 (76.66) Prec@5 89.06 (91.68) + train[2018-10-23-08:54:54] Epoch: [206][8200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.741 (2.872) Prec@1 82.81 (76.65) Prec@5 92.97 (91.68) + train[2018-10-23-08:56:40] Epoch: [206][8400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.746 (2.871) Prec@1 79.69 (76.66) Prec@5 93.75 (91.68) + train[2018-10-23-08:58:27] Epoch: [206][8600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.933 (2.871) Prec@1 77.34 (76.66) Prec@5 91.41 (91.68) + train[2018-10-23-09:00:14] Epoch: [206][8800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.690 (2.871) Prec@1 78.91 (76.67) Prec@5 94.53 (91.68) + train[2018-10-23-09:02:02] Epoch: [206][9000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.717 (2.871) Prec@1 80.47 (76.67) Prec@5 92.19 (91.68) + train[2018-10-23-09:03:46] Epoch: [206][9200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.620 (2.871) Prec@1 78.12 (76.67) Prec@5 96.09 (91.68) + train[2018-10-23-09:05:31] Epoch: [206][9400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.948 (2.871) Prec@1 78.12 (76.66) Prec@5 89.84 (91.68) + train[2018-10-23-09:07:17] Epoch: [206][9600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.852 (2.871) Prec@1 75.78 (76.67) Prec@5 92.97 (91.68) + train[2018-10-23-09:09:04] Epoch: [206][9800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.061 (2.871) Prec@1 73.44 (76.67) Prec@5 89.06 (91.69) + train[2018-10-23-09:10:51] Epoch: [206][10000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.834 (2.871) Prec@1 80.47 (76.67) Prec@5 93.75 (91.69) + train[2018-10-23-09:10:55] Epoch: [206][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 2.957 (2.871) Prec@1 86.67 (76.67) Prec@5 93.33 (91.69) +[2018-10-23-09:10:55] **train** Prec@1 76.67 Prec@5 91.69 Error@1 23.33 Error@5 8.31 Loss:2.871 + test [2018-10-23-09:11:00] Epoch: [206][000/391] Time 4.51 (4.51) Data 4.37 (4.37) Loss 0.568 (0.568) Prec@1 91.41 (91.41) Prec@5 98.44 (98.44) + test [2018-10-23-09:11:27] Epoch: [206][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.223 (1.006) Prec@1 67.19 (77.54) Prec@5 91.41 (93.64) + test [2018-10-23-09:11:53] Epoch: [206][390/391] Time 0.09 (0.15) Data 0.00 (0.02) Loss 2.087 (1.174) Prec@1 48.75 (73.82) Prec@5 85.00 (91.38) +[2018-10-23-09:11:53] **test** Prec@1 73.82 Prec@5 91.38 Error@1 26.18 Error@5 8.62 Loss:1.174 +----> Best Accuracy : Acc@1=73.92, Acc@5=91.51, Error@1=26.08, Error@5=8.49 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-23-09:11:54] [Epoch=207/250] [Need: 64:28:53] LR=0.0002 ~ 0.0002, Batch=128 + train[2018-10-23-09:11:59] Epoch: [207][000/10010] Time 5.81 (5.81) Data 5.23 (5.23) Loss 2.935 (2.935) Prec@1 70.31 (70.31) Prec@5 93.75 (93.75) + train[2018-10-23-09:13:44] Epoch: [207][200/10010] Time 0.53 (0.55) Data 0.00 (0.03) Loss 2.804 (2.855) Prec@1 78.12 (77.02) Prec@5 92.97 (91.90) + train[2018-10-23-09:15:30] Epoch: [207][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.509 (2.859) Prec@1 84.38 (76.92) Prec@5 93.75 (91.78) + train[2018-10-23-09:17:15] Epoch: [207][600/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 3.057 (2.863) Prec@1 73.44 (76.92) Prec@5 88.28 (91.72) + train[2018-10-23-09:19:01] Epoch: [207][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 2.861 (2.863) Prec@1 72.66 (76.90) Prec@5 94.53 (91.73) + train[2018-10-23-09:20:46] Epoch: [207][1000/10010] Time 0.59 (0.53) Data 0.00 (0.01) Loss 3.102 (2.865) Prec@1 71.88 (76.82) Prec@5 90.62 (91.73) + train[2018-10-23-09:22:32] Epoch: [207][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.255 (2.866) Prec@1 69.53 (76.76) Prec@5 87.50 (91.73) + train[2018-10-23-09:24:17] Epoch: [207][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.958 (2.867) Prec@1 75.00 (76.75) Prec@5 89.84 (91.71) + train[2018-10-23-09:26:02] Epoch: [207][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.785 (2.866) Prec@1 76.56 (76.77) Prec@5 89.84 (91.73) + train[2018-10-23-09:27:48] Epoch: [207][1800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.984 (2.866) Prec@1 75.00 (76.79) Prec@5 90.62 (91.72) + train[2018-10-23-09:29:34] Epoch: [207][2000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.781 (2.866) Prec@1 80.47 (76.79) Prec@5 91.41 (91.74) + train[2018-10-23-09:31:22] Epoch: [207][2200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.097 (2.867) Prec@1 71.09 (76.79) Prec@5 89.84 (91.74) + train[2018-10-23-09:33:10] Epoch: [207][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.775 (2.865) Prec@1 78.91 (76.81) Prec@5 92.97 (91.75) + train[2018-10-23-09:34:57] Epoch: [207][2600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.497 (2.865) Prec@1 84.38 (76.83) Prec@5 96.88 (91.75) + train[2018-10-23-09:36:43] Epoch: [207][2800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.746 (2.866) Prec@1 78.91 (76.80) Prec@5 94.53 (91.73) + train[2018-10-23-09:38:28] Epoch: [207][3000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.767 (2.867) Prec@1 79.69 (76.79) Prec@5 94.53 (91.71) + train[2018-10-23-09:40:13] Epoch: [207][3200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.868 (2.868) Prec@1 77.34 (76.77) Prec@5 93.75 (91.71) + train[2018-10-23-09:42:00] Epoch: [207][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.020 (2.868) Prec@1 78.91 (76.75) Prec@5 89.06 (91.70) + train[2018-10-23-09:43:45] Epoch: [207][3600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.011 (2.869) Prec@1 73.44 (76.74) Prec@5 90.62 (91.71) + train[2018-10-23-09:45:31] Epoch: [207][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.792 (2.868) Prec@1 76.56 (76.74) Prec@5 92.19 (91.70) + train[2018-10-23-09:47:17] Epoch: [207][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.931 (2.868) Prec@1 72.66 (76.75) Prec@5 90.62 (91.70) + train[2018-10-23-09:49:03] Epoch: [207][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.086 (2.868) Prec@1 69.53 (76.75) Prec@5 91.41 (91.71) + train[2018-10-23-09:50:50] Epoch: [207][4400/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.799 (2.868) Prec@1 78.91 (76.76) Prec@5 93.75 (91.71) + train[2018-10-23-09:52:38] Epoch: [207][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.901 (2.868) Prec@1 75.78 (76.74) Prec@5 93.75 (91.71) + train[2018-10-23-09:54:23] Epoch: [207][4800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.128 (2.869) Prec@1 71.88 (76.73) Prec@5 89.06 (91.70) + train[2018-10-23-09:56:08] Epoch: [207][5000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.876 (2.870) Prec@1 73.44 (76.72) Prec@5 92.19 (91.70) + train[2018-10-23-09:57:54] Epoch: [207][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.014 (2.870) Prec@1 72.66 (76.71) Prec@5 91.41 (91.69) + train[2018-10-23-09:59:39] Epoch: [207][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.834 (2.870) Prec@1 75.00 (76.70) Prec@5 92.19 (91.69) + train[2018-10-23-10:01:26] Epoch: [207][5600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.655 (2.870) Prec@1 81.25 (76.71) Prec@5 92.97 (91.69) + train[2018-10-23-10:03:12] Epoch: [207][5800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.835 (2.870) Prec@1 75.78 (76.70) Prec@5 92.19 (91.68) + train[2018-10-23-10:04:58] Epoch: [207][6000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.776 (2.870) Prec@1 81.25 (76.70) Prec@5 90.62 (91.67) + train[2018-10-23-10:06:45] Epoch: [207][6200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.228 (2.871) Prec@1 68.75 (76.69) Prec@5 89.06 (91.66) + train[2018-10-23-10:08:30] Epoch: [207][6400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.881 (2.871) Prec@1 75.00 (76.69) Prec@5 92.97 (91.66) + train[2018-10-23-10:10:15] Epoch: [207][6600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.984 (2.871) Prec@1 75.78 (76.69) Prec@5 92.19 (91.66) + train[2018-10-23-10:12:02] Epoch: [207][6800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.765 (2.871) Prec@1 75.78 (76.69) Prec@5 93.75 (91.66) + train[2018-10-23-10:13:49] Epoch: [207][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.931 (2.871) Prec@1 74.22 (76.67) Prec@5 94.53 (91.65) + train[2018-10-23-10:15:37] Epoch: [207][7200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.511 (2.872) Prec@1 85.94 (76.66) Prec@5 94.53 (91.65) + train[2018-10-23-10:17:24] Epoch: [207][7400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.014 (2.872) Prec@1 75.78 (76.67) Prec@5 89.06 (91.64) + train[2018-10-23-10:19:12] Epoch: [207][7600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.953 (2.871) Prec@1 76.56 (76.67) Prec@5 91.41 (91.65) + train[2018-10-23-10:20:59] Epoch: [207][7800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.767 (2.871) Prec@1 80.47 (76.67) Prec@5 93.75 (91.65) + train[2018-10-23-10:22:47] Epoch: [207][8000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.935 (2.871) Prec@1 74.22 (76.67) Prec@5 92.97 (91.65) + train[2018-10-23-10:24:34] Epoch: [207][8200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.112 (2.872) Prec@1 72.66 (76.66) Prec@5 88.28 (91.65) + train[2018-10-23-10:26:20] Epoch: [207][8400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.945 (2.872) Prec@1 75.78 (76.65) Prec@5 91.41 (91.64) + train[2018-10-23-10:28:06] Epoch: [207][8600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.918 (2.872) Prec@1 74.22 (76.65) Prec@5 90.62 (91.64) + train[2018-10-23-10:29:52] Epoch: [207][8800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.025 (2.872) Prec@1 70.31 (76.65) Prec@5 91.41 (91.65) + train[2018-10-23-10:31:37] Epoch: [207][9000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.893 (2.871) Prec@1 77.34 (76.66) Prec@5 92.97 (91.65) + train[2018-10-23-10:33:23] Epoch: [207][9200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.920 (2.871) Prec@1 78.12 (76.66) Prec@5 89.84 (91.65) + train[2018-10-23-10:35:11] Epoch: [207][9400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.765 (2.871) Prec@1 78.12 (76.66) Prec@5 90.62 (91.65) + train[2018-10-23-10:36:58] Epoch: [207][9600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.135 (2.872) Prec@1 72.66 (76.66) Prec@5 88.28 (91.65) + train[2018-10-23-10:38:45] Epoch: [207][9800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.953 (2.872) Prec@1 75.00 (76.65) Prec@5 91.41 (91.64) + train[2018-10-23-10:40:31] Epoch: [207][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.900 (2.872) Prec@1 78.91 (76.66) Prec@5 89.84 (91.65) + train[2018-10-23-10:40:35] Epoch: [207][10009/10010] Time 0.22 (0.53) Data 0.00 (0.00) Loss 3.391 (2.872) Prec@1 73.33 (76.66) Prec@5 80.00 (91.65) +[2018-10-23-10:40:35] **train** Prec@1 76.66 Prec@5 91.65 Error@1 23.34 Error@5 8.35 Loss:2.872 + test [2018-10-23-10:40:39] Epoch: [207][000/391] Time 4.02 (4.02) Data 3.88 (3.88) Loss 0.567 (0.567) Prec@1 92.19 (92.19) Prec@5 98.44 (98.44) + test [2018-10-23-10:41:07] Epoch: [207][200/391] Time 0.14 (0.16) Data 0.00 (0.03) Loss 1.173 (0.992) Prec@1 67.97 (77.43) Prec@5 91.41 (93.58) + test [2018-10-23-10:41:33] Epoch: [207][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.121 (1.163) Prec@1 48.75 (73.81) Prec@5 81.25 (91.38) +[2018-10-23-10:41:33] **test** Prec@1 73.81 Prec@5 91.38 Error@1 26.19 Error@5 8.62 Loss:1.163 +----> Best Accuracy : Acc@1=73.92, Acc@5=91.51, Error@1=26.08, Error@5=8.49 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-23-10:41:33] [Epoch=208/250] [Need: 62:45:39] LR=0.0002 ~ 0.0002, Batch=128 + train[2018-10-23-10:41:37] Epoch: [208][000/10010] Time 4.46 (4.46) Data 3.86 (3.86) Loss 2.666 (2.666) Prec@1 79.69 (79.69) Prec@5 95.31 (95.31) + train[2018-10-23-10:43:24] Epoch: [208][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.261 (2.872) Prec@1 67.97 (76.70) Prec@5 86.72 (91.64) + train[2018-10-23-10:45:10] Epoch: [208][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.983 (2.861) Prec@1 71.88 (76.79) Prec@5 89.84 (91.78) + train[2018-10-23-10:46:56] Epoch: [208][600/10010] Time 0.54 (0.54) Data 0.00 (0.01) Loss 2.847 (2.860) Prec@1 80.47 (76.93) Prec@5 92.19 (91.80) + train[2018-10-23-10:48:43] Epoch: [208][800/10010] Time 0.56 (0.54) Data 0.00 (0.01) Loss 2.750 (2.869) Prec@1 78.91 (76.72) Prec@5 93.75 (91.72) + train[2018-10-23-10:50:31] Epoch: [208][1000/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.783 (2.866) Prec@1 78.91 (76.71) Prec@5 93.75 (91.73) + train[2018-10-23-10:52:17] Epoch: [208][1200/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.217 (2.869) Prec@1 69.53 (76.65) Prec@5 89.84 (91.69) + train[2018-10-23-10:54:04] Epoch: [208][1400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.015 (2.869) Prec@1 75.78 (76.64) Prec@5 91.41 (91.67) + train[2018-10-23-10:55:52] Epoch: [208][1600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.944 (2.866) Prec@1 72.66 (76.72) Prec@5 92.19 (91.71) + train[2018-10-23-10:57:39] Epoch: [208][1800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 3.109 (2.867) Prec@1 72.66 (76.71) Prec@5 87.50 (91.69) + train[2018-10-23-10:59:25] Epoch: [208][2000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.781 (2.867) Prec@1 80.47 (76.70) Prec@5 90.62 (91.69) + train[2018-10-23-11:01:11] Epoch: [208][2200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.928 (2.870) Prec@1 71.88 (76.68) Prec@5 92.19 (91.67) + train[2018-10-23-11:02:57] Epoch: [208][2400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.938 (2.870) Prec@1 75.78 (76.69) Prec@5 92.97 (91.66) + train[2018-10-23-11:04:44] Epoch: [208][2600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.668 (2.871) Prec@1 82.03 (76.68) Prec@5 93.75 (91.64) + train[2018-10-23-11:06:31] Epoch: [208][2800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.008 (2.871) Prec@1 77.34 (76.70) Prec@5 90.62 (91.63) + train[2018-10-23-11:08:17] Epoch: [208][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.898 (2.871) Prec@1 78.12 (76.70) Prec@5 90.62 (91.62) + train[2018-10-23-11:10:05] Epoch: [208][3200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.923 (2.870) Prec@1 75.00 (76.73) Prec@5 92.19 (91.64) + train[2018-10-23-11:11:53] Epoch: [208][3400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.818 (2.870) Prec@1 77.34 (76.72) Prec@5 91.41 (91.65) + train[2018-10-23-11:13:41] Epoch: [208][3600/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.956 (2.870) Prec@1 75.78 (76.70) Prec@5 94.53 (91.66) + train[2018-10-23-11:15:27] Epoch: [208][3800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.732 (2.871) Prec@1 79.69 (76.68) Prec@5 93.75 (91.66) + train[2018-10-23-11:17:13] Epoch: [208][4000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.814 (2.871) Prec@1 75.78 (76.67) Prec@5 92.97 (91.66) + train[2018-10-23-11:19:01] Epoch: [208][4200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.772 (2.872) Prec@1 78.12 (76.66) Prec@5 91.41 (91.65) + train[2018-10-23-11:20:49] Epoch: [208][4400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.806 (2.872) Prec@1 78.91 (76.66) Prec@5 92.97 (91.64) + train[2018-10-23-11:22:35] Epoch: [208][4600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.830 (2.872) Prec@1 76.56 (76.65) Prec@5 91.41 (91.64) + train[2018-10-23-11:24:21] Epoch: [208][4800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.722 (2.872) Prec@1 76.56 (76.65) Prec@5 93.75 (91.64) + train[2018-10-23-11:26:08] Epoch: [208][5000/10010] Time 0.61 (0.53) Data 0.00 (0.00) Loss 3.129 (2.873) Prec@1 73.44 (76.63) Prec@5 88.28 (91.64) + train[2018-10-23-11:27:56] Epoch: [208][5200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.865 (2.873) Prec@1 76.56 (76.63) Prec@5 92.97 (91.64) + train[2018-10-23-11:29:44] Epoch: [208][5400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.948 (2.873) Prec@1 76.56 (76.62) Prec@5 90.62 (91.64) + train[2018-10-23-11:31:30] Epoch: [208][5600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.802 (2.873) Prec@1 78.12 (76.63) Prec@5 92.19 (91.64) + train[2018-10-23-11:33:18] Epoch: [208][5800/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.762 (2.873) Prec@1 77.34 (76.64) Prec@5 92.19 (91.64) + train[2018-10-23-11:35:05] Epoch: [208][6000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.900 (2.873) Prec@1 75.78 (76.64) Prec@5 91.41 (91.64) + train[2018-10-23-11:36:52] Epoch: [208][6200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.837 (2.872) Prec@1 78.12 (76.63) Prec@5 90.62 (91.64) + train[2018-10-23-11:38:37] Epoch: [208][6400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.149 (2.873) Prec@1 75.00 (76.63) Prec@5 88.28 (91.63) + train[2018-10-23-11:40:25] Epoch: [208][6600/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 2.823 (2.872) Prec@1 82.81 (76.65) Prec@5 90.62 (91.64) + train[2018-10-23-11:42:12] Epoch: [208][6800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.944 (2.872) Prec@1 73.44 (76.66) Prec@5 92.19 (91.64) + train[2018-10-23-11:43:58] Epoch: [208][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.835 (2.872) Prec@1 75.78 (76.65) Prec@5 92.97 (91.64) + train[2018-10-23-11:45:46] Epoch: [208][7200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.754 (2.873) Prec@1 82.03 (76.63) Prec@5 89.84 (91.63) + train[2018-10-23-11:47:34] Epoch: [208][7400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.620 (2.873) Prec@1 78.12 (76.63) Prec@5 95.31 (91.63) + train[2018-10-23-11:49:21] Epoch: [208][7600/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.974 (2.873) Prec@1 75.78 (76.63) Prec@5 90.62 (91.63) + train[2018-10-23-11:51:10] Epoch: [208][7800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.631 (2.874) Prec@1 81.25 (76.62) Prec@5 92.19 (91.62) + train[2018-10-23-11:52:58] Epoch: [208][8000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.671 (2.874) Prec@1 78.91 (76.62) Prec@5 92.97 (91.62) + train[2018-10-23-11:54:47] Epoch: [208][8200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.890 (2.874) Prec@1 74.22 (76.62) Prec@5 90.62 (91.62) + train[2018-10-23-11:56:35] Epoch: [208][8400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.840 (2.874) Prec@1 74.22 (76.62) Prec@5 92.19 (91.62) + train[2018-10-23-11:58:23] Epoch: [208][8600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.586 (2.874) Prec@1 82.03 (76.61) Prec@5 95.31 (91.62) + train[2018-10-23-12:00:12] Epoch: [208][8800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.627 (2.874) Prec@1 78.91 (76.61) Prec@5 96.09 (91.62) + train[2018-10-23-12:01:58] Epoch: [208][9000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.704 (2.874) Prec@1 83.59 (76.61) Prec@5 96.09 (91.62) + train[2018-10-23-12:03:46] Epoch: [208][9200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.981 (2.874) Prec@1 73.44 (76.61) Prec@5 90.62 (91.62) + train[2018-10-23-12:05:34] Epoch: [208][9400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.488 (2.874) Prec@1 78.12 (76.62) Prec@5 96.09 (91.62) + train[2018-10-23-12:07:22] Epoch: [208][9600/10010] Time 0.60 (0.54) Data 0.00 (0.00) Loss 2.616 (2.874) Prec@1 79.69 (76.61) Prec@5 95.31 (91.62) + train[2018-10-23-12:09:10] Epoch: [208][9800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.549 (2.874) Prec@1 84.38 (76.63) Prec@5 96.09 (91.62) + train[2018-10-23-12:10:58] Epoch: [208][10000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.953 (2.873) Prec@1 78.12 (76.63) Prec@5 90.62 (91.63) + train[2018-10-23-12:11:02] Epoch: [208][10009/10010] Time 0.19 (0.54) Data 0.00 (0.00) Loss 3.549 (2.873) Prec@1 80.00 (76.63) Prec@5 93.33 (91.63) +[2018-10-23-12:11:02] **train** Prec@1 76.63 Prec@5 91.63 Error@1 23.37 Error@5 8.37 Loss:2.873 + test [2018-10-23-12:11:07] Epoch: [208][000/391] Time 4.45 (4.45) Data 4.31 (4.31) Loss 0.541 (0.541) Prec@1 92.97 (92.97) Prec@5 98.44 (98.44) + test [2018-10-23-12:11:34] Epoch: [208][200/391] Time 0.14 (0.16) Data 0.00 (0.03) Loss 1.172 (0.995) Prec@1 68.75 (77.50) Prec@5 92.19 (93.68) + test [2018-10-23-12:12:02] Epoch: [208][390/391] Time 0.09 (0.15) Data 0.00 (0.02) Loss 2.148 (1.162) Prec@1 47.50 (73.98) Prec@5 83.75 (91.44) +[2018-10-23-12:12:02] **test** Prec@1 73.98 Prec@5 91.44 Error@1 26.02 Error@5 8.56 Loss:1.162 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-23-12:12:02] [Epoch=209/250] [Need: 61:50:01] LR=0.0002 ~ 0.0002, Batch=128 + train[2018-10-23-12:12:08] Epoch: [209][000/10010] Time 5.59 (5.59) Data 5.03 (5.03) Loss 2.549 (2.549) Prec@1 84.38 (84.38) Prec@5 94.53 (94.53) + train[2018-10-23-12:13:53] Epoch: [209][200/10010] Time 0.51 (0.55) Data 0.00 (0.03) Loss 2.767 (2.870) Prec@1 83.59 (77.00) Prec@5 92.19 (91.63) + train[2018-10-23-12:15:39] Epoch: [209][400/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.888 (2.862) Prec@1 78.12 (77.05) Prec@5 91.41 (91.75) + train[2018-10-23-12:17:25] Epoch: [209][600/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.987 (2.858) Prec@1 78.12 (77.03) Prec@5 86.72 (91.75) + train[2018-10-23-12:19:11] Epoch: [209][800/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.891 (2.859) Prec@1 74.22 (77.03) Prec@5 92.97 (91.76) + train[2018-10-23-12:20:59] Epoch: [209][1000/10010] Time 0.54 (0.54) Data 0.00 (0.01) Loss 3.246 (2.861) Prec@1 75.00 (76.93) Prec@5 87.50 (91.76) + train[2018-10-23-12:22:46] Epoch: [209][1200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.755 (2.868) Prec@1 78.91 (76.82) Prec@5 92.97 (91.71) + train[2018-10-23-12:24:34] Epoch: [209][1400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.425 (2.867) Prec@1 85.94 (76.83) Prec@5 96.09 (91.72) + train[2018-10-23-12:26:21] Epoch: [209][1600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.841 (2.867) Prec@1 74.22 (76.81) Prec@5 90.62 (91.69) + train[2018-10-23-12:28:08] Epoch: [209][1800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 3.059 (2.867) Prec@1 72.66 (76.83) Prec@5 89.06 (91.69) + train[2018-10-23-12:29:56] Epoch: [209][2000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.960 (2.867) Prec@1 73.44 (76.83) Prec@5 94.53 (91.71) + train[2018-10-23-12:31:44] Epoch: [209][2200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.983 (2.866) Prec@1 75.78 (76.84) Prec@5 90.62 (91.71) + train[2018-10-23-12:33:31] Epoch: [209][2400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.028 (2.867) Prec@1 77.34 (76.80) Prec@5 85.16 (91.70) + train[2018-10-23-12:35:18] Epoch: [209][2600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.255 (2.867) Prec@1 67.97 (76.82) Prec@5 86.72 (91.71) + train[2018-10-23-12:37:05] Epoch: [209][2800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.775 (2.867) Prec@1 76.56 (76.83) Prec@5 95.31 (91.69) + train[2018-10-23-12:38:52] Epoch: [209][3000/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.024 (2.867) Prec@1 73.44 (76.82) Prec@5 88.28 (91.67) + train[2018-10-23-12:40:40] Epoch: [209][3200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.776 (2.867) Prec@1 78.91 (76.80) Prec@5 94.53 (91.68) + train[2018-10-23-12:42:27] Epoch: [209][3400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.156 (2.867) Prec@1 67.97 (76.79) Prec@5 89.84 (91.68) + train[2018-10-23-12:44:14] Epoch: [209][3600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.839 (2.867) Prec@1 79.69 (76.79) Prec@5 89.84 (91.68) + train[2018-10-23-12:46:01] Epoch: [209][3800/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.738 (2.866) Prec@1 81.25 (76.80) Prec@5 90.62 (91.68) + train[2018-10-23-12:47:49] Epoch: [209][4000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.818 (2.867) Prec@1 75.78 (76.79) Prec@5 93.75 (91.68) + train[2018-10-23-12:49:36] Epoch: [209][4200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.799 (2.868) Prec@1 78.91 (76.77) Prec@5 94.53 (91.68) + train[2018-10-23-12:51:24] Epoch: [209][4400/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 3.034 (2.868) Prec@1 75.00 (76.77) Prec@5 89.84 (91.67) + train[2018-10-23-12:53:10] Epoch: [209][4600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.922 (2.868) Prec@1 78.91 (76.77) Prec@5 90.62 (91.67) + train[2018-10-23-12:54:57] Epoch: [209][4800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.139 (2.869) Prec@1 70.31 (76.75) Prec@5 89.84 (91.66) + train[2018-10-23-12:56:44] Epoch: [209][5000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.704 (2.869) Prec@1 78.12 (76.74) Prec@5 93.75 (91.65) + train[2018-10-23-12:58:32] Epoch: [209][5200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.943 (2.869) Prec@1 78.12 (76.75) Prec@5 93.75 (91.66) + train[2018-10-23-13:00:19] Epoch: [209][5400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.948 (2.869) Prec@1 75.00 (76.75) Prec@5 89.06 (91.66) + train[2018-10-23-13:02:07] Epoch: [209][5600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.894 (2.870) Prec@1 71.88 (76.73) Prec@5 91.41 (91.65) + train[2018-10-23-13:03:53] Epoch: [209][5800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.684 (2.870) Prec@1 79.69 (76.73) Prec@5 92.19 (91.65) + train[2018-10-23-13:05:41] Epoch: [209][6000/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.740 (2.870) Prec@1 75.78 (76.73) Prec@5 95.31 (91.64) + train[2018-10-23-13:07:28] Epoch: [209][6200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 3.103 (2.870) Prec@1 75.00 (76.74) Prec@5 89.06 (91.65) + train[2018-10-23-13:09:16] Epoch: [209][6400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.276 (2.870) Prec@1 70.31 (76.74) Prec@5 87.50 (91.64) + train[2018-10-23-13:11:03] Epoch: [209][6600/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.885 (2.869) Prec@1 76.56 (76.75) Prec@5 93.75 (91.65) + train[2018-10-23-13:12:50] Epoch: [209][6800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.660 (2.869) Prec@1 81.25 (76.76) Prec@5 92.19 (91.66) + train[2018-10-23-13:14:37] Epoch: [209][7000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 3.015 (2.869) Prec@1 75.00 (76.75) Prec@5 89.84 (91.66) + train[2018-10-23-13:16:25] Epoch: [209][7200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.659 (2.870) Prec@1 79.69 (76.75) Prec@5 94.53 (91.66) + train[2018-10-23-13:18:13] Epoch: [209][7400/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.714 (2.870) Prec@1 84.38 (76.76) Prec@5 92.97 (91.66) + train[2018-10-23-13:20:01] Epoch: [209][7600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.008 (2.870) Prec@1 76.56 (76.75) Prec@5 89.06 (91.66) + train[2018-10-23-13:21:48] Epoch: [209][7800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.878 (2.870) Prec@1 81.25 (76.75) Prec@5 89.84 (91.66) + train[2018-10-23-13:23:37] Epoch: [209][8000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.844 (2.870) Prec@1 74.22 (76.75) Prec@5 95.31 (91.67) + train[2018-10-23-13:25:24] Epoch: [209][8200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.718 (2.870) Prec@1 82.03 (76.75) Prec@5 93.75 (91.67) + train[2018-10-23-13:27:12] Epoch: [209][8400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.901 (2.870) Prec@1 73.44 (76.74) Prec@5 91.41 (91.67) + train[2018-10-23-13:28:58] Epoch: [209][8600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.646 (2.870) Prec@1 78.91 (76.75) Prec@5 95.31 (91.67) + train[2018-10-23-13:30:46] Epoch: [209][8800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.889 (2.870) Prec@1 75.00 (76.75) Prec@5 91.41 (91.67) + train[2018-10-23-13:32:34] Epoch: [209][9000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.544 (2.870) Prec@1 82.81 (76.75) Prec@5 95.31 (91.67) + train[2018-10-23-13:34:22] Epoch: [209][9200/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.866 (2.870) Prec@1 71.88 (76.74) Prec@5 91.41 (91.67) + train[2018-10-23-13:36:09] Epoch: [209][9400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.720 (2.870) Prec@1 78.12 (76.73) Prec@5 92.97 (91.68) + train[2018-10-23-13:37:55] Epoch: [209][9600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.703 (2.870) Prec@1 82.03 (76.72) Prec@5 92.97 (91.67) + train[2018-10-23-13:39:42] Epoch: [209][9800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.819 (2.870) Prec@1 79.69 (76.73) Prec@5 91.41 (91.67) + train[2018-10-23-13:41:29] Epoch: [209][10000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.738 (2.870) Prec@1 81.25 (76.73) Prec@5 94.53 (91.67) + train[2018-10-23-13:41:33] Epoch: [209][10009/10010] Time 0.20 (0.54) Data 0.00 (0.00) Loss 3.549 (2.870) Prec@1 66.67 (76.73) Prec@5 93.33 (91.67) +[2018-10-23-13:41:33] **train** Prec@1 76.73 Prec@5 91.67 Error@1 23.27 Error@5 8.33 Loss:2.870 + test [2018-10-23-13:41:38] Epoch: [209][000/391] Time 4.39 (4.39) Data 4.25 (4.25) Loss 0.546 (0.546) Prec@1 92.97 (92.97) Prec@5 98.44 (98.44) + test [2018-10-23-13:42:07] Epoch: [209][200/391] Time 0.15 (0.17) Data 0.00 (0.03) Loss 1.170 (0.989) Prec@1 71.09 (77.31) Prec@5 91.41 (93.64) + test [2018-10-23-13:42:33] Epoch: [209][390/391] Time 0.09 (0.15) Data 0.00 (0.02) Loss 2.139 (1.157) Prec@1 45.00 (73.81) Prec@5 82.50 (91.45) +[2018-10-23-13:42:33] **test** Prec@1 73.81 Prec@5 91.45 Error@1 26.19 Error@5 8.55 Loss:1.157 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-23-13:42:33] [Epoch=210/250] [Need: 60:20:43] LR=0.0002 ~ 0.0002, Batch=128 + train[2018-10-23-13:42:38] Epoch: [210][000/10010] Time 4.71 (4.71) Data 4.09 (4.09) Loss 3.104 (3.104) Prec@1 71.09 (71.09) Prec@5 87.50 (87.50) + train[2018-10-23-13:44:24] Epoch: [210][200/10010] Time 0.52 (0.55) Data 0.00 (0.02) Loss 3.347 (2.873) Prec@1 70.31 (76.92) Prec@5 85.94 (91.62) + train[2018-10-23-13:46:09] Epoch: [210][400/10010] Time 0.57 (0.54) Data 0.00 (0.01) Loss 3.158 (2.869) Prec@1 69.53 (76.89) Prec@5 88.28 (91.61) + train[2018-10-23-13:47:55] Epoch: [210][600/10010] Time 0.54 (0.54) Data 0.00 (0.01) Loss 3.241 (2.866) Prec@1 69.53 (76.93) Prec@5 90.62 (91.66) + train[2018-10-23-13:49:40] Epoch: [210][800/10010] Time 0.57 (0.53) Data 0.00 (0.01) Loss 2.676 (2.862) Prec@1 77.34 (76.98) Prec@5 94.53 (91.69) + train[2018-10-23-13:51:26] Epoch: [210][1000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.935 (2.862) Prec@1 78.91 (76.99) Prec@5 88.28 (91.71) + train[2018-10-23-13:53:11] Epoch: [210][1200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.753 (2.866) Prec@1 79.69 (76.85) Prec@5 92.97 (91.67) + train[2018-10-23-13:54:57] Epoch: [210][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.172 (2.867) Prec@1 74.22 (76.85) Prec@5 85.94 (91.69) + train[2018-10-23-13:56:42] Epoch: [210][1600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.884 (2.866) Prec@1 78.91 (76.82) Prec@5 91.41 (91.71) + train[2018-10-23-13:58:29] Epoch: [210][1800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.915 (2.870) Prec@1 78.91 (76.77) Prec@5 89.84 (91.67) + train[2018-10-23-14:00:14] Epoch: [210][2000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.086 (2.869) Prec@1 71.88 (76.78) Prec@5 88.28 (91.70) + train[2018-10-23-14:02:01] Epoch: [210][2200/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.520 (2.869) Prec@1 83.59 (76.78) Prec@5 94.53 (91.69) + train[2018-10-23-14:03:48] Epoch: [210][2400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.697 (2.868) Prec@1 80.47 (76.80) Prec@5 94.53 (91.69) + train[2018-10-23-14:05:35] Epoch: [210][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.807 (2.868) Prec@1 79.69 (76.76) Prec@5 90.62 (91.69) + train[2018-10-23-14:07:21] Epoch: [210][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.751 (2.868) Prec@1 77.34 (76.75) Prec@5 93.75 (91.70) + train[2018-10-23-14:09:06] Epoch: [210][3000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.798 (2.868) Prec@1 80.47 (76.75) Prec@5 89.84 (91.71) + train[2018-10-23-14:10:54] Epoch: [210][3200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.003 (2.868) Prec@1 77.34 (76.74) Prec@5 89.84 (91.71) + train[2018-10-23-14:12:40] Epoch: [210][3400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.722 (2.868) Prec@1 79.69 (76.75) Prec@5 91.41 (91.70) + train[2018-10-23-14:14:26] Epoch: [210][3600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.839 (2.867) Prec@1 77.34 (76.76) Prec@5 92.19 (91.71) + train[2018-10-23-14:16:12] Epoch: [210][3800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.869 (2.868) Prec@1 79.69 (76.74) Prec@5 90.62 (91.70) + train[2018-10-23-14:17:58] Epoch: [210][4000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.259 (2.867) Prec@1 74.22 (76.77) Prec@5 85.16 (91.71) + train[2018-10-23-14:19:44] Epoch: [210][4200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.484 (2.867) Prec@1 80.47 (76.77) Prec@5 96.88 (91.71) + train[2018-10-23-14:21:30] Epoch: [210][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.948 (2.868) Prec@1 76.56 (76.74) Prec@5 89.06 (91.70) + train[2018-10-23-14:23:17] Epoch: [210][4600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.916 (2.869) Prec@1 75.78 (76.71) Prec@5 93.75 (91.70) + train[2018-10-23-14:25:02] Epoch: [210][4800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.084 (2.870) Prec@1 75.78 (76.70) Prec@5 89.06 (91.69) + train[2018-10-23-14:26:50] Epoch: [210][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.657 (2.870) Prec@1 79.69 (76.69) Prec@5 96.88 (91.68) + train[2018-10-23-14:28:36] Epoch: [210][5200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.873 (2.871) Prec@1 75.00 (76.69) Prec@5 93.75 (91.68) + train[2018-10-23-14:30:23] Epoch: [210][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.136 (2.871) Prec@1 71.09 (76.69) Prec@5 89.06 (91.68) + train[2018-10-23-14:32:10] Epoch: [210][5600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.043 (2.870) Prec@1 75.78 (76.69) Prec@5 88.28 (91.69) + train[2018-10-23-14:33:57] Epoch: [210][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.685 (2.870) Prec@1 77.34 (76.70) Prec@5 94.53 (91.70) + train[2018-10-23-14:35:43] Epoch: [210][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.111 (2.870) Prec@1 72.66 (76.70) Prec@5 87.50 (91.71) + train[2018-10-23-14:37:29] Epoch: [210][6200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.052 (2.870) Prec@1 71.09 (76.69) Prec@5 88.28 (91.70) + train[2018-10-23-14:39:15] Epoch: [210][6400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.110 (2.870) Prec@1 78.12 (76.70) Prec@5 89.06 (91.69) + train[2018-10-23-14:41:02] Epoch: [210][6600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.894 (2.870) Prec@1 75.78 (76.69) Prec@5 89.06 (91.69) + train[2018-10-23-14:42:50] Epoch: [210][6800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.045 (2.870) Prec@1 74.22 (76.70) Prec@5 89.84 (91.70) + train[2018-10-23-14:44:37] Epoch: [210][7000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.647 (2.870) Prec@1 82.81 (76.71) Prec@5 93.75 (91.70) + train[2018-10-23-14:46:24] Epoch: [210][7200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.960 (2.870) Prec@1 75.00 (76.70) Prec@5 89.84 (91.69) + train[2018-10-23-14:48:10] Epoch: [210][7400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.889 (2.870) Prec@1 75.78 (76.70) Prec@5 89.06 (91.69) + train[2018-10-23-14:49:57] Epoch: [210][7600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.133 (2.870) Prec@1 72.66 (76.70) Prec@5 89.84 (91.69) + train[2018-10-23-14:51:44] Epoch: [210][7800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.765 (2.870) Prec@1 79.69 (76.70) Prec@5 92.97 (91.69) + train[2018-10-23-14:53:32] Epoch: [210][8000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.697 (2.870) Prec@1 78.91 (76.71) Prec@5 93.75 (91.69) + train[2018-10-23-14:55:18] Epoch: [210][8200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.820 (2.870) Prec@1 79.69 (76.72) Prec@5 92.19 (91.69) + train[2018-10-23-14:57:05] Epoch: [210][8400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.913 (2.870) Prec@1 78.12 (76.71) Prec@5 91.41 (91.69) + train[2018-10-23-14:58:51] Epoch: [210][8600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.810 (2.870) Prec@1 78.91 (76.71) Prec@5 90.62 (91.68) + train[2018-10-23-15:00:39] Epoch: [210][8800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.140 (2.871) Prec@1 71.09 (76.70) Prec@5 89.84 (91.68) + train[2018-10-23-15:02:26] Epoch: [210][9000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.128 (2.871) Prec@1 74.22 (76.70) Prec@5 89.06 (91.68) + train[2018-10-23-15:04:13] Epoch: [210][9200/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.863 (2.871) Prec@1 78.12 (76.70) Prec@5 90.62 (91.67) + train[2018-10-23-15:06:01] Epoch: [210][9400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.742 (2.871) Prec@1 76.56 (76.71) Prec@5 93.75 (91.68) + train[2018-10-23-15:07:48] Epoch: [210][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.858 (2.870) Prec@1 75.00 (76.72) Prec@5 92.19 (91.68) + train[2018-10-23-15:09:35] Epoch: [210][9800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.859 (2.870) Prec@1 73.44 (76.72) Prec@5 91.41 (91.68) + train[2018-10-23-15:11:22] Epoch: [210][10000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.717 (2.870) Prec@1 79.69 (76.72) Prec@5 93.75 (91.68) + train[2018-10-23-15:11:27] Epoch: [210][10009/10010] Time 0.15 (0.53) Data 0.00 (0.00) Loss 3.741 (2.870) Prec@1 53.33 (76.72) Prec@5 86.67 (91.68) +[2018-10-23-15:11:27] **train** Prec@1 76.72 Prec@5 91.68 Error@1 23.28 Error@5 8.32 Loss:2.870 + test [2018-10-23-15:11:31] Epoch: [210][000/391] Time 4.06 (4.06) Data 3.91 (3.91) Loss 0.536 (0.536) Prec@1 92.97 (92.97) Prec@5 99.22 (99.22) + test [2018-10-23-15:11:59] Epoch: [210][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.171 (1.001) Prec@1 68.75 (77.33) Prec@5 91.41 (93.51) + test [2018-10-23-15:12:24] Epoch: [210][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.158 (1.167) Prec@1 46.25 (73.88) Prec@5 82.50 (91.34) +[2018-10-23-15:12:24] **test** Prec@1 73.88 Prec@5 91.34 Error@1 26.12 Error@5 8.66 Loss:1.167 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-23-15:12:24] [Epoch=211/250] [Need: 58:24:08] LR=0.0002 ~ 0.0002, Batch=128 + train[2018-10-23-15:12:29] Epoch: [211][000/10010] Time 4.90 (4.90) Data 4.31 (4.31) Loss 2.877 (2.877) Prec@1 81.25 (81.25) Prec@5 92.19 (92.19) + train[2018-10-23-15:14:15] Epoch: [211][200/10010] Time 0.55 (0.55) Data 0.00 (0.02) Loss 2.995 (2.860) Prec@1 75.00 (76.97) Prec@5 91.41 (91.74) + train[2018-10-23-15:16:00] Epoch: [211][400/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.974 (2.860) Prec@1 71.88 (76.89) Prec@5 92.19 (91.72) + train[2018-10-23-15:17:45] Epoch: [211][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 2.808 (2.867) Prec@1 78.91 (76.75) Prec@5 92.97 (91.71) + train[2018-10-23-15:19:31] Epoch: [211][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 2.853 (2.862) Prec@1 77.34 (76.80) Prec@5 92.19 (91.79) + train[2018-10-23-15:21:18] Epoch: [211][1000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.077 (2.857) Prec@1 74.22 (76.95) Prec@5 87.50 (91.85) + train[2018-10-23-15:23:06] Epoch: [211][1200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.592 (2.859) Prec@1 83.59 (76.91) Prec@5 95.31 (91.83) + train[2018-10-23-15:24:52] Epoch: [211][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.967 (2.861) Prec@1 76.56 (76.86) Prec@5 89.06 (91.83) + train[2018-10-23-15:26:40] Epoch: [211][1600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.005 (2.863) Prec@1 74.22 (76.81) Prec@5 91.41 (91.80) + train[2018-10-23-15:28:26] Epoch: [211][1800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.729 (2.864) Prec@1 79.69 (76.84) Prec@5 92.97 (91.78) + train[2018-10-23-15:30:13] Epoch: [211][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.837 (2.865) Prec@1 79.69 (76.84) Prec@5 90.62 (91.75) + train[2018-10-23-15:31:59] Epoch: [211][2200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.098 (2.866) Prec@1 73.44 (76.81) Prec@5 89.06 (91.75) + train[2018-10-23-15:33:45] Epoch: [211][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.871 (2.866) Prec@1 76.56 (76.82) Prec@5 91.41 (91.75) + train[2018-10-23-15:35:31] Epoch: [211][2600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.754 (2.866) Prec@1 78.91 (76.81) Prec@5 94.53 (91.75) + train[2018-10-23-15:37:18] Epoch: [211][2800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.713 (2.866) Prec@1 77.34 (76.79) Prec@5 92.97 (91.74) + train[2018-10-23-15:39:03] Epoch: [211][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.975 (2.868) Prec@1 75.00 (76.77) Prec@5 89.84 (91.73) + train[2018-10-23-15:40:50] Epoch: [211][3200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.890 (2.868) Prec@1 75.78 (76.77) Prec@5 91.41 (91.73) + train[2018-10-23-15:42:37] Epoch: [211][3400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.686 (2.868) Prec@1 80.47 (76.76) Prec@5 94.53 (91.74) + train[2018-10-23-15:44:24] Epoch: [211][3600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.072 (2.867) Prec@1 75.00 (76.78) Prec@5 89.06 (91.73) + train[2018-10-23-15:46:11] Epoch: [211][3800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.741 (2.866) Prec@1 83.59 (76.80) Prec@5 92.97 (91.73) + train[2018-10-23-15:47:58] Epoch: [211][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.122 (2.867) Prec@1 74.22 (76.79) Prec@5 84.38 (91.71) + train[2018-10-23-15:49:46] Epoch: [211][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.764 (2.867) Prec@1 74.22 (76.78) Prec@5 93.75 (91.69) + train[2018-10-23-15:51:32] Epoch: [211][4400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.039 (2.867) Prec@1 75.00 (76.78) Prec@5 89.84 (91.69) + train[2018-10-23-15:53:19] Epoch: [211][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.903 (2.867) Prec@1 78.91 (76.78) Prec@5 91.41 (91.69) + train[2018-10-23-15:55:06] Epoch: [211][4800/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 2.829 (2.866) Prec@1 75.00 (76.78) Prec@5 92.19 (91.70) + train[2018-10-23-15:56:54] Epoch: [211][5000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.790 (2.866) Prec@1 78.91 (76.79) Prec@5 92.97 (91.71) + train[2018-10-23-15:58:40] Epoch: [211][5200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.768 (2.866) Prec@1 80.47 (76.79) Prec@5 91.41 (91.70) + train[2018-10-23-16:00:27] Epoch: [211][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.810 (2.866) Prec@1 80.47 (76.79) Prec@5 90.62 (91.70) + train[2018-10-23-16:02:13] Epoch: [211][5600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.784 (2.866) Prec@1 79.69 (76.79) Prec@5 91.41 (91.70) + train[2018-10-23-16:04:01] Epoch: [211][5800/10010] Time 0.68 (0.53) Data 0.00 (0.00) Loss 2.708 (2.866) Prec@1 81.25 (76.81) Prec@5 93.75 (91.70) + train[2018-10-23-16:05:48] Epoch: [211][6000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.763 (2.866) Prec@1 76.56 (76.81) Prec@5 92.19 (91.70) + train[2018-10-23-16:07:36] Epoch: [211][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.701 (2.867) Prec@1 78.12 (76.80) Prec@5 93.75 (91.69) + train[2018-10-23-16:09:23] Epoch: [211][6400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.793 (2.867) Prec@1 80.47 (76.80) Prec@5 92.19 (91.69) + train[2018-10-23-16:11:10] Epoch: [211][6600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.033 (2.867) Prec@1 68.75 (76.79) Prec@5 88.28 (91.69) + train[2018-10-23-16:12:56] Epoch: [211][6800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.077 (2.867) Prec@1 68.75 (76.79) Prec@5 88.28 (91.70) + train[2018-10-23-16:14:43] Epoch: [211][7000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.081 (2.867) Prec@1 72.66 (76.79) Prec@5 90.62 (91.69) + train[2018-10-23-16:16:30] Epoch: [211][7200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.831 (2.867) Prec@1 75.00 (76.80) Prec@5 90.62 (91.69) + train[2018-10-23-16:18:18] Epoch: [211][7400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.992 (2.868) Prec@1 75.78 (76.78) Prec@5 90.62 (91.68) + train[2018-10-23-16:20:04] Epoch: [211][7600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.711 (2.867) Prec@1 80.47 (76.79) Prec@5 92.19 (91.68) + train[2018-10-23-16:21:51] Epoch: [211][7800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.123 (2.867) Prec@1 70.31 (76.79) Prec@5 91.41 (91.68) + train[2018-10-23-16:23:39] Epoch: [211][8000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.920 (2.868) Prec@1 71.09 (76.78) Prec@5 92.97 (91.67) + train[2018-10-23-16:25:27] Epoch: [211][8200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.748 (2.868) Prec@1 78.91 (76.78) Prec@5 92.19 (91.67) + train[2018-10-23-16:27:15] Epoch: [211][8400/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.055 (2.869) Prec@1 71.88 (76.77) Prec@5 90.62 (91.67) + train[2018-10-23-16:29:03] Epoch: [211][8600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.755 (2.869) Prec@1 76.56 (76.77) Prec@5 92.97 (91.66) + train[2018-10-23-16:30:50] Epoch: [211][8800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.130 (2.869) Prec@1 71.09 (76.77) Prec@5 89.06 (91.66) + train[2018-10-23-16:32:38] Epoch: [211][9000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.157 (2.869) Prec@1 70.31 (76.77) Prec@5 85.94 (91.66) + train[2018-10-23-16:34:25] Epoch: [211][9200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.717 (2.869) Prec@1 78.91 (76.77) Prec@5 94.53 (91.66) + train[2018-10-23-16:36:12] Epoch: [211][9400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.690 (2.869) Prec@1 81.25 (76.77) Prec@5 93.75 (91.67) + train[2018-10-23-16:37:59] Epoch: [211][9600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.518 (2.870) Prec@1 84.38 (76.77) Prec@5 95.31 (91.66) + train[2018-10-23-16:39:45] Epoch: [211][9800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.929 (2.870) Prec@1 71.09 (76.76) Prec@5 91.41 (91.66) + train[2018-10-23-16:41:32] Epoch: [211][10000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.776 (2.870) Prec@1 78.12 (76.75) Prec@5 92.97 (91.66) + train[2018-10-23-16:41:37] Epoch: [211][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.475 (2.870) Prec@1 73.33 (76.75) Prec@5 93.33 (91.66) +[2018-10-23-16:41:37] **train** Prec@1 76.75 Prec@5 91.66 Error@1 23.25 Error@5 8.34 Loss:2.870 + test [2018-10-23-16:41:41] Epoch: [211][000/391] Time 4.19 (4.19) Data 4.05 (4.05) Loss 0.530 (0.530) Prec@1 92.19 (92.19) Prec@5 99.22 (99.22) + test [2018-10-23-16:42:08] Epoch: [211][200/391] Time 0.17 (0.16) Data 0.00 (0.03) Loss 1.140 (0.983) Prec@1 71.09 (77.49) Prec@5 92.19 (93.66) + test [2018-10-23-16:42:34] Epoch: [211][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.087 (1.153) Prec@1 45.00 (73.94) Prec@5 82.50 (91.48) +[2018-10-23-16:42:34] **test** Prec@1 73.94 Prec@5 91.48 Error@1 26.06 Error@5 8.52 Loss:1.153 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-23-16:42:34] [Epoch=212/250] [Need: 57:05:55] LR=0.0002 ~ 0.0002, Batch=128 + train[2018-10-23-16:42:39] Epoch: [212][000/10010] Time 4.94 (4.94) Data 4.35 (4.35) Loss 2.682 (2.682) Prec@1 78.12 (78.12) Prec@5 93.75 (93.75) + train[2018-10-23-16:44:24] Epoch: [212][200/10010] Time 0.53 (0.55) Data 0.00 (0.02) Loss 2.857 (2.861) Prec@1 77.34 (76.98) Prec@5 93.75 (91.60) + train[2018-10-23-16:46:10] Epoch: [212][400/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.922 (2.852) Prec@1 78.12 (77.08) Prec@5 89.84 (91.82) + train[2018-10-23-16:47:55] Epoch: [212][600/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.700 (2.857) Prec@1 81.25 (76.89) Prec@5 91.41 (91.77) + train[2018-10-23-16:49:40] Epoch: [212][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.269 (2.861) Prec@1 71.88 (76.84) Prec@5 84.38 (91.72) + train[2018-10-23-16:51:27] Epoch: [212][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.786 (2.861) Prec@1 78.91 (76.86) Prec@5 91.41 (91.73) + train[2018-10-23-16:53:14] Epoch: [212][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.726 (2.864) Prec@1 76.56 (76.81) Prec@5 92.97 (91.71) + train[2018-10-23-16:54:59] Epoch: [212][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.789 (2.866) Prec@1 78.12 (76.80) Prec@5 92.97 (91.70) + train[2018-10-23-16:56:45] Epoch: [212][1600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.873 (2.864) Prec@1 78.91 (76.83) Prec@5 92.97 (91.72) + train[2018-10-23-16:58:31] Epoch: [212][1800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.773 (2.865) Prec@1 78.91 (76.81) Prec@5 95.31 (91.72) + train[2018-10-23-17:00:18] Epoch: [212][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.513 (2.868) Prec@1 82.03 (76.77) Prec@5 96.88 (91.69) + train[2018-10-23-17:02:03] Epoch: [212][2200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.776 (2.867) Prec@1 80.47 (76.78) Prec@5 93.75 (91.71) + train[2018-10-23-17:03:49] Epoch: [212][2400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.069 (2.867) Prec@1 72.66 (76.76) Prec@5 89.84 (91.70) + train[2018-10-23-17:05:34] Epoch: [212][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.832 (2.866) Prec@1 78.12 (76.78) Prec@5 95.31 (91.70) + train[2018-10-23-17:07:20] Epoch: [212][2800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.648 (2.865) Prec@1 80.47 (76.79) Prec@5 91.41 (91.73) + train[2018-10-23-17:09:06] Epoch: [212][3000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.829 (2.865) Prec@1 76.56 (76.82) Prec@5 91.41 (91.73) + train[2018-10-23-17:10:52] Epoch: [212][3200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.836 (2.866) Prec@1 79.69 (76.80) Prec@5 89.84 (91.72) + train[2018-10-23-17:12:38] Epoch: [212][3400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.824 (2.866) Prec@1 76.56 (76.80) Prec@5 92.97 (91.73) + train[2018-10-23-17:14:23] Epoch: [212][3600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.009 (2.866) Prec@1 73.44 (76.79) Prec@5 89.84 (91.73) + train[2018-10-23-17:16:09] Epoch: [212][3800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.966 (2.866) Prec@1 77.34 (76.79) Prec@5 89.84 (91.74) + train[2018-10-23-17:17:54] Epoch: [212][4000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.742 (2.865) Prec@1 78.12 (76.82) Prec@5 94.53 (91.75) + train[2018-10-23-17:19:39] Epoch: [212][4200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.875 (2.865) Prec@1 79.69 (76.81) Prec@5 93.75 (91.75) + train[2018-10-23-17:21:25] Epoch: [212][4400/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.097 (2.865) Prec@1 72.66 (76.81) Prec@5 88.28 (91.74) + train[2018-10-23-17:23:11] Epoch: [212][4600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.194 (2.864) Prec@1 71.88 (76.82) Prec@5 88.28 (91.75) + train[2018-10-23-17:24:56] Epoch: [212][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.727 (2.864) Prec@1 78.91 (76.83) Prec@5 90.62 (91.75) + train[2018-10-23-17:26:41] Epoch: [212][5000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.009 (2.865) Prec@1 67.97 (76.81) Prec@5 89.84 (91.75) + train[2018-10-23-17:28:27] Epoch: [212][5200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.035 (2.864) Prec@1 73.44 (76.81) Prec@5 89.84 (91.75) + train[2018-10-23-17:30:15] Epoch: [212][5400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.878 (2.864) Prec@1 73.44 (76.80) Prec@5 92.97 (91.75) + train[2018-10-23-17:32:01] Epoch: [212][5600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.651 (2.865) Prec@1 81.25 (76.80) Prec@5 91.41 (91.74) + train[2018-10-23-17:33:46] Epoch: [212][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.759 (2.865) Prec@1 78.91 (76.80) Prec@5 89.84 (91.73) + train[2018-10-23-17:35:32] Epoch: [212][6000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.949 (2.867) Prec@1 75.00 (76.77) Prec@5 89.84 (91.72) + train[2018-10-23-17:37:17] Epoch: [212][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.632 (2.867) Prec@1 82.81 (76.76) Prec@5 93.75 (91.70) + train[2018-10-23-17:39:03] Epoch: [212][6400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.824 (2.867) Prec@1 76.56 (76.76) Prec@5 92.97 (91.70) + train[2018-10-23-17:40:48] Epoch: [212][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.884 (2.867) Prec@1 77.34 (76.76) Prec@5 90.62 (91.70) + train[2018-10-23-17:42:36] Epoch: [212][6800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.986 (2.867) Prec@1 77.34 (76.76) Prec@5 89.84 (91.70) + train[2018-10-23-17:44:24] Epoch: [212][7000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.092 (2.868) Prec@1 73.44 (76.74) Prec@5 89.84 (91.69) + train[2018-10-23-17:46:10] Epoch: [212][7200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.815 (2.868) Prec@1 73.44 (76.75) Prec@5 92.97 (91.69) + train[2018-10-23-17:47:57] Epoch: [212][7400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.989 (2.868) Prec@1 76.56 (76.74) Prec@5 89.06 (91.69) + train[2018-10-23-17:49:43] Epoch: [212][7600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.772 (2.868) Prec@1 78.12 (76.74) Prec@5 92.19 (91.69) + train[2018-10-23-17:51:30] Epoch: [212][7800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.931 (2.868) Prec@1 73.44 (76.74) Prec@5 91.41 (91.69) + train[2018-10-23-17:53:16] Epoch: [212][8000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.963 (2.868) Prec@1 76.56 (76.74) Prec@5 89.84 (91.69) + train[2018-10-23-17:55:01] Epoch: [212][8200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.740 (2.868) Prec@1 78.12 (76.74) Prec@5 90.62 (91.70) + train[2018-10-23-17:56:47] Epoch: [212][8400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.816 (2.868) Prec@1 72.66 (76.74) Prec@5 91.41 (91.69) + train[2018-10-23-17:58:33] Epoch: [212][8600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.797 (2.868) Prec@1 78.91 (76.75) Prec@5 92.19 (91.68) + train[2018-10-23-18:00:19] Epoch: [212][8800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.784 (2.868) Prec@1 75.78 (76.74) Prec@5 91.41 (91.68) + train[2018-10-23-18:02:06] Epoch: [212][9000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.315 (2.868) Prec@1 64.84 (76.75) Prec@5 85.94 (91.69) + train[2018-10-23-18:03:52] Epoch: [212][9200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.763 (2.869) Prec@1 78.91 (76.73) Prec@5 92.19 (91.68) + train[2018-10-23-18:05:39] Epoch: [212][9400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.152 (2.869) Prec@1 70.31 (76.73) Prec@5 89.06 (91.68) + train[2018-10-23-18:07:27] Epoch: [212][9600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.241 (2.869) Prec@1 68.75 (76.73) Prec@5 87.50 (91.67) + train[2018-10-23-18:09:13] Epoch: [212][9800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.044 (2.869) Prec@1 75.00 (76.72) Prec@5 89.84 (91.67) + train[2018-10-23-18:10:59] Epoch: [212][10000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.876 (2.869) Prec@1 76.56 (76.72) Prec@5 91.41 (91.67) + train[2018-10-23-18:11:04] Epoch: [212][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 4.280 (2.870) Prec@1 53.33 (76.72) Prec@5 80.00 (91.67) +[2018-10-23-18:11:04] **train** Prec@1 76.72 Prec@5 91.67 Error@1 23.28 Error@5 8.33 Loss:2.870 + test [2018-10-23-18:11:07] Epoch: [212][000/391] Time 3.53 (3.53) Data 3.37 (3.37) Loss 0.558 (0.558) Prec@1 92.19 (92.19) Prec@5 98.44 (98.44) + test [2018-10-23-18:11:35] Epoch: [212][200/391] Time 0.12 (0.16) Data 0.00 (0.02) Loss 1.192 (0.992) Prec@1 67.19 (77.41) Prec@5 92.97 (93.66) + test [2018-10-23-18:12:01] Epoch: [212][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.076 (1.161) Prec@1 46.25 (73.79) Prec@5 82.50 (91.39) +[2018-10-23-18:12:01] **test** Prec@1 73.79 Prec@5 91.39 Error@1 26.21 Error@5 8.61 Loss:1.161 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-23-18:12:01] [Epoch=213/250] [Need: 55:09:40] LR=0.0002 ~ 0.0002, Batch=128 + train[2018-10-23-18:12:06] Epoch: [213][000/10010] Time 5.46 (5.46) Data 4.78 (4.78) Loss 3.059 (3.059) Prec@1 73.44 (73.44) Prec@5 89.06 (89.06) + train[2018-10-23-18:13:52] Epoch: [213][200/10010] Time 0.55 (0.55) Data 0.00 (0.02) Loss 2.669 (2.868) Prec@1 77.34 (76.69) Prec@5 95.31 (91.59) + train[2018-10-23-18:15:38] Epoch: [213][400/10010] Time 0.53 (0.54) Data 0.00 (0.01) Loss 2.645 (2.861) Prec@1 78.12 (76.79) Prec@5 96.09 (91.67) + train[2018-10-23-18:17:25] Epoch: [213][600/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.769 (2.860) Prec@1 79.69 (76.87) Prec@5 94.53 (91.73) + train[2018-10-23-18:19:11] Epoch: [213][800/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 2.959 (2.856) Prec@1 75.00 (76.95) Prec@5 88.28 (91.80) + train[2018-10-23-18:20:57] Epoch: [213][1000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.731 (2.859) Prec@1 78.91 (76.90) Prec@5 91.41 (91.75) + train[2018-10-23-18:22:44] Epoch: [213][1200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.028 (2.863) Prec@1 70.31 (76.83) Prec@5 89.84 (91.75) + train[2018-10-23-18:24:32] Epoch: [213][1400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.956 (2.865) Prec@1 72.66 (76.78) Prec@5 91.41 (91.74) + train[2018-10-23-18:26:19] Epoch: [213][1600/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.592 (2.864) Prec@1 81.25 (76.84) Prec@5 93.75 (91.74) + train[2018-10-23-18:28:06] Epoch: [213][1800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.957 (2.864) Prec@1 75.78 (76.85) Prec@5 91.41 (91.74) + train[2018-10-23-18:29:53] Epoch: [213][2000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.676 (2.866) Prec@1 79.69 (76.81) Prec@5 94.53 (91.71) + train[2018-10-23-18:31:42] Epoch: [213][2200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.799 (2.865) Prec@1 76.56 (76.85) Prec@5 92.97 (91.71) + train[2018-10-23-18:33:29] Epoch: [213][2400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.849 (2.865) Prec@1 74.22 (76.86) Prec@5 91.41 (91.70) + train[2018-10-23-18:35:17] Epoch: [213][2600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.664 (2.865) Prec@1 81.25 (76.86) Prec@5 92.19 (91.71) + train[2018-10-23-18:37:03] Epoch: [213][2800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.002 (2.866) Prec@1 73.44 (76.83) Prec@5 92.97 (91.70) + train[2018-10-23-18:38:51] Epoch: [213][3000/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.997 (2.866) Prec@1 75.00 (76.84) Prec@5 88.28 (91.70) + train[2018-10-23-18:40:38] Epoch: [213][3200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.843 (2.866) Prec@1 80.47 (76.85) Prec@5 89.84 (91.69) + train[2018-10-23-18:42:24] Epoch: [213][3400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.818 (2.866) Prec@1 78.91 (76.86) Prec@5 95.31 (91.69) + train[2018-10-23-18:44:12] Epoch: [213][3600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.895 (2.867) Prec@1 75.78 (76.84) Prec@5 92.19 (91.68) + train[2018-10-23-18:45:59] Epoch: [213][3800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.729 (2.867) Prec@1 79.69 (76.82) Prec@5 92.19 (91.68) + train[2018-10-23-18:47:47] Epoch: [213][4000/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.687 (2.868) Prec@1 80.47 (76.80) Prec@5 91.41 (91.66) + train[2018-10-23-18:49:35] Epoch: [213][4200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.976 (2.868) Prec@1 69.53 (76.78) Prec@5 89.84 (91.65) + train[2018-10-23-18:51:21] Epoch: [213][4400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.763 (2.868) Prec@1 78.12 (76.78) Prec@5 92.97 (91.67) + train[2018-10-23-18:53:08] Epoch: [213][4600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.896 (2.868) Prec@1 77.34 (76.77) Prec@5 91.41 (91.67) + train[2018-10-23-18:54:55] Epoch: [213][4800/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.892 (2.869) Prec@1 75.78 (76.77) Prec@5 93.75 (91.66) + train[2018-10-23-18:56:42] Epoch: [213][5000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.940 (2.869) Prec@1 77.34 (76.77) Prec@5 89.06 (91.66) + train[2018-10-23-18:58:29] Epoch: [213][5200/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.744 (2.869) Prec@1 80.47 (76.76) Prec@5 91.41 (91.66) + train[2018-10-23-19:00:18] Epoch: [213][5400/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.534 (2.869) Prec@1 80.47 (76.73) Prec@5 95.31 (91.66) + train[2018-10-23-19:02:06] Epoch: [213][5600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.172 (2.870) Prec@1 70.31 (76.73) Prec@5 90.62 (91.65) + train[2018-10-23-19:03:54] Epoch: [213][5800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.747 (2.871) Prec@1 75.78 (76.72) Prec@5 92.97 (91.65) + train[2018-10-23-19:05:41] Epoch: [213][6000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.759 (2.871) Prec@1 79.69 (76.71) Prec@5 92.97 (91.64) + train[2018-10-23-19:07:29] Epoch: [213][6200/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.617 (2.872) Prec@1 82.81 (76.70) Prec@5 94.53 (91.63) + train[2018-10-23-19:09:16] Epoch: [213][6400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.637 (2.872) Prec@1 83.59 (76.69) Prec@5 92.19 (91.63) + train[2018-10-23-19:11:02] Epoch: [213][6600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.971 (2.871) Prec@1 74.22 (76.69) Prec@5 90.62 (91.63) + train[2018-10-23-19:12:50] Epoch: [213][6800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.873 (2.871) Prec@1 75.00 (76.70) Prec@5 96.09 (91.64) + train[2018-10-23-19:14:37] Epoch: [213][7000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.282 (2.871) Prec@1 67.19 (76.70) Prec@5 87.50 (91.64) + train[2018-10-23-19:16:25] Epoch: [213][7200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.507 (2.870) Prec@1 80.47 (76.72) Prec@5 97.66 (91.65) + train[2018-10-23-19:18:12] Epoch: [213][7400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.927 (2.870) Prec@1 75.00 (76.73) Prec@5 89.84 (91.65) + train[2018-10-23-19:19:59] Epoch: [213][7600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.922 (2.870) Prec@1 75.78 (76.73) Prec@5 90.62 (91.65) + train[2018-10-23-19:21:47] Epoch: [213][7800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.046 (2.870) Prec@1 71.88 (76.73) Prec@5 91.41 (91.65) + train[2018-10-23-19:23:34] Epoch: [213][8000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.779 (2.870) Prec@1 76.56 (76.72) Prec@5 92.97 (91.65) + train[2018-10-23-19:25:21] Epoch: [213][8200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.554 (2.870) Prec@1 82.81 (76.72) Prec@5 93.75 (91.65) + train[2018-10-23-19:27:08] Epoch: [213][8400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.112 (2.870) Prec@1 75.00 (76.72) Prec@5 91.41 (91.64) + train[2018-10-23-19:28:56] Epoch: [213][8600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.843 (2.871) Prec@1 76.56 (76.72) Prec@5 91.41 (91.64) + train[2018-10-23-19:30:44] Epoch: [213][8800/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.000 (2.870) Prec@1 72.66 (76.72) Prec@5 90.62 (91.65) + train[2018-10-23-19:32:32] Epoch: [213][9000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.853 (2.870) Prec@1 75.78 (76.73) Prec@5 93.75 (91.64) + train[2018-10-23-19:34:20] Epoch: [213][9200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.783 (2.870) Prec@1 78.12 (76.73) Prec@5 93.75 (91.65) + train[2018-10-23-19:36:07] Epoch: [213][9400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.631 (2.870) Prec@1 83.59 (76.74) Prec@5 94.53 (91.65) + train[2018-10-23-19:37:53] Epoch: [213][9600/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 3.124 (2.870) Prec@1 69.53 (76.74) Prec@5 88.28 (91.65) + train[2018-10-23-19:39:40] Epoch: [213][9800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.503 (2.869) Prec@1 85.16 (76.75) Prec@5 95.31 (91.66) + train[2018-10-23-19:41:27] Epoch: [213][10000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.653 (2.869) Prec@1 79.69 (76.75) Prec@5 95.31 (91.66) + train[2018-10-23-19:41:32] Epoch: [213][10009/10010] Time 0.19 (0.54) Data 0.00 (0.00) Loss 3.302 (2.869) Prec@1 73.33 (76.74) Prec@5 93.33 (91.66) +[2018-10-23-19:41:32] **train** Prec@1 76.74 Prec@5 91.66 Error@1 23.26 Error@5 8.34 Loss:2.869 + test [2018-10-23-19:41:36] Epoch: [213][000/391] Time 4.14 (4.14) Data 3.99 (3.99) Loss 0.518 (0.518) Prec@1 92.19 (92.19) Prec@5 99.22 (99.22) + test [2018-10-23-19:42:06] Epoch: [213][200/391] Time 0.12 (0.17) Data 0.00 (0.04) Loss 1.205 (0.990) Prec@1 67.97 (77.50) Prec@5 92.19 (93.61) + test [2018-10-23-19:42:31] Epoch: [213][390/391] Time 0.09 (0.15) Data 0.00 (0.02) Loss 2.188 (1.158) Prec@1 46.25 (73.93) Prec@5 82.50 (91.43) +[2018-10-23-19:42:31] **test** Prec@1 73.93 Prec@5 91.43 Error@1 26.07 Error@5 8.57 Loss:1.158 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-23-19:42:31] [Epoch=214/250] [Need: 54:18:21] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-23-19:42:36] Epoch: [214][000/10010] Time 5.07 (5.07) Data 4.38 (4.38) Loss 2.878 (2.878) Prec@1 77.34 (77.34) Prec@5 90.62 (90.62) + train[2018-10-23-19:44:22] Epoch: [214][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 3.058 (2.863) Prec@1 70.31 (77.12) Prec@5 88.28 (91.67) + train[2018-10-23-19:46:08] Epoch: [214][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.978 (2.862) Prec@1 78.12 (77.02) Prec@5 92.19 (91.73) + train[2018-10-23-19:47:54] Epoch: [214][600/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 2.878 (2.871) Prec@1 75.00 (76.77) Prec@5 91.41 (91.66) + train[2018-10-23-19:49:39] Epoch: [214][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.301 (2.874) Prec@1 67.19 (76.81) Prec@5 89.06 (91.64) + train[2018-10-23-19:51:25] Epoch: [214][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.937 (2.874) Prec@1 77.34 (76.79) Prec@5 90.62 (91.61) + train[2018-10-23-19:53:12] Epoch: [214][1200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.944 (2.870) Prec@1 78.91 (76.82) Prec@5 91.41 (91.65) + train[2018-10-23-19:55:01] Epoch: [214][1400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.676 (2.868) Prec@1 77.34 (76.84) Prec@5 94.53 (91.67) + train[2018-10-23-19:56:48] Epoch: [214][1600/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.648 (2.869) Prec@1 78.91 (76.81) Prec@5 92.19 (91.64) + train[2018-10-23-19:58:37] Epoch: [214][1800/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.673 (2.867) Prec@1 78.12 (76.81) Prec@5 92.19 (91.68) + train[2018-10-23-20:00:24] Epoch: [214][2000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.974 (2.866) Prec@1 75.78 (76.85) Prec@5 92.19 (91.70) + train[2018-10-23-20:02:12] Epoch: [214][2200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.771 (2.865) Prec@1 78.12 (76.86) Prec@5 92.19 (91.70) + train[2018-10-23-20:04:01] Epoch: [214][2400/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 3.041 (2.864) Prec@1 71.88 (76.86) Prec@5 89.06 (91.70) + train[2018-10-23-20:05:49] Epoch: [214][2600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.715 (2.863) Prec@1 81.25 (76.88) Prec@5 91.41 (91.72) + train[2018-10-23-20:07:37] Epoch: [214][2800/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.837 (2.865) Prec@1 76.56 (76.84) Prec@5 91.41 (91.70) + train[2018-10-23-20:09:24] Epoch: [214][3000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.981 (2.865) Prec@1 70.31 (76.85) Prec@5 91.41 (91.70) + train[2018-10-23-20:11:13] Epoch: [214][3200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.701 (2.865) Prec@1 78.12 (76.87) Prec@5 93.75 (91.70) + train[2018-10-23-20:13:01] Epoch: [214][3400/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.860 (2.864) Prec@1 78.91 (76.88) Prec@5 92.97 (91.73) + train[2018-10-23-20:14:49] Epoch: [214][3600/10010] Time 0.61 (0.54) Data 0.00 (0.00) Loss 2.716 (2.863) Prec@1 75.78 (76.88) Prec@5 93.75 (91.74) + train[2018-10-23-20:16:38] Epoch: [214][3800/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.630 (2.864) Prec@1 80.47 (76.87) Prec@5 92.19 (91.73) + train[2018-10-23-20:18:25] Epoch: [214][4000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.795 (2.864) Prec@1 75.78 (76.87) Prec@5 92.97 (91.73) + train[2018-10-23-20:20:13] Epoch: [214][4200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.786 (2.864) Prec@1 82.81 (76.86) Prec@5 89.84 (91.72) + train[2018-10-23-20:22:00] Epoch: [214][4400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.913 (2.864) Prec@1 76.56 (76.86) Prec@5 88.28 (91.72) + train[2018-10-23-20:23:49] Epoch: [214][4600/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.926 (2.865) Prec@1 75.78 (76.86) Prec@5 92.97 (91.72) + train[2018-10-23-20:25:36] Epoch: [214][4800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 3.022 (2.865) Prec@1 78.91 (76.86) Prec@5 89.06 (91.71) + train[2018-10-23-20:27:24] Epoch: [214][5000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.800 (2.866) Prec@1 77.34 (76.86) Prec@5 94.53 (91.70) + train[2018-10-23-20:29:12] Epoch: [214][5200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.915 (2.866) Prec@1 72.66 (76.85) Prec@5 92.97 (91.71) + train[2018-10-23-20:31:00] Epoch: [214][5400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.852 (2.866) Prec@1 78.91 (76.85) Prec@5 92.19 (91.71) + train[2018-10-23-20:32:48] Epoch: [214][5600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.720 (2.867) Prec@1 79.69 (76.84) Prec@5 93.75 (91.70) + train[2018-10-23-20:34:35] Epoch: [214][5800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.746 (2.867) Prec@1 78.12 (76.84) Prec@5 91.41 (91.70) + train[2018-10-23-20:36:23] Epoch: [214][6000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.659 (2.866) Prec@1 78.91 (76.85) Prec@5 95.31 (91.70) + train[2018-10-23-20:38:10] Epoch: [214][6200/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 3.183 (2.867) Prec@1 74.22 (76.84) Prec@5 88.28 (91.69) + train[2018-10-23-20:39:59] Epoch: [214][6400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.831 (2.868) Prec@1 75.00 (76.82) Prec@5 94.53 (91.69) + train[2018-10-23-20:41:48] Epoch: [214][6600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.806 (2.868) Prec@1 78.12 (76.82) Prec@5 92.19 (91.68) + train[2018-10-23-20:43:37] Epoch: [214][6800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.997 (2.868) Prec@1 71.88 (76.82) Prec@5 86.72 (91.68) + train[2018-10-23-20:45:27] Epoch: [214][7000/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.592 (2.867) Prec@1 80.47 (76.83) Prec@5 92.19 (91.69) + train[2018-10-23-20:47:14] Epoch: [214][7200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.779 (2.867) Prec@1 78.91 (76.83) Prec@5 92.19 (91.69) + train[2018-10-23-20:49:03] Epoch: [214][7400/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.906 (2.868) Prec@1 75.78 (76.81) Prec@5 92.19 (91.69) + train[2018-10-23-20:50:51] Epoch: [214][7600/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 3.034 (2.868) Prec@1 73.44 (76.81) Prec@5 91.41 (91.69) + train[2018-10-23-20:52:38] Epoch: [214][7800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.871 (2.868) Prec@1 73.44 (76.81) Prec@5 92.19 (91.70) + train[2018-10-23-20:54:28] Epoch: [214][8000/10010] Time 0.60 (0.54) Data 0.00 (0.00) Loss 2.980 (2.867) Prec@1 75.00 (76.82) Prec@5 89.84 (91.70) + train[2018-10-23-20:56:16] Epoch: [214][8200/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.944 (2.867) Prec@1 73.44 (76.82) Prec@5 90.62 (91.70) + train[2018-10-23-20:58:06] Epoch: [214][8400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.784 (2.867) Prec@1 78.91 (76.82) Prec@5 91.41 (91.69) + train[2018-10-23-20:59:54] Epoch: [214][8600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.791 (2.867) Prec@1 78.91 (76.83) Prec@5 93.75 (91.70) + train[2018-10-23-21:01:43] Epoch: [214][8800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.879 (2.867) Prec@1 73.44 (76.83) Prec@5 93.75 (91.70) + train[2018-10-23-21:03:31] Epoch: [214][9000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.667 (2.867) Prec@1 77.34 (76.83) Prec@5 93.75 (91.70) + train[2018-10-23-21:05:18] Epoch: [214][9200/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.842 (2.867) Prec@1 79.69 (76.83) Prec@5 93.75 (91.70) + train[2018-10-23-21:07:06] Epoch: [214][9400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.951 (2.868) Prec@1 72.66 (76.82) Prec@5 89.84 (91.70) + train[2018-10-23-21:08:53] Epoch: [214][9600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.635 (2.868) Prec@1 78.91 (76.82) Prec@5 93.75 (91.70) + train[2018-10-23-21:10:42] Epoch: [214][9800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.919 (2.868) Prec@1 74.22 (76.81) Prec@5 92.19 (91.69) + train[2018-10-23-21:12:30] Epoch: [214][10000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.920 (2.868) Prec@1 71.88 (76.81) Prec@5 93.75 (91.70) + train[2018-10-23-21:12:34] Epoch: [214][10009/10010] Time 0.15 (0.54) Data 0.00 (0.00) Loss 2.928 (2.868) Prec@1 80.00 (76.81) Prec@5 93.33 (91.70) +[2018-10-23-21:12:35] **train** Prec@1 76.81 Prec@5 91.70 Error@1 23.19 Error@5 8.30 Loss:2.868 + test [2018-10-23-21:12:39] Epoch: [214][000/391] Time 4.41 (4.41) Data 4.27 (4.27) Loss 0.573 (0.573) Prec@1 92.97 (92.97) Prec@5 98.44 (98.44) + test [2018-10-23-21:13:07] Epoch: [214][200/391] Time 0.12 (0.16) Data 0.00 (0.03) Loss 1.132 (0.994) Prec@1 71.09 (77.39) Prec@5 92.97 (93.61) + test [2018-10-23-21:13:32] Epoch: [214][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.161 (1.161) Prec@1 48.75 (73.87) Prec@5 83.75 (91.45) +[2018-10-23-21:13:32] **test** Prec@1 73.87 Prec@5 91.45 Error@1 26.13 Error@5 8.55 Loss:1.161 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-23-21:13:32] [Epoch=215/250] [Need: 53:05:19] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-23-21:13:37] Epoch: [215][000/10010] Time 4.90 (4.90) Data 4.23 (4.23) Loss 2.801 (2.801) Prec@1 77.34 (77.34) Prec@5 92.97 (92.97) + train[2018-10-23-21:15:23] Epoch: [215][200/10010] Time 0.53 (0.55) Data 0.00 (0.02) Loss 2.951 (2.848) Prec@1 72.66 (76.69) Prec@5 92.19 (91.93) + train[2018-10-23-21:17:08] Epoch: [215][400/10010] Time 0.59 (0.54) Data 0.00 (0.01) Loss 2.912 (2.860) Prec@1 73.44 (76.67) Prec@5 93.75 (91.80) + train[2018-10-23-21:18:54] Epoch: [215][600/10010] Time 0.53 (0.54) Data 0.00 (0.01) Loss 3.113 (2.857) Prec@1 73.44 (76.80) Prec@5 90.62 (91.82) + train[2018-10-23-21:20:40] Epoch: [215][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.185 (2.866) Prec@1 75.78 (76.64) Prec@5 89.84 (91.75) + train[2018-10-23-21:22:26] Epoch: [215][1000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.933 (2.864) Prec@1 75.00 (76.72) Prec@5 91.41 (91.76) + train[2018-10-23-21:24:12] Epoch: [215][1200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.864 (2.863) Prec@1 75.00 (76.78) Prec@5 92.19 (91.74) + train[2018-10-23-21:25:58] Epoch: [215][1400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.588 (2.865) Prec@1 81.25 (76.73) Prec@5 93.75 (91.72) + train[2018-10-23-21:27:44] Epoch: [215][1600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.685 (2.866) Prec@1 78.91 (76.72) Prec@5 92.97 (91.71) + train[2018-10-23-21:29:30] Epoch: [215][1800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.705 (2.864) Prec@1 75.00 (76.78) Prec@5 94.53 (91.75) + train[2018-10-23-21:31:16] Epoch: [215][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.048 (2.863) Prec@1 77.34 (76.81) Prec@5 87.50 (91.76) + train[2018-10-23-21:33:02] Epoch: [215][2200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.844 (2.863) Prec@1 72.66 (76.81) Prec@5 93.75 (91.77) + train[2018-10-23-21:34:49] Epoch: [215][2400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.815 (2.862) Prec@1 80.47 (76.84) Prec@5 91.41 (91.78) + train[2018-10-23-21:36:35] Epoch: [215][2600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.892 (2.862) Prec@1 78.91 (76.85) Prec@5 92.97 (91.78) + train[2018-10-23-21:38:21] Epoch: [215][2800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.247 (2.863) Prec@1 71.09 (76.84) Prec@5 85.94 (91.78) + train[2018-10-23-21:40:07] Epoch: [215][3000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.695 (2.865) Prec@1 80.47 (76.81) Prec@5 95.31 (91.76) + train[2018-10-23-21:41:51] Epoch: [215][3200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.789 (2.866) Prec@1 78.91 (76.80) Prec@5 94.53 (91.76) + train[2018-10-23-21:43:37] Epoch: [215][3400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.829 (2.867) Prec@1 74.22 (76.76) Prec@5 93.75 (91.74) + train[2018-10-23-21:45:23] Epoch: [215][3600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.953 (2.867) Prec@1 78.91 (76.78) Prec@5 89.84 (91.75) + train[2018-10-23-21:47:10] Epoch: [215][3800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.725 (2.867) Prec@1 78.12 (76.77) Prec@5 93.75 (91.74) + train[2018-10-23-21:48:56] Epoch: [215][4000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.949 (2.867) Prec@1 75.00 (76.79) Prec@5 89.84 (91.75) + train[2018-10-23-21:50:42] Epoch: [215][4200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.835 (2.866) Prec@1 77.34 (76.80) Prec@5 91.41 (91.75) + train[2018-10-23-21:52:28] Epoch: [215][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.882 (2.866) Prec@1 77.34 (76.81) Prec@5 92.19 (91.75) + train[2018-10-23-21:54:14] Epoch: [215][4600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.847 (2.866) Prec@1 78.12 (76.82) Prec@5 94.53 (91.75) + train[2018-10-23-21:56:00] Epoch: [215][4800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.868 (2.866) Prec@1 76.56 (76.82) Prec@5 92.97 (91.76) + train[2018-10-23-21:57:47] Epoch: [215][5000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.556 (2.865) Prec@1 81.25 (76.84) Prec@5 96.09 (91.77) + train[2018-10-23-21:59:34] Epoch: [215][5200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.913 (2.865) Prec@1 75.00 (76.82) Prec@5 88.28 (91.77) + train[2018-10-23-22:01:21] Epoch: [215][5400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.064 (2.866) Prec@1 70.31 (76.79) Prec@5 86.72 (91.76) + train[2018-10-23-22:03:08] Epoch: [215][5600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.723 (2.866) Prec@1 76.56 (76.80) Prec@5 94.53 (91.76) + train[2018-10-23-22:04:55] Epoch: [215][5800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.949 (2.864) Prec@1 80.47 (76.82) Prec@5 90.62 (91.78) + train[2018-10-23-22:06:41] Epoch: [215][6000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.995 (2.864) Prec@1 73.44 (76.82) Prec@5 89.84 (91.79) + train[2018-10-23-22:08:27] Epoch: [215][6200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.651 (2.864) Prec@1 79.69 (76.81) Prec@5 95.31 (91.78) + train[2018-10-23-22:10:13] Epoch: [215][6400/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.972 (2.864) Prec@1 74.22 (76.80) Prec@5 89.06 (91.78) + train[2018-10-23-22:12:00] Epoch: [215][6600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.717 (2.864) Prec@1 78.12 (76.80) Prec@5 90.62 (91.77) + train[2018-10-23-22:13:47] Epoch: [215][6800/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.707 (2.865) Prec@1 78.91 (76.79) Prec@5 92.19 (91.77) + train[2018-10-23-22:15:34] Epoch: [215][7000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.835 (2.865) Prec@1 76.56 (76.79) Prec@5 93.75 (91.77) + train[2018-10-23-22:17:23] Epoch: [215][7200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.994 (2.866) Prec@1 77.34 (76.77) Prec@5 91.41 (91.76) + train[2018-10-23-22:19:10] Epoch: [215][7400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.808 (2.866) Prec@1 84.38 (76.77) Prec@5 92.19 (91.76) + train[2018-10-23-22:20:59] Epoch: [215][7600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.914 (2.866) Prec@1 76.56 (76.77) Prec@5 92.19 (91.76) + train[2018-10-23-22:22:46] Epoch: [215][7800/10010] Time 0.63 (0.53) Data 0.00 (0.00) Loss 3.036 (2.866) Prec@1 74.22 (76.77) Prec@5 89.84 (91.76) + train[2018-10-23-22:24:34] Epoch: [215][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.028 (2.866) Prec@1 70.31 (76.76) Prec@5 94.53 (91.77) + train[2018-10-23-22:26:21] Epoch: [215][8200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.898 (2.866) Prec@1 75.00 (76.76) Prec@5 92.19 (91.76) + train[2018-10-23-22:28:08] Epoch: [215][8400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.852 (2.866) Prec@1 77.34 (76.77) Prec@5 95.31 (91.76) + train[2018-10-23-22:29:55] Epoch: [215][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.912 (2.866) Prec@1 78.12 (76.76) Prec@5 91.41 (91.77) + train[2018-10-23-22:31:42] Epoch: [215][8800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.582 (2.866) Prec@1 81.25 (76.77) Prec@5 93.75 (91.76) + train[2018-10-23-22:33:29] Epoch: [215][9000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.753 (2.866) Prec@1 77.34 (76.76) Prec@5 91.41 (91.75) + train[2018-10-23-22:35:17] Epoch: [215][9200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.093 (2.866) Prec@1 71.09 (76.77) Prec@5 87.50 (91.76) + train[2018-10-23-22:37:04] Epoch: [215][9400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.431 (2.866) Prec@1 82.03 (76.77) Prec@5 96.88 (91.76) + train[2018-10-23-22:38:51] Epoch: [215][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.905 (2.866) Prec@1 75.78 (76.77) Prec@5 92.19 (91.75) + train[2018-10-23-22:40:38] Epoch: [215][9800/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.811 (2.866) Prec@1 78.91 (76.77) Prec@5 93.75 (91.75) + train[2018-10-23-22:42:25] Epoch: [215][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.611 (2.866) Prec@1 83.59 (76.77) Prec@5 95.31 (91.75) + train[2018-10-23-22:42:29] Epoch: [215][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.422 (2.866) Prec@1 53.33 (76.77) Prec@5 93.33 (91.75) +[2018-10-23-22:42:29] **train** Prec@1 76.77 Prec@5 91.75 Error@1 23.23 Error@5 8.25 Loss:2.866 + test [2018-10-23-22:42:34] Epoch: [215][000/391] Time 4.53 (4.53) Data 4.39 (4.39) Loss 0.539 (0.539) Prec@1 91.41 (91.41) Prec@5 99.22 (99.22) + test [2018-10-23-22:43:02] Epoch: [215][200/391] Time 0.14 (0.16) Data 0.00 (0.03) Loss 1.193 (0.985) Prec@1 67.19 (77.48) Prec@5 92.97 (93.65) + test [2018-10-23-22:43:27] Epoch: [215][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.138 (1.154) Prec@1 45.00 (73.90) Prec@5 82.50 (91.48) +[2018-10-23-22:43:27] **test** Prec@1 73.90 Prec@5 91.48 Error@1 26.10 Error@5 8.52 Loss:1.154 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-23-22:43:27] [Epoch=216/250] [Need: 50:57:12] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-23-22:43:32] Epoch: [216][000/10010] Time 5.50 (5.50) Data 4.90 (4.90) Loss 2.665 (2.665) Prec@1 77.34 (77.34) Prec@5 94.53 (94.53) + train[2018-10-23-22:45:18] Epoch: [216][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 2.642 (2.872) Prec@1 83.59 (76.68) Prec@5 93.75 (91.65) + train[2018-10-23-22:47:05] Epoch: [216][400/10010] Time 0.56 (0.54) Data 0.00 (0.01) Loss 2.668 (2.866) Prec@1 78.91 (76.80) Prec@5 94.53 (91.74) + train[2018-10-23-22:48:52] Epoch: [216][600/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 3.078 (2.862) Prec@1 75.78 (76.78) Prec@5 89.06 (91.80) + train[2018-10-23-22:50:39] Epoch: [216][800/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.871 (2.863) Prec@1 76.56 (76.74) Prec@5 92.97 (91.77) + train[2018-10-23-22:52:26] Epoch: [216][1000/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.910 (2.862) Prec@1 76.56 (76.79) Prec@5 90.62 (91.77) + train[2018-10-23-22:54:15] Epoch: [216][1200/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.485 (2.860) Prec@1 83.59 (76.86) Prec@5 95.31 (91.83) + train[2018-10-23-22:56:02] Epoch: [216][1400/10010] Time 0.60 (0.54) Data 0.00 (0.00) Loss 2.774 (2.862) Prec@1 78.91 (76.83) Prec@5 92.97 (91.81) + train[2018-10-23-22:57:50] Epoch: [216][1600/10010] Time 0.63 (0.54) Data 0.00 (0.00) Loss 2.653 (2.862) Prec@1 81.25 (76.81) Prec@5 94.53 (91.79) + train[2018-10-23-22:59:36] Epoch: [216][1800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.996 (2.865) Prec@1 76.56 (76.76) Prec@5 89.84 (91.73) + train[2018-10-23-23:01:23] Epoch: [216][2000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.899 (2.866) Prec@1 77.34 (76.75) Prec@5 88.28 (91.71) + train[2018-10-23-23:03:11] Epoch: [216][2200/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.831 (2.866) Prec@1 74.22 (76.72) Prec@5 91.41 (91.71) + train[2018-10-23-23:04:57] Epoch: [216][2400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.850 (2.865) Prec@1 76.56 (76.74) Prec@5 89.84 (91.73) + train[2018-10-23-23:06:43] Epoch: [216][2600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.169 (2.865) Prec@1 77.34 (76.78) Prec@5 89.06 (91.74) + train[2018-10-23-23:08:31] Epoch: [216][2800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.825 (2.865) Prec@1 76.56 (76.78) Prec@5 90.62 (91.76) + train[2018-10-23-23:10:18] Epoch: [216][3000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.064 (2.866) Prec@1 75.78 (76.75) Prec@5 90.62 (91.75) + train[2018-10-23-23:12:05] Epoch: [216][3200/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.753 (2.867) Prec@1 78.91 (76.74) Prec@5 94.53 (91.74) + train[2018-10-23-23:13:52] Epoch: [216][3400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.699 (2.867) Prec@1 78.91 (76.76) Prec@5 96.09 (91.74) + train[2018-10-23-23:15:39] Epoch: [216][3600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.775 (2.867) Prec@1 81.25 (76.77) Prec@5 92.19 (91.74) + train[2018-10-23-23:17:26] Epoch: [216][3800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.876 (2.867) Prec@1 74.22 (76.75) Prec@5 88.28 (91.73) + train[2018-10-23-23:19:14] Epoch: [216][4000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.880 (2.868) Prec@1 77.34 (76.74) Prec@5 92.19 (91.74) + train[2018-10-23-23:20:59] Epoch: [216][4200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.749 (2.868) Prec@1 78.91 (76.73) Prec@5 92.97 (91.74) + train[2018-10-23-23:22:47] Epoch: [216][4400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.904 (2.868) Prec@1 76.56 (76.74) Prec@5 92.19 (91.74) + train[2018-10-23-23:24:33] Epoch: [216][4600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.064 (2.867) Prec@1 74.22 (76.76) Prec@5 90.62 (91.74) + train[2018-10-23-23:26:20] Epoch: [216][4800/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.883 (2.868) Prec@1 78.12 (76.76) Prec@5 89.84 (91.74) + train[2018-10-23-23:28:07] Epoch: [216][5000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 3.163 (2.867) Prec@1 71.09 (76.76) Prec@5 85.94 (91.73) + train[2018-10-23-23:29:54] Epoch: [216][5200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.867 (2.867) Prec@1 79.69 (76.76) Prec@5 91.41 (91.73) + train[2018-10-23-23:31:41] Epoch: [216][5400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.645 (2.867) Prec@1 85.16 (76.76) Prec@5 94.53 (91.73) + train[2018-10-23-23:33:27] Epoch: [216][5600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.552 (2.868) Prec@1 78.12 (76.75) Prec@5 97.66 (91.73) + train[2018-10-23-23:35:14] Epoch: [216][5800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.686 (2.868) Prec@1 77.34 (76.74) Prec@5 94.53 (91.73) + train[2018-10-23-23:36:59] Epoch: [216][6000/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 2.693 (2.867) Prec@1 78.91 (76.75) Prec@5 92.19 (91.74) + train[2018-10-23-23:38:45] Epoch: [216][6200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.048 (2.867) Prec@1 78.12 (76.76) Prec@5 90.62 (91.73) + train[2018-10-23-23:40:32] Epoch: [216][6400/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.629 (2.867) Prec@1 80.47 (76.76) Prec@5 96.09 (91.73) + train[2018-10-23-23:42:19] Epoch: [216][6600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.201 (2.867) Prec@1 72.66 (76.75) Prec@5 87.50 (91.73) + train[2018-10-23-23:44:06] Epoch: [216][6800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.873 (2.867) Prec@1 79.69 (76.76) Prec@5 92.97 (91.74) + train[2018-10-23-23:45:54] Epoch: [216][7000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.808 (2.867) Prec@1 78.12 (76.76) Prec@5 90.62 (91.74) + train[2018-10-23-23:47:41] Epoch: [216][7200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.225 (2.867) Prec@1 75.78 (76.75) Prec@5 89.84 (91.73) + train[2018-10-23-23:49:28] Epoch: [216][7400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.648 (2.867) Prec@1 79.69 (76.75) Prec@5 96.88 (91.73) + train[2018-10-23-23:51:15] Epoch: [216][7600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.791 (2.867) Prec@1 78.91 (76.76) Prec@5 92.97 (91.73) + train[2018-10-23-23:53:02] Epoch: [216][7800/10010] Time 0.62 (0.54) Data 0.00 (0.00) Loss 3.142 (2.867) Prec@1 69.53 (76.76) Prec@5 93.75 (91.73) + train[2018-10-23-23:54:49] Epoch: [216][8000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.869 (2.867) Prec@1 75.00 (76.76) Prec@5 92.19 (91.73) + train[2018-10-23-23:56:36] Epoch: [216][8200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.106 (2.867) Prec@1 71.09 (76.75) Prec@5 86.72 (91.72) + train[2018-10-23-23:58:23] Epoch: [216][8400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.870 (2.868) Prec@1 75.78 (76.75) Prec@5 92.19 (91.72) + train[2018-10-24-00:00:10] Epoch: [216][8600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.494 (2.868) Prec@1 80.47 (76.74) Prec@5 96.09 (91.72) + train[2018-10-24-00:01:57] Epoch: [216][8800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.794 (2.868) Prec@1 77.34 (76.74) Prec@5 94.53 (91.71) + train[2018-10-24-00:03:44] Epoch: [216][9000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.696 (2.868) Prec@1 81.25 (76.74) Prec@5 92.97 (91.71) + train[2018-10-24-00:05:31] Epoch: [216][9200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.705 (2.868) Prec@1 78.91 (76.74) Prec@5 94.53 (91.72) + train[2018-10-24-00:07:19] Epoch: [216][9400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.854 (2.868) Prec@1 75.00 (76.75) Prec@5 92.97 (91.72) + train[2018-10-24-00:09:06] Epoch: [216][9600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.011 (2.868) Prec@1 76.56 (76.74) Prec@5 89.84 (91.71) + train[2018-10-24-00:10:54] Epoch: [216][9800/10010] Time 0.61 (0.54) Data 0.00 (0.00) Loss 2.727 (2.868) Prec@1 81.25 (76.74) Prec@5 92.19 (91.72) + train[2018-10-24-00:12:39] Epoch: [216][10000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.913 (2.868) Prec@1 78.91 (76.74) Prec@5 93.75 (91.72) + train[2018-10-24-00:12:44] Epoch: [216][10009/10010] Time 0.14 (0.54) Data 0.00 (0.00) Loss 3.295 (2.867) Prec@1 80.00 (76.75) Prec@5 80.00 (91.72) +[2018-10-24-00:12:44] **train** Prec@1 76.75 Prec@5 91.72 Error@1 23.25 Error@5 8.28 Loss:2.867 + test [2018-10-24-00:12:48] Epoch: [216][000/391] Time 4.14 (4.14) Data 4.00 (4.00) Loss 0.522 (0.522) Prec@1 94.53 (94.53) Prec@5 99.22 (99.22) + test [2018-10-24-00:13:18] Epoch: [216][200/391] Time 0.12 (0.17) Data 0.00 (0.04) Loss 1.185 (0.987) Prec@1 66.41 (77.32) Prec@5 92.19 (93.59) + test [2018-10-24-00:13:43] Epoch: [216][390/391] Time 0.09 (0.15) Data 0.00 (0.02) Loss 2.128 (1.154) Prec@1 46.25 (73.84) Prec@5 82.50 (91.45) +[2018-10-24-00:13:43] **test** Prec@1 73.84 Prec@5 91.45 Error@1 26.16 Error@5 8.55 Loss:1.154 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-24-00:13:43] [Epoch=217/250] [Need: 49:39:00] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-24-00:13:49] Epoch: [217][000/10010] Time 5.98 (5.98) Data 5.35 (5.35) Loss 2.994 (2.994) Prec@1 75.00 (75.00) Prec@5 88.28 (88.28) + train[2018-10-24-00:15:35] Epoch: [217][200/10010] Time 0.52 (0.56) Data 0.00 (0.03) Loss 3.023 (2.862) Prec@1 77.34 (76.86) Prec@5 89.06 (91.74) + train[2018-10-24-00:17:21] Epoch: [217][400/10010] Time 0.57 (0.54) Data 0.00 (0.01) Loss 2.892 (2.867) Prec@1 76.56 (76.80) Prec@5 92.19 (91.70) + train[2018-10-24-00:19:06] Epoch: [217][600/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 3.017 (2.860) Prec@1 75.00 (76.98) Prec@5 89.84 (91.78) + train[2018-10-24-00:20:55] Epoch: [217][800/10010] Time 0.53 (0.54) Data 0.00 (0.01) Loss 2.828 (2.863) Prec@1 75.00 (76.94) Prec@5 95.31 (91.76) + train[2018-10-24-00:22:43] Epoch: [217][1000/10010] Time 0.58 (0.54) Data 0.00 (0.01) Loss 2.847 (2.864) Prec@1 77.34 (76.91) Prec@5 92.97 (91.77) + train[2018-10-24-00:24:32] Epoch: [217][1200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.676 (2.863) Prec@1 79.69 (76.92) Prec@5 94.53 (91.79) + train[2018-10-24-00:26:20] Epoch: [217][1400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.804 (2.864) Prec@1 74.22 (76.90) Prec@5 94.53 (91.78) + train[2018-10-24-00:28:07] Epoch: [217][1600/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 3.122 (2.860) Prec@1 73.44 (76.94) Prec@5 88.28 (91.82) + train[2018-10-24-00:29:53] Epoch: [217][1800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.625 (2.862) Prec@1 83.59 (76.90) Prec@5 95.31 (91.79) + train[2018-10-24-00:31:40] Epoch: [217][2000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.809 (2.863) Prec@1 79.69 (76.86) Prec@5 92.19 (91.78) + train[2018-10-24-00:33:29] Epoch: [217][2200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.496 (2.863) Prec@1 85.16 (76.86) Prec@5 96.88 (91.79) + train[2018-10-24-00:35:16] Epoch: [217][2400/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.749 (2.863) Prec@1 80.47 (76.85) Prec@5 95.31 (91.79) + train[2018-10-24-00:37:03] Epoch: [217][2600/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 2.838 (2.862) Prec@1 74.22 (76.85) Prec@5 93.75 (91.80) + train[2018-10-24-00:38:51] Epoch: [217][2800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.755 (2.863) Prec@1 78.12 (76.83) Prec@5 92.19 (91.81) + train[2018-10-24-00:40:38] Epoch: [217][3000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.842 (2.865) Prec@1 80.47 (76.79) Prec@5 91.41 (91.79) + train[2018-10-24-00:42:26] Epoch: [217][3200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.854 (2.866) Prec@1 76.56 (76.78) Prec@5 90.62 (91.78) + train[2018-10-24-00:44:14] Epoch: [217][3400/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 2.823 (2.865) Prec@1 76.56 (76.78) Prec@5 92.97 (91.77) + train[2018-10-24-00:46:03] Epoch: [217][3600/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.775 (2.865) Prec@1 78.91 (76.78) Prec@5 95.31 (91.79) + train[2018-10-24-00:47:51] Epoch: [217][3800/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.028 (2.866) Prec@1 70.31 (76.75) Prec@5 93.75 (91.78) + train[2018-10-24-00:49:39] Epoch: [217][4000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.994 (2.866) Prec@1 69.53 (76.76) Prec@5 91.41 (91.77) + train[2018-10-24-00:51:26] Epoch: [217][4200/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.975 (2.866) Prec@1 74.22 (76.76) Prec@5 89.84 (91.77) + train[2018-10-24-00:53:14] Epoch: [217][4400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.724 (2.866) Prec@1 76.56 (76.74) Prec@5 93.75 (91.76) + train[2018-10-24-00:55:01] Epoch: [217][4600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.719 (2.866) Prec@1 71.88 (76.73) Prec@5 93.75 (91.76) + train[2018-10-24-00:56:49] Epoch: [217][4800/10010] Time 0.63 (0.54) Data 0.00 (0.00) Loss 2.833 (2.867) Prec@1 78.91 (76.71) Prec@5 89.84 (91.75) + train[2018-10-24-00:58:36] Epoch: [217][5000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.909 (2.867) Prec@1 74.22 (76.73) Prec@5 92.97 (91.75) + train[2018-10-24-01:00:25] Epoch: [217][5200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.075 (2.867) Prec@1 70.31 (76.72) Prec@5 90.62 (91.75) + train[2018-10-24-01:02:12] Epoch: [217][5400/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.583 (2.867) Prec@1 82.81 (76.72) Prec@5 94.53 (91.75) + train[2018-10-24-01:04:00] Epoch: [217][5600/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.883 (2.867) Prec@1 75.78 (76.72) Prec@5 91.41 (91.75) + train[2018-10-24-01:05:48] Epoch: [217][5800/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.699 (2.867) Prec@1 78.91 (76.73) Prec@5 92.97 (91.75) + train[2018-10-24-01:07:34] Epoch: [217][6000/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 2.991 (2.867) Prec@1 71.88 (76.73) Prec@5 90.62 (91.74) + train[2018-10-24-01:09:22] Epoch: [217][6200/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 3.162 (2.868) Prec@1 70.31 (76.72) Prec@5 88.28 (91.73) + train[2018-10-24-01:11:10] Epoch: [217][6400/10010] Time 0.62 (0.54) Data 0.00 (0.00) Loss 2.737 (2.868) Prec@1 78.91 (76.71) Prec@5 90.62 (91.73) + train[2018-10-24-01:12:58] Epoch: [217][6600/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 3.018 (2.869) Prec@1 77.34 (76.70) Prec@5 89.06 (91.73) + train[2018-10-24-01:14:47] Epoch: [217][6800/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.499 (2.869) Prec@1 83.59 (76.71) Prec@5 96.88 (91.74) + train[2018-10-24-01:16:35] Epoch: [217][7000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.706 (2.868) Prec@1 78.91 (76.71) Prec@5 92.19 (91.74) + train[2018-10-24-01:18:23] Epoch: [217][7200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.972 (2.868) Prec@1 73.44 (76.71) Prec@5 87.50 (91.74) + train[2018-10-24-01:20:11] Epoch: [217][7400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.992 (2.868) Prec@1 75.78 (76.72) Prec@5 89.06 (91.75) + train[2018-10-24-01:21:58] Epoch: [217][7600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.065 (2.868) Prec@1 74.22 (76.73) Prec@5 88.28 (91.75) + train[2018-10-24-01:23:45] Epoch: [217][7800/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 2.845 (2.868) Prec@1 78.91 (76.72) Prec@5 92.19 (91.75) + train[2018-10-24-01:25:32] Epoch: [217][8000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.870 (2.867) Prec@1 77.34 (76.72) Prec@5 92.19 (91.75) + train[2018-10-24-01:27:19] Epoch: [217][8200/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.866 (2.868) Prec@1 76.56 (76.72) Prec@5 91.41 (91.75) + train[2018-10-24-01:29:08] Epoch: [217][8400/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.708 (2.868) Prec@1 80.47 (76.73) Prec@5 91.41 (91.75) + train[2018-10-24-01:30:56] Epoch: [217][8600/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.947 (2.867) Prec@1 77.34 (76.73) Prec@5 89.84 (91.75) + train[2018-10-24-01:32:44] Epoch: [217][8800/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.688 (2.867) Prec@1 80.47 (76.73) Prec@5 93.75 (91.76) + train[2018-10-24-01:34:32] Epoch: [217][9000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.847 (2.867) Prec@1 74.22 (76.74) Prec@5 91.41 (91.76) + train[2018-10-24-01:36:20] Epoch: [217][9200/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.630 (2.867) Prec@1 80.47 (76.73) Prec@5 95.31 (91.76) + train[2018-10-24-01:38:08] Epoch: [217][9400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.701 (2.867) Prec@1 76.56 (76.72) Prec@5 93.75 (91.76) + train[2018-10-24-01:39:56] Epoch: [217][9600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.793 (2.867) Prec@1 78.91 (76.73) Prec@5 92.19 (91.76) + train[2018-10-24-01:41:44] Epoch: [217][9800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 3.054 (2.868) Prec@1 73.44 (76.72) Prec@5 86.72 (91.75) + train[2018-10-24-01:43:32] Epoch: [217][10000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.708 (2.868) Prec@1 76.56 (76.71) Prec@5 94.53 (91.75) + train[2018-10-24-01:43:36] Epoch: [217][10009/10010] Time 0.19 (0.54) Data 0.00 (0.00) Loss 4.527 (2.868) Prec@1 53.33 (76.70) Prec@5 80.00 (91.75) +[2018-10-24-01:43:36] **train** Prec@1 76.70 Prec@5 91.75 Error@1 23.30 Error@5 8.25 Loss:2.868 + test [2018-10-24-01:43:40] Epoch: [217][000/391] Time 3.78 (3.78) Data 3.64 (3.64) Loss 0.508 (0.508) Prec@1 93.75 (93.75) Prec@5 98.44 (98.44) + test [2018-10-24-01:44:09] Epoch: [217][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.260 (1.000) Prec@1 64.84 (77.37) Prec@5 91.41 (93.64) + test [2018-10-24-01:44:34] Epoch: [217][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.175 (1.168) Prec@1 43.75 (73.83) Prec@5 85.00 (91.40) +[2018-10-24-01:44:34] **test** Prec@1 73.83 Prec@5 91.40 Error@1 26.17 Error@5 8.60 Loss:1.168 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-24-01:44:34] [Epoch=218/250] [Need: 48:26:53] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-24-01:44:39] Epoch: [218][000/10010] Time 5.21 (5.21) Data 4.58 (4.58) Loss 2.772 (2.772) Prec@1 80.47 (80.47) Prec@5 94.53 (94.53) + train[2018-10-24-01:46:24] Epoch: [218][200/10010] Time 0.51 (0.55) Data 0.00 (0.02) Loss 2.544 (2.843) Prec@1 84.38 (77.44) Prec@5 94.53 (92.09) + train[2018-10-24-01:48:10] Epoch: [218][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.997 (2.854) Prec@1 78.12 (77.16) Prec@5 88.28 (91.99) + train[2018-10-24-01:49:57] Epoch: [218][600/10010] Time 0.53 (0.54) Data 0.00 (0.01) Loss 3.112 (2.857) Prec@1 73.44 (77.08) Prec@5 89.84 (91.91) + train[2018-10-24-01:51:42] Epoch: [218][800/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 2.937 (2.855) Prec@1 75.78 (77.08) Prec@5 90.62 (91.87) + train[2018-10-24-01:53:29] Epoch: [218][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.723 (2.858) Prec@1 75.78 (77.00) Prec@5 91.41 (91.86) + train[2018-10-24-01:55:16] Epoch: [218][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.777 (2.859) Prec@1 77.34 (76.98) Prec@5 92.19 (91.83) + train[2018-10-24-01:57:02] Epoch: [218][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.060 (2.859) Prec@1 75.78 (76.98) Prec@5 85.94 (91.82) + train[2018-10-24-01:58:48] Epoch: [218][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.925 (2.860) Prec@1 77.34 (76.96) Prec@5 91.41 (91.83) + train[2018-10-24-02:00:34] Epoch: [218][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.917 (2.861) Prec@1 79.69 (76.94) Prec@5 91.41 (91.81) + train[2018-10-24-02:02:21] Epoch: [218][2000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.865 (2.861) Prec@1 71.09 (76.91) Prec@5 92.97 (91.82) + train[2018-10-24-02:04:08] Epoch: [218][2200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.808 (2.861) Prec@1 74.22 (76.93) Prec@5 93.75 (91.82) + train[2018-10-24-02:05:55] Epoch: [218][2400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.509 (2.861) Prec@1 82.81 (76.92) Prec@5 96.09 (91.81) + train[2018-10-24-02:07:41] Epoch: [218][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.942 (2.862) Prec@1 75.78 (76.90) Prec@5 92.19 (91.79) + train[2018-10-24-02:09:29] Epoch: [218][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.099 (2.863) Prec@1 69.53 (76.90) Prec@5 91.41 (91.77) + train[2018-10-24-02:11:16] Epoch: [218][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.039 (2.863) Prec@1 75.78 (76.88) Prec@5 89.84 (91.76) + train[2018-10-24-02:13:02] Epoch: [218][3200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.880 (2.863) Prec@1 78.12 (76.86) Prec@5 92.19 (91.76) + train[2018-10-24-02:14:47] Epoch: [218][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.464 (2.863) Prec@1 82.81 (76.86) Prec@5 92.97 (91.77) + train[2018-10-24-02:16:33] Epoch: [218][3600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.994 (2.863) Prec@1 77.34 (76.85) Prec@5 90.62 (91.77) + train[2018-10-24-02:18:18] Epoch: [218][3800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.004 (2.863) Prec@1 74.22 (76.84) Prec@5 89.06 (91.77) + train[2018-10-24-02:20:05] Epoch: [218][4000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.513 (2.863) Prec@1 82.03 (76.86) Prec@5 97.66 (91.78) + train[2018-10-24-02:21:52] Epoch: [218][4200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.771 (2.863) Prec@1 74.22 (76.85) Prec@5 92.97 (91.77) + train[2018-10-24-02:23:39] Epoch: [218][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.832 (2.863) Prec@1 78.12 (76.86) Prec@5 92.97 (91.77) + train[2018-10-24-02:25:25] Epoch: [218][4600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.984 (2.863) Prec@1 75.00 (76.86) Prec@5 88.28 (91.77) + train[2018-10-24-02:27:12] Epoch: [218][4800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.886 (2.863) Prec@1 75.78 (76.87) Prec@5 92.97 (91.77) + train[2018-10-24-02:28:59] Epoch: [218][5000/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.739 (2.864) Prec@1 82.03 (76.86) Prec@5 93.75 (91.75) + train[2018-10-24-02:30:47] Epoch: [218][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.831 (2.864) Prec@1 75.78 (76.86) Prec@5 90.62 (91.75) + train[2018-10-24-02:32:35] Epoch: [218][5400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.760 (2.864) Prec@1 81.25 (76.86) Prec@5 91.41 (91.75) + train[2018-10-24-02:34:22] Epoch: [218][5600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.843 (2.864) Prec@1 75.78 (76.87) Prec@5 94.53 (91.76) + train[2018-10-24-02:36:09] Epoch: [218][5800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.957 (2.864) Prec@1 77.34 (76.86) Prec@5 94.53 (91.75) + train[2018-10-24-02:37:57] Epoch: [218][6000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.951 (2.865) Prec@1 75.00 (76.86) Prec@5 89.06 (91.75) + train[2018-10-24-02:39:44] Epoch: [218][6200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.995 (2.865) Prec@1 77.34 (76.87) Prec@5 89.06 (91.74) + train[2018-10-24-02:41:32] Epoch: [218][6400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.235 (2.865) Prec@1 70.31 (76.87) Prec@5 89.06 (91.74) + train[2018-10-24-02:43:20] Epoch: [218][6600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.115 (2.864) Prec@1 69.53 (76.87) Prec@5 92.19 (91.75) + train[2018-10-24-02:45:07] Epoch: [218][6800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.113 (2.864) Prec@1 68.75 (76.88) Prec@5 89.84 (91.75) + train[2018-10-24-02:46:53] Epoch: [218][7000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.872 (2.865) Prec@1 78.12 (76.87) Prec@5 92.19 (91.74) + train[2018-10-24-02:48:39] Epoch: [218][7200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.533 (2.865) Prec@1 65.62 (76.87) Prec@5 85.94 (91.75) + train[2018-10-24-02:50:26] Epoch: [218][7400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.987 (2.865) Prec@1 78.12 (76.87) Prec@5 87.50 (91.75) + train[2018-10-24-02:52:14] Epoch: [218][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.276 (2.865) Prec@1 70.31 (76.86) Prec@5 88.28 (91.74) + train[2018-10-24-02:54:01] Epoch: [218][7800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.139 (2.866) Prec@1 73.44 (76.87) Prec@5 86.72 (91.73) + train[2018-10-24-02:55:49] Epoch: [218][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.770 (2.865) Prec@1 78.12 (76.87) Prec@5 94.53 (91.74) + train[2018-10-24-02:57:36] Epoch: [218][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.984 (2.865) Prec@1 73.44 (76.86) Prec@5 90.62 (91.74) + train[2018-10-24-02:59:23] Epoch: [218][8400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.853 (2.866) Prec@1 75.00 (76.86) Prec@5 91.41 (91.74) + train[2018-10-24-03:01:10] Epoch: [218][8600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.742 (2.865) Prec@1 79.69 (76.86) Prec@5 91.41 (91.74) + train[2018-10-24-03:02:57] Epoch: [218][8800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.932 (2.866) Prec@1 76.56 (76.86) Prec@5 89.06 (91.74) + train[2018-10-24-03:04:45] Epoch: [218][9000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.684 (2.865) Prec@1 78.91 (76.86) Prec@5 94.53 (91.74) + train[2018-10-24-03:06:32] Epoch: [218][9200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.624 (2.865) Prec@1 81.25 (76.87) Prec@5 94.53 (91.74) + train[2018-10-24-03:08:20] Epoch: [218][9400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.986 (2.866) Prec@1 78.12 (76.85) Prec@5 88.28 (91.73) + train[2018-10-24-03:10:06] Epoch: [218][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.804 (2.866) Prec@1 81.25 (76.84) Prec@5 92.19 (91.73) + train[2018-10-24-03:11:52] Epoch: [218][9800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.715 (2.866) Prec@1 76.56 (76.85) Prec@5 94.53 (91.73) + train[2018-10-24-03:13:38] Epoch: [218][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.179 (2.865) Prec@1 72.66 (76.85) Prec@5 89.84 (91.74) + train[2018-10-24-03:13:43] Epoch: [218][10009/10010] Time 0.22 (0.53) Data 0.00 (0.00) Loss 3.386 (2.865) Prec@1 73.33 (76.85) Prec@5 86.67 (91.74) +[2018-10-24-03:13:43] **train** Prec@1 76.85 Prec@5 91.74 Error@1 23.15 Error@5 8.26 Loss:2.865 + test [2018-10-24-03:13:47] Epoch: [218][000/391] Time 4.29 (4.29) Data 4.15 (4.15) Loss 0.551 (0.551) Prec@1 92.97 (92.97) Prec@5 97.66 (97.66) + test [2018-10-24-03:14:17] Epoch: [218][200/391] Time 0.13 (0.17) Data 0.00 (0.03) Loss 1.220 (0.993) Prec@1 66.41 (77.36) Prec@5 91.41 (93.66) + test [2018-10-24-03:14:41] Epoch: [218][390/391] Time 0.08 (0.15) Data 0.00 (0.02) Loss 2.076 (1.162) Prec@1 50.00 (73.84) Prec@5 83.75 (91.43) +[2018-10-24-03:14:42] **test** Prec@1 73.84 Prec@5 91.43 Error@1 26.16 Error@5 8.57 Loss:1.162 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-24-03:14:42] [Epoch=219/250] [Need: 46:34:05] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-24-03:14:47] Epoch: [219][000/10010] Time 5.23 (5.23) Data 4.58 (4.58) Loss 3.087 (3.087) Prec@1 72.66 (72.66) Prec@5 85.94 (85.94) + train[2018-10-24-03:16:32] Epoch: [219][200/10010] Time 0.57 (0.55) Data 0.00 (0.02) Loss 2.688 (2.853) Prec@1 82.81 (76.96) Prec@5 94.53 (92.12) + train[2018-10-24-03:18:18] Epoch: [219][400/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 3.102 (2.856) Prec@1 75.00 (76.99) Prec@5 86.72 (91.90) + train[2018-10-24-03:20:02] Epoch: [219][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.689 (2.858) Prec@1 78.91 (76.99) Prec@5 92.97 (91.84) + train[2018-10-24-03:21:48] Epoch: [219][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.883 (2.861) Prec@1 79.69 (77.00) Prec@5 91.41 (91.79) + train[2018-10-24-03:23:35] Epoch: [219][1000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.965 (2.863) Prec@1 71.09 (76.98) Prec@5 92.19 (91.72) + train[2018-10-24-03:25:24] Epoch: [219][1200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.730 (2.862) Prec@1 77.34 (76.98) Prec@5 94.53 (91.71) + train[2018-10-24-03:27:12] Epoch: [219][1400/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 3.099 (2.862) Prec@1 75.00 (76.95) Prec@5 89.84 (91.69) + train[2018-10-24-03:28:59] Epoch: [219][1600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.853 (2.863) Prec@1 75.78 (76.93) Prec@5 92.97 (91.70) + train[2018-10-24-03:30:48] Epoch: [219][1800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.764 (2.862) Prec@1 82.03 (76.94) Prec@5 91.41 (91.71) + train[2018-10-24-03:32:35] Epoch: [219][2000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.699 (2.860) Prec@1 83.59 (76.98) Prec@5 96.09 (91.75) + train[2018-10-24-03:34:23] Epoch: [219][2200/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.684 (2.860) Prec@1 82.81 (76.97) Prec@5 91.41 (91.74) + train[2018-10-24-03:36:10] Epoch: [219][2400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.167 (2.861) Prec@1 68.75 (76.95) Prec@5 90.62 (91.73) + train[2018-10-24-03:37:57] Epoch: [219][2600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.685 (2.863) Prec@1 80.47 (76.90) Prec@5 93.75 (91.72) + train[2018-10-24-03:39:44] Epoch: [219][2800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.860 (2.862) Prec@1 78.91 (76.88) Prec@5 90.62 (91.73) + train[2018-10-24-03:41:31] Epoch: [219][3000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.554 (2.862) Prec@1 78.91 (76.89) Prec@5 96.09 (91.73) + train[2018-10-24-03:43:19] Epoch: [219][3200/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.885 (2.864) Prec@1 72.66 (76.86) Prec@5 90.62 (91.72) + train[2018-10-24-03:45:07] Epoch: [219][3400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.653 (2.865) Prec@1 82.03 (76.88) Prec@5 92.19 (91.71) + train[2018-10-24-03:46:55] Epoch: [219][3600/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.894 (2.865) Prec@1 75.78 (76.87) Prec@5 90.62 (91.70) + train[2018-10-24-03:48:43] Epoch: [219][3800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.657 (2.865) Prec@1 78.12 (76.88) Prec@5 91.41 (91.71) + train[2018-10-24-03:50:30] Epoch: [219][4000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.890 (2.865) Prec@1 77.34 (76.88) Prec@5 92.19 (91.71) + train[2018-10-24-03:52:18] Epoch: [219][4200/10010] Time 0.60 (0.54) Data 0.00 (0.00) Loss 2.807 (2.865) Prec@1 78.91 (76.88) Prec@5 91.41 (91.71) + train[2018-10-24-03:54:06] Epoch: [219][4400/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.748 (2.864) Prec@1 78.12 (76.91) Prec@5 93.75 (91.72) + train[2018-10-24-03:55:54] Epoch: [219][4600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.719 (2.863) Prec@1 78.91 (76.92) Prec@5 94.53 (91.75) + train[2018-10-24-03:57:42] Epoch: [219][4800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.971 (2.863) Prec@1 74.22 (76.92) Prec@5 93.75 (91.74) + train[2018-10-24-03:59:29] Epoch: [219][5000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.823 (2.864) Prec@1 78.91 (76.89) Prec@5 93.75 (91.73) + train[2018-10-24-04:01:17] Epoch: [219][5200/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.981 (2.865) Prec@1 73.44 (76.87) Prec@5 89.84 (91.73) + train[2018-10-24-04:03:05] Epoch: [219][5400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.604 (2.865) Prec@1 80.47 (76.86) Prec@5 95.31 (91.72) + train[2018-10-24-04:04:52] Epoch: [219][5600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.655 (2.865) Prec@1 82.81 (76.85) Prec@5 92.19 (91.73) + train[2018-10-24-04:06:40] Epoch: [219][5800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.840 (2.865) Prec@1 75.78 (76.86) Prec@5 91.41 (91.73) + train[2018-10-24-04:08:28] Epoch: [219][6000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.091 (2.865) Prec@1 71.88 (76.86) Prec@5 90.62 (91.73) + train[2018-10-24-04:10:15] Epoch: [219][6200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.928 (2.865) Prec@1 78.91 (76.86) Prec@5 88.28 (91.73) + train[2018-10-24-04:12:04] Epoch: [219][6400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.605 (2.865) Prec@1 79.69 (76.86) Prec@5 96.09 (91.74) + train[2018-10-24-04:13:52] Epoch: [219][6600/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.942 (2.865) Prec@1 80.47 (76.84) Prec@5 89.06 (91.74) + train[2018-10-24-04:15:40] Epoch: [219][6800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 3.110 (2.866) Prec@1 70.31 (76.83) Prec@5 89.84 (91.74) + train[2018-10-24-04:17:28] Epoch: [219][7000/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.817 (2.865) Prec@1 77.34 (76.84) Prec@5 93.75 (91.74) + train[2018-10-24-04:19:16] Epoch: [219][7200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.567 (2.865) Prec@1 82.81 (76.83) Prec@5 95.31 (91.74) + train[2018-10-24-04:21:03] Epoch: [219][7400/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.948 (2.866) Prec@1 79.69 (76.83) Prec@5 91.41 (91.74) + train[2018-10-24-04:22:51] Epoch: [219][7600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.154 (2.866) Prec@1 75.00 (76.82) Prec@5 86.72 (91.74) + train[2018-10-24-04:24:39] Epoch: [219][7800/10010] Time 0.60 (0.54) Data 0.00 (0.00) Loss 2.804 (2.866) Prec@1 72.66 (76.82) Prec@5 93.75 (91.74) + train[2018-10-24-04:26:27] Epoch: [219][8000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.124 (2.866) Prec@1 68.75 (76.82) Prec@5 88.28 (91.74) + train[2018-10-24-04:28:15] Epoch: [219][8200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.889 (2.865) Prec@1 80.47 (76.83) Prec@5 92.19 (91.74) + train[2018-10-24-04:30:03] Epoch: [219][8400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.827 (2.866) Prec@1 78.91 (76.83) Prec@5 92.19 (91.74) + train[2018-10-24-04:31:50] Epoch: [219][8600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.820 (2.866) Prec@1 77.34 (76.83) Prec@5 92.97 (91.74) + train[2018-10-24-04:33:35] Epoch: [219][8800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.821 (2.866) Prec@1 78.12 (76.83) Prec@5 92.97 (91.74) + train[2018-10-24-04:35:21] Epoch: [219][9000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.957 (2.866) Prec@1 81.25 (76.84) Prec@5 89.06 (91.74) + train[2018-10-24-04:37:08] Epoch: [219][9200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.855 (2.866) Prec@1 78.12 (76.84) Prec@5 89.84 (91.73) + train[2018-10-24-04:38:56] Epoch: [219][9400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.694 (2.866) Prec@1 82.03 (76.83) Prec@5 94.53 (91.73) + train[2018-10-24-04:40:44] Epoch: [219][9600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 3.042 (2.866) Prec@1 75.00 (76.84) Prec@5 89.06 (91.74) + train[2018-10-24-04:42:31] Epoch: [219][9800/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.789 (2.866) Prec@1 80.47 (76.83) Prec@5 91.41 (91.74) + train[2018-10-24-04:44:17] Epoch: [219][10000/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.115 (2.866) Prec@1 72.66 (76.83) Prec@5 89.06 (91.73) + train[2018-10-24-04:44:21] Epoch: [219][10009/10010] Time 0.20 (0.54) Data 0.00 (0.00) Loss 3.160 (2.866) Prec@1 86.67 (76.83) Prec@5 100.00 (91.73) +[2018-10-24-04:44:22] **train** Prec@1 76.83 Prec@5 91.73 Error@1 23.17 Error@5 8.27 Loss:2.866 + test [2018-10-24-04:44:25] Epoch: [219][000/391] Time 3.70 (3.70) Data 3.57 (3.57) Loss 0.542 (0.542) Prec@1 93.75 (93.75) Prec@5 98.44 (98.44) + test [2018-10-24-04:44:53] Epoch: [219][200/391] Time 0.14 (0.16) Data 0.00 (0.02) Loss 1.248 (1.009) Prec@1 69.53 (77.60) Prec@5 92.19 (93.66) + test [2018-10-24-04:45:19] Epoch: [219][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.160 (1.178) Prec@1 43.75 (73.89) Prec@5 83.75 (91.51) +[2018-10-24-04:45:19] **test** Prec@1 73.89 Prec@5 91.51 Error@1 26.11 Error@5 8.49 Loss:1.178 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-24-04:45:19] [Epoch=220/250] [Need: 45:18:34] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-24-04:45:24] Epoch: [220][000/10010] Time 5.55 (5.55) Data 4.87 (4.87) Loss 2.782 (2.782) Prec@1 82.03 (82.03) Prec@5 90.62 (90.62) + train[2018-10-24-04:47:11] Epoch: [220][200/10010] Time 0.59 (0.56) Data 0.00 (0.02) Loss 3.227 (2.866) Prec@1 73.44 (77.29) Prec@5 86.72 (91.50) + train[2018-10-24-04:48:56] Epoch: [220][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.811 (2.855) Prec@1 80.47 (77.22) Prec@5 92.19 (91.68) + train[2018-10-24-04:50:43] Epoch: [220][600/10010] Time 0.54 (0.54) Data 0.00 (0.01) Loss 3.123 (2.855) Prec@1 71.88 (77.18) Prec@5 91.41 (91.70) + train[2018-10-24-04:52:29] Epoch: [220][800/10010] Time 0.53 (0.54) Data 0.00 (0.01) Loss 2.999 (2.852) Prec@1 75.00 (77.19) Prec@5 92.19 (91.77) + train[2018-10-24-04:54:16] Epoch: [220][1000/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 2.756 (2.856) Prec@1 80.47 (77.11) Prec@5 92.97 (91.74) + train[2018-10-24-04:56:02] Epoch: [220][1200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.248 (2.859) Prec@1 69.53 (77.01) Prec@5 87.50 (91.72) + train[2018-10-24-04:57:49] Epoch: [220][1400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.931 (2.857) Prec@1 74.22 (77.03) Prec@5 92.97 (91.76) + train[2018-10-24-04:59:35] Epoch: [220][1600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.518 (2.856) Prec@1 80.47 (77.06) Prec@5 96.09 (91.79) + train[2018-10-24-05:01:23] Epoch: [220][1800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.102 (2.854) Prec@1 71.09 (77.07) Prec@5 88.28 (91.80) + train[2018-10-24-05:03:10] Epoch: [220][2000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.979 (2.855) Prec@1 77.34 (77.07) Prec@5 89.84 (91.80) + train[2018-10-24-05:04:57] Epoch: [220][2200/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.208 (2.856) Prec@1 72.66 (77.06) Prec@5 87.50 (91.79) + train[2018-10-24-05:06:44] Epoch: [220][2400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.556 (2.857) Prec@1 81.25 (77.04) Prec@5 94.53 (91.77) + train[2018-10-24-05:08:30] Epoch: [220][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.845 (2.857) Prec@1 78.91 (77.03) Prec@5 89.84 (91.77) + train[2018-10-24-05:10:16] Epoch: [220][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.911 (2.858) Prec@1 77.34 (77.01) Prec@5 89.06 (91.76) + train[2018-10-24-05:12:03] Epoch: [220][3000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.850 (2.860) Prec@1 75.78 (76.97) Prec@5 93.75 (91.74) + train[2018-10-24-05:13:51] Epoch: [220][3200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.835 (2.861) Prec@1 78.91 (76.95) Prec@5 93.75 (91.73) + train[2018-10-24-05:15:38] Epoch: [220][3400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.209 (2.861) Prec@1 70.31 (76.97) Prec@5 87.50 (91.73) + train[2018-10-24-05:17:24] Epoch: [220][3600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.945 (2.862) Prec@1 75.78 (76.94) Prec@5 92.19 (91.73) + train[2018-10-24-05:19:11] Epoch: [220][3800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.059 (2.863) Prec@1 68.75 (76.93) Prec@5 89.06 (91.74) + train[2018-10-24-05:20:57] Epoch: [220][4000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.811 (2.862) Prec@1 75.00 (76.92) Prec@5 94.53 (91.74) + train[2018-10-24-05:22:43] Epoch: [220][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.883 (2.863) Prec@1 71.88 (76.92) Prec@5 92.19 (91.74) + train[2018-10-24-05:24:30] Epoch: [220][4400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.952 (2.862) Prec@1 76.56 (76.92) Prec@5 90.62 (91.75) + train[2018-10-24-05:26:17] Epoch: [220][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.715 (2.862) Prec@1 78.91 (76.95) Prec@5 93.75 (91.75) + train[2018-10-24-05:28:05] Epoch: [220][4800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.639 (2.862) Prec@1 79.69 (76.93) Prec@5 92.97 (91.75) + train[2018-10-24-05:29:51] Epoch: [220][5000/10010] Time 0.61 (0.53) Data 0.00 (0.00) Loss 2.768 (2.863) Prec@1 83.59 (76.92) Prec@5 90.62 (91.73) + train[2018-10-24-05:31:37] Epoch: [220][5200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.793 (2.863) Prec@1 82.81 (76.92) Prec@5 92.97 (91.74) + train[2018-10-24-05:33:23] Epoch: [220][5400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.990 (2.864) Prec@1 71.88 (76.91) Prec@5 89.06 (91.73) + train[2018-10-24-05:35:10] Epoch: [220][5600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.866 (2.864) Prec@1 77.34 (76.90) Prec@5 92.19 (91.73) + train[2018-10-24-05:36:57] Epoch: [220][5800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.041 (2.864) Prec@1 79.69 (76.90) Prec@5 89.06 (91.73) + train[2018-10-24-05:38:43] Epoch: [220][6000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.970 (2.864) Prec@1 77.34 (76.91) Prec@5 90.62 (91.73) + train[2018-10-24-05:40:30] Epoch: [220][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.783 (2.865) Prec@1 79.69 (76.89) Prec@5 93.75 (91.72) + train[2018-10-24-05:42:17] Epoch: [220][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.923 (2.865) Prec@1 78.12 (76.89) Prec@5 89.84 (91.72) + train[2018-10-24-05:44:03] Epoch: [220][6600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.820 (2.865) Prec@1 81.25 (76.89) Prec@5 92.19 (91.72) + train[2018-10-24-05:45:49] Epoch: [220][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.867 (2.864) Prec@1 76.56 (76.90) Prec@5 89.06 (91.72) + train[2018-10-24-05:47:35] Epoch: [220][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.875 (2.864) Prec@1 81.25 (76.89) Prec@5 90.62 (91.72) + train[2018-10-24-05:49:23] Epoch: [220][7200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.348 (2.864) Prec@1 67.19 (76.89) Prec@5 88.28 (91.73) + train[2018-10-24-05:51:08] Epoch: [220][7400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.627 (2.864) Prec@1 82.81 (76.89) Prec@5 95.31 (91.73) + train[2018-10-24-05:52:54] Epoch: [220][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.854 (2.864) Prec@1 79.69 (76.88) Prec@5 90.62 (91.73) + train[2018-10-24-05:54:41] Epoch: [220][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.967 (2.864) Prec@1 75.00 (76.88) Prec@5 89.84 (91.73) + train[2018-10-24-05:56:28] Epoch: [220][8000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.929 (2.864) Prec@1 77.34 (76.89) Prec@5 89.84 (91.73) + train[2018-10-24-05:58:14] Epoch: [220][8200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.857 (2.864) Prec@1 75.78 (76.89) Prec@5 94.53 (91.73) + train[2018-10-24-06:00:00] Epoch: [220][8400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.818 (2.864) Prec@1 77.34 (76.90) Prec@5 93.75 (91.74) + train[2018-10-24-06:01:46] Epoch: [220][8600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.759 (2.864) Prec@1 76.56 (76.89) Prec@5 92.97 (91.74) + train[2018-10-24-06:03:33] Epoch: [220][8800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.753 (2.864) Prec@1 79.69 (76.89) Prec@5 90.62 (91.75) + train[2018-10-24-06:05:19] Epoch: [220][9000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.945 (2.864) Prec@1 73.44 (76.89) Prec@5 92.97 (91.74) + train[2018-10-24-06:07:06] Epoch: [220][9200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.828 (2.864) Prec@1 78.12 (76.89) Prec@5 93.75 (91.75) + train[2018-10-24-06:08:51] Epoch: [220][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.830 (2.864) Prec@1 75.78 (76.88) Prec@5 91.41 (91.74) + train[2018-10-24-06:10:36] Epoch: [220][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.734 (2.865) Prec@1 81.25 (76.87) Prec@5 92.19 (91.74) + train[2018-10-24-06:12:22] Epoch: [220][9800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.131 (2.865) Prec@1 73.44 (76.86) Prec@5 89.06 (91.73) + train[2018-10-24-06:14:08] Epoch: [220][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.577 (2.865) Prec@1 83.59 (76.86) Prec@5 96.09 (91.73) + train[2018-10-24-06:14:12] Epoch: [220][10009/10010] Time 0.21 (0.53) Data 0.00 (0.00) Loss 2.484 (2.865) Prec@1 93.33 (76.85) Prec@5 93.33 (91.73) +[2018-10-24-06:14:12] **train** Prec@1 76.85 Prec@5 91.73 Error@1 23.15 Error@5 8.27 Loss:2.865 + test [2018-10-24-06:14:16] Epoch: [220][000/391] Time 4.07 (4.07) Data 3.93 (3.93) Loss 0.556 (0.556) Prec@1 92.97 (92.97) Prec@5 99.22 (99.22) + test [2018-10-24-06:14:47] Epoch: [220][200/391] Time 0.13 (0.17) Data 0.00 (0.04) Loss 1.180 (1.003) Prec@1 64.84 (77.41) Prec@5 91.41 (93.63) + test [2018-10-24-06:15:12] Epoch: [220][390/391] Time 0.08 (0.15) Data 0.00 (0.02) Loss 2.123 (1.169) Prec@1 47.50 (73.87) Prec@5 83.75 (91.51) +[2018-10-24-06:15:12] **test** Prec@1 73.87 Prec@5 91.51 Error@1 26.13 Error@5 8.49 Loss:1.169 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-24-06:15:12] [Epoch=221/250] [Need: 43:26:34] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-24-06:15:16] Epoch: [221][000/10010] Time 4.28 (4.28) Data 3.56 (3.56) Loss 2.860 (2.860) Prec@1 78.12 (78.12) Prec@5 91.41 (91.41) + train[2018-10-24-06:17:02] Epoch: [221][200/10010] Time 0.51 (0.55) Data 0.00 (0.02) Loss 2.893 (2.876) Prec@1 79.69 (76.60) Prec@5 91.41 (91.54) + train[2018-10-24-06:18:48] Epoch: [221][400/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 3.110 (2.872) Prec@1 71.88 (76.73) Prec@5 90.62 (91.53) + train[2018-10-24-06:20:34] Epoch: [221][600/10010] Time 0.64 (0.54) Data 0.00 (0.01) Loss 2.744 (2.870) Prec@1 75.78 (76.74) Prec@5 92.19 (91.58) + train[2018-10-24-06:22:20] Epoch: [221][800/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 3.022 (2.870) Prec@1 75.00 (76.75) Prec@5 92.19 (91.61) + train[2018-10-24-06:24:07] Epoch: [221][1000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.766 (2.872) Prec@1 74.22 (76.74) Prec@5 92.97 (91.58) + train[2018-10-24-06:25:53] Epoch: [221][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.542 (2.868) Prec@1 79.69 (76.80) Prec@5 94.53 (91.64) + train[2018-10-24-06:27:39] Epoch: [221][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.769 (2.867) Prec@1 75.78 (76.81) Prec@5 92.97 (91.64) + train[2018-10-24-06:29:25] Epoch: [221][1600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.943 (2.866) Prec@1 73.44 (76.80) Prec@5 95.31 (91.67) + train[2018-10-24-06:31:12] Epoch: [221][1800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.058 (2.864) Prec@1 71.09 (76.84) Prec@5 90.62 (91.68) + train[2018-10-24-06:32:59] Epoch: [221][2000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.749 (2.864) Prec@1 80.47 (76.84) Prec@5 95.31 (91.70) + train[2018-10-24-06:34:46] Epoch: [221][2200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.696 (2.863) Prec@1 78.91 (76.85) Prec@5 92.19 (91.70) + train[2018-10-24-06:36:32] Epoch: [221][2400/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.837 (2.864) Prec@1 75.00 (76.85) Prec@5 92.19 (91.70) + train[2018-10-24-06:38:19] Epoch: [221][2600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.119 (2.865) Prec@1 70.31 (76.84) Prec@5 89.06 (91.71) + train[2018-10-24-06:40:06] Epoch: [221][2800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.897 (2.864) Prec@1 75.00 (76.85) Prec@5 92.97 (91.72) + train[2018-10-24-06:41:54] Epoch: [221][3000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.109 (2.865) Prec@1 74.22 (76.83) Prec@5 87.50 (91.70) + train[2018-10-24-06:43:41] Epoch: [221][3200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.060 (2.864) Prec@1 73.44 (76.86) Prec@5 89.84 (91.72) + train[2018-10-24-06:45:29] Epoch: [221][3400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.896 (2.865) Prec@1 69.53 (76.83) Prec@5 91.41 (91.71) + train[2018-10-24-06:47:16] Epoch: [221][3600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.559 (2.866) Prec@1 82.03 (76.83) Prec@5 95.31 (91.71) + train[2018-10-24-06:49:04] Epoch: [221][3800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.951 (2.866) Prec@1 75.78 (76.82) Prec@5 92.97 (91.72) + train[2018-10-24-06:50:51] Epoch: [221][4000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.615 (2.865) Prec@1 81.25 (76.84) Prec@5 95.31 (91.73) + train[2018-10-24-06:52:37] Epoch: [221][4200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.852 (2.864) Prec@1 82.03 (76.85) Prec@5 92.19 (91.73) + train[2018-10-24-06:54:25] Epoch: [221][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.595 (2.864) Prec@1 82.03 (76.85) Prec@5 95.31 (91.74) + train[2018-10-24-06:56:12] Epoch: [221][4600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.895 (2.863) Prec@1 78.91 (76.87) Prec@5 90.62 (91.74) + train[2018-10-24-06:57:58] Epoch: [221][4800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.944 (2.863) Prec@1 71.88 (76.87) Prec@5 89.84 (91.74) + train[2018-10-24-06:59:45] Epoch: [221][5000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.764 (2.864) Prec@1 78.12 (76.86) Prec@5 92.97 (91.73) + train[2018-10-24-07:01:33] Epoch: [221][5200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.824 (2.864) Prec@1 77.34 (76.85) Prec@5 91.41 (91.73) + train[2018-10-24-07:03:21] Epoch: [221][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.002 (2.864) Prec@1 74.22 (76.85) Prec@5 90.62 (91.73) + train[2018-10-24-07:05:07] Epoch: [221][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.841 (2.864) Prec@1 78.91 (76.86) Prec@5 91.41 (91.74) + train[2018-10-24-07:06:55] Epoch: [221][5800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.879 (2.864) Prec@1 79.69 (76.86) Prec@5 92.19 (91.74) + train[2018-10-24-07:08:44] Epoch: [221][6000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.994 (2.864) Prec@1 76.56 (76.85) Prec@5 89.84 (91.74) + train[2018-10-24-07:10:31] Epoch: [221][6200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.833 (2.864) Prec@1 77.34 (76.84) Prec@5 90.62 (91.73) + train[2018-10-24-07:12:17] Epoch: [221][6400/10010] Time 0.60 (0.54) Data 0.00 (0.00) Loss 2.855 (2.864) Prec@1 78.91 (76.85) Prec@5 92.97 (91.73) + train[2018-10-24-07:14:04] Epoch: [221][6600/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.872 (2.863) Prec@1 71.88 (76.87) Prec@5 93.75 (91.75) + train[2018-10-24-07:15:51] Epoch: [221][6800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.784 (2.863) Prec@1 77.34 (76.88) Prec@5 92.97 (91.75) + train[2018-10-24-07:17:37] Epoch: [221][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.713 (2.863) Prec@1 82.81 (76.88) Prec@5 93.75 (91.75) + train[2018-10-24-07:19:25] Epoch: [221][7200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.839 (2.863) Prec@1 77.34 (76.88) Prec@5 92.19 (91.75) + train[2018-10-24-07:21:12] Epoch: [221][7400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.725 (2.863) Prec@1 78.12 (76.88) Prec@5 92.97 (91.75) + train[2018-10-24-07:22:59] Epoch: [221][7600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.046 (2.863) Prec@1 76.56 (76.89) Prec@5 86.72 (91.75) + train[2018-10-24-07:24:46] Epoch: [221][7800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.821 (2.863) Prec@1 78.12 (76.89) Prec@5 92.19 (91.75) + train[2018-10-24-07:26:33] Epoch: [221][8000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.674 (2.863) Prec@1 76.56 (76.89) Prec@5 92.97 (91.74) + train[2018-10-24-07:28:20] Epoch: [221][8200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.694 (2.863) Prec@1 77.34 (76.89) Prec@5 92.19 (91.74) + train[2018-10-24-07:30:08] Epoch: [221][8400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.901 (2.864) Prec@1 79.69 (76.89) Prec@5 92.97 (91.74) + train[2018-10-24-07:31:53] Epoch: [221][8600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.930 (2.864) Prec@1 75.78 (76.88) Prec@5 89.84 (91.74) + train[2018-10-24-07:33:40] Epoch: [221][8800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.789 (2.864) Prec@1 75.78 (76.88) Prec@5 93.75 (91.74) + train[2018-10-24-07:35:27] Epoch: [221][9000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.677 (2.864) Prec@1 78.12 (76.87) Prec@5 97.66 (91.75) + train[2018-10-24-07:37:15] Epoch: [221][9200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.624 (2.864) Prec@1 84.38 (76.87) Prec@5 93.75 (91.75) + train[2018-10-24-07:39:02] Epoch: [221][9400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.761 (2.865) Prec@1 78.12 (76.86) Prec@5 91.41 (91.74) + train[2018-10-24-07:40:49] Epoch: [221][9600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.806 (2.865) Prec@1 79.69 (76.86) Prec@5 91.41 (91.74) + train[2018-10-24-07:42:35] Epoch: [221][9800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.929 (2.865) Prec@1 77.34 (76.86) Prec@5 89.06 (91.74) + train[2018-10-24-07:44:21] Epoch: [221][10000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.837 (2.864) Prec@1 82.03 (76.87) Prec@5 95.31 (91.75) + train[2018-10-24-07:44:26] Epoch: [221][10009/10010] Time 0.21 (0.53) Data 0.00 (0.00) Loss 3.962 (2.865) Prec@1 73.33 (76.87) Prec@5 86.67 (91.75) +[2018-10-24-07:44:26] **train** Prec@1 76.87 Prec@5 91.75 Error@1 23.13 Error@5 8.25 Loss:2.865 + test [2018-10-24-07:44:30] Epoch: [221][000/391] Time 4.31 (4.31) Data 4.18 (4.18) Loss 0.539 (0.539) Prec@1 94.53 (94.53) Prec@5 98.44 (98.44) + test [2018-10-24-07:44:58] Epoch: [221][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.195 (0.990) Prec@1 64.84 (77.43) Prec@5 91.41 (93.57) + test [2018-10-24-07:45:23] Epoch: [221][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.082 (1.157) Prec@1 45.00 (73.82) Prec@5 82.50 (91.37) +[2018-10-24-07:45:23] **test** Prec@1 73.82 Prec@5 91.37 Error@1 26.18 Error@5 8.63 Loss:1.157 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-24-07:45:23] [Epoch=222/250] [Need: 42:05:15] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-24-07:45:27] Epoch: [222][000/10010] Time 4.35 (4.35) Data 3.73 (3.73) Loss 3.034 (3.034) Prec@1 75.78 (75.78) Prec@5 91.41 (91.41) + train[2018-10-24-07:47:14] Epoch: [222][200/10010] Time 0.56 (0.55) Data 0.00 (0.02) Loss 3.241 (2.887) Prec@1 72.66 (76.52) Prec@5 88.28 (91.34) + train[2018-10-24-07:48:59] Epoch: [222][400/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 3.123 (2.870) Prec@1 72.66 (76.76) Prec@5 85.16 (91.57) + train[2018-10-24-07:50:44] Epoch: [222][600/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.722 (2.869) Prec@1 80.47 (76.73) Prec@5 93.75 (91.59) + train[2018-10-24-07:52:30] Epoch: [222][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.931 (2.868) Prec@1 76.56 (76.79) Prec@5 90.62 (91.61) + train[2018-10-24-07:54:17] Epoch: [222][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.918 (2.870) Prec@1 76.56 (76.75) Prec@5 92.97 (91.60) + train[2018-10-24-07:56:04] Epoch: [222][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.748 (2.866) Prec@1 77.34 (76.81) Prec@5 92.19 (91.64) + train[2018-10-24-07:57:53] Epoch: [222][1400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.690 (2.861) Prec@1 79.69 (76.89) Prec@5 95.31 (91.73) + train[2018-10-24-07:59:41] Epoch: [222][1600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.808 (2.864) Prec@1 77.34 (76.84) Prec@5 92.97 (91.72) + train[2018-10-24-08:01:27] Epoch: [222][1800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.007 (2.863) Prec@1 75.00 (76.88) Prec@5 88.28 (91.72) + train[2018-10-24-08:03:14] Epoch: [222][2000/10010] Time 0.60 (0.54) Data 0.00 (0.00) Loss 2.604 (2.862) Prec@1 82.81 (76.89) Prec@5 92.97 (91.73) + train[2018-10-24-08:05:02] Epoch: [222][2200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.024 (2.862) Prec@1 73.44 (76.91) Prec@5 89.84 (91.71) + train[2018-10-24-08:06:48] Epoch: [222][2400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.748 (2.862) Prec@1 81.25 (76.93) Prec@5 93.75 (91.71) + train[2018-10-24-08:08:34] Epoch: [222][2600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.887 (2.861) Prec@1 76.56 (76.94) Prec@5 91.41 (91.72) + train[2018-10-24-08:10:22] Epoch: [222][2800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.924 (2.860) Prec@1 74.22 (76.95) Prec@5 89.84 (91.72) + train[2018-10-24-08:12:09] Epoch: [222][3000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.748 (2.861) Prec@1 77.34 (76.95) Prec@5 92.97 (91.72) + train[2018-10-24-08:13:59] Epoch: [222][3200/10010] Time 0.61 (0.54) Data 0.00 (0.00) Loss 2.791 (2.861) Prec@1 78.12 (76.95) Prec@5 94.53 (91.73) + train[2018-10-24-08:15:47] Epoch: [222][3400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.750 (2.861) Prec@1 76.56 (76.92) Prec@5 94.53 (91.74) + train[2018-10-24-08:17:35] Epoch: [222][3600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.781 (2.862) Prec@1 80.47 (76.91) Prec@5 92.97 (91.73) + train[2018-10-24-08:19:22] Epoch: [222][3800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.835 (2.862) Prec@1 75.78 (76.89) Prec@5 90.62 (91.72) + train[2018-10-24-08:21:10] Epoch: [222][4000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.757 (2.863) Prec@1 80.47 (76.87) Prec@5 92.19 (91.71) + train[2018-10-24-08:22:58] Epoch: [222][4200/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.862 (2.862) Prec@1 75.78 (76.88) Prec@5 92.19 (91.72) + train[2018-10-24-08:24:46] Epoch: [222][4400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.141 (2.864) Prec@1 75.00 (76.86) Prec@5 85.94 (91.71) + train[2018-10-24-08:26:34] Epoch: [222][4600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.540 (2.863) Prec@1 84.38 (76.87) Prec@5 93.75 (91.72) + train[2018-10-24-08:28:22] Epoch: [222][4800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.042 (2.863) Prec@1 75.78 (76.87) Prec@5 89.84 (91.72) + train[2018-10-24-08:30:10] Epoch: [222][5000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.942 (2.864) Prec@1 75.78 (76.87) Prec@5 90.62 (91.72) + train[2018-10-24-08:31:58] Epoch: [222][5200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.556 (2.863) Prec@1 82.81 (76.86) Prec@5 95.31 (91.73) + train[2018-10-24-08:33:46] Epoch: [222][5400/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.940 (2.863) Prec@1 75.78 (76.87) Prec@5 94.53 (91.73) + train[2018-10-24-08:35:36] Epoch: [222][5600/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.822 (2.863) Prec@1 75.00 (76.87) Prec@5 92.97 (91.73) + train[2018-10-24-08:37:24] Epoch: [222][5800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.186 (2.862) Prec@1 70.31 (76.87) Prec@5 89.84 (91.74) + train[2018-10-24-08:39:12] Epoch: [222][6000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.043 (2.863) Prec@1 70.31 (76.88) Prec@5 90.62 (91.73) + train[2018-10-24-08:41:00] Epoch: [222][6200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.860 (2.863) Prec@1 75.78 (76.87) Prec@5 90.62 (91.74) + train[2018-10-24-08:42:47] Epoch: [222][6400/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.725 (2.862) Prec@1 77.34 (76.89) Prec@5 92.97 (91.74) + train[2018-10-24-08:44:36] Epoch: [222][6600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.656 (2.863) Prec@1 78.91 (76.88) Prec@5 94.53 (91.74) + train[2018-10-24-08:46:24] Epoch: [222][6800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.738 (2.862) Prec@1 78.12 (76.90) Prec@5 95.31 (91.74) + train[2018-10-24-08:48:12] Epoch: [222][7000/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.672 (2.862) Prec@1 82.81 (76.89) Prec@5 90.62 (91.74) + train[2018-10-24-08:50:00] Epoch: [222][7200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.798 (2.862) Prec@1 77.34 (76.89) Prec@5 89.84 (91.74) + train[2018-10-24-08:51:49] Epoch: [222][7400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.172 (2.862) Prec@1 74.22 (76.89) Prec@5 86.72 (91.74) + train[2018-10-24-08:53:37] Epoch: [222][7600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.988 (2.863) Prec@1 76.56 (76.89) Prec@5 89.84 (91.74) + train[2018-10-24-08:55:26] Epoch: [222][7800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.725 (2.862) Prec@1 80.47 (76.90) Prec@5 93.75 (91.75) + train[2018-10-24-08:57:14] Epoch: [222][8000/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.852 (2.863) Prec@1 78.12 (76.89) Prec@5 91.41 (91.74) + train[2018-10-24-08:59:01] Epoch: [222][8200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.047 (2.863) Prec@1 72.66 (76.88) Prec@5 92.97 (91.74) + train[2018-10-24-09:00:50] Epoch: [222][8400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.728 (2.862) Prec@1 82.81 (76.90) Prec@5 94.53 (91.74) + train[2018-10-24-09:02:38] Epoch: [222][8600/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 3.200 (2.862) Prec@1 70.31 (76.89) Prec@5 89.06 (91.75) + train[2018-10-24-09:04:27] Epoch: [222][8800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.872 (2.863) Prec@1 69.53 (76.89) Prec@5 92.19 (91.74) + train[2018-10-24-09:06:15] Epoch: [222][9000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.517 (2.863) Prec@1 80.47 (76.89) Prec@5 96.88 (91.74) + train[2018-10-24-09:08:03] Epoch: [222][9200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.785 (2.863) Prec@1 77.34 (76.88) Prec@5 92.19 (91.74) + train[2018-10-24-09:09:50] Epoch: [222][9400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.698 (2.863) Prec@1 77.34 (76.88) Prec@5 94.53 (91.75) + train[2018-10-24-09:11:38] Epoch: [222][9600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.809 (2.863) Prec@1 75.78 (76.87) Prec@5 90.62 (91.74) + train[2018-10-24-09:13:25] Epoch: [222][9800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.746 (2.863) Prec@1 79.69 (76.88) Prec@5 95.31 (91.74) + train[2018-10-24-09:15:14] Epoch: [222][10000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.889 (2.863) Prec@1 75.78 (76.88) Prec@5 90.62 (91.74) + train[2018-10-24-09:15:18] Epoch: [222][10009/10010] Time 0.19 (0.54) Data 0.00 (0.00) Loss 4.343 (2.863) Prec@1 60.00 (76.88) Prec@5 73.33 (91.74) +[2018-10-24-09:15:18] **train** Prec@1 76.88 Prec@5 91.74 Error@1 23.12 Error@5 8.26 Loss:2.863 + test [2018-10-24-09:15:22] Epoch: [222][000/391] Time 4.11 (4.11) Data 3.97 (3.97) Loss 0.571 (0.571) Prec@1 91.41 (91.41) Prec@5 99.22 (99.22) + test [2018-10-24-09:15:51] Epoch: [222][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.191 (1.001) Prec@1 71.09 (77.53) Prec@5 92.19 (93.63) + test [2018-10-24-09:16:16] Epoch: [222][390/391] Time 0.09 (0.15) Data 0.00 (0.02) Loss 2.150 (1.172) Prec@1 45.00 (73.85) Prec@5 82.50 (91.42) +[2018-10-24-09:16:16] **test** Prec@1 73.85 Prec@5 91.42 Error@1 26.15 Error@5 8.58 Loss:1.172 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-24-09:16:16] [Epoch=223/250] [Need: 40:53:52] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-24-09:16:22] Epoch: [223][000/10010] Time 5.63 (5.63) Data 5.04 (5.04) Loss 2.940 (2.940) Prec@1 71.88 (71.88) Prec@5 89.84 (89.84) + train[2018-10-24-09:18:08] Epoch: [223][200/10010] Time 0.52 (0.56) Data 0.00 (0.03) Loss 2.681 (2.851) Prec@1 80.47 (77.01) Prec@5 92.97 (91.97) + train[2018-10-24-09:19:53] Epoch: [223][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 3.023 (2.852) Prec@1 72.66 (76.95) Prec@5 89.84 (92.00) + train[2018-10-24-09:21:38] Epoch: [223][600/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.728 (2.863) Prec@1 75.78 (76.81) Prec@5 93.75 (91.85) + train[2018-10-24-09:23:24] Epoch: [223][800/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.684 (2.868) Prec@1 82.81 (76.75) Prec@5 92.97 (91.80) + train[2018-10-24-09:25:10] Epoch: [223][1000/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 3.138 (2.866) Prec@1 74.22 (76.78) Prec@5 89.84 (91.79) + train[2018-10-24-09:26:55] Epoch: [223][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.910 (2.868) Prec@1 78.12 (76.72) Prec@5 90.62 (91.75) + train[2018-10-24-09:28:42] Epoch: [223][1400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.714 (2.870) Prec@1 77.34 (76.70) Prec@5 93.75 (91.69) + train[2018-10-24-09:30:28] Epoch: [223][1600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.038 (2.868) Prec@1 74.22 (76.77) Prec@5 89.84 (91.69) + train[2018-10-24-09:32:15] Epoch: [223][1800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.878 (2.867) Prec@1 76.56 (76.76) Prec@5 92.19 (91.72) + train[2018-10-24-09:34:03] Epoch: [223][2000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.762 (2.865) Prec@1 83.59 (76.83) Prec@5 92.19 (91.74) + train[2018-10-24-09:35:49] Epoch: [223][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.695 (2.865) Prec@1 80.47 (76.84) Prec@5 93.75 (91.72) + train[2018-10-24-09:37:35] Epoch: [223][2400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.686 (2.865) Prec@1 79.69 (76.84) Prec@5 93.75 (91.72) + train[2018-10-24-09:39:21] Epoch: [223][2600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.208 (2.864) Prec@1 70.31 (76.86) Prec@5 89.06 (91.72) + train[2018-10-24-09:41:07] Epoch: [223][2800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.729 (2.863) Prec@1 85.94 (76.88) Prec@5 91.41 (91.74) + train[2018-10-24-09:42:54] Epoch: [223][3000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.148 (2.863) Prec@1 71.09 (76.86) Prec@5 86.72 (91.73) + train[2018-10-24-09:44:39] Epoch: [223][3200/10010] Time 0.61 (0.53) Data 0.00 (0.00) Loss 3.031 (2.864) Prec@1 73.44 (76.86) Prec@5 89.84 (91.73) + train[2018-10-24-09:46:26] Epoch: [223][3400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.024 (2.864) Prec@1 78.12 (76.85) Prec@5 91.41 (91.74) + train[2018-10-24-09:48:13] Epoch: [223][3600/10010] Time 0.62 (0.53) Data 0.00 (0.00) Loss 3.134 (2.863) Prec@1 71.09 (76.87) Prec@5 91.41 (91.76) + train[2018-10-24-09:50:00] Epoch: [223][3800/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.758 (2.863) Prec@1 81.25 (76.86) Prec@5 92.19 (91.77) + train[2018-10-24-09:51:47] Epoch: [223][4000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.868 (2.863) Prec@1 75.78 (76.85) Prec@5 91.41 (91.75) + train[2018-10-24-09:53:33] Epoch: [223][4200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.752 (2.862) Prec@1 82.03 (76.89) Prec@5 93.75 (91.76) + train[2018-10-24-09:55:19] Epoch: [223][4400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.640 (2.862) Prec@1 81.25 (76.88) Prec@5 96.09 (91.76) + train[2018-10-24-09:57:05] Epoch: [223][4600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.970 (2.862) Prec@1 75.78 (76.88) Prec@5 90.62 (91.76) + train[2018-10-24-09:58:52] Epoch: [223][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.895 (2.862) Prec@1 74.22 (76.86) Prec@5 88.28 (91.76) + train[2018-10-24-10:00:38] Epoch: [223][5000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.663 (2.862) Prec@1 79.69 (76.86) Prec@5 96.09 (91.77) + train[2018-10-24-10:02:26] Epoch: [223][5200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.741 (2.862) Prec@1 75.78 (76.86) Prec@5 92.19 (91.77) + train[2018-10-24-10:04:14] Epoch: [223][5400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.027 (2.863) Prec@1 71.88 (76.86) Prec@5 90.62 (91.77) + train[2018-10-24-10:06:01] Epoch: [223][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.935 (2.863) Prec@1 75.78 (76.86) Prec@5 91.41 (91.76) + train[2018-10-24-10:07:47] Epoch: [223][5800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.551 (2.863) Prec@1 81.25 (76.86) Prec@5 95.31 (91.77) + train[2018-10-24-10:09:34] Epoch: [223][6000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.115 (2.863) Prec@1 70.31 (76.84) Prec@5 87.50 (91.77) + train[2018-10-24-10:11:21] Epoch: [223][6200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.713 (2.864) Prec@1 84.38 (76.83) Prec@5 92.19 (91.76) + train[2018-10-24-10:13:06] Epoch: [223][6400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.121 (2.864) Prec@1 67.97 (76.84) Prec@5 91.41 (91.77) + train[2018-10-24-10:14:53] Epoch: [223][6600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.032 (2.864) Prec@1 73.44 (76.84) Prec@5 89.84 (91.76) + train[2018-10-24-10:16:40] Epoch: [223][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.868 (2.864) Prec@1 81.25 (76.84) Prec@5 89.06 (91.76) + train[2018-10-24-10:18:26] Epoch: [223][7000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.985 (2.863) Prec@1 77.34 (76.86) Prec@5 90.62 (91.77) + train[2018-10-24-10:20:13] Epoch: [223][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.683 (2.862) Prec@1 79.69 (76.87) Prec@5 93.75 (91.77) + train[2018-10-24-10:22:00] Epoch: [223][7400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.928 (2.862) Prec@1 78.91 (76.86) Prec@5 92.19 (91.77) + train[2018-10-24-10:23:46] Epoch: [223][7600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.590 (2.862) Prec@1 85.16 (76.86) Prec@5 96.09 (91.78) + train[2018-10-24-10:25:32] Epoch: [223][7800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.035 (2.862) Prec@1 71.09 (76.89) Prec@5 89.06 (91.78) + train[2018-10-24-10:27:19] Epoch: [223][8000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.836 (2.861) Prec@1 76.56 (76.90) Prec@5 91.41 (91.78) + train[2018-10-24-10:29:07] Epoch: [223][8200/10010] Time 0.61 (0.53) Data 0.00 (0.00) Loss 2.802 (2.862) Prec@1 79.69 (76.90) Prec@5 94.53 (91.77) + train[2018-10-24-10:30:54] Epoch: [223][8400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.849 (2.862) Prec@1 78.91 (76.90) Prec@5 90.62 (91.77) + train[2018-10-24-10:32:39] Epoch: [223][8600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.002 (2.862) Prec@1 75.00 (76.89) Prec@5 89.84 (91.76) + train[2018-10-24-10:34:25] Epoch: [223][8800/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.965 (2.862) Prec@1 73.44 (76.89) Prec@5 90.62 (91.76) + train[2018-10-24-10:36:12] Epoch: [223][9000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.541 (2.862) Prec@1 79.69 (76.89) Prec@5 94.53 (91.76) + train[2018-10-24-10:37:58] Epoch: [223][9200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.828 (2.862) Prec@1 75.00 (76.89) Prec@5 89.84 (91.76) + train[2018-10-24-10:39:46] Epoch: [223][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.823 (2.862) Prec@1 75.78 (76.88) Prec@5 93.75 (91.75) + train[2018-10-24-10:41:32] Epoch: [223][9600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.072 (2.863) Prec@1 73.44 (76.87) Prec@5 90.62 (91.75) + train[2018-10-24-10:43:18] Epoch: [223][9800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.119 (2.863) Prec@1 67.97 (76.87) Prec@5 89.84 (91.75) + train[2018-10-24-10:45:05] Epoch: [223][10000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.792 (2.863) Prec@1 83.59 (76.87) Prec@5 93.75 (91.75) + train[2018-10-24-10:45:09] Epoch: [223][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 3.630 (2.863) Prec@1 66.67 (76.87) Prec@5 86.67 (91.75) +[2018-10-24-10:45:09] **train** Prec@1 76.87 Prec@5 91.75 Error@1 23.13 Error@5 8.25 Loss:2.863 + test [2018-10-24-10:45:13] Epoch: [223][000/391] Time 4.04 (4.04) Data 3.89 (3.89) Loss 0.526 (0.526) Prec@1 92.19 (92.19) Prec@5 99.22 (99.22) + test [2018-10-24-10:45:41] Epoch: [223][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.198 (0.995) Prec@1 69.53 (77.44) Prec@5 91.41 (93.66) + test [2018-10-24-10:46:07] Epoch: [223][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.141 (1.164) Prec@1 48.75 (73.85) Prec@5 82.50 (91.46) +[2018-10-24-10:46:07] **test** Prec@1 73.85 Prec@5 91.46 Error@1 26.15 Error@5 8.54 Loss:1.164 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-24-10:46:07] [Epoch=224/250] [Need: 38:56:03] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-24-10:46:12] Epoch: [224][000/10010] Time 4.74 (4.74) Data 4.01 (4.01) Loss 2.603 (2.603) Prec@1 78.12 (78.12) Prec@5 97.66 (97.66) + train[2018-10-24-10:47:58] Epoch: [224][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 2.791 (2.871) Prec@1 75.78 (76.92) Prec@5 94.53 (91.59) + train[2018-10-24-10:49:43] Epoch: [224][400/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.708 (2.855) Prec@1 78.91 (77.12) Prec@5 96.09 (91.76) + train[2018-10-24-10:51:29] Epoch: [224][600/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.936 (2.858) Prec@1 81.25 (77.04) Prec@5 89.06 (91.70) + train[2018-10-24-10:53:15] Epoch: [224][800/10010] Time 0.64 (0.53) Data 0.00 (0.01) Loss 2.892 (2.857) Prec@1 73.44 (76.97) Prec@5 90.62 (91.74) + train[2018-10-24-10:55:02] Epoch: [224][1000/10010] Time 0.55 (0.53) Data 0.00 (0.01) Loss 2.638 (2.860) Prec@1 77.34 (76.93) Prec@5 95.31 (91.69) + train[2018-10-24-10:56:50] Epoch: [224][1200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.906 (2.861) Prec@1 77.34 (76.93) Prec@5 92.97 (91.74) + train[2018-10-24-10:58:37] Epoch: [224][1400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.875 (2.860) Prec@1 76.56 (76.94) Prec@5 91.41 (91.75) + train[2018-10-24-11:00:25] Epoch: [224][1600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.829 (2.856) Prec@1 78.12 (77.01) Prec@5 92.97 (91.80) + train[2018-10-24-11:02:12] Epoch: [224][1800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.719 (2.854) Prec@1 78.91 (77.00) Prec@5 92.19 (91.82) + train[2018-10-24-11:03:58] Epoch: [224][2000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.723 (2.856) Prec@1 80.47 (76.97) Prec@5 95.31 (91.80) + train[2018-10-24-11:05:46] Epoch: [224][2200/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 3.004 (2.856) Prec@1 77.34 (76.96) Prec@5 89.84 (91.79) + train[2018-10-24-11:07:32] Epoch: [224][2400/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.671 (2.857) Prec@1 81.25 (76.97) Prec@5 94.53 (91.80) + train[2018-10-24-11:09:20] Epoch: [224][2600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.450 (2.857) Prec@1 83.59 (76.95) Prec@5 95.31 (91.79) + train[2018-10-24-11:11:07] Epoch: [224][2800/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.923 (2.859) Prec@1 78.91 (76.91) Prec@5 93.75 (91.77) + train[2018-10-24-11:12:54] Epoch: [224][3000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.159 (2.860) Prec@1 66.41 (76.90) Prec@5 89.84 (91.76) + train[2018-10-24-11:14:42] Epoch: [224][3200/10010] Time 0.61 (0.54) Data 0.00 (0.00) Loss 2.862 (2.860) Prec@1 77.34 (76.90) Prec@5 92.97 (91.76) + train[2018-10-24-11:16:30] Epoch: [224][3400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.879 (2.860) Prec@1 75.00 (76.89) Prec@5 91.41 (91.77) + train[2018-10-24-11:18:18] Epoch: [224][3600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.728 (2.861) Prec@1 78.12 (76.87) Prec@5 93.75 (91.75) + train[2018-10-24-11:20:06] Epoch: [224][3800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.055 (2.861) Prec@1 70.31 (76.88) Prec@5 91.41 (91.76) + train[2018-10-24-11:21:52] Epoch: [224][4000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.968 (2.861) Prec@1 78.12 (76.86) Prec@5 89.84 (91.75) + train[2018-10-24-11:23:37] Epoch: [224][4200/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.610 (2.863) Prec@1 82.81 (76.84) Prec@5 92.97 (91.73) + train[2018-10-24-11:25:23] Epoch: [224][4400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.660 (2.862) Prec@1 81.25 (76.84) Prec@5 93.75 (91.73) + train[2018-10-24-11:27:10] Epoch: [224][4600/10010] Time 0.60 (0.54) Data 0.00 (0.00) Loss 2.932 (2.862) Prec@1 71.09 (76.84) Prec@5 91.41 (91.74) + train[2018-10-24-11:28:57] Epoch: [224][4800/10010] Time 0.67 (0.54) Data 0.00 (0.00) Loss 2.819 (2.862) Prec@1 75.00 (76.84) Prec@5 92.19 (91.74) + train[2018-10-24-11:30:44] Epoch: [224][5000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.735 (2.863) Prec@1 77.34 (76.83) Prec@5 95.31 (91.73) + train[2018-10-24-11:32:31] Epoch: [224][5200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 3.173 (2.863) Prec@1 73.44 (76.83) Prec@5 88.28 (91.74) + train[2018-10-24-11:34:18] Epoch: [224][5400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.840 (2.862) Prec@1 75.00 (76.84) Prec@5 92.19 (91.75) + train[2018-10-24-11:36:06] Epoch: [224][5600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.749 (2.862) Prec@1 75.00 (76.84) Prec@5 92.19 (91.74) + train[2018-10-24-11:37:52] Epoch: [224][5800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.891 (2.862) Prec@1 76.56 (76.85) Prec@5 90.62 (91.74) + train[2018-10-24-11:39:41] Epoch: [224][6000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.787 (2.862) Prec@1 81.25 (76.85) Prec@5 92.19 (91.75) + train[2018-10-24-11:41:29] Epoch: [224][6200/10010] Time 0.60 (0.54) Data 0.00 (0.00) Loss 3.014 (2.862) Prec@1 73.44 (76.85) Prec@5 89.84 (91.75) + train[2018-10-24-11:43:17] Epoch: [224][6400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.790 (2.862) Prec@1 74.22 (76.84) Prec@5 91.41 (91.75) + train[2018-10-24-11:45:05] Epoch: [224][6600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.015 (2.862) Prec@1 72.66 (76.84) Prec@5 92.97 (91.75) + train[2018-10-24-11:46:53] Epoch: [224][6800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.838 (2.862) Prec@1 78.12 (76.83) Prec@5 90.62 (91.76) + train[2018-10-24-11:48:41] Epoch: [224][7000/10010] Time 0.61 (0.54) Data 0.00 (0.00) Loss 2.837 (2.863) Prec@1 75.78 (76.82) Prec@5 90.62 (91.75) + train[2018-10-24-11:50:29] Epoch: [224][7200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.761 (2.862) Prec@1 82.03 (76.83) Prec@5 92.97 (91.76) + train[2018-10-24-11:52:17] Epoch: [224][7400/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.630 (2.862) Prec@1 80.47 (76.83) Prec@5 94.53 (91.76) + train[2018-10-24-11:54:06] Epoch: [224][7600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.633 (2.861) Prec@1 83.59 (76.84) Prec@5 96.88 (91.76) + train[2018-10-24-11:55:54] Epoch: [224][7800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.907 (2.861) Prec@1 75.78 (76.84) Prec@5 90.62 (91.77) + train[2018-10-24-11:57:43] Epoch: [224][8000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.951 (2.861) Prec@1 71.09 (76.84) Prec@5 90.62 (91.77) + train[2018-10-24-11:59:28] Epoch: [224][8200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.905 (2.862) Prec@1 76.56 (76.83) Prec@5 91.41 (91.77) + train[2018-10-24-12:01:16] Epoch: [224][8400/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.870 (2.862) Prec@1 76.56 (76.83) Prec@5 94.53 (91.76) + train[2018-10-24-12:03:05] Epoch: [224][8600/10010] Time 0.61 (0.54) Data 0.00 (0.00) Loss 2.899 (2.862) Prec@1 75.78 (76.84) Prec@5 91.41 (91.77) + train[2018-10-24-12:04:54] Epoch: [224][8800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.706 (2.862) Prec@1 81.25 (76.84) Prec@5 92.19 (91.77) + train[2018-10-24-12:06:42] Epoch: [224][9000/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 3.049 (2.862) Prec@1 73.44 (76.84) Prec@5 89.84 (91.77) + train[2018-10-24-12:08:28] Epoch: [224][9200/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.656 (2.862) Prec@1 79.69 (76.84) Prec@5 92.19 (91.77) + train[2018-10-24-12:10:17] Epoch: [224][9400/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.893 (2.862) Prec@1 77.34 (76.86) Prec@5 89.06 (91.77) + train[2018-10-24-12:12:04] Epoch: [224][9600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.747 (2.862) Prec@1 76.56 (76.86) Prec@5 91.41 (91.77) + train[2018-10-24-12:13:52] Epoch: [224][9800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.060 (2.862) Prec@1 74.22 (76.86) Prec@5 89.06 (91.77) + train[2018-10-24-12:15:39] Epoch: [224][10000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.632 (2.862) Prec@1 82.81 (76.86) Prec@5 96.09 (91.77) + train[2018-10-24-12:15:43] Epoch: [224][10009/10010] Time 0.21 (0.54) Data 0.00 (0.00) Loss 3.504 (2.862) Prec@1 73.33 (76.86) Prec@5 80.00 (91.77) +[2018-10-24-12:15:43] **train** Prec@1 76.86 Prec@5 91.77 Error@1 23.14 Error@5 8.23 Loss:2.862 + test [2018-10-24-12:15:47] Epoch: [224][000/391] Time 4.13 (4.13) Data 3.99 (3.99) Loss 0.541 (0.541) Prec@1 93.75 (93.75) Prec@5 97.66 (97.66) + test [2018-10-24-12:16:17] Epoch: [224][200/391] Time 0.13 (0.17) Data 0.00 (0.04) Loss 1.167 (0.999) Prec@1 67.97 (77.43) Prec@5 91.41 (93.57) + test [2018-10-24-12:16:47] Epoch: [224][390/391] Time 0.08 (0.16) Data 0.00 (0.03) Loss 2.101 (1.166) Prec@1 46.25 (73.86) Prec@5 82.50 (91.41) +[2018-10-24-12:16:47] **test** Prec@1 73.86 Prec@5 91.41 Error@1 26.14 Error@5 8.59 Loss:1.166 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-24-12:16:47] [Epoch=225/250] [Need: 37:46:38] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-24-12:16:52] Epoch: [225][000/10010] Time 5.10 (5.10) Data 4.41 (4.41) Loss 2.848 (2.848) Prec@1 74.22 (74.22) Prec@5 92.97 (92.97) + train[2018-10-24-12:18:39] Epoch: [225][200/10010] Time 0.53 (0.56) Data 0.00 (0.02) Loss 2.872 (2.847) Prec@1 75.78 (77.26) Prec@5 91.41 (91.99) + train[2018-10-24-12:20:24] Epoch: [225][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.685 (2.852) Prec@1 75.78 (77.07) Prec@5 94.53 (91.99) + train[2018-10-24-12:22:12] Epoch: [225][600/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.796 (2.855) Prec@1 78.91 (77.02) Prec@5 92.19 (91.85) + train[2018-10-24-12:23:59] Epoch: [225][800/10010] Time 0.54 (0.54) Data 0.00 (0.01) Loss 2.788 (2.857) Prec@1 78.91 (77.01) Prec@5 93.75 (91.83) + train[2018-10-24-12:25:47] Epoch: [225][1000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.535 (2.857) Prec@1 81.25 (76.99) Prec@5 96.09 (91.81) + train[2018-10-24-12:27:34] Epoch: [225][1200/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.953 (2.859) Prec@1 79.69 (76.91) Prec@5 89.06 (91.81) + train[2018-10-24-12:29:22] Epoch: [225][1400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.101 (2.860) Prec@1 74.22 (76.91) Prec@5 89.84 (91.77) + train[2018-10-24-12:31:09] Epoch: [225][1600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.050 (2.861) Prec@1 75.78 (76.93) Prec@5 90.62 (91.76) + train[2018-10-24-12:32:55] Epoch: [225][1800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.779 (2.862) Prec@1 82.03 (76.88) Prec@5 92.97 (91.76) + train[2018-10-24-12:34:43] Epoch: [225][2000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.824 (2.864) Prec@1 75.78 (76.87) Prec@5 92.97 (91.75) + train[2018-10-24-12:36:30] Epoch: [225][2200/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 3.046 (2.863) Prec@1 75.00 (76.87) Prec@5 91.41 (91.76) + train[2018-10-24-12:38:18] Epoch: [225][2400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.860 (2.864) Prec@1 76.56 (76.84) Prec@5 92.97 (91.75) + train[2018-10-24-12:40:05] Epoch: [225][2600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.581 (2.865) Prec@1 80.47 (76.82) Prec@5 95.31 (91.75) + train[2018-10-24-12:41:52] Epoch: [225][2800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.669 (2.866) Prec@1 82.03 (76.82) Prec@5 96.09 (91.73) + train[2018-10-24-12:43:39] Epoch: [225][3000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.702 (2.865) Prec@1 78.12 (76.82) Prec@5 93.75 (91.73) + train[2018-10-24-12:45:26] Epoch: [225][3200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.667 (2.865) Prec@1 82.03 (76.82) Prec@5 93.75 (91.73) + train[2018-10-24-12:47:14] Epoch: [225][3400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.657 (2.865) Prec@1 78.91 (76.84) Prec@5 94.53 (91.75) + train[2018-10-24-12:49:00] Epoch: [225][3600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.969 (2.865) Prec@1 73.44 (76.85) Prec@5 89.06 (91.75) + train[2018-10-24-12:50:47] Epoch: [225][3800/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.694 (2.865) Prec@1 81.25 (76.85) Prec@5 92.97 (91.74) + train[2018-10-24-12:52:34] Epoch: [225][4000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.873 (2.865) Prec@1 78.12 (76.86) Prec@5 92.97 (91.76) + train[2018-10-24-12:54:22] Epoch: [225][4200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.921 (2.866) Prec@1 75.78 (76.82) Prec@5 94.53 (91.75) + train[2018-10-24-12:56:09] Epoch: [225][4400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.804 (2.865) Prec@1 75.78 (76.84) Prec@5 91.41 (91.75) + train[2018-10-24-12:57:55] Epoch: [225][4600/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 3.123 (2.865) Prec@1 69.53 (76.84) Prec@5 89.84 (91.74) + train[2018-10-24-12:59:42] Epoch: [225][4800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.014 (2.865) Prec@1 75.78 (76.85) Prec@5 89.84 (91.75) + train[2018-10-24-13:01:28] Epoch: [225][5000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.625 (2.865) Prec@1 81.25 (76.84) Prec@5 95.31 (91.75) + train[2018-10-24-13:03:15] Epoch: [225][5200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.758 (2.865) Prec@1 80.47 (76.84) Prec@5 89.84 (91.75) + train[2018-10-24-13:05:04] Epoch: [225][5400/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.908 (2.864) Prec@1 78.12 (76.85) Prec@5 90.62 (91.76) + train[2018-10-24-13:06:51] Epoch: [225][5600/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 2.895 (2.865) Prec@1 75.00 (76.84) Prec@5 91.41 (91.75) + train[2018-10-24-13:08:39] Epoch: [225][5800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.823 (2.865) Prec@1 78.91 (76.85) Prec@5 89.84 (91.74) + train[2018-10-24-13:10:26] Epoch: [225][6000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 3.146 (2.865) Prec@1 71.88 (76.86) Prec@5 88.28 (91.74) + train[2018-10-24-13:12:12] Epoch: [225][6200/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.821 (2.865) Prec@1 81.25 (76.86) Prec@5 90.62 (91.74) + train[2018-10-24-13:14:00] Epoch: [225][6400/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 3.063 (2.865) Prec@1 71.09 (76.86) Prec@5 92.19 (91.73) + train[2018-10-24-13:15:47] Epoch: [225][6600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.993 (2.865) Prec@1 75.78 (76.87) Prec@5 89.06 (91.73) + train[2018-10-24-13:17:34] Epoch: [225][6800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.613 (2.864) Prec@1 82.03 (76.88) Prec@5 94.53 (91.73) + train[2018-10-24-13:19:20] Epoch: [225][7000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.850 (2.864) Prec@1 78.12 (76.88) Prec@5 90.62 (91.73) + train[2018-10-24-13:21:07] Epoch: [225][7200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.904 (2.864) Prec@1 78.91 (76.88) Prec@5 91.41 (91.74) + train[2018-10-24-13:22:54] Epoch: [225][7400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.936 (2.864) Prec@1 77.34 (76.88) Prec@5 88.28 (91.74) + train[2018-10-24-13:24:40] Epoch: [225][7600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.823 (2.864) Prec@1 78.12 (76.87) Prec@5 91.41 (91.73) + train[2018-10-24-13:26:28] Epoch: [225][7800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.853 (2.864) Prec@1 82.03 (76.88) Prec@5 89.84 (91.74) + train[2018-10-24-13:28:16] Epoch: [225][8000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.706 (2.864) Prec@1 84.38 (76.88) Prec@5 93.75 (91.74) + train[2018-10-24-13:30:03] Epoch: [225][8200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.777 (2.863) Prec@1 78.12 (76.88) Prec@5 94.53 (91.74) + train[2018-10-24-13:31:50] Epoch: [225][8400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.787 (2.863) Prec@1 76.56 (76.89) Prec@5 92.97 (91.75) + train[2018-10-24-13:33:37] Epoch: [225][8600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.800 (2.863) Prec@1 78.12 (76.89) Prec@5 89.84 (91.75) + train[2018-10-24-13:35:24] Epoch: [225][8800/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.719 (2.863) Prec@1 82.03 (76.89) Prec@5 92.19 (91.75) + train[2018-10-24-13:37:10] Epoch: [225][9000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.732 (2.863) Prec@1 80.47 (76.88) Prec@5 92.97 (91.74) + train[2018-10-24-13:38:56] Epoch: [225][9200/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.769 (2.863) Prec@1 81.25 (76.89) Prec@5 91.41 (91.74) + train[2018-10-24-13:40:43] Epoch: [225][9400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.639 (2.863) Prec@1 78.12 (76.88) Prec@5 92.97 (91.74) + train[2018-10-24-13:42:31] Epoch: [225][9600/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.774 (2.863) Prec@1 75.00 (76.89) Prec@5 92.97 (91.74) + train[2018-10-24-13:44:17] Epoch: [225][9800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.908 (2.863) Prec@1 78.12 (76.88) Prec@5 91.41 (91.74) + train[2018-10-24-13:46:04] Epoch: [225][10000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.979 (2.863) Prec@1 76.56 (76.88) Prec@5 89.06 (91.74) + train[2018-10-24-13:46:08] Epoch: [225][10009/10010] Time 0.19 (0.54) Data 0.00 (0.00) Loss 2.590 (2.863) Prec@1 86.67 (76.88) Prec@5 100.00 (91.74) +[2018-10-24-13:46:08] **train** Prec@1 76.88 Prec@5 91.74 Error@1 23.12 Error@5 8.26 Loss:2.863 + test [2018-10-24-13:46:13] Epoch: [225][000/391] Time 4.40 (4.40) Data 4.27 (4.27) Loss 0.530 (0.530) Prec@1 92.19 (92.19) Prec@5 98.44 (98.44) + test [2018-10-24-13:46:41] Epoch: [225][200/391] Time 0.12 (0.16) Data 0.00 (0.03) Loss 1.156 (0.983) Prec@1 69.53 (77.36) Prec@5 92.19 (93.61) + test [2018-10-24-13:47:06] Epoch: [225][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.131 (1.150) Prec@1 45.00 (73.88) Prec@5 82.50 (91.42) +[2018-10-24-13:47:06] **test** Prec@1 73.88 Prec@5 91.42 Error@1 26.12 Error@5 8.58 Loss:1.150 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-24-13:47:06] [Epoch=226/250] [Need: 36:07:47] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-24-13:47:12] Epoch: [226][000/10010] Time 5.88 (5.88) Data 5.15 (5.15) Loss 2.949 (2.949) Prec@1 75.00 (75.00) Prec@5 90.62 (90.62) + train[2018-10-24-13:48:57] Epoch: [226][200/10010] Time 0.55 (0.55) Data 0.00 (0.03) Loss 2.804 (2.858) Prec@1 78.91 (76.98) Prec@5 90.62 (91.84) + train[2018-10-24-13:50:43] Epoch: [226][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 3.166 (2.860) Prec@1 70.31 (76.95) Prec@5 88.28 (91.81) + train[2018-10-24-13:52:28] Epoch: [226][600/10010] Time 0.59 (0.54) Data 0.00 (0.01) Loss 2.999 (2.865) Prec@1 73.44 (76.95) Prec@5 89.84 (91.72) + train[2018-10-24-13:54:15] Epoch: [226][800/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.606 (2.861) Prec@1 85.16 (77.02) Prec@5 96.09 (91.77) + train[2018-10-24-13:56:02] Epoch: [226][1000/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.774 (2.860) Prec@1 75.78 (77.08) Prec@5 92.19 (91.76) + train[2018-10-24-13:57:49] Epoch: [226][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.597 (2.859) Prec@1 80.47 (77.06) Prec@5 95.31 (91.78) + train[2018-10-24-13:59:34] Epoch: [226][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.840 (2.858) Prec@1 78.12 (77.05) Prec@5 91.41 (91.80) + train[2018-10-24-14:01:21] Epoch: [226][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.008 (2.856) Prec@1 71.09 (77.08) Prec@5 92.19 (91.81) + train[2018-10-24-14:03:07] Epoch: [226][1800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.913 (2.859) Prec@1 76.56 (77.03) Prec@5 89.84 (91.74) + train[2018-10-24-14:04:53] Epoch: [226][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.089 (2.860) Prec@1 71.88 (76.99) Prec@5 89.84 (91.74) + train[2018-10-24-14:06:40] Epoch: [226][2200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.788 (2.861) Prec@1 78.91 (77.00) Prec@5 92.19 (91.73) + train[2018-10-24-14:08:27] Epoch: [226][2400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.568 (2.859) Prec@1 82.81 (77.01) Prec@5 92.19 (91.77) + train[2018-10-24-14:10:12] Epoch: [226][2600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.795 (2.859) Prec@1 80.47 (77.01) Prec@5 92.19 (91.77) + train[2018-10-24-14:11:58] Epoch: [226][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.775 (2.860) Prec@1 75.78 (77.00) Prec@5 91.41 (91.76) + train[2018-10-24-14:13:44] Epoch: [226][3000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.770 (2.860) Prec@1 81.25 (77.00) Prec@5 92.97 (91.76) + train[2018-10-24-14:15:30] Epoch: [226][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.931 (2.859) Prec@1 72.66 (77.02) Prec@5 92.19 (91.77) + train[2018-10-24-14:17:15] Epoch: [226][3400/10010] Time 0.65 (0.53) Data 0.00 (0.00) Loss 2.914 (2.860) Prec@1 75.78 (77.01) Prec@5 89.84 (91.77) + train[2018-10-24-14:19:02] Epoch: [226][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.852 (2.861) Prec@1 77.34 (76.98) Prec@5 91.41 (91.77) + train[2018-10-24-14:20:48] Epoch: [226][3800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.725 (2.861) Prec@1 82.03 (76.98) Prec@5 95.31 (91.77) + train[2018-10-24-14:22:34] Epoch: [226][4000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.999 (2.861) Prec@1 71.09 (76.96) Prec@5 92.19 (91.77) + train[2018-10-24-14:24:20] Epoch: [226][4200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.654 (2.860) Prec@1 82.03 (76.96) Prec@5 95.31 (91.78) + train[2018-10-24-14:26:05] Epoch: [226][4400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.967 (2.861) Prec@1 80.47 (76.97) Prec@5 92.97 (91.77) + train[2018-10-24-14:27:51] Epoch: [226][4600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.996 (2.862) Prec@1 75.78 (76.94) Prec@5 88.28 (91.76) + train[2018-10-24-14:29:36] Epoch: [226][4800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.914 (2.862) Prec@1 69.53 (76.93) Prec@5 89.84 (91.75) + train[2018-10-24-14:31:22] Epoch: [226][5000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.728 (2.862) Prec@1 76.56 (76.94) Prec@5 95.31 (91.76) + train[2018-10-24-14:33:08] Epoch: [226][5200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.751 (2.862) Prec@1 79.69 (76.93) Prec@5 94.53 (91.76) + train[2018-10-24-14:34:53] Epoch: [226][5400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.786 (2.862) Prec@1 81.25 (76.91) Prec@5 88.28 (91.76) + train[2018-10-24-14:36:39] Epoch: [226][5600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.834 (2.862) Prec@1 73.44 (76.93) Prec@5 91.41 (91.78) + train[2018-10-24-14:38:24] Epoch: [226][5800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.927 (2.861) Prec@1 76.56 (76.94) Prec@5 89.06 (91.79) + train[2018-10-24-14:40:10] Epoch: [226][6000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.917 (2.861) Prec@1 75.78 (76.94) Prec@5 92.97 (91.79) + train[2018-10-24-14:41:57] Epoch: [226][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.688 (2.861) Prec@1 82.03 (76.94) Prec@5 93.75 (91.78) + train[2018-10-24-14:43:44] Epoch: [226][6400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.125 (2.862) Prec@1 72.66 (76.95) Prec@5 87.50 (91.79) + train[2018-10-24-14:45:31] Epoch: [226][6600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.864 (2.862) Prec@1 80.47 (76.94) Prec@5 92.19 (91.78) + train[2018-10-24-14:47:19] Epoch: [226][6800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.191 (2.862) Prec@1 72.66 (76.94) Prec@5 88.28 (91.78) + train[2018-10-24-14:49:06] Epoch: [226][7000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.123 (2.862) Prec@1 71.88 (76.93) Prec@5 89.84 (91.77) + train[2018-10-24-14:50:53] Epoch: [226][7200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.917 (2.862) Prec@1 81.25 (76.92) Prec@5 92.19 (91.77) + train[2018-10-24-14:52:39] Epoch: [226][7400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.431 (2.862) Prec@1 84.38 (76.92) Prec@5 96.09 (91.77) + train[2018-10-24-14:54:26] Epoch: [226][7600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.805 (2.862) Prec@1 81.25 (76.93) Prec@5 91.41 (91.77) + train[2018-10-24-14:56:12] Epoch: [226][7800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.752 (2.863) Prec@1 80.47 (76.91) Prec@5 91.41 (91.76) + train[2018-10-24-14:57:59] Epoch: [226][8000/10010] Time 0.61 (0.53) Data 0.00 (0.00) Loss 2.914 (2.863) Prec@1 78.12 (76.91) Prec@5 90.62 (91.76) + train[2018-10-24-14:59:47] Epoch: [226][8200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.909 (2.862) Prec@1 76.56 (76.91) Prec@5 89.84 (91.76) + train[2018-10-24-15:01:34] Epoch: [226][8400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.977 (2.862) Prec@1 75.00 (76.91) Prec@5 90.62 (91.76) + train[2018-10-24-15:03:22] Epoch: [226][8600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.715 (2.863) Prec@1 80.47 (76.91) Prec@5 92.97 (91.76) + train[2018-10-24-15:05:10] Epoch: [226][8800/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.650 (2.864) Prec@1 78.12 (76.88) Prec@5 94.53 (91.75) + train[2018-10-24-15:06:57] Epoch: [226][9000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.631 (2.864) Prec@1 80.47 (76.89) Prec@5 94.53 (91.75) + train[2018-10-24-15:08:44] Epoch: [226][9200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.848 (2.864) Prec@1 75.78 (76.89) Prec@5 89.84 (91.75) + train[2018-10-24-15:10:31] Epoch: [226][9400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.750 (2.864) Prec@1 81.25 (76.88) Prec@5 92.97 (91.75) + train[2018-10-24-15:12:18] Epoch: [226][9600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.863 (2.864) Prec@1 78.12 (76.88) Prec@5 92.19 (91.74) + train[2018-10-24-15:14:06] Epoch: [226][9800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.704 (2.865) Prec@1 81.25 (76.88) Prec@5 92.19 (91.74) + train[2018-10-24-15:15:53] Epoch: [226][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.002 (2.865) Prec@1 73.44 (76.87) Prec@5 90.62 (91.74) + train[2018-10-24-15:15:58] Epoch: [226][10009/10010] Time 0.17 (0.53) Data 0.00 (0.00) Loss 3.428 (2.865) Prec@1 80.00 (76.87) Prec@5 80.00 (91.74) +[2018-10-24-15:15:58] **train** Prec@1 76.87 Prec@5 91.74 Error@1 23.13 Error@5 8.26 Loss:2.865 + test [2018-10-24-15:16:02] Epoch: [226][000/391] Time 4.14 (4.14) Data 4.01 (4.01) Loss 0.522 (0.522) Prec@1 92.97 (92.97) Prec@5 98.44 (98.44) + test [2018-10-24-15:16:32] Epoch: [226][200/391] Time 0.14 (0.17) Data 0.00 (0.04) Loss 1.185 (0.979) Prec@1 69.53 (77.65) Prec@5 91.41 (93.75) + test [2018-10-24-15:16:58] Epoch: [226][390/391] Time 0.08 (0.15) Data 0.00 (0.02) Loss 2.154 (1.151) Prec@1 46.25 (73.97) Prec@5 82.50 (91.47) +[2018-10-24-15:16:58] **test** Prec@1 73.97 Prec@5 91.47 Error@1 26.03 Error@5 8.53 Loss:1.151 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-24-15:16:58] [Epoch=227/250] [Need: 34:26:42] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-24-15:17:02] Epoch: [227][000/10010] Time 4.22 (4.22) Data 3.65 (3.65) Loss 2.713 (2.713) Prec@1 78.91 (78.91) Prec@5 95.31 (95.31) + train[2018-10-24-15:18:48] Epoch: [227][200/10010] Time 0.56 (0.55) Data 0.00 (0.02) Loss 2.699 (2.871) Prec@1 82.81 (76.64) Prec@5 93.75 (91.67) + train[2018-10-24-15:20:34] Epoch: [227][400/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.719 (2.862) Prec@1 78.12 (76.87) Prec@5 94.53 (91.80) + train[2018-10-24-15:22:19] Epoch: [227][600/10010] Time 0.53 (0.53) Data 0.00 (0.01) Loss 2.874 (2.863) Prec@1 78.12 (76.90) Prec@5 91.41 (91.81) + train[2018-10-24-15:24:05] Epoch: [227][800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.925 (2.864) Prec@1 75.00 (76.89) Prec@5 89.06 (91.75) + train[2018-10-24-15:25:52] Epoch: [227][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.851 (2.862) Prec@1 78.12 (76.93) Prec@5 89.84 (91.75) + train[2018-10-24-15:27:38] Epoch: [227][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.694 (2.862) Prec@1 82.81 (76.90) Prec@5 92.19 (91.76) + train[2018-10-24-15:29:23] Epoch: [227][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.651 (2.863) Prec@1 77.34 (76.88) Prec@5 93.75 (91.77) + train[2018-10-24-15:31:09] Epoch: [227][1600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.713 (2.861) Prec@1 77.34 (76.92) Prec@5 95.31 (91.78) + train[2018-10-24-15:32:54] Epoch: [227][1800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.722 (2.860) Prec@1 78.12 (76.96) Prec@5 92.19 (91.79) + train[2018-10-24-15:34:41] Epoch: [227][2000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.877 (2.860) Prec@1 76.56 (76.95) Prec@5 92.19 (91.80) + train[2018-10-24-15:36:27] Epoch: [227][2200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.045 (2.860) Prec@1 71.88 (76.96) Prec@5 89.84 (91.80) + train[2018-10-24-15:38:15] Epoch: [227][2400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.969 (2.860) Prec@1 67.97 (76.98) Prec@5 91.41 (91.79) + train[2018-10-24-15:40:01] Epoch: [227][2600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.068 (2.861) Prec@1 69.53 (76.97) Prec@5 89.84 (91.78) + train[2018-10-24-15:41:48] Epoch: [227][2800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.742 (2.861) Prec@1 78.91 (76.95) Prec@5 91.41 (91.77) + train[2018-10-24-15:43:34] Epoch: [227][3000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.456 (2.861) Prec@1 82.03 (76.95) Prec@5 94.53 (91.74) + train[2018-10-24-15:45:22] Epoch: [227][3200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.649 (2.862) Prec@1 82.81 (76.93) Prec@5 94.53 (91.74) + train[2018-10-24-15:47:09] Epoch: [227][3400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.037 (2.862) Prec@1 71.88 (76.93) Prec@5 89.06 (91.74) + train[2018-10-24-15:48:57] Epoch: [227][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.032 (2.862) Prec@1 71.09 (76.93) Prec@5 91.41 (91.74) + train[2018-10-24-15:50:44] Epoch: [227][3800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.896 (2.863) Prec@1 78.91 (76.91) Prec@5 88.28 (91.72) + train[2018-10-24-15:52:30] Epoch: [227][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.091 (2.864) Prec@1 73.44 (76.91) Prec@5 89.06 (91.71) + train[2018-10-24-15:54:18] Epoch: [227][4200/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 3.264 (2.865) Prec@1 71.88 (76.90) Prec@5 86.72 (91.70) + train[2018-10-24-15:56:04] Epoch: [227][4400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.740 (2.863) Prec@1 79.69 (76.93) Prec@5 95.31 (91.72) + train[2018-10-24-15:57:51] Epoch: [227][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.939 (2.863) Prec@1 74.22 (76.94) Prec@5 92.97 (91.72) + train[2018-10-24-15:59:38] Epoch: [227][4800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.733 (2.863) Prec@1 78.12 (76.93) Prec@5 95.31 (91.72) + train[2018-10-24-16:01:28] Epoch: [227][5000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.273 (2.863) Prec@1 72.66 (76.94) Prec@5 84.38 (91.73) + train[2018-10-24-16:03:15] Epoch: [227][5200/10010] Time 0.62 (0.53) Data 0.00 (0.00) Loss 3.056 (2.863) Prec@1 75.00 (76.92) Prec@5 89.84 (91.72) + train[2018-10-24-16:05:03] Epoch: [227][5400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.729 (2.864) Prec@1 78.12 (76.93) Prec@5 93.75 (91.72) + train[2018-10-24-16:06:51] Epoch: [227][5600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.771 (2.863) Prec@1 80.47 (76.93) Prec@5 92.97 (91.73) + train[2018-10-24-16:08:38] Epoch: [227][5800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.879 (2.863) Prec@1 71.09 (76.93) Prec@5 92.97 (91.74) + train[2018-10-24-16:10:25] Epoch: [227][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.776 (2.862) Prec@1 79.69 (76.94) Prec@5 92.97 (91.75) + train[2018-10-24-16:12:13] Epoch: [227][6200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.885 (2.863) Prec@1 74.22 (76.93) Prec@5 90.62 (91.75) + train[2018-10-24-16:14:01] Epoch: [227][6400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.954 (2.863) Prec@1 72.66 (76.92) Prec@5 89.84 (91.74) + train[2018-10-24-16:15:50] Epoch: [227][6600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.990 (2.863) Prec@1 73.44 (76.92) Prec@5 89.06 (91.74) + train[2018-10-24-16:17:36] Epoch: [227][6800/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.680 (2.863) Prec@1 80.47 (76.92) Prec@5 93.75 (91.74) + train[2018-10-24-16:19:23] Epoch: [227][7000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.661 (2.863) Prec@1 79.69 (76.92) Prec@5 96.09 (91.74) + train[2018-10-24-16:21:10] Epoch: [227][7200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.903 (2.864) Prec@1 78.91 (76.90) Prec@5 92.97 (91.74) + train[2018-10-24-16:22:57] Epoch: [227][7400/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.769 (2.863) Prec@1 80.47 (76.90) Prec@5 89.84 (91.74) + train[2018-10-24-16:24:44] Epoch: [227][7600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.667 (2.863) Prec@1 80.47 (76.92) Prec@5 95.31 (91.74) + train[2018-10-24-16:26:31] Epoch: [227][7800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.805 (2.863) Prec@1 77.34 (76.91) Prec@5 94.53 (91.74) + train[2018-10-24-16:28:18] Epoch: [227][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.482 (2.863) Prec@1 82.03 (76.91) Prec@5 96.09 (91.74) + train[2018-10-24-16:30:04] Epoch: [227][8200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.345 (2.863) Prec@1 69.53 (76.92) Prec@5 87.50 (91.74) + train[2018-10-24-16:31:51] Epoch: [227][8400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.843 (2.863) Prec@1 78.12 (76.92) Prec@5 91.41 (91.74) + train[2018-10-24-16:33:38] Epoch: [227][8600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.423 (2.863) Prec@1 88.28 (76.93) Prec@5 94.53 (91.74) + train[2018-10-24-16:35:26] Epoch: [227][8800/10010] Time 0.61 (0.53) Data 0.00 (0.00) Loss 2.843 (2.863) Prec@1 73.44 (76.92) Prec@5 91.41 (91.74) + train[2018-10-24-16:37:13] Epoch: [227][9000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.742 (2.863) Prec@1 82.03 (76.92) Prec@5 91.41 (91.74) + train[2018-10-24-16:39:01] Epoch: [227][9200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.061 (2.863) Prec@1 73.44 (76.91) Prec@5 89.06 (91.73) + train[2018-10-24-16:40:47] Epoch: [227][9400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.865 (2.863) Prec@1 75.78 (76.92) Prec@5 92.97 (91.74) + train[2018-10-24-16:42:35] Epoch: [227][9600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.036 (2.863) Prec@1 75.00 (76.92) Prec@5 90.62 (91.74) + train[2018-10-24-16:44:21] Epoch: [227][9800/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.786 (2.863) Prec@1 78.12 (76.92) Prec@5 92.97 (91.73) + train[2018-10-24-16:46:07] Epoch: [227][10000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.279 (2.863) Prec@1 68.75 (76.92) Prec@5 87.50 (91.74) + train[2018-10-24-16:46:12] Epoch: [227][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 2.985 (2.863) Prec@1 73.33 (76.92) Prec@5 93.33 (91.74) +[2018-10-24-16:46:12] **train** Prec@1 76.92 Prec@5 91.74 Error@1 23.08 Error@5 8.26 Loss:2.863 + test [2018-10-24-16:46:16] Epoch: [227][000/391] Time 4.43 (4.43) Data 4.29 (4.29) Loss 0.530 (0.530) Prec@1 92.97 (92.97) Prec@5 98.44 (98.44) + test [2018-10-24-16:46:46] Epoch: [227][200/391] Time 0.13 (0.17) Data 0.00 (0.04) Loss 1.207 (0.983) Prec@1 67.97 (77.47) Prec@5 91.41 (93.61) + test [2018-10-24-16:47:14] Epoch: [227][390/391] Time 0.09 (0.16) Data 0.00 (0.03) Loss 2.219 (1.155) Prec@1 47.50 (73.86) Prec@5 81.25 (91.42) +[2018-10-24-16:47:14] **test** Prec@1 73.86 Prec@5 91.42 Error@1 26.14 Error@5 8.58 Loss:1.155 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-24-16:47:15] [Epoch=228/250] [Need: 33:06:12] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-24-16:47:20] Epoch: [228][000/10010] Time 5.14 (5.14) Data 4.47 (4.47) Loss 2.504 (2.504) Prec@1 82.81 (82.81) Prec@5 93.75 (93.75) + train[2018-10-24-16:49:09] Epoch: [228][200/10010] Time 0.55 (0.57) Data 0.00 (0.02) Loss 2.704 (2.858) Prec@1 77.34 (76.65) Prec@5 91.41 (91.72) + train[2018-10-24-16:50:57] Epoch: [228][400/10010] Time 0.54 (0.55) Data 0.00 (0.01) Loss 2.692 (2.854) Prec@1 78.91 (76.96) Prec@5 92.97 (91.65) + train[2018-10-24-16:52:44] Epoch: [228][600/10010] Time 0.51 (0.55) Data 0.00 (0.01) Loss 2.647 (2.859) Prec@1 80.47 (76.99) Prec@5 94.53 (91.58) + train[2018-10-24-16:54:31] Epoch: [228][800/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 2.851 (2.858) Prec@1 75.00 (76.99) Prec@5 93.75 (91.62) + train[2018-10-24-16:56:18] Epoch: [228][1000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.516 (2.856) Prec@1 82.03 (77.07) Prec@5 95.31 (91.66) + train[2018-10-24-16:58:07] Epoch: [228][1200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.222 (2.856) Prec@1 67.19 (77.05) Prec@5 89.06 (91.71) + train[2018-10-24-16:59:54] Epoch: [228][1400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.162 (2.859) Prec@1 71.09 (76.95) Prec@5 88.28 (91.72) + train[2018-10-24-17:01:43] Epoch: [228][1600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.875 (2.858) Prec@1 78.91 (76.99) Prec@5 92.19 (91.77) + train[2018-10-24-17:03:30] Epoch: [228][1800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.036 (2.857) Prec@1 72.66 (77.02) Prec@5 89.06 (91.80) + train[2018-10-24-17:05:16] Epoch: [228][2000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.848 (2.857) Prec@1 77.34 (77.00) Prec@5 90.62 (91.80) + train[2018-10-24-17:07:04] Epoch: [228][2200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.208 (2.857) Prec@1 69.53 (76.96) Prec@5 88.28 (91.81) + train[2018-10-24-17:08:51] Epoch: [228][2400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.269 (2.856) Prec@1 70.31 (76.99) Prec@5 85.94 (91.81) + train[2018-10-24-17:10:37] Epoch: [228][2600/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.923 (2.856) Prec@1 77.34 (77.00) Prec@5 92.19 (91.82) + train[2018-10-24-17:12:24] Epoch: [228][2800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.703 (2.856) Prec@1 82.03 (77.01) Prec@5 93.75 (91.80) + train[2018-10-24-17:14:11] Epoch: [228][3000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.775 (2.856) Prec@1 78.91 (77.01) Prec@5 92.19 (91.82) + train[2018-10-24-17:15:58] Epoch: [228][3200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.897 (2.855) Prec@1 78.12 (77.03) Prec@5 89.06 (91.84) + train[2018-10-24-17:17:45] Epoch: [228][3400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.838 (2.856) Prec@1 77.34 (77.01) Prec@5 92.19 (91.84) + train[2018-10-24-17:19:31] Epoch: [228][3600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.957 (2.858) Prec@1 73.44 (76.99) Prec@5 92.19 (91.82) + train[2018-10-24-17:21:17] Epoch: [228][3800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.988 (2.859) Prec@1 76.56 (76.97) Prec@5 88.28 (91.80) + train[2018-10-24-17:23:05] Epoch: [228][4000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.871 (2.860) Prec@1 78.91 (76.95) Prec@5 92.19 (91.79) + train[2018-10-24-17:24:51] Epoch: [228][4200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.985 (2.859) Prec@1 73.44 (76.96) Prec@5 92.97 (91.80) + train[2018-10-24-17:26:39] Epoch: [228][4400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.892 (2.859) Prec@1 77.34 (76.97) Prec@5 89.06 (91.80) + train[2018-10-24-17:28:28] Epoch: [228][4600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.853 (2.859) Prec@1 79.69 (76.98) Prec@5 91.41 (91.80) + train[2018-10-24-17:30:15] Epoch: [228][4800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.165 (2.860) Prec@1 69.53 (76.97) Prec@5 84.38 (91.78) + train[2018-10-24-17:32:03] Epoch: [228][5000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.804 (2.860) Prec@1 76.56 (76.98) Prec@5 91.41 (91.78) + train[2018-10-24-17:33:51] Epoch: [228][5200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.955 (2.860) Prec@1 78.91 (76.97) Prec@5 90.62 (91.77) + train[2018-10-24-17:35:39] Epoch: [228][5400/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.775 (2.860) Prec@1 78.12 (76.95) Prec@5 92.19 (91.77) + train[2018-10-24-17:37:27] Epoch: [228][5600/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.939 (2.860) Prec@1 78.12 (76.96) Prec@5 89.06 (91.78) + train[2018-10-24-17:39:15] Epoch: [228][5800/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.495 (2.861) Prec@1 82.03 (76.94) Prec@5 95.31 (91.77) + train[2018-10-24-17:41:03] Epoch: [228][6000/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.788 (2.860) Prec@1 78.12 (76.96) Prec@5 89.06 (91.78) + train[2018-10-24-17:42:50] Epoch: [228][6200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.169 (2.861) Prec@1 74.22 (76.95) Prec@5 89.06 (91.78) + train[2018-10-24-17:44:39] Epoch: [228][6400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.802 (2.860) Prec@1 78.91 (76.96) Prec@5 95.31 (91.78) + train[2018-10-24-17:46:27] Epoch: [228][6600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.480 (2.860) Prec@1 83.59 (76.96) Prec@5 95.31 (91.78) + train[2018-10-24-17:48:15] Epoch: [228][6800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.869 (2.860) Prec@1 78.91 (76.95) Prec@5 91.41 (91.78) + train[2018-10-24-17:50:02] Epoch: [228][7000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.871 (2.861) Prec@1 75.00 (76.94) Prec@5 91.41 (91.78) + train[2018-10-24-17:51:49] Epoch: [228][7200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.826 (2.861) Prec@1 75.78 (76.95) Prec@5 89.84 (91.78) + train[2018-10-24-17:53:36] Epoch: [228][7400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.665 (2.861) Prec@1 76.56 (76.94) Prec@5 94.53 (91.77) + train[2018-10-24-17:55:23] Epoch: [228][7600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.789 (2.861) Prec@1 74.22 (76.93) Prec@5 92.97 (91.77) + train[2018-10-24-17:57:11] Epoch: [228][7800/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.005 (2.861) Prec@1 73.44 (76.93) Prec@5 90.62 (91.77) + train[2018-10-24-17:58:58] Epoch: [228][8000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.839 (2.861) Prec@1 78.91 (76.93) Prec@5 92.97 (91.77) + train[2018-10-24-18:00:46] Epoch: [228][8200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.056 (2.861) Prec@1 77.34 (76.93) Prec@5 91.41 (91.77) + train[2018-10-24-18:02:34] Epoch: [228][8400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.883 (2.862) Prec@1 76.56 (76.92) Prec@5 92.97 (91.77) + train[2018-10-24-18:04:22] Epoch: [228][8600/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.789 (2.861) Prec@1 75.00 (76.92) Prec@5 89.84 (91.77) + train[2018-10-24-18:06:10] Epoch: [228][8800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.134 (2.861) Prec@1 68.75 (76.92) Prec@5 86.72 (91.77) + train[2018-10-24-18:07:57] Epoch: [228][9000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.735 (2.861) Prec@1 82.81 (76.92) Prec@5 92.97 (91.77) + train[2018-10-24-18:09:44] Epoch: [228][9200/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.036 (2.861) Prec@1 75.78 (76.92) Prec@5 89.84 (91.77) + train[2018-10-24-18:11:33] Epoch: [228][9400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.826 (2.861) Prec@1 79.69 (76.92) Prec@5 91.41 (91.77) + train[2018-10-24-18:13:21] Epoch: [228][9600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.639 (2.861) Prec@1 80.47 (76.92) Prec@5 95.31 (91.77) + train[2018-10-24-18:15:07] Epoch: [228][9800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.897 (2.861) Prec@1 71.09 (76.92) Prec@5 95.31 (91.77) + train[2018-10-24-18:16:53] Epoch: [228][10000/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.893 (2.861) Prec@1 71.88 (76.92) Prec@5 92.19 (91.77) + train[2018-10-24-18:16:58] Epoch: [228][10009/10010] Time 0.19 (0.54) Data 0.00 (0.00) Loss 4.102 (2.861) Prec@1 66.67 (76.92) Prec@5 80.00 (91.77) +[2018-10-24-18:16:58] **train** Prec@1 76.92 Prec@5 91.77 Error@1 23.08 Error@5 8.23 Loss:2.861 + test [2018-10-24-18:17:02] Epoch: [228][000/391] Time 3.85 (3.85) Data 3.71 (3.71) Loss 0.525 (0.525) Prec@1 93.75 (93.75) Prec@5 98.44 (98.44) + test [2018-10-24-18:17:31] Epoch: [228][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.187 (0.990) Prec@1 68.75 (77.48) Prec@5 92.19 (93.66) + test [2018-10-24-18:17:57] Epoch: [228][390/391] Time 0.09 (0.15) Data 0.00 (0.02) Loss 2.180 (1.158) Prec@1 43.75 (73.92) Prec@5 83.75 (91.48) +[2018-10-24-18:17:57] **test** Prec@1 73.92 Prec@5 91.48 Error@1 26.08 Error@5 8.52 Loss:1.158 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-24-18:17:57] [Epoch=229/250] [Need: 31:44:55] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-24-18:18:03] Epoch: [229][000/10010] Time 5.87 (5.87) Data 5.30 (5.30) Loss 2.598 (2.598) Prec@1 84.38 (84.38) Prec@5 93.75 (93.75) + train[2018-10-24-18:19:51] Epoch: [229][200/10010] Time 0.50 (0.56) Data 0.00 (0.03) Loss 2.551 (2.845) Prec@1 82.03 (77.16) Prec@5 96.09 (91.83) + train[2018-10-24-18:21:37] Epoch: [229][400/10010] Time 0.51 (0.55) Data 0.00 (0.01) Loss 2.813 (2.860) Prec@1 80.47 (76.83) Prec@5 91.41 (91.77) + train[2018-10-24-18:23:23] Epoch: [229][600/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 3.155 (2.861) Prec@1 70.31 (76.98) Prec@5 86.72 (91.71) + train[2018-10-24-18:25:08] Epoch: [229][800/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.603 (2.860) Prec@1 83.59 (76.91) Prec@5 96.09 (91.70) + train[2018-10-24-18:26:53] Epoch: [229][1000/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 3.049 (2.860) Prec@1 69.53 (76.91) Prec@5 86.72 (91.75) + train[2018-10-24-18:28:39] Epoch: [229][1200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.712 (2.860) Prec@1 78.91 (76.90) Prec@5 94.53 (91.74) + train[2018-10-24-18:30:25] Epoch: [229][1400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.761 (2.860) Prec@1 79.69 (76.94) Prec@5 92.97 (91.77) + train[2018-10-24-18:32:11] Epoch: [229][1600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.797 (2.861) Prec@1 75.78 (76.93) Prec@5 91.41 (91.75) + train[2018-10-24-18:33:56] Epoch: [229][1800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.707 (2.859) Prec@1 79.69 (76.96) Prec@5 92.19 (91.80) + train[2018-10-24-18:35:42] Epoch: [229][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.796 (2.860) Prec@1 75.78 (76.94) Prec@5 92.19 (91.79) + train[2018-10-24-18:37:28] Epoch: [229][2200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.002 (2.861) Prec@1 78.12 (76.92) Prec@5 89.84 (91.79) + train[2018-10-24-18:39:15] Epoch: [229][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.864 (2.861) Prec@1 74.22 (76.93) Prec@5 92.97 (91.79) + train[2018-10-24-18:41:00] Epoch: [229][2600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.023 (2.860) Prec@1 73.44 (76.95) Prec@5 92.19 (91.79) + train[2018-10-24-18:42:45] Epoch: [229][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.300 (2.861) Prec@1 65.62 (76.93) Prec@5 86.72 (91.78) + train[2018-10-24-18:44:31] Epoch: [229][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.772 (2.861) Prec@1 72.66 (76.90) Prec@5 94.53 (91.77) + train[2018-10-24-18:46:17] Epoch: [229][3200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.820 (2.861) Prec@1 76.56 (76.91) Prec@5 92.97 (91.78) + train[2018-10-24-18:48:02] Epoch: [229][3400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.517 (2.861) Prec@1 86.72 (76.92) Prec@5 96.09 (91.78) + train[2018-10-24-18:49:48] Epoch: [229][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.945 (2.862) Prec@1 78.12 (76.92) Prec@5 89.84 (91.77) + train[2018-10-24-18:51:33] Epoch: [229][3800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.057 (2.862) Prec@1 73.44 (76.92) Prec@5 89.06 (91.77) + train[2018-10-24-18:53:20] Epoch: [229][4000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.065 (2.862) Prec@1 72.66 (76.92) Prec@5 89.84 (91.76) + train[2018-10-24-18:55:05] Epoch: [229][4200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.736 (2.862) Prec@1 82.03 (76.94) Prec@5 90.62 (91.76) + train[2018-10-24-18:56:52] Epoch: [229][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.070 (2.861) Prec@1 75.78 (76.95) Prec@5 85.94 (91.76) + train[2018-10-24-18:58:38] Epoch: [229][4600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.679 (2.861) Prec@1 83.59 (76.95) Prec@5 91.41 (91.76) + train[2018-10-24-19:00:25] Epoch: [229][4800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.801 (2.862) Prec@1 79.69 (76.95) Prec@5 92.19 (91.76) + train[2018-10-24-19:02:13] Epoch: [229][5000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.908 (2.860) Prec@1 75.00 (76.98) Prec@5 92.97 (91.78) + train[2018-10-24-19:04:00] Epoch: [229][5200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.728 (2.859) Prec@1 75.78 (76.98) Prec@5 93.75 (91.79) + train[2018-10-24-19:05:46] Epoch: [229][5400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.573 (2.860) Prec@1 78.91 (76.97) Prec@5 94.53 (91.78) + train[2018-10-24-19:07:33] Epoch: [229][5600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.770 (2.859) Prec@1 80.47 (76.98) Prec@5 92.97 (91.79) + train[2018-10-24-19:09:19] Epoch: [229][5800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.675 (2.859) Prec@1 82.03 (76.97) Prec@5 92.19 (91.78) + train[2018-10-24-19:11:06] Epoch: [229][6000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.750 (2.860) Prec@1 82.03 (76.96) Prec@5 91.41 (91.77) + train[2018-10-24-19:12:51] Epoch: [229][6200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.806 (2.861) Prec@1 76.56 (76.94) Prec@5 95.31 (91.76) + train[2018-10-24-19:14:38] Epoch: [229][6400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.901 (2.862) Prec@1 77.34 (76.93) Prec@5 89.06 (91.74) + train[2018-10-24-19:16:25] Epoch: [229][6600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.990 (2.862) Prec@1 72.66 (76.92) Prec@5 91.41 (91.75) + train[2018-10-24-19:18:12] Epoch: [229][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.140 (2.862) Prec@1 68.75 (76.92) Prec@5 89.84 (91.75) + train[2018-10-24-19:19:57] Epoch: [229][7000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.303 (2.863) Prec@1 69.53 (76.91) Prec@5 85.16 (91.74) + train[2018-10-24-19:21:44] Epoch: [229][7200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.879 (2.863) Prec@1 77.34 (76.89) Prec@5 89.06 (91.73) + train[2018-10-24-19:23:31] Epoch: [229][7400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.682 (2.863) Prec@1 75.00 (76.89) Prec@5 96.88 (91.72) + train[2018-10-24-19:25:18] Epoch: [229][7600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.614 (2.864) Prec@1 85.16 (76.89) Prec@5 93.75 (91.72) + train[2018-10-24-19:27:03] Epoch: [229][7800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.999 (2.864) Prec@1 76.56 (76.89) Prec@5 89.06 (91.72) + train[2018-10-24-19:28:50] Epoch: [229][8000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.066 (2.864) Prec@1 76.56 (76.90) Prec@5 85.94 (91.72) + train[2018-10-24-19:30:37] Epoch: [229][8200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.600 (2.863) Prec@1 80.47 (76.90) Prec@5 95.31 (91.73) + train[2018-10-24-19:32:23] Epoch: [229][8400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.915 (2.863) Prec@1 76.56 (76.90) Prec@5 90.62 (91.73) + train[2018-10-24-19:34:11] Epoch: [229][8600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.564 (2.863) Prec@1 82.03 (76.91) Prec@5 94.53 (91.73) + train[2018-10-24-19:35:56] Epoch: [229][8800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.856 (2.862) Prec@1 73.44 (76.91) Prec@5 90.62 (91.74) + train[2018-10-24-19:37:42] Epoch: [229][9000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.969 (2.862) Prec@1 71.09 (76.91) Prec@5 91.41 (91.74) + train[2018-10-24-19:39:30] Epoch: [229][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.533 (2.862) Prec@1 82.03 (76.92) Prec@5 95.31 (91.74) + train[2018-10-24-19:41:16] Epoch: [229][9400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.083 (2.862) Prec@1 72.66 (76.92) Prec@5 88.28 (91.75) + train[2018-10-24-19:43:02] Epoch: [229][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.757 (2.862) Prec@1 76.56 (76.91) Prec@5 94.53 (91.74) + train[2018-10-24-19:44:48] Epoch: [229][9800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.944 (2.862) Prec@1 71.88 (76.90) Prec@5 92.19 (91.74) + train[2018-10-24-19:46:35] Epoch: [229][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.068 (2.862) Prec@1 77.34 (76.91) Prec@5 86.72 (91.74) + train[2018-10-24-19:46:39] Epoch: [229][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 5.443 (2.862) Prec@1 40.00 (76.91) Prec@5 60.00 (91.74) +[2018-10-24-19:46:39] **train** Prec@1 76.91 Prec@5 91.74 Error@1 23.09 Error@5 8.26 Loss:2.862 + test [2018-10-24-19:46:43] Epoch: [229][000/391] Time 4.27 (4.27) Data 4.10 (4.10) Loss 0.528 (0.528) Prec@1 93.75 (93.75) Prec@5 99.22 (99.22) + test [2018-10-24-19:47:11] Epoch: [229][200/391] Time 0.14 (0.16) Data 0.01 (0.03) Loss 1.159 (0.994) Prec@1 67.19 (77.41) Prec@5 92.19 (93.63) + test [2018-10-24-19:47:36] Epoch: [229][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.139 (1.164) Prec@1 45.00 (73.87) Prec@5 82.50 (91.43) +[2018-10-24-19:47:36] **test** Prec@1 73.87 Prec@5 91.43 Error@1 26.13 Error@5 8.57 Loss:1.164 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-24-19:47:36] [Epoch=230/250] [Need: 29:53:00] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-24-19:47:42] Epoch: [230][000/10010] Time 5.30 (5.30) Data 4.65 (4.65) Loss 2.898 (2.898) Prec@1 77.34 (77.34) Prec@5 91.41 (91.41) + train[2018-10-24-19:49:26] Epoch: [230][200/10010] Time 0.54 (0.55) Data 0.00 (0.02) Loss 2.779 (2.861) Prec@1 78.91 (76.78) Prec@5 92.19 (91.76) + train[2018-10-24-19:51:12] Epoch: [230][400/10010] Time 0.56 (0.54) Data 0.00 (0.01) Loss 3.056 (2.857) Prec@1 72.66 (76.99) Prec@5 89.06 (91.75) + train[2018-10-24-19:52:59] Epoch: [230][600/10010] Time 0.57 (0.54) Data 0.00 (0.01) Loss 2.833 (2.851) Prec@1 80.47 (77.18) Prec@5 91.41 (91.81) + train[2018-10-24-19:54:45] Epoch: [230][800/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 2.852 (2.856) Prec@1 78.91 (77.10) Prec@5 92.19 (91.79) + train[2018-10-24-19:56:30] Epoch: [230][1000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.885 (2.857) Prec@1 79.69 (77.01) Prec@5 89.84 (91.81) + train[2018-10-24-19:58:17] Epoch: [230][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.790 (2.856) Prec@1 76.56 (77.03) Prec@5 92.97 (91.82) + train[2018-10-24-20:00:06] Epoch: [230][1400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.710 (2.856) Prec@1 75.78 (76.99) Prec@5 94.53 (91.82) + train[2018-10-24-20:01:54] Epoch: [230][1600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.598 (2.858) Prec@1 78.91 (76.96) Prec@5 95.31 (91.80) + train[2018-10-24-20:03:42] Epoch: [230][1800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.840 (2.858) Prec@1 78.12 (76.97) Prec@5 93.75 (91.81) + train[2018-10-24-20:05:31] Epoch: [230][2000/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.605 (2.861) Prec@1 81.25 (76.92) Prec@5 95.31 (91.77) + train[2018-10-24-20:07:20] Epoch: [230][2200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.842 (2.861) Prec@1 71.88 (76.92) Prec@5 89.84 (91.78) + train[2018-10-24-20:09:08] Epoch: [230][2400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.877 (2.863) Prec@1 76.56 (76.88) Prec@5 92.97 (91.75) + train[2018-10-24-20:10:55] Epoch: [230][2600/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.690 (2.862) Prec@1 82.03 (76.92) Prec@5 93.75 (91.78) + train[2018-10-24-20:12:44] Epoch: [230][2800/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.925 (2.863) Prec@1 82.81 (76.91) Prec@5 92.97 (91.76) + train[2018-10-24-20:14:32] Epoch: [230][3000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.686 (2.863) Prec@1 82.03 (76.90) Prec@5 92.97 (91.74) + train[2018-10-24-20:16:21] Epoch: [230][3200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.728 (2.864) Prec@1 78.12 (76.91) Prec@5 94.53 (91.75) + train[2018-10-24-20:18:10] Epoch: [230][3400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.943 (2.865) Prec@1 74.22 (76.88) Prec@5 94.53 (91.74) + train[2018-10-24-20:19:59] Epoch: [230][3600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.060 (2.864) Prec@1 73.44 (76.88) Prec@5 88.28 (91.74) + train[2018-10-24-20:21:47] Epoch: [230][3800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 3.158 (2.863) Prec@1 72.66 (76.88) Prec@5 91.41 (91.74) + train[2018-10-24-20:23:35] Epoch: [230][4000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.115 (2.863) Prec@1 71.09 (76.88) Prec@5 89.06 (91.74) + train[2018-10-24-20:25:24] Epoch: [230][4200/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 3.116 (2.864) Prec@1 71.88 (76.88) Prec@5 90.62 (91.74) + train[2018-10-24-20:27:13] Epoch: [230][4400/10010] Time 0.61 (0.54) Data 0.00 (0.00) Loss 2.724 (2.863) Prec@1 79.69 (76.88) Prec@5 95.31 (91.75) + train[2018-10-24-20:29:00] Epoch: [230][4600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.004 (2.862) Prec@1 74.22 (76.89) Prec@5 91.41 (91.75) + train[2018-10-24-20:30:49] Epoch: [230][4800/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.106 (2.862) Prec@1 75.78 (76.89) Prec@5 86.72 (91.75) + train[2018-10-24-20:32:37] Epoch: [230][5000/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.809 (2.861) Prec@1 80.47 (76.91) Prec@5 91.41 (91.76) + train[2018-10-24-20:34:25] Epoch: [230][5200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.741 (2.861) Prec@1 80.47 (76.92) Prec@5 94.53 (91.76) + train[2018-10-24-20:36:13] Epoch: [230][5400/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 3.021 (2.861) Prec@1 74.22 (76.91) Prec@5 91.41 (91.77) + train[2018-10-24-20:38:01] Epoch: [230][5600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.952 (2.860) Prec@1 74.22 (76.91) Prec@5 93.75 (91.77) + train[2018-10-24-20:39:51] Epoch: [230][5800/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 2.630 (2.861) Prec@1 82.03 (76.90) Prec@5 91.41 (91.77) + train[2018-10-24-20:41:39] Epoch: [230][6000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.807 (2.861) Prec@1 77.34 (76.90) Prec@5 92.19 (91.77) + train[2018-10-24-20:43:27] Epoch: [230][6200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.672 (2.861) Prec@1 78.91 (76.89) Prec@5 94.53 (91.76) + train[2018-10-24-20:45:17] Epoch: [230][6400/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 3.004 (2.861) Prec@1 74.22 (76.90) Prec@5 89.84 (91.77) + train[2018-10-24-20:47:05] Epoch: [230][6600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.047 (2.861) Prec@1 75.00 (76.90) Prec@5 85.94 (91.76) + train[2018-10-24-20:48:53] Epoch: [230][6800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.655 (2.861) Prec@1 75.00 (76.89) Prec@5 96.09 (91.77) + train[2018-10-24-20:50:42] Epoch: [230][7000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.818 (2.861) Prec@1 76.56 (76.89) Prec@5 91.41 (91.76) + train[2018-10-24-20:52:29] Epoch: [230][7200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.143 (2.862) Prec@1 69.53 (76.88) Prec@5 88.28 (91.76) + train[2018-10-24-20:54:15] Epoch: [230][7400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.877 (2.861) Prec@1 76.56 (76.89) Prec@5 92.97 (91.77) + train[2018-10-24-20:56:01] Epoch: [230][7600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.061 (2.861) Prec@1 75.00 (76.90) Prec@5 89.06 (91.77) + train[2018-10-24-20:57:47] Epoch: [230][7800/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.621 (2.861) Prec@1 81.25 (76.90) Prec@5 94.53 (91.77) + train[2018-10-24-20:59:33] Epoch: [230][8000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.888 (2.861) Prec@1 77.34 (76.90) Prec@5 91.41 (91.77) + train[2018-10-24-21:01:22] Epoch: [230][8200/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.835 (2.861) Prec@1 79.69 (76.90) Prec@5 92.97 (91.76) + train[2018-10-24-21:03:10] Epoch: [230][8400/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.775 (2.861) Prec@1 77.34 (76.90) Prec@5 94.53 (91.76) + train[2018-10-24-21:04:59] Epoch: [230][8600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.423 (2.862) Prec@1 64.84 (76.90) Prec@5 85.16 (91.75) + train[2018-10-24-21:06:47] Epoch: [230][8800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.809 (2.862) Prec@1 76.56 (76.90) Prec@5 89.84 (91.75) + train[2018-10-24-21:08:36] Epoch: [230][9000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.992 (2.862) Prec@1 73.44 (76.89) Prec@5 90.62 (91.74) + train[2018-10-24-21:10:23] Epoch: [230][9200/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.881 (2.862) Prec@1 77.34 (76.90) Prec@5 92.97 (91.74) + train[2018-10-24-21:12:10] Epoch: [230][9400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.951 (2.862) Prec@1 77.34 (76.90) Prec@5 91.41 (91.75) + train[2018-10-24-21:13:59] Epoch: [230][9600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.050 (2.862) Prec@1 73.44 (76.90) Prec@5 90.62 (91.75) + train[2018-10-24-21:15:46] Epoch: [230][9800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.807 (2.862) Prec@1 77.34 (76.90) Prec@5 91.41 (91.75) + train[2018-10-24-21:17:35] Epoch: [230][10000/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.926 (2.862) Prec@1 75.78 (76.90) Prec@5 92.97 (91.75) + train[2018-10-24-21:17:40] Epoch: [230][10009/10010] Time 0.33 (0.54) Data 0.00 (0.00) Loss 2.998 (2.862) Prec@1 73.33 (76.89) Prec@5 86.67 (91.75) +[2018-10-24-21:17:40] **train** Prec@1 76.89 Prec@5 91.75 Error@1 23.11 Error@5 8.25 Loss:2.862 + test [2018-10-24-21:17:44] Epoch: [230][000/391] Time 4.16 (4.16) Data 4.02 (4.02) Loss 0.539 (0.539) Prec@1 92.97 (92.97) Prec@5 99.22 (99.22) + test [2018-10-24-21:18:12] Epoch: [230][200/391] Time 0.12 (0.16) Data 0.00 (0.03) Loss 1.203 (0.982) Prec@1 69.53 (77.41) Prec@5 92.19 (93.67) + test [2018-10-24-21:18:37] Epoch: [230][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.105 (1.150) Prec@1 46.25 (73.88) Prec@5 82.50 (91.47) +[2018-10-24-21:18:37] **test** Prec@1 73.88 Prec@5 91.47 Error@1 26.12 Error@5 8.53 Loss:1.150 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-24-21:18:37] [Epoch=231/250] [Need: 28:49:09] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-24-21:18:42] Epoch: [231][000/10010] Time 5.45 (5.45) Data 4.82 (4.82) Loss 2.917 (2.917) Prec@1 72.66 (72.66) Prec@5 91.41 (91.41) + train[2018-10-24-21:20:28] Epoch: [231][200/10010] Time 0.52 (0.55) Data 0.00 (0.02) Loss 3.064 (2.845) Prec@1 75.00 (77.43) Prec@5 89.84 (91.99) + train[2018-10-24-21:22:13] Epoch: [231][400/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.833 (2.861) Prec@1 76.56 (77.07) Prec@5 93.75 (91.78) + train[2018-10-24-21:23:59] Epoch: [231][600/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.824 (2.861) Prec@1 75.78 (77.01) Prec@5 93.75 (91.72) + train[2018-10-24-21:25:46] Epoch: [231][800/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 3.065 (2.859) Prec@1 70.31 (77.08) Prec@5 90.62 (91.77) + train[2018-10-24-21:27:32] Epoch: [231][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.896 (2.858) Prec@1 81.25 (77.08) Prec@5 90.62 (91.76) + train[2018-10-24-21:29:20] Epoch: [231][1200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.656 (2.858) Prec@1 80.47 (77.09) Prec@5 95.31 (91.78) + train[2018-10-24-21:31:05] Epoch: [231][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.858 (2.861) Prec@1 82.03 (76.99) Prec@5 90.62 (91.78) + train[2018-10-24-21:32:51] Epoch: [231][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.924 (2.860) Prec@1 79.69 (77.01) Prec@5 89.84 (91.80) + train[2018-10-24-21:34:37] Epoch: [231][1800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.991 (2.860) Prec@1 71.09 (77.02) Prec@5 92.19 (91.80) + train[2018-10-24-21:36:23] Epoch: [231][2000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.855 (2.860) Prec@1 77.34 (77.00) Prec@5 93.75 (91.80) + train[2018-10-24-21:38:08] Epoch: [231][2200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.044 (2.860) Prec@1 77.34 (76.98) Prec@5 90.62 (91.80) + train[2018-10-24-21:39:54] Epoch: [231][2400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.801 (2.861) Prec@1 77.34 (76.96) Prec@5 92.97 (91.79) + train[2018-10-24-21:41:39] Epoch: [231][2600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.578 (2.861) Prec@1 84.38 (76.96) Prec@5 93.75 (91.79) + train[2018-10-24-21:43:27] Epoch: [231][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.721 (2.862) Prec@1 81.25 (76.96) Prec@5 91.41 (91.80) + train[2018-10-24-21:45:14] Epoch: [231][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.011 (2.862) Prec@1 68.75 (76.93) Prec@5 89.84 (91.80) + train[2018-10-24-21:47:01] Epoch: [231][3200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.880 (2.863) Prec@1 75.00 (76.90) Prec@5 93.75 (91.78) + train[2018-10-24-21:48:48] Epoch: [231][3400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.898 (2.862) Prec@1 75.78 (76.90) Prec@5 92.97 (91.79) + train[2018-10-24-21:50:37] Epoch: [231][3600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.802 (2.862) Prec@1 78.91 (76.90) Prec@5 88.28 (91.79) + train[2018-10-24-21:52:26] Epoch: [231][3800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.742 (2.862) Prec@1 78.91 (76.92) Prec@5 94.53 (91.79) + train[2018-10-24-21:54:13] Epoch: [231][4000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.996 (2.861) Prec@1 79.69 (76.93) Prec@5 91.41 (91.80) + train[2018-10-24-21:56:00] Epoch: [231][4200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.568 (2.861) Prec@1 82.03 (76.93) Prec@5 94.53 (91.79) + train[2018-10-24-21:57:48] Epoch: [231][4400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.020 (2.862) Prec@1 71.88 (76.91) Prec@5 89.84 (91.77) + train[2018-10-24-21:59:36] Epoch: [231][4600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.730 (2.861) Prec@1 81.25 (76.93) Prec@5 93.75 (91.78) + train[2018-10-24-22:01:23] Epoch: [231][4800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.854 (2.860) Prec@1 78.12 (76.94) Prec@5 90.62 (91.79) + train[2018-10-24-22:03:10] Epoch: [231][5000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.993 (2.861) Prec@1 76.56 (76.93) Prec@5 90.62 (91.78) + train[2018-10-24-22:04:59] Epoch: [231][5200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.753 (2.861) Prec@1 82.03 (76.94) Prec@5 92.97 (91.79) + train[2018-10-24-22:06:46] Epoch: [231][5400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.862 (2.861) Prec@1 75.00 (76.95) Prec@5 92.97 (91.79) + train[2018-10-24-22:08:34] Epoch: [231][5600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.710 (2.861) Prec@1 77.34 (76.94) Prec@5 93.75 (91.78) + train[2018-10-24-22:10:21] Epoch: [231][5800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.711 (2.860) Prec@1 79.69 (76.96) Prec@5 92.97 (91.79) + train[2018-10-24-22:12:08] Epoch: [231][6000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.831 (2.860) Prec@1 76.56 (76.96) Prec@5 89.84 (91.79) + train[2018-10-24-22:13:56] Epoch: [231][6200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.674 (2.860) Prec@1 82.03 (76.96) Prec@5 89.84 (91.79) + train[2018-10-24-22:15:43] Epoch: [231][6400/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.544 (2.860) Prec@1 79.69 (76.97) Prec@5 95.31 (91.79) + train[2018-10-24-22:17:31] Epoch: [231][6600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.808 (2.860) Prec@1 77.34 (76.96) Prec@5 94.53 (91.79) + train[2018-10-24-22:19:19] Epoch: [231][6800/10010] Time 0.61 (0.54) Data 0.00 (0.00) Loss 2.929 (2.861) Prec@1 76.56 (76.94) Prec@5 92.97 (91.78) + train[2018-10-24-22:21:07] Epoch: [231][7000/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 3.056 (2.861) Prec@1 72.66 (76.96) Prec@5 89.06 (91.79) + train[2018-10-24-22:22:54] Epoch: [231][7200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.728 (2.860) Prec@1 78.91 (76.96) Prec@5 92.97 (91.79) + train[2018-10-24-22:24:42] Epoch: [231][7400/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 3.074 (2.860) Prec@1 77.34 (76.97) Prec@5 89.06 (91.79) + train[2018-10-24-22:26:29] Epoch: [231][7600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.051 (2.860) Prec@1 75.78 (76.97) Prec@5 88.28 (91.80) + train[2018-10-24-22:28:17] Epoch: [231][7800/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.858 (2.859) Prec@1 77.34 (76.98) Prec@5 92.97 (91.80) + train[2018-10-24-22:30:03] Epoch: [231][8000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.803 (2.860) Prec@1 80.47 (76.97) Prec@5 90.62 (91.80) + train[2018-10-24-22:31:51] Epoch: [231][8200/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 3.172 (2.860) Prec@1 71.88 (76.96) Prec@5 87.50 (91.79) + train[2018-10-24-22:33:38] Epoch: [231][8400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.511 (2.860) Prec@1 85.94 (76.96) Prec@5 94.53 (91.79) + train[2018-10-24-22:35:25] Epoch: [231][8600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.705 (2.860) Prec@1 84.38 (76.97) Prec@5 93.75 (91.79) + train[2018-10-24-22:37:13] Epoch: [231][8800/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 2.898 (2.860) Prec@1 73.44 (76.97) Prec@5 90.62 (91.80) + train[2018-10-24-22:39:01] Epoch: [231][9000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.776 (2.860) Prec@1 79.69 (76.97) Prec@5 92.19 (91.80) + train[2018-10-24-22:40:48] Epoch: [231][9200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.967 (2.860) Prec@1 77.34 (76.97) Prec@5 91.41 (91.79) + train[2018-10-24-22:42:36] Epoch: [231][9400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.785 (2.860) Prec@1 75.78 (76.97) Prec@5 94.53 (91.79) + train[2018-10-24-22:44:24] Epoch: [231][9600/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 2.807 (2.860) Prec@1 79.69 (76.97) Prec@5 91.41 (91.79) + train[2018-10-24-22:46:12] Epoch: [231][9800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.788 (2.860) Prec@1 81.25 (76.96) Prec@5 93.75 (91.79) + train[2018-10-24-22:48:00] Epoch: [231][10000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.963 (2.860) Prec@1 72.66 (76.96) Prec@5 89.84 (91.78) + train[2018-10-24-22:48:04] Epoch: [231][10009/10010] Time 0.20 (0.54) Data 0.00 (0.00) Loss 4.333 (2.860) Prec@1 73.33 (76.96) Prec@5 73.33 (91.78) +[2018-10-24-22:48:04] **train** Prec@1 76.96 Prec@5 91.78 Error@1 23.04 Error@5 8.22 Loss:2.860 + test [2018-10-24-22:48:08] Epoch: [231][000/391] Time 3.84 (3.84) Data 3.70 (3.70) Loss 0.569 (0.569) Prec@1 92.19 (92.19) Prec@5 98.44 (98.44) + test [2018-10-24-22:48:37] Epoch: [231][200/391] Time 0.12 (0.17) Data 0.00 (0.03) Loss 1.193 (1.003) Prec@1 68.75 (77.42) Prec@5 91.41 (93.67) + test [2018-10-24-22:49:02] Epoch: [231][390/391] Time 0.08 (0.15) Data 0.00 (0.02) Loss 2.129 (1.171) Prec@1 48.75 (73.95) Prec@5 83.75 (91.42) +[2018-10-24-22:49:02] **test** Prec@1 73.95 Prec@5 91.42 Error@1 26.05 Error@5 8.58 Loss:1.171 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-24-22:49:03] [Epoch=232/250] [Need: 27:07:42] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-24-22:49:08] Epoch: [232][000/10010] Time 5.05 (5.05) Data 4.42 (4.42) Loss 2.788 (2.788) Prec@1 74.22 (74.22) Prec@5 94.53 (94.53) + train[2018-10-24-22:50:53] Epoch: [232][200/10010] Time 0.55 (0.55) Data 0.00 (0.02) Loss 2.934 (2.852) Prec@1 76.56 (77.11) Prec@5 90.62 (91.80) + train[2018-10-24-22:52:39] Epoch: [232][400/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.998 (2.856) Prec@1 73.44 (76.99) Prec@5 89.06 (91.88) + train[2018-10-24-22:54:25] Epoch: [232][600/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.785 (2.858) Prec@1 75.78 (76.88) Prec@5 92.97 (91.81) + train[2018-10-24-22:56:12] Epoch: [232][800/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.707 (2.861) Prec@1 78.91 (76.82) Prec@5 92.97 (91.75) + train[2018-10-24-22:57:58] Epoch: [232][1000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.994 (2.863) Prec@1 78.91 (76.82) Prec@5 89.84 (91.66) + train[2018-10-24-22:59:45] Epoch: [232][1200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.095 (2.861) Prec@1 73.44 (76.83) Prec@5 89.06 (91.67) + train[2018-10-24-23:01:32] Epoch: [232][1400/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.733 (2.861) Prec@1 82.03 (76.83) Prec@5 92.97 (91.67) + train[2018-10-24-23:03:20] Epoch: [232][1600/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.801 (2.860) Prec@1 75.78 (76.87) Prec@5 93.75 (91.71) + train[2018-10-24-23:05:06] Epoch: [232][1800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.694 (2.861) Prec@1 82.03 (76.89) Prec@5 94.53 (91.71) + train[2018-10-24-23:06:54] Epoch: [232][2000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.806 (2.860) Prec@1 78.12 (76.91) Prec@5 92.97 (91.72) + train[2018-10-24-23:08:41] Epoch: [232][2200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.707 (2.858) Prec@1 79.69 (76.95) Prec@5 92.97 (91.75) + train[2018-10-24-23:10:28] Epoch: [232][2400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.756 (2.860) Prec@1 79.69 (76.92) Prec@5 93.75 (91.75) + train[2018-10-24-23:12:13] Epoch: [232][2600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.792 (2.859) Prec@1 81.25 (76.94) Prec@5 92.19 (91.75) + train[2018-10-24-23:14:00] Epoch: [232][2800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.918 (2.860) Prec@1 76.56 (76.94) Prec@5 90.62 (91.75) + train[2018-10-24-23:15:47] Epoch: [232][3000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.685 (2.860) Prec@1 80.47 (76.91) Prec@5 92.97 (91.75) + train[2018-10-24-23:17:34] Epoch: [232][3200/10010] Time 0.61 (0.53) Data 0.00 (0.00) Loss 2.971 (2.860) Prec@1 73.44 (76.92) Prec@5 92.97 (91.76) + train[2018-10-24-23:19:20] Epoch: [232][3400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.176 (2.861) Prec@1 72.66 (76.91) Prec@5 88.28 (91.75) + train[2018-10-24-23:21:07] Epoch: [232][3600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.752 (2.860) Prec@1 76.56 (76.93) Prec@5 91.41 (91.75) + train[2018-10-24-23:22:53] Epoch: [232][3800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.786 (2.858) Prec@1 78.12 (76.96) Prec@5 91.41 (91.78) + train[2018-10-24-23:24:40] Epoch: [232][4000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.076 (2.859) Prec@1 75.00 (76.95) Prec@5 88.28 (91.77) + train[2018-10-24-23:26:26] Epoch: [232][4200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.594 (2.860) Prec@1 84.38 (76.92) Prec@5 95.31 (91.75) + train[2018-10-24-23:28:15] Epoch: [232][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.906 (2.859) Prec@1 76.56 (76.93) Prec@5 90.62 (91.75) + train[2018-10-24-23:30:01] Epoch: [232][4600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.933 (2.859) Prec@1 77.34 (76.93) Prec@5 89.06 (91.75) + train[2018-10-24-23:31:47] Epoch: [232][4800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.783 (2.859) Prec@1 77.34 (76.95) Prec@5 92.97 (91.76) + train[2018-10-24-23:33:35] Epoch: [232][5000/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 2.980 (2.859) Prec@1 78.12 (76.95) Prec@5 91.41 (91.75) + train[2018-10-24-23:35:21] Epoch: [232][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.819 (2.859) Prec@1 77.34 (76.94) Prec@5 95.31 (91.75) + train[2018-10-24-23:37:08] Epoch: [232][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.787 (2.860) Prec@1 76.56 (76.92) Prec@5 91.41 (91.74) + train[2018-10-24-23:38:55] Epoch: [232][5600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.978 (2.861) Prec@1 75.00 (76.91) Prec@5 88.28 (91.73) + train[2018-10-24-23:40:42] Epoch: [232][5800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.690 (2.861) Prec@1 81.25 (76.90) Prec@5 92.19 (91.73) + train[2018-10-24-23:42:30] Epoch: [232][6000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.753 (2.861) Prec@1 78.12 (76.90) Prec@5 92.97 (91.73) + train[2018-10-24-23:44:17] Epoch: [232][6200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.175 (2.861) Prec@1 67.19 (76.90) Prec@5 87.50 (91.73) + train[2018-10-24-23:46:04] Epoch: [232][6400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.911 (2.862) Prec@1 74.22 (76.89) Prec@5 92.97 (91.72) + train[2018-10-24-23:47:52] Epoch: [232][6600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.108 (2.862) Prec@1 73.44 (76.91) Prec@5 88.28 (91.72) + train[2018-10-24-23:49:39] Epoch: [232][6800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.342 (2.861) Prec@1 68.75 (76.91) Prec@5 86.72 (91.73) + train[2018-10-24-23:51:24] Epoch: [232][7000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.681 (2.863) Prec@1 80.47 (76.89) Prec@5 92.97 (91.72) + train[2018-10-24-23:53:09] Epoch: [232][7200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.413 (2.863) Prec@1 68.75 (76.89) Prec@5 87.50 (91.72) + train[2018-10-24-23:54:56] Epoch: [232][7400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.489 (2.862) Prec@1 83.59 (76.89) Prec@5 95.31 (91.73) + train[2018-10-24-23:56:43] Epoch: [232][7600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.761 (2.863) Prec@1 77.34 (76.89) Prec@5 91.41 (91.73) + train[2018-10-24-23:58:31] Epoch: [232][7800/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 3.116 (2.862) Prec@1 71.09 (76.89) Prec@5 87.50 (91.73) + train[2018-10-25-00:00:18] Epoch: [232][8000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.345 (2.862) Prec@1 70.31 (76.89) Prec@5 86.72 (91.73) + train[2018-10-25-00:02:06] Epoch: [232][8200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.458 (2.862) Prec@1 85.94 (76.89) Prec@5 92.97 (91.73) + train[2018-10-25-00:03:54] Epoch: [232][8400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.792 (2.863) Prec@1 73.44 (76.89) Prec@5 92.19 (91.73) + train[2018-10-25-00:05:41] Epoch: [232][8600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.663 (2.862) Prec@1 78.12 (76.89) Prec@5 95.31 (91.73) + train[2018-10-25-00:07:29] Epoch: [232][8800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.995 (2.862) Prec@1 74.22 (76.88) Prec@5 90.62 (91.73) + train[2018-10-25-00:09:16] Epoch: [232][9000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.951 (2.863) Prec@1 75.78 (76.88) Prec@5 92.19 (91.73) + train[2018-10-25-00:11:04] Epoch: [232][9200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.969 (2.863) Prec@1 74.22 (76.88) Prec@5 90.62 (91.73) + train[2018-10-25-00:12:52] Epoch: [232][9400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.564 (2.862) Prec@1 84.38 (76.88) Prec@5 92.97 (91.73) + train[2018-10-25-00:14:38] Epoch: [232][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.215 (2.862) Prec@1 73.44 (76.89) Prec@5 85.94 (91.74) + train[2018-10-25-00:16:25] Epoch: [232][9800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.945 (2.862) Prec@1 76.56 (76.89) Prec@5 91.41 (91.74) + train[2018-10-25-00:18:12] Epoch: [232][10000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.805 (2.862) Prec@1 77.34 (76.89) Prec@5 90.62 (91.74) + train[2018-10-25-00:18:16] Epoch: [232][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 4.223 (2.862) Prec@1 53.33 (76.89) Prec@5 73.33 (91.74) +[2018-10-25-00:18:16] **train** Prec@1 76.89 Prec@5 91.74 Error@1 23.11 Error@5 8.26 Loss:2.862 + test [2018-10-25-00:18:20] Epoch: [232][000/391] Time 3.85 (3.85) Data 3.71 (3.71) Loss 0.544 (0.544) Prec@1 92.97 (92.97) Prec@5 99.22 (99.22) + test [2018-10-25-00:18:51] Epoch: [232][200/391] Time 0.13 (0.17) Data 0.00 (0.04) Loss 1.147 (0.985) Prec@1 69.53 (77.46) Prec@5 91.41 (93.65) + test [2018-10-25-00:19:17] Epoch: [232][390/391] Time 0.08 (0.15) Data 0.00 (0.02) Loss 2.110 (1.155) Prec@1 48.75 (73.89) Prec@5 83.75 (91.47) +[2018-10-25-00:19:17] **test** Prec@1 73.89 Prec@5 91.47 Error@1 26.11 Error@5 8.53 Loss:1.155 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-25-00:19:17] [Epoch=233/250] [Need: 25:34:01] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-25-00:19:23] Epoch: [233][000/10010] Time 6.18 (6.18) Data 5.56 (5.56) Loss 2.900 (2.900) Prec@1 78.12 (78.12) Prec@5 91.41 (91.41) + train[2018-10-25-00:21:11] Epoch: [233][200/10010] Time 0.58 (0.57) Data 0.00 (0.03) Loss 2.636 (2.840) Prec@1 81.25 (77.36) Prec@5 93.75 (91.99) + train[2018-10-25-00:23:00] Epoch: [233][400/10010] Time 0.51 (0.56) Data 0.00 (0.01) Loss 2.726 (2.849) Prec@1 77.34 (77.21) Prec@5 93.75 (91.83) + train[2018-10-25-00:24:47] Epoch: [233][600/10010] Time 0.53 (0.55) Data 0.00 (0.01) Loss 2.727 (2.852) Prec@1 77.34 (77.18) Prec@5 96.09 (91.80) + train[2018-10-25-00:26:36] Epoch: [233][800/10010] Time 0.53 (0.55) Data 0.00 (0.01) Loss 2.964 (2.850) Prec@1 76.56 (77.15) Prec@5 89.06 (91.85) + train[2018-10-25-00:28:22] Epoch: [233][1000/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.721 (2.851) Prec@1 80.47 (77.15) Prec@5 92.97 (91.83) + train[2018-10-25-00:30:09] Epoch: [233][1200/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 2.680 (2.852) Prec@1 82.03 (77.17) Prec@5 91.41 (91.84) + train[2018-10-25-00:31:58] Epoch: [233][1400/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.949 (2.853) Prec@1 78.91 (77.15) Prec@5 90.62 (91.84) + train[2018-10-25-00:33:45] Epoch: [233][1600/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 3.025 (2.858) Prec@1 72.66 (77.06) Prec@5 88.28 (91.79) + train[2018-10-25-00:35:34] Epoch: [233][1800/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 3.051 (2.857) Prec@1 75.78 (77.05) Prec@5 89.84 (91.78) + train[2018-10-25-00:37:21] Epoch: [233][2000/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.923 (2.856) Prec@1 75.78 (77.08) Prec@5 90.62 (91.80) + train[2018-10-25-00:39:09] Epoch: [233][2200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.778 (2.855) Prec@1 75.78 (77.09) Prec@5 92.19 (91.80) + train[2018-10-25-00:40:58] Epoch: [233][2400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.675 (2.855) Prec@1 80.47 (77.09) Prec@5 95.31 (91.81) + train[2018-10-25-00:42:45] Epoch: [233][2600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.026 (2.854) Prec@1 71.09 (77.09) Prec@5 89.84 (91.82) + train[2018-10-25-00:44:33] Epoch: [233][2800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.745 (2.854) Prec@1 82.03 (77.09) Prec@5 92.19 (91.82) + train[2018-10-25-00:46:20] Epoch: [233][3000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.824 (2.853) Prec@1 77.34 (77.11) Prec@5 91.41 (91.83) + train[2018-10-25-00:48:08] Epoch: [233][3200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.757 (2.852) Prec@1 77.34 (77.12) Prec@5 92.19 (91.83) + train[2018-10-25-00:49:56] Epoch: [233][3400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.809 (2.852) Prec@1 78.91 (77.11) Prec@5 90.62 (91.83) + train[2018-10-25-00:51:44] Epoch: [233][3600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 3.033 (2.852) Prec@1 75.78 (77.10) Prec@5 85.94 (91.83) + train[2018-10-25-00:53:31] Epoch: [233][3800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.893 (2.852) Prec@1 77.34 (77.11) Prec@5 91.41 (91.83) + train[2018-10-25-00:55:19] Epoch: [233][4000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.020 (2.853) Prec@1 77.34 (77.09) Prec@5 90.62 (91.83) + train[2018-10-25-00:57:07] Epoch: [233][4200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.723 (2.853) Prec@1 77.34 (77.09) Prec@5 90.62 (91.82) + train[2018-10-25-00:58:54] Epoch: [233][4400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.900 (2.853) Prec@1 77.34 (77.09) Prec@5 90.62 (91.82) + train[2018-10-25-01:00:41] Epoch: [233][4600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.114 (2.854) Prec@1 73.44 (77.09) Prec@5 89.06 (91.82) + train[2018-10-25-01:02:29] Epoch: [233][4800/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 3.063 (2.855) Prec@1 78.12 (77.07) Prec@5 89.84 (91.80) + train[2018-10-25-01:04:15] Epoch: [233][5000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.023 (2.854) Prec@1 74.22 (77.08) Prec@5 89.84 (91.81) + train[2018-10-25-01:06:03] Epoch: [233][5200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.900 (2.854) Prec@1 74.22 (77.07) Prec@5 90.62 (91.82) + train[2018-10-25-01:07:51] Epoch: [233][5400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.603 (2.855) Prec@1 82.81 (77.06) Prec@5 93.75 (91.82) + train[2018-10-25-01:09:39] Epoch: [233][5600/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.886 (2.856) Prec@1 78.91 (77.03) Prec@5 89.06 (91.80) + train[2018-10-25-01:11:26] Epoch: [233][5800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 3.025 (2.856) Prec@1 76.56 (77.02) Prec@5 89.06 (91.82) + train[2018-10-25-01:13:13] Epoch: [233][6000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.929 (2.856) Prec@1 75.00 (77.01) Prec@5 89.84 (91.80) + train[2018-10-25-01:15:02] Epoch: [233][6200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.615 (2.857) Prec@1 79.69 (77.01) Prec@5 95.31 (91.80) + train[2018-10-25-01:16:49] Epoch: [233][6400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.760 (2.857) Prec@1 76.56 (77.00) Prec@5 95.31 (91.79) + train[2018-10-25-01:18:37] Epoch: [233][6600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.716 (2.857) Prec@1 78.12 (77.00) Prec@5 93.75 (91.78) + train[2018-10-25-01:20:25] Epoch: [233][6800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.695 (2.858) Prec@1 78.91 (76.99) Prec@5 95.31 (91.78) + train[2018-10-25-01:22:12] Epoch: [233][7000/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 3.018 (2.858) Prec@1 77.34 (76.99) Prec@5 88.28 (91.78) + train[2018-10-25-01:23:59] Epoch: [233][7200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.819 (2.858) Prec@1 77.34 (76.98) Prec@5 92.97 (91.78) + train[2018-10-25-01:25:46] Epoch: [233][7400/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.798 (2.858) Prec@1 78.91 (76.98) Prec@5 92.19 (91.78) + train[2018-10-25-01:27:34] Epoch: [233][7600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.086 (2.858) Prec@1 73.44 (76.98) Prec@5 89.06 (91.78) + train[2018-10-25-01:29:22] Epoch: [233][7800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.771 (2.858) Prec@1 81.25 (76.98) Prec@5 89.84 (91.79) + train[2018-10-25-01:31:09] Epoch: [233][8000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.832 (2.858) Prec@1 78.91 (76.97) Prec@5 89.84 (91.79) + train[2018-10-25-01:32:56] Epoch: [233][8200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.522 (2.858) Prec@1 85.16 (76.97) Prec@5 96.09 (91.79) + train[2018-10-25-01:34:44] Epoch: [233][8400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.804 (2.858) Prec@1 78.12 (76.97) Prec@5 92.19 (91.79) + train[2018-10-25-01:36:31] Epoch: [233][8600/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.856 (2.858) Prec@1 74.22 (76.97) Prec@5 89.84 (91.79) + train[2018-10-25-01:38:16] Epoch: [233][8800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.979 (2.858) Prec@1 76.56 (76.97) Prec@5 89.06 (91.80) + train[2018-10-25-01:40:02] Epoch: [233][9000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.776 (2.858) Prec@1 79.69 (76.97) Prec@5 91.41 (91.79) + train[2018-10-25-01:41:48] Epoch: [233][9200/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.696 (2.858) Prec@1 80.47 (76.98) Prec@5 95.31 (91.80) + train[2018-10-25-01:43:35] Epoch: [233][9400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.562 (2.858) Prec@1 82.03 (76.97) Prec@5 92.97 (91.79) + train[2018-10-25-01:45:22] Epoch: [233][9600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.153 (2.858) Prec@1 71.88 (76.98) Prec@5 86.72 (91.79) + train[2018-10-25-01:47:09] Epoch: [233][9800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.796 (2.859) Prec@1 78.12 (76.98) Prec@5 91.41 (91.78) + train[2018-10-25-01:48:55] Epoch: [233][10000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.572 (2.858) Prec@1 78.12 (76.98) Prec@5 96.09 (91.79) + train[2018-10-25-01:48:59] Epoch: [233][10009/10010] Time 0.19 (0.54) Data 0.00 (0.00) Loss 4.523 (2.858) Prec@1 40.00 (76.98) Prec@5 66.67 (91.79) +[2018-10-25-01:48:59] **train** Prec@1 76.98 Prec@5 91.79 Error@1 23.02 Error@5 8.21 Loss:2.858 + test [2018-10-25-01:49:04] Epoch: [233][000/391] Time 4.28 (4.28) Data 4.12 (4.12) Loss 0.554 (0.554) Prec@1 92.19 (92.19) Prec@5 99.22 (99.22) + test [2018-10-25-01:49:31] Epoch: [233][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.176 (0.996) Prec@1 70.31 (77.51) Prec@5 92.19 (93.65) + test [2018-10-25-01:49:56] Epoch: [233][390/391] Time 0.08 (0.15) Data 0.00 (0.01) Loss 2.107 (1.166) Prec@1 46.25 (73.93) Prec@5 83.75 (91.48) +[2018-10-25-01:49:56] **test** Prec@1 73.93 Prec@5 91.48 Error@1 26.07 Error@5 8.52 Loss:1.166 +----> Best Accuracy : Acc@1=73.98, Acc@5=91.44, Error@1=26.02, Error@5=8.56 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-25-01:49:56] [Epoch=234/250] [Need: 24:10:35] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-25-01:50:01] Epoch: [234][000/10010] Time 4.87 (4.87) Data 4.27 (4.27) Loss 3.058 (3.058) Prec@1 71.88 (71.88) Prec@5 89.06 (89.06) + train[2018-10-25-01:51:47] Epoch: [234][200/10010] Time 0.52 (0.55) Data 0.00 (0.02) Loss 2.832 (2.851) Prec@1 80.47 (77.34) Prec@5 92.97 (91.73) + train[2018-10-25-01:53:31] Epoch: [234][400/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.861 (2.842) Prec@1 75.78 (77.55) Prec@5 90.62 (91.90) + train[2018-10-25-01:55:19] Epoch: [234][600/10010] Time 0.54 (0.54) Data 0.00 (0.01) Loss 3.061 (2.847) Prec@1 71.88 (77.38) Prec@5 90.62 (91.89) + train[2018-10-25-01:57:06] Epoch: [234][800/10010] Time 0.56 (0.54) Data 0.00 (0.01) Loss 3.038 (2.852) Prec@1 75.00 (77.26) Prec@5 89.06 (91.83) + train[2018-10-25-01:58:54] Epoch: [234][1000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.580 (2.853) Prec@1 81.25 (77.22) Prec@5 93.75 (91.81) + train[2018-10-25-02:00:40] Epoch: [234][1200/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 3.078 (2.851) Prec@1 75.00 (77.21) Prec@5 89.06 (91.84) + train[2018-10-25-02:02:27] Epoch: [234][1400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.348 (2.855) Prec@1 62.50 (77.12) Prec@5 85.16 (91.80) + train[2018-10-25-02:04:14] Epoch: [234][1600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.064 (2.855) Prec@1 73.44 (77.11) Prec@5 87.50 (91.83) + train[2018-10-25-02:06:01] Epoch: [234][1800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.837 (2.858) Prec@1 78.12 (77.07) Prec@5 91.41 (91.80) + train[2018-10-25-02:07:49] Epoch: [234][2000/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.671 (2.858) Prec@1 81.25 (77.06) Prec@5 92.97 (91.79) + train[2018-10-25-02:09:36] Epoch: [234][2200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.568 (2.858) Prec@1 81.25 (77.02) Prec@5 94.53 (91.78) + train[2018-10-25-02:11:23] Epoch: [234][2400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.742 (2.857) Prec@1 79.69 (77.03) Prec@5 93.75 (91.81) + train[2018-10-25-02:13:11] Epoch: [234][2600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.908 (2.856) Prec@1 71.09 (77.02) Prec@5 92.19 (91.83) + train[2018-10-25-02:14:58] Epoch: [234][2800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.841 (2.856) Prec@1 77.34 (77.04) Prec@5 92.97 (91.83) + train[2018-10-25-02:16:46] Epoch: [234][3000/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.957 (2.856) Prec@1 76.56 (77.02) Prec@5 91.41 (91.82) + train[2018-10-25-02:18:33] Epoch: [234][3200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.606 (2.857) Prec@1 81.25 (77.01) Prec@5 94.53 (91.82) + train[2018-10-25-02:20:19] Epoch: [234][3400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.793 (2.858) Prec@1 79.69 (76.98) Prec@5 92.97 (91.82) + train[2018-10-25-02:22:07] Epoch: [234][3600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.089 (2.858) Prec@1 74.22 (76.98) Prec@5 88.28 (91.82) + train[2018-10-25-02:23:53] Epoch: [234][3800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.928 (2.858) Prec@1 75.00 (76.98) Prec@5 89.84 (91.82) + train[2018-10-25-02:25:42] Epoch: [234][4000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.684 (2.857) Prec@1 79.69 (77.01) Prec@5 91.41 (91.83) + train[2018-10-25-02:27:29] Epoch: [234][4200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.796 (2.856) Prec@1 81.25 (77.02) Prec@5 92.19 (91.84) + train[2018-10-25-02:29:16] Epoch: [234][4400/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.710 (2.857) Prec@1 78.91 (77.02) Prec@5 95.31 (91.83) + train[2018-10-25-02:31:04] Epoch: [234][4600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.892 (2.857) Prec@1 76.56 (77.00) Prec@5 91.41 (91.82) + train[2018-10-25-02:32:51] Epoch: [234][4800/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.742 (2.857) Prec@1 80.47 (76.99) Prec@5 93.75 (91.83) + train[2018-10-25-02:34:39] Epoch: [234][5000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.926 (2.857) Prec@1 71.88 (76.98) Prec@5 90.62 (91.83) + train[2018-10-25-02:36:26] Epoch: [234][5200/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.588 (2.857) Prec@1 80.47 (76.98) Prec@5 93.75 (91.83) + train[2018-10-25-02:38:13] Epoch: [234][5400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.881 (2.857) Prec@1 76.56 (76.97) Prec@5 91.41 (91.83) + train[2018-10-25-02:40:01] Epoch: [234][5600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.602 (2.857) Prec@1 82.81 (76.98) Prec@5 96.09 (91.83) + train[2018-10-25-02:41:47] Epoch: [234][5800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.512 (2.857) Prec@1 82.03 (76.99) Prec@5 96.09 (91.83) + train[2018-10-25-02:43:35] Epoch: [234][6000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.754 (2.857) Prec@1 75.00 (77.00) Prec@5 89.84 (91.83) + train[2018-10-25-02:45:22] Epoch: [234][6200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 3.122 (2.857) Prec@1 75.00 (76.99) Prec@5 89.06 (91.84) + train[2018-10-25-02:47:10] Epoch: [234][6400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.673 (2.856) Prec@1 80.47 (77.00) Prec@5 92.97 (91.84) + train[2018-10-25-02:48:57] Epoch: [234][6600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.965 (2.857) Prec@1 77.34 (77.00) Prec@5 89.84 (91.84) + train[2018-10-25-02:50:41] Epoch: [234][6800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.975 (2.857) Prec@1 71.09 (77.00) Prec@5 89.84 (91.83) + train[2018-10-25-02:52:27] Epoch: [234][7000/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.922 (2.857) Prec@1 78.12 (76.99) Prec@5 91.41 (91.84) + train[2018-10-25-02:54:11] Epoch: [234][7200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.883 (2.857) Prec@1 76.56 (76.98) Prec@5 90.62 (91.84) + train[2018-10-25-02:55:58] Epoch: [234][7400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.207 (2.857) Prec@1 68.75 (76.98) Prec@5 87.50 (91.84) + train[2018-10-25-02:57:45] Epoch: [234][7600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.714 (2.857) Prec@1 78.91 (76.97) Prec@5 94.53 (91.83) + train[2018-10-25-02:59:32] Epoch: [234][7800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.961 (2.857) Prec@1 73.44 (76.98) Prec@5 92.97 (91.84) + train[2018-10-25-03:01:20] Epoch: [234][8000/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.719 (2.857) Prec@1 78.91 (76.97) Prec@5 95.31 (91.85) + train[2018-10-25-03:03:07] Epoch: [234][8200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.920 (2.857) Prec@1 77.34 (76.97) Prec@5 91.41 (91.84) + train[2018-10-25-03:04:54] Epoch: [234][8400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.779 (2.858) Prec@1 75.78 (76.95) Prec@5 93.75 (91.84) + train[2018-10-25-03:06:40] Epoch: [234][8600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.848 (2.858) Prec@1 77.34 (76.94) Prec@5 90.62 (91.83) + train[2018-10-25-03:08:26] Epoch: [234][8800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.655 (2.859) Prec@1 81.25 (76.93) Prec@5 96.09 (91.82) + train[2018-10-25-03:10:14] Epoch: [234][9000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.566 (2.859) Prec@1 85.16 (76.92) Prec@5 92.97 (91.82) + train[2018-10-25-03:12:01] Epoch: [234][9200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.902 (2.859) Prec@1 75.00 (76.91) Prec@5 92.97 (91.82) + train[2018-10-25-03:13:49] Epoch: [234][9400/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.859 (2.860) Prec@1 79.69 (76.90) Prec@5 88.28 (91.82) + train[2018-10-25-03:15:37] Epoch: [234][9600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.925 (2.860) Prec@1 75.00 (76.90) Prec@5 94.53 (91.82) + train[2018-10-25-03:17:24] Epoch: [234][9800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.718 (2.860) Prec@1 78.91 (76.90) Prec@5 95.31 (91.81) + train[2018-10-25-03:19:12] Epoch: [234][10000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.995 (2.860) Prec@1 78.91 (76.90) Prec@5 88.28 (91.82) + train[2018-10-25-03:19:16] Epoch: [234][10009/10010] Time 0.18 (0.54) Data 0.00 (0.00) Loss 3.238 (2.860) Prec@1 73.33 (76.90) Prec@5 93.33 (91.82) +[2018-10-25-03:19:16] **train** Prec@1 76.90 Prec@5 91.82 Error@1 23.10 Error@5 8.18 Loss:2.860 + test [2018-10-25-03:19:20] Epoch: [234][000/391] Time 3.84 (3.84) Data 3.70 (3.70) Loss 0.563 (0.563) Prec@1 89.84 (89.84) Prec@5 98.44 (98.44) + test [2018-10-25-03:19:49] Epoch: [234][200/391] Time 0.12 (0.16) Data 0.00 (0.03) Loss 1.160 (0.982) Prec@1 70.31 (77.51) Prec@5 90.62 (93.68) + test [2018-10-25-03:20:14] Epoch: [234][390/391] Time 0.09 (0.15) Data 0.00 (0.02) Loss 2.124 (1.149) Prec@1 45.00 (74.00) Prec@5 83.75 (91.49) +[2018-10-25-03:20:14] **test** Prec@1 74.00 Prec@5 91.49 Error@1 26.00 Error@5 8.51 Loss:1.149 +----> Best Accuracy : Acc@1=74.00, Acc@5=91.49, Error@1=26.00, Error@5=8.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-25-03:20:14] [Epoch=235/250] [Need: 22:34:18] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-25-03:20:19] Epoch: [235][000/10010] Time 5.56 (5.56) Data 4.85 (4.85) Loss 2.838 (2.838) Prec@1 80.47 (80.47) Prec@5 90.62 (90.62) + train[2018-10-25-03:22:06] Epoch: [235][200/10010] Time 0.58 (0.56) Data 0.00 (0.02) Loss 3.062 (2.879) Prec@1 75.00 (76.66) Prec@5 87.50 (91.68) + train[2018-10-25-03:23:52] Epoch: [235][400/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 3.071 (2.879) Prec@1 71.09 (76.64) Prec@5 89.06 (91.59) + train[2018-10-25-03:25:37] Epoch: [235][600/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.960 (2.872) Prec@1 77.34 (76.81) Prec@5 91.41 (91.67) + train[2018-10-25-03:27:23] Epoch: [235][800/10010] Time 0.53 (0.54) Data 0.00 (0.01) Loss 2.927 (2.870) Prec@1 75.78 (76.84) Prec@5 92.97 (91.68) + train[2018-10-25-03:29:08] Epoch: [235][1000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.700 (2.867) Prec@1 78.12 (76.94) Prec@5 94.53 (91.68) + train[2018-10-25-03:30:56] Epoch: [235][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.259 (2.866) Prec@1 67.97 (76.92) Prec@5 88.28 (91.68) + train[2018-10-25-03:32:44] Epoch: [235][1400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.131 (2.865) Prec@1 70.31 (76.91) Prec@5 89.84 (91.71) + train[2018-10-25-03:34:31] Epoch: [235][1600/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.598 (2.865) Prec@1 82.03 (76.91) Prec@5 94.53 (91.74) + train[2018-10-25-03:36:20] Epoch: [235][1800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.662 (2.863) Prec@1 82.03 (76.95) Prec@5 95.31 (91.77) + train[2018-10-25-03:38:07] Epoch: [235][2000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.138 (2.863) Prec@1 72.66 (76.95) Prec@5 89.06 (91.78) + train[2018-10-25-03:39:55] Epoch: [235][2200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.910 (2.864) Prec@1 72.66 (76.95) Prec@5 89.84 (91.77) + train[2018-10-25-03:41:42] Epoch: [235][2400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.123 (2.863) Prec@1 73.44 (76.96) Prec@5 89.84 (91.76) + train[2018-10-25-03:43:29] Epoch: [235][2600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.867 (2.862) Prec@1 73.44 (76.97) Prec@5 92.19 (91.76) + train[2018-10-25-03:45:17] Epoch: [235][2800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.640 (2.861) Prec@1 81.25 (76.99) Prec@5 94.53 (91.79) + train[2018-10-25-03:47:06] Epoch: [235][3000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.704 (2.861) Prec@1 79.69 (76.98) Prec@5 92.97 (91.80) + train[2018-10-25-03:48:54] Epoch: [235][3200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.746 (2.863) Prec@1 79.69 (76.94) Prec@5 92.97 (91.78) + train[2018-10-25-03:50:43] Epoch: [235][3400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 3.003 (2.862) Prec@1 71.88 (76.95) Prec@5 91.41 (91.77) + train[2018-10-25-03:52:32] Epoch: [235][3600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.043 (2.861) Prec@1 71.09 (76.96) Prec@5 89.84 (91.79) + train[2018-10-25-03:54:21] Epoch: [235][3800/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.713 (2.861) Prec@1 79.69 (76.97) Prec@5 91.41 (91.79) + train[2018-10-25-03:56:10] Epoch: [235][4000/10010] Time 0.65 (0.54) Data 0.00 (0.00) Loss 2.745 (2.862) Prec@1 83.59 (76.95) Prec@5 91.41 (91.79) + train[2018-10-25-03:57:58] Epoch: [235][4200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.022 (2.860) Prec@1 73.44 (76.98) Prec@5 89.06 (91.81) + train[2018-10-25-03:59:46] Epoch: [235][4400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.847 (2.860) Prec@1 79.69 (76.98) Prec@5 95.31 (91.81) + train[2018-10-25-04:01:32] Epoch: [235][4600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.129 (2.860) Prec@1 71.88 (76.97) Prec@5 88.28 (91.81) + train[2018-10-25-04:03:21] Epoch: [235][4800/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 2.928 (2.860) Prec@1 75.78 (76.96) Prec@5 90.62 (91.79) + train[2018-10-25-04:05:09] Epoch: [235][5000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 3.037 (2.860) Prec@1 71.09 (76.97) Prec@5 87.50 (91.80) + train[2018-10-25-04:06:57] Epoch: [235][5200/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.936 (2.860) Prec@1 75.00 (76.96) Prec@5 91.41 (91.80) + train[2018-10-25-04:08:45] Epoch: [235][5400/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.880 (2.861) Prec@1 79.69 (76.95) Prec@5 89.84 (91.79) + train[2018-10-25-04:10:33] Epoch: [235][5600/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.787 (2.861) Prec@1 78.91 (76.94) Prec@5 89.06 (91.78) + train[2018-10-25-04:12:21] Epoch: [235][5800/10010] Time 0.62 (0.54) Data 0.00 (0.00) Loss 2.698 (2.861) Prec@1 82.81 (76.96) Prec@5 93.75 (91.79) + train[2018-10-25-04:14:08] Epoch: [235][6000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.804 (2.860) Prec@1 78.91 (76.95) Prec@5 93.75 (91.79) + train[2018-10-25-04:15:56] Epoch: [235][6200/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.927 (2.861) Prec@1 80.47 (76.95) Prec@5 90.62 (91.79) + train[2018-10-25-04:17:45] Epoch: [235][6400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.769 (2.861) Prec@1 76.56 (76.95) Prec@5 92.97 (91.78) + train[2018-10-25-04:19:32] Epoch: [235][6600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.120 (2.861) Prec@1 71.88 (76.95) Prec@5 91.41 (91.78) + train[2018-10-25-04:21:19] Epoch: [235][6800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.788 (2.861) Prec@1 78.91 (76.94) Prec@5 93.75 (91.78) + train[2018-10-25-04:23:07] Epoch: [235][7000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.757 (2.861) Prec@1 79.69 (76.94) Prec@5 94.53 (91.79) + train[2018-10-25-04:24:55] Epoch: [235][7200/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.855 (2.861) Prec@1 78.12 (76.93) Prec@5 91.41 (91.78) + train[2018-10-25-04:26:44] Epoch: [235][7400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.859 (2.861) Prec@1 74.22 (76.94) Prec@5 90.62 (91.79) + train[2018-10-25-04:28:32] Epoch: [235][7600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.640 (2.861) Prec@1 85.16 (76.94) Prec@5 92.97 (91.78) + train[2018-10-25-04:30:21] Epoch: [235][7800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.908 (2.861) Prec@1 71.88 (76.95) Prec@5 94.53 (91.79) + train[2018-10-25-04:32:09] Epoch: [235][8000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.776 (2.860) Prec@1 76.56 (76.96) Prec@5 94.53 (91.79) + train[2018-10-25-04:33:55] Epoch: [235][8200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.040 (2.860) Prec@1 73.44 (76.96) Prec@5 92.97 (91.79) + train[2018-10-25-04:35:43] Epoch: [235][8400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.856 (2.860) Prec@1 79.69 (76.96) Prec@5 92.19 (91.79) + train[2018-10-25-04:37:31] Epoch: [235][8600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.871 (2.860) Prec@1 77.34 (76.97) Prec@5 92.19 (91.79) + train[2018-10-25-04:39:19] Epoch: [235][8800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.826 (2.860) Prec@1 82.03 (76.96) Prec@5 92.97 (91.79) + train[2018-10-25-04:41:07] Epoch: [235][9000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.864 (2.860) Prec@1 76.56 (76.96) Prec@5 90.62 (91.79) + train[2018-10-25-04:42:55] Epoch: [235][9200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.802 (2.860) Prec@1 78.12 (76.95) Prec@5 91.41 (91.79) + train[2018-10-25-04:44:42] Epoch: [235][9400/10010] Time 0.60 (0.54) Data 0.00 (0.00) Loss 2.762 (2.860) Prec@1 79.69 (76.96) Prec@5 89.06 (91.79) + train[2018-10-25-04:46:29] Epoch: [235][9600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.613 (2.860) Prec@1 78.91 (76.94) Prec@5 96.09 (91.79) + train[2018-10-25-04:48:17] Epoch: [235][9800/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.801 (2.860) Prec@1 76.56 (76.95) Prec@5 93.75 (91.79) + train[2018-10-25-04:50:05] Epoch: [235][10000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.676 (2.860) Prec@1 77.34 (76.94) Prec@5 93.75 (91.79) + train[2018-10-25-04:50:09] Epoch: [235][10009/10010] Time 0.19 (0.54) Data 0.00 (0.00) Loss 3.855 (2.860) Prec@1 60.00 (76.94) Prec@5 86.67 (91.80) +[2018-10-25-04:50:09] **train** Prec@1 76.94 Prec@5 91.80 Error@1 23.06 Error@5 8.20 Loss:2.860 + test [2018-10-25-04:50:13] Epoch: [235][000/391] Time 4.24 (4.24) Data 4.11 (4.11) Loss 0.547 (0.547) Prec@1 92.97 (92.97) Prec@5 98.44 (98.44) + test [2018-10-25-04:50:43] Epoch: [235][200/391] Time 0.13 (0.17) Data 0.00 (0.04) Loss 1.178 (0.989) Prec@1 67.97 (77.49) Prec@5 92.19 (93.67) + test [2018-10-25-04:51:09] Epoch: [235][390/391] Time 0.08 (0.15) Data 0.00 (0.02) Loss 2.078 (1.160) Prec@1 48.75 (73.89) Prec@5 83.75 (91.45) +[2018-10-25-04:51:09] **test** Prec@1 73.89 Prec@5 91.45 Error@1 26.11 Error@5 8.55 Loss:1.160 +----> Best Accuracy : Acc@1=74.00, Acc@5=91.49, Error@1=26.00, Error@5=8.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-25-04:51:09] [Epoch=236/250] [Need: 21:12:58] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-25-04:51:15] Epoch: [236][000/10010] Time 5.66 (5.66) Data 5.08 (5.08) Loss 2.490 (2.490) Prec@1 85.94 (85.94) Prec@5 95.31 (95.31) + train[2018-10-25-04:53:03] Epoch: [236][200/10010] Time 0.50 (0.56) Data 0.00 (0.03) Loss 3.173 (2.843) Prec@1 71.88 (77.30) Prec@5 88.28 (91.75) + train[2018-10-25-04:54:50] Epoch: [236][400/10010] Time 0.53 (0.55) Data 0.00 (0.01) Loss 2.783 (2.856) Prec@1 78.12 (77.11) Prec@5 91.41 (91.64) + train[2018-10-25-04:56:37] Epoch: [236][600/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 2.742 (2.858) Prec@1 78.91 (77.15) Prec@5 92.97 (91.66) + train[2018-10-25-04:58:25] Epoch: [236][800/10010] Time 0.56 (0.54) Data 0.00 (0.01) Loss 2.810 (2.860) Prec@1 78.12 (77.05) Prec@5 92.19 (91.64) + train[2018-10-25-05:00:12] Epoch: [236][1000/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.918 (2.859) Prec@1 73.44 (77.08) Prec@5 93.75 (91.65) + train[2018-10-25-05:01:59] Epoch: [236][1200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.837 (2.859) Prec@1 76.56 (77.02) Prec@5 91.41 (91.69) + train[2018-10-25-05:03:46] Epoch: [236][1400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.934 (2.859) Prec@1 75.00 (77.02) Prec@5 93.75 (91.71) + train[2018-10-25-05:05:34] Epoch: [236][1600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.798 (2.858) Prec@1 78.91 (77.00) Prec@5 92.19 (91.74) + train[2018-10-25-05:07:20] Epoch: [236][1800/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.753 (2.858) Prec@1 75.78 (76.96) Prec@5 96.88 (91.78) + train[2018-10-25-05:09:06] Epoch: [236][2000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.760 (2.857) Prec@1 78.12 (76.96) Prec@5 93.75 (91.78) + train[2018-10-25-05:10:53] Epoch: [236][2200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.964 (2.857) Prec@1 75.78 (76.99) Prec@5 91.41 (91.78) + train[2018-10-25-05:12:40] Epoch: [236][2400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.806 (2.857) Prec@1 77.34 (76.97) Prec@5 93.75 (91.77) + train[2018-10-25-05:14:28] Epoch: [236][2600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.977 (2.858) Prec@1 75.00 (76.94) Prec@5 89.06 (91.77) + train[2018-10-25-05:16:14] Epoch: [236][2800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.845 (2.859) Prec@1 74.22 (76.92) Prec@5 90.62 (91.75) + train[2018-10-25-05:18:02] Epoch: [236][3000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.727 (2.860) Prec@1 82.81 (76.92) Prec@5 92.97 (91.74) + train[2018-10-25-05:19:50] Epoch: [236][3200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.767 (2.860) Prec@1 79.69 (76.91) Prec@5 94.53 (91.74) + train[2018-10-25-05:21:37] Epoch: [236][3400/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 2.671 (2.859) Prec@1 79.69 (76.93) Prec@5 92.97 (91.75) + train[2018-10-25-05:23:25] Epoch: [236][3600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.935 (2.859) Prec@1 70.31 (76.94) Prec@5 93.75 (91.75) + train[2018-10-25-05:25:12] Epoch: [236][3800/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.869 (2.860) Prec@1 75.00 (76.93) Prec@5 89.84 (91.74) + train[2018-10-25-05:27:00] Epoch: [236][4000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.543 (2.859) Prec@1 82.81 (76.93) Prec@5 95.31 (91.74) + train[2018-10-25-05:28:47] Epoch: [236][4200/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.920 (2.860) Prec@1 72.66 (76.91) Prec@5 92.97 (91.73) + train[2018-10-25-05:30:35] Epoch: [236][4400/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 2.671 (2.859) Prec@1 78.91 (76.93) Prec@5 96.09 (91.74) + train[2018-10-25-05:32:21] Epoch: [236][4600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.032 (2.858) Prec@1 77.34 (76.95) Prec@5 90.62 (91.74) + train[2018-10-25-05:34:08] Epoch: [236][4800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.815 (2.859) Prec@1 76.56 (76.95) Prec@5 93.75 (91.74) + train[2018-10-25-05:35:55] Epoch: [236][5000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.610 (2.859) Prec@1 82.03 (76.95) Prec@5 94.53 (91.75) + train[2018-10-25-05:37:42] Epoch: [236][5200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.285 (2.858) Prec@1 74.22 (76.95) Prec@5 87.50 (91.76) + train[2018-10-25-05:39:28] Epoch: [236][5400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.709 (2.859) Prec@1 79.69 (76.96) Prec@5 95.31 (91.76) + train[2018-10-25-05:41:16] Epoch: [236][5600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.699 (2.859) Prec@1 80.47 (76.96) Prec@5 92.19 (91.76) + train[2018-10-25-05:43:03] Epoch: [236][5800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.760 (2.859) Prec@1 77.34 (76.96) Prec@5 92.19 (91.76) + train[2018-10-25-05:44:51] Epoch: [236][6000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.906 (2.859) Prec@1 76.56 (76.96) Prec@5 89.84 (91.76) + train[2018-10-25-05:46:38] Epoch: [236][6200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.564 (2.858) Prec@1 79.69 (76.98) Prec@5 96.09 (91.77) + train[2018-10-25-05:48:25] Epoch: [236][6400/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.615 (2.858) Prec@1 79.69 (76.98) Prec@5 95.31 (91.77) + train[2018-10-25-05:50:12] Epoch: [236][6600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.761 (2.859) Prec@1 75.78 (76.97) Prec@5 92.97 (91.77) + train[2018-10-25-05:51:59] Epoch: [236][6800/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.738 (2.858) Prec@1 78.91 (76.98) Prec@5 92.19 (91.78) + train[2018-10-25-05:53:47] Epoch: [236][7000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.654 (2.858) Prec@1 82.81 (76.97) Prec@5 95.31 (91.77) + train[2018-10-25-05:55:34] Epoch: [236][7200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.012 (2.858) Prec@1 76.56 (76.98) Prec@5 91.41 (91.77) + train[2018-10-25-05:57:22] Epoch: [236][7400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 3.090 (2.858) Prec@1 71.88 (76.97) Prec@5 87.50 (91.78) + train[2018-10-25-05:59:09] Epoch: [236][7600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.901 (2.858) Prec@1 78.91 (76.98) Prec@5 92.19 (91.78) + train[2018-10-25-06:00:56] Epoch: [236][7800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.858 (2.859) Prec@1 78.91 (76.97) Prec@5 90.62 (91.77) + train[2018-10-25-06:02:43] Epoch: [236][8000/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.663 (2.859) Prec@1 77.34 (76.96) Prec@5 94.53 (91.76) + train[2018-10-25-06:04:30] Epoch: [236][8200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.651 (2.859) Prec@1 80.47 (76.95) Prec@5 96.88 (91.76) + train[2018-10-25-06:06:18] Epoch: [236][8400/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 3.035 (2.860) Prec@1 72.66 (76.94) Prec@5 91.41 (91.75) + train[2018-10-25-06:08:05] Epoch: [236][8600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.959 (2.860) Prec@1 78.91 (76.94) Prec@5 91.41 (91.76) + train[2018-10-25-06:09:53] Epoch: [236][8800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.011 (2.860) Prec@1 77.34 (76.94) Prec@5 91.41 (91.76) + train[2018-10-25-06:11:40] Epoch: [236][9000/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.846 (2.860) Prec@1 74.22 (76.93) Prec@5 90.62 (91.76) + train[2018-10-25-06:13:28] Epoch: [236][9200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.933 (2.860) Prec@1 73.44 (76.92) Prec@5 92.19 (91.76) + train[2018-10-25-06:15:15] Epoch: [236][9400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.166 (2.860) Prec@1 71.09 (76.93) Prec@5 86.72 (91.76) + train[2018-10-25-06:17:03] Epoch: [236][9600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.016 (2.860) Prec@1 75.00 (76.93) Prec@5 89.06 (91.76) + train[2018-10-25-06:18:51] Epoch: [236][9800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.711 (2.860) Prec@1 78.91 (76.93) Prec@5 95.31 (91.76) + train[2018-10-25-06:20:37] Epoch: [236][10000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.485 (2.860) Prec@1 85.94 (76.94) Prec@5 94.53 (91.76) + train[2018-10-25-06:20:41] Epoch: [236][10009/10010] Time 0.21 (0.54) Data 0.00 (0.00) Loss 3.904 (2.860) Prec@1 60.00 (76.94) Prec@5 80.00 (91.76) +[2018-10-25-06:20:41] **train** Prec@1 76.94 Prec@5 91.76 Error@1 23.06 Error@5 8.24 Loss:2.860 + test [2018-10-25-06:20:46] Epoch: [236][000/391] Time 4.60 (4.60) Data 4.47 (4.47) Loss 0.518 (0.518) Prec@1 92.97 (92.97) Prec@5 99.22 (99.22) + test [2018-10-25-06:21:14] Epoch: [236][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.187 (0.993) Prec@1 67.97 (77.47) Prec@5 90.62 (93.66) + test [2018-10-25-06:21:41] Epoch: [236][390/391] Time 0.09 (0.15) Data 0.00 (0.02) Loss 2.092 (1.162) Prec@1 46.25 (73.90) Prec@5 83.75 (91.43) +[2018-10-25-06:21:41] **test** Prec@1 73.90 Prec@5 91.43 Error@1 26.10 Error@5 8.57 Loss:1.162 +----> Best Accuracy : Acc@1=74.00, Acc@5=91.49, Error@1=26.00, Error@5=8.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-25-06:21:41] [Epoch=237/250] [Need: 19:36:48] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-25-06:21:47] Epoch: [237][000/10010] Time 6.08 (6.08) Data 5.40 (5.40) Loss 3.161 (3.161) Prec@1 71.88 (71.88) Prec@5 88.28 (88.28) + train[2018-10-25-06:23:35] Epoch: [237][200/10010] Time 0.50 (0.57) Data 0.00 (0.03) Loss 2.652 (2.865) Prec@1 80.47 (76.86) Prec@5 93.75 (91.66) + train[2018-10-25-06:25:23] Epoch: [237][400/10010] Time 0.51 (0.55) Data 0.00 (0.01) Loss 2.506 (2.867) Prec@1 83.59 (76.79) Prec@5 95.31 (91.69) + train[2018-10-25-06:27:11] Epoch: [237][600/10010] Time 0.55 (0.55) Data 0.00 (0.01) Loss 2.789 (2.863) Prec@1 75.78 (76.96) Prec@5 93.75 (91.71) + train[2018-10-25-06:28:59] Epoch: [237][800/10010] Time 0.51 (0.55) Data 0.00 (0.01) Loss 2.736 (2.861) Prec@1 78.91 (76.96) Prec@5 94.53 (91.79) + train[2018-10-25-06:30:47] Epoch: [237][1000/10010] Time 0.50 (0.55) Data 0.00 (0.01) Loss 2.827 (2.862) Prec@1 78.12 (76.96) Prec@5 89.84 (91.78) + train[2018-10-25-06:32:34] Epoch: [237][1200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.785 (2.864) Prec@1 78.12 (76.84) Prec@5 93.75 (91.75) + train[2018-10-25-06:34:21] Epoch: [237][1400/10010] Time 0.60 (0.54) Data 0.00 (0.00) Loss 3.047 (2.862) Prec@1 75.78 (76.82) Prec@5 88.28 (91.77) + train[2018-10-25-06:36:09] Epoch: [237][1600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.735 (2.864) Prec@1 75.78 (76.80) Prec@5 92.97 (91.74) + train[2018-10-25-06:37:55] Epoch: [237][1800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.900 (2.860) Prec@1 74.22 (76.89) Prec@5 91.41 (91.78) + train[2018-10-25-06:39:44] Epoch: [237][2000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.946 (2.858) Prec@1 76.56 (76.93) Prec@5 90.62 (91.80) + train[2018-10-25-06:41:31] Epoch: [237][2200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.546 (2.857) Prec@1 82.03 (76.94) Prec@5 94.53 (91.81) + train[2018-10-25-06:43:19] Epoch: [237][2400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.908 (2.857) Prec@1 77.34 (76.94) Prec@5 90.62 (91.80) + train[2018-10-25-06:45:05] Epoch: [237][2600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.681 (2.856) Prec@1 80.47 (76.94) Prec@5 92.97 (91.80) + train[2018-10-25-06:46:50] Epoch: [237][2800/10010] Time 0.60 (0.54) Data 0.00 (0.00) Loss 3.030 (2.856) Prec@1 67.97 (76.96) Prec@5 90.62 (91.81) + train[2018-10-25-06:48:37] Epoch: [237][3000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.872 (2.856) Prec@1 75.78 (76.95) Prec@5 87.50 (91.80) + train[2018-10-25-06:50:24] Epoch: [237][3200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.919 (2.857) Prec@1 81.25 (76.93) Prec@5 90.62 (91.80) + train[2018-10-25-06:52:11] Epoch: [237][3400/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.632 (2.856) Prec@1 80.47 (76.96) Prec@5 94.53 (91.79) + train[2018-10-25-06:53:58] Epoch: [237][3600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.690 (2.856) Prec@1 78.91 (76.95) Prec@5 92.97 (91.79) + train[2018-10-25-06:55:46] Epoch: [237][3800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.946 (2.857) Prec@1 76.56 (76.96) Prec@5 92.97 (91.79) + train[2018-10-25-06:57:35] Epoch: [237][4000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.610 (2.856) Prec@1 78.91 (76.97) Prec@5 95.31 (91.80) + train[2018-10-25-06:59:21] Epoch: [237][4200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.806 (2.857) Prec@1 82.81 (76.96) Prec@5 93.75 (91.79) + train[2018-10-25-07:01:08] Epoch: [237][4400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.303 (2.858) Prec@1 74.22 (76.96) Prec@5 87.50 (91.79) + train[2018-10-25-07:02:56] Epoch: [237][4600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.923 (2.858) Prec@1 78.91 (76.95) Prec@5 92.97 (91.80) + train[2018-10-25-07:04:42] Epoch: [237][4800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.758 (2.858) Prec@1 77.34 (76.96) Prec@5 92.97 (91.80) + train[2018-10-25-07:06:29] Epoch: [237][5000/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 3.019 (2.857) Prec@1 72.66 (76.97) Prec@5 88.28 (91.80) + train[2018-10-25-07:08:16] Epoch: [237][5200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.878 (2.857) Prec@1 77.34 (76.99) Prec@5 92.19 (91.81) + train[2018-10-25-07:10:03] Epoch: [237][5400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.969 (2.857) Prec@1 72.66 (76.98) Prec@5 91.41 (91.81) + train[2018-10-25-07:11:51] Epoch: [237][5600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.410 (2.857) Prec@1 86.72 (76.99) Prec@5 96.09 (91.81) + train[2018-10-25-07:13:38] Epoch: [237][5800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.532 (2.857) Prec@1 83.59 (76.99) Prec@5 94.53 (91.80) + train[2018-10-25-07:15:25] Epoch: [237][6000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.523 (2.857) Prec@1 82.03 (76.99) Prec@5 95.31 (91.81) + train[2018-10-25-07:17:12] Epoch: [237][6200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.817 (2.857) Prec@1 75.78 (76.99) Prec@5 92.19 (91.81) + train[2018-10-25-07:19:00] Epoch: [237][6400/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.783 (2.857) Prec@1 77.34 (76.99) Prec@5 92.97 (91.80) + train[2018-10-25-07:20:47] Epoch: [237][6600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.637 (2.857) Prec@1 80.47 (76.99) Prec@5 92.97 (91.80) + train[2018-10-25-07:22:34] Epoch: [237][6800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.983 (2.857) Prec@1 76.56 (77.01) Prec@5 88.28 (91.80) + train[2018-10-25-07:24:21] Epoch: [237][7000/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.790 (2.857) Prec@1 78.91 (77.00) Prec@5 92.19 (91.80) + train[2018-10-25-07:26:08] Epoch: [237][7200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.024 (2.858) Prec@1 71.88 (77.00) Prec@5 88.28 (91.80) + train[2018-10-25-07:27:56] Epoch: [237][7400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.827 (2.858) Prec@1 78.91 (77.00) Prec@5 91.41 (91.80) + train[2018-10-25-07:29:45] Epoch: [237][7600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.768 (2.858) Prec@1 75.00 (76.99) Prec@5 96.09 (91.80) + train[2018-10-25-07:31:33] Epoch: [237][7800/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 3.014 (2.858) Prec@1 71.88 (76.98) Prec@5 89.06 (91.80) + train[2018-10-25-07:33:20] Epoch: [237][8000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.906 (2.859) Prec@1 78.91 (76.98) Prec@5 90.62 (91.80) + train[2018-10-25-07:35:06] Epoch: [237][8200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.621 (2.858) Prec@1 81.25 (76.99) Prec@5 94.53 (91.80) + train[2018-10-25-07:36:54] Epoch: [237][8400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.926 (2.858) Prec@1 76.56 (77.00) Prec@5 90.62 (91.81) + train[2018-10-25-07:38:42] Epoch: [237][8600/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.781 (2.857) Prec@1 76.56 (77.00) Prec@5 95.31 (91.82) + train[2018-10-25-07:40:29] Epoch: [237][8800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.664 (2.858) Prec@1 80.47 (77.00) Prec@5 90.62 (91.81) + train[2018-10-25-07:42:16] Epoch: [237][9000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.604 (2.857) Prec@1 80.47 (77.01) Prec@5 95.31 (91.81) + train[2018-10-25-07:44:03] Epoch: [237][9200/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.873 (2.858) Prec@1 78.91 (77.00) Prec@5 93.75 (91.81) + train[2018-10-25-07:45:50] Epoch: [237][9400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.774 (2.858) Prec@1 78.12 (77.00) Prec@5 92.19 (91.81) + train[2018-10-25-07:47:37] Epoch: [237][9600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.816 (2.857) Prec@1 77.34 (77.00) Prec@5 90.62 (91.81) + train[2018-10-25-07:49:25] Epoch: [237][9800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.666 (2.857) Prec@1 81.25 (77.00) Prec@5 92.97 (91.81) + train[2018-10-25-07:51:12] Epoch: [237][10000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.912 (2.857) Prec@1 75.00 (77.00) Prec@5 91.41 (91.81) + train[2018-10-25-07:51:16] Epoch: [237][10009/10010] Time 0.19 (0.54) Data 0.00 (0.00) Loss 3.539 (2.857) Prec@1 66.67 (77.00) Prec@5 86.67 (91.81) +[2018-10-25-07:51:16] **train** Prec@1 77.00 Prec@5 91.81 Error@1 23.00 Error@5 8.19 Loss:2.857 + test [2018-10-25-07:51:21] Epoch: [237][000/391] Time 4.74 (4.74) Data 4.61 (4.61) Loss 0.558 (0.558) Prec@1 92.19 (92.19) Prec@5 98.44 (98.44) + test [2018-10-25-07:51:50] Epoch: [237][200/391] Time 0.12 (0.17) Data 0.00 (0.04) Loss 1.168 (0.986) Prec@1 67.97 (77.46) Prec@5 91.41 (93.70) + test [2018-10-25-07:52:16] Epoch: [237][390/391] Time 0.08 (0.15) Data 0.00 (0.02) Loss 2.099 (1.156) Prec@1 48.75 (73.91) Prec@5 83.75 (91.41) +[2018-10-25-07:52:16] **test** Prec@1 73.91 Prec@5 91.41 Error@1 26.09 Error@5 8.59 Loss:1.156 +----> Best Accuracy : Acc@1=74.00, Acc@5=91.49, Error@1=26.00, Error@5=8.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-25-07:52:16] [Epoch=238/250] [Need: 18:07:02] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-25-07:52:20] Epoch: [238][000/10010] Time 4.43 (4.43) Data 3.80 (3.80) Loss 2.986 (2.986) Prec@1 71.88 (71.88) Prec@5 89.06 (89.06) + train[2018-10-25-07:54:09] Epoch: [238][200/10010] Time 0.50 (0.56) Data 0.00 (0.02) Loss 2.840 (2.864) Prec@1 78.12 (76.72) Prec@5 92.19 (91.81) + train[2018-10-25-07:55:56] Epoch: [238][400/10010] Time 0.51 (0.55) Data 0.00 (0.01) Loss 2.667 (2.853) Prec@1 82.03 (77.04) Prec@5 93.75 (91.89) + train[2018-10-25-07:57:44] Epoch: [238][600/10010] Time 0.51 (0.55) Data 0.00 (0.01) Loss 2.913 (2.858) Prec@1 73.44 (76.95) Prec@5 91.41 (91.84) + train[2018-10-25-07:59:32] Epoch: [238][800/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.940 (2.861) Prec@1 74.22 (76.92) Prec@5 90.62 (91.76) + train[2018-10-25-08:01:21] Epoch: [238][1000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.863 (2.861) Prec@1 75.00 (76.93) Prec@5 90.62 (91.75) + train[2018-10-25-08:03:09] Epoch: [238][1200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.777 (2.859) Prec@1 75.00 (76.92) Prec@5 94.53 (91.78) + train[2018-10-25-08:04:57] Epoch: [238][1400/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 3.159 (2.860) Prec@1 71.88 (76.87) Prec@5 85.94 (91.77) + train[2018-10-25-08:06:45] Epoch: [238][1600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.029 (2.861) Prec@1 77.34 (76.86) Prec@5 91.41 (91.77) + train[2018-10-25-08:08:34] Epoch: [238][1800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.900 (2.862) Prec@1 71.88 (76.83) Prec@5 92.19 (91.75) + train[2018-10-25-08:10:21] Epoch: [238][2000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.770 (2.861) Prec@1 76.56 (76.85) Prec@5 92.97 (91.75) + train[2018-10-25-08:12:08] Epoch: [238][2200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 3.082 (2.863) Prec@1 73.44 (76.82) Prec@5 89.84 (91.73) + train[2018-10-25-08:13:56] Epoch: [238][2400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.110 (2.863) Prec@1 70.31 (76.85) Prec@5 90.62 (91.76) + train[2018-10-25-08:15:42] Epoch: [238][2600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.739 (2.863) Prec@1 81.25 (76.84) Prec@5 92.19 (91.75) + train[2018-10-25-08:17:28] Epoch: [238][2800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.902 (2.862) Prec@1 75.00 (76.86) Prec@5 90.62 (91.78) + train[2018-10-25-08:19:15] Epoch: [238][3000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.005 (2.862) Prec@1 74.22 (76.88) Prec@5 90.62 (91.79) + train[2018-10-25-08:21:02] Epoch: [238][3200/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.720 (2.860) Prec@1 82.03 (76.91) Prec@5 93.75 (91.80) + train[2018-10-25-08:22:50] Epoch: [238][3400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.723 (2.860) Prec@1 78.91 (76.93) Prec@5 95.31 (91.80) + train[2018-10-25-08:24:37] Epoch: [238][3600/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.899 (2.860) Prec@1 75.78 (76.92) Prec@5 89.84 (91.79) + train[2018-10-25-08:26:24] Epoch: [238][3800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.690 (2.860) Prec@1 80.47 (76.93) Prec@5 93.75 (91.80) + train[2018-10-25-08:28:12] Epoch: [238][4000/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.159 (2.860) Prec@1 72.66 (76.93) Prec@5 86.72 (91.79) + train[2018-10-25-08:29:59] Epoch: [238][4200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.224 (2.859) Prec@1 73.44 (76.94) Prec@5 88.28 (91.79) + train[2018-10-25-08:31:48] Epoch: [238][4400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.650 (2.859) Prec@1 80.47 (76.95) Prec@5 92.97 (91.79) + train[2018-10-25-08:33:36] Epoch: [238][4600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.956 (2.859) Prec@1 73.44 (76.94) Prec@5 90.62 (91.79) + train[2018-10-25-08:35:24] Epoch: [238][4800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.770 (2.860) Prec@1 77.34 (76.93) Prec@5 92.97 (91.78) + train[2018-10-25-08:37:11] Epoch: [238][5000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.556 (2.860) Prec@1 82.81 (76.92) Prec@5 94.53 (91.77) + train[2018-10-25-08:38:58] Epoch: [238][5200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.652 (2.861) Prec@1 82.81 (76.91) Prec@5 97.66 (91.77) + train[2018-10-25-08:40:45] Epoch: [238][5400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.182 (2.861) Prec@1 69.53 (76.92) Prec@5 86.72 (91.78) + train[2018-10-25-08:42:32] Epoch: [238][5600/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.689 (2.861) Prec@1 81.25 (76.91) Prec@5 92.19 (91.78) + train[2018-10-25-08:44:20] Epoch: [238][5800/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.872 (2.860) Prec@1 72.66 (76.91) Prec@5 90.62 (91.78) + train[2018-10-25-08:46:08] Epoch: [238][6000/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.055 (2.860) Prec@1 70.31 (76.92) Prec@5 91.41 (91.79) + train[2018-10-25-08:47:56] Epoch: [238][6200/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 3.106 (2.859) Prec@1 76.56 (76.93) Prec@5 88.28 (91.79) + train[2018-10-25-08:49:45] Epoch: [238][6400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.766 (2.859) Prec@1 78.12 (76.93) Prec@5 91.41 (91.79) + train[2018-10-25-08:51:32] Epoch: [238][6600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.205 (2.860) Prec@1 74.22 (76.92) Prec@5 88.28 (91.77) + train[2018-10-25-08:53:19] Epoch: [238][6800/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.823 (2.859) Prec@1 79.69 (76.94) Prec@5 92.19 (91.78) + train[2018-10-25-08:55:08] Epoch: [238][7000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.042 (2.859) Prec@1 74.22 (76.93) Prec@5 91.41 (91.78) + train[2018-10-25-08:56:54] Epoch: [238][7200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.981 (2.859) Prec@1 75.00 (76.94) Prec@5 89.84 (91.78) + train[2018-10-25-08:58:42] Epoch: [238][7400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.823 (2.859) Prec@1 78.91 (76.94) Prec@5 91.41 (91.78) + train[2018-10-25-09:00:30] Epoch: [238][7600/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 3.008 (2.859) Prec@1 71.88 (76.94) Prec@5 91.41 (91.78) + train[2018-10-25-09:02:17] Epoch: [238][7800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.425 (2.860) Prec@1 85.16 (76.94) Prec@5 96.88 (91.78) + train[2018-10-25-09:04:05] Epoch: [238][8000/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.586 (2.859) Prec@1 79.69 (76.94) Prec@5 91.41 (91.79) + train[2018-10-25-09:05:54] Epoch: [238][8200/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.756 (2.859) Prec@1 80.47 (76.95) Prec@5 91.41 (91.79) + train[2018-10-25-09:07:43] Epoch: [238][8400/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.676 (2.859) Prec@1 80.47 (76.95) Prec@5 93.75 (91.79) + train[2018-10-25-09:09:31] Epoch: [238][8600/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.849 (2.858) Prec@1 75.00 (76.95) Prec@5 92.19 (91.80) + train[2018-10-25-09:11:19] Epoch: [238][8800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.737 (2.859) Prec@1 78.91 (76.94) Prec@5 93.75 (91.79) + train[2018-10-25-09:13:08] Epoch: [238][9000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.679 (2.859) Prec@1 76.56 (76.94) Prec@5 96.09 (91.80) + train[2018-10-25-09:14:55] Epoch: [238][9200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.779 (2.858) Prec@1 78.12 (76.95) Prec@5 92.19 (91.80) + train[2018-10-25-09:16:43] Epoch: [238][9400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.918 (2.858) Prec@1 75.78 (76.95) Prec@5 94.53 (91.80) + train[2018-10-25-09:18:31] Epoch: [238][9600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.821 (2.858) Prec@1 78.12 (76.95) Prec@5 92.19 (91.80) + train[2018-10-25-09:20:18] Epoch: [238][9800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.939 (2.859) Prec@1 77.34 (76.94) Prec@5 92.19 (91.80) + train[2018-10-25-09:22:07] Epoch: [238][10000/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.704 (2.859) Prec@1 80.47 (76.93) Prec@5 95.31 (91.80) + train[2018-10-25-09:22:11] Epoch: [238][10009/10010] Time 0.25 (0.54) Data 0.00 (0.00) Loss 2.803 (2.859) Prec@1 80.00 (76.94) Prec@5 93.33 (91.80) +[2018-10-25-09:22:11] **train** Prec@1 76.94 Prec@5 91.80 Error@1 23.06 Error@5 8.20 Loss:2.859 + test [2018-10-25-09:22:16] Epoch: [238][000/391] Time 4.20 (4.20) Data 4.06 (4.06) Loss 0.535 (0.535) Prec@1 92.97 (92.97) Prec@5 97.66 (97.66) + test [2018-10-25-09:22:43] Epoch: [238][200/391] Time 0.14 (0.16) Data 0.00 (0.03) Loss 1.185 (0.978) Prec@1 68.75 (77.62) Prec@5 91.41 (93.68) + test [2018-10-25-09:23:08] Epoch: [238][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.100 (1.147) Prec@1 46.25 (73.95) Prec@5 82.50 (91.47) +[2018-10-25-09:23:08] **test** Prec@1 73.95 Prec@5 91.47 Error@1 26.05 Error@5 8.53 Loss:1.147 +----> Best Accuracy : Acc@1=74.00, Acc@5=91.49, Error@1=26.00, Error@5=8.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-25-09:23:08] [Epoch=239/250] [Need: 16:39:36] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-25-09:23:14] Epoch: [239][000/10010] Time 5.40 (5.40) Data 4.81 (4.81) Loss 2.795 (2.795) Prec@1 76.56 (76.56) Prec@5 92.97 (92.97) + train[2018-10-25-09:25:01] Epoch: [239][200/10010] Time 0.52 (0.56) Data 0.00 (0.03) Loss 2.847 (2.875) Prec@1 77.34 (76.43) Prec@5 87.50 (91.75) + train[2018-10-25-09:26:46] Epoch: [239][400/10010] Time 0.57 (0.54) Data 0.00 (0.01) Loss 2.784 (2.861) Prec@1 81.25 (76.66) Prec@5 89.84 (91.74) + train[2018-10-25-09:28:32] Epoch: [239][600/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.876 (2.856) Prec@1 75.78 (76.87) Prec@5 90.62 (91.78) + train[2018-10-25-09:30:19] Epoch: [239][800/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 3.318 (2.861) Prec@1 71.09 (76.79) Prec@5 88.28 (91.74) + train[2018-10-25-09:32:06] Epoch: [239][1000/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 3.079 (2.862) Prec@1 74.22 (76.80) Prec@5 92.19 (91.72) + train[2018-10-25-09:33:52] Epoch: [239][1200/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.841 (2.863) Prec@1 80.47 (76.77) Prec@5 92.97 (91.72) + train[2018-10-25-09:35:39] Epoch: [239][1400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.841 (2.861) Prec@1 78.91 (76.82) Prec@5 92.97 (91.74) + train[2018-10-25-09:37:27] Epoch: [239][1600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.524 (2.860) Prec@1 84.38 (76.83) Prec@5 93.75 (91.75) + train[2018-10-25-09:39:13] Epoch: [239][1800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.848 (2.862) Prec@1 78.12 (76.80) Prec@5 89.06 (91.73) + train[2018-10-25-09:41:00] Epoch: [239][2000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 3.053 (2.863) Prec@1 71.88 (76.77) Prec@5 91.41 (91.73) + train[2018-10-25-09:42:47] Epoch: [239][2200/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 3.026 (2.862) Prec@1 73.44 (76.82) Prec@5 88.28 (91.73) + train[2018-10-25-09:44:34] Epoch: [239][2400/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.749 (2.862) Prec@1 79.69 (76.86) Prec@5 93.75 (91.72) + train[2018-10-25-09:46:20] Epoch: [239][2600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.009 (2.862) Prec@1 77.34 (76.86) Prec@5 89.06 (91.72) + train[2018-10-25-09:48:07] Epoch: [239][2800/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 2.879 (2.862) Prec@1 81.25 (76.87) Prec@5 91.41 (91.71) + train[2018-10-25-09:49:54] Epoch: [239][3000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.952 (2.862) Prec@1 74.22 (76.87) Prec@5 89.84 (91.71) + train[2018-10-25-09:51:41] Epoch: [239][3200/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 2.449 (2.861) Prec@1 83.59 (76.89) Prec@5 98.44 (91.74) + train[2018-10-25-09:53:29] Epoch: [239][3400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.692 (2.862) Prec@1 82.81 (76.87) Prec@5 92.97 (91.72) + train[2018-10-25-09:55:18] Epoch: [239][3600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.680 (2.861) Prec@1 85.16 (76.90) Prec@5 91.41 (91.74) + train[2018-10-25-09:57:04] Epoch: [239][3800/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.825 (2.860) Prec@1 76.56 (76.92) Prec@5 92.19 (91.75) + train[2018-10-25-09:58:51] Epoch: [239][4000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.674 (2.859) Prec@1 79.69 (76.93) Prec@5 93.75 (91.75) + train[2018-10-25-10:00:38] Epoch: [239][4200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.929 (2.858) Prec@1 74.22 (76.94) Prec@5 90.62 (91.77) + train[2018-10-25-10:02:24] Epoch: [239][4400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.102 (2.859) Prec@1 71.88 (76.91) Prec@5 90.62 (91.76) + train[2018-10-25-10:04:10] Epoch: [239][4600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.620 (2.859) Prec@1 81.25 (76.90) Prec@5 92.97 (91.76) + train[2018-10-25-10:05:57] Epoch: [239][4800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.975 (2.858) Prec@1 78.12 (76.92) Prec@5 90.62 (91.78) + train[2018-10-25-10:07:44] Epoch: [239][5000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.172 (2.858) Prec@1 71.88 (76.93) Prec@5 86.72 (91.77) + train[2018-10-25-10:09:31] Epoch: [239][5200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.024 (2.857) Prec@1 71.88 (76.94) Prec@5 91.41 (91.78) + train[2018-10-25-10:11:18] Epoch: [239][5400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.844 (2.857) Prec@1 77.34 (76.95) Prec@5 90.62 (91.78) + train[2018-10-25-10:13:05] Epoch: [239][5600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.676 (2.857) Prec@1 77.34 (76.94) Prec@5 92.19 (91.79) + train[2018-10-25-10:14:52] Epoch: [239][5800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.650 (2.857) Prec@1 83.59 (76.94) Prec@5 94.53 (91.79) + train[2018-10-25-10:16:37] Epoch: [239][6000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.768 (2.857) Prec@1 77.34 (76.94) Prec@5 92.97 (91.79) + train[2018-10-25-10:18:25] Epoch: [239][6200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.879 (2.856) Prec@1 74.22 (76.96) Prec@5 90.62 (91.80) + train[2018-10-25-10:20:10] Epoch: [239][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.973 (2.856) Prec@1 75.78 (76.96) Prec@5 92.19 (91.80) + train[2018-10-25-10:21:57] Epoch: [239][6600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.130 (2.857) Prec@1 72.66 (76.97) Prec@5 88.28 (91.80) + train[2018-10-25-10:23:43] Epoch: [239][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.088 (2.857) Prec@1 71.88 (76.96) Prec@5 91.41 (91.80) + train[2018-10-25-10:25:30] Epoch: [239][7000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.788 (2.857) Prec@1 78.91 (76.96) Prec@5 92.97 (91.80) + train[2018-10-25-10:27:17] Epoch: [239][7200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.781 (2.857) Prec@1 76.56 (76.96) Prec@5 92.19 (91.80) + train[2018-10-25-10:29:04] Epoch: [239][7400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.825 (2.857) Prec@1 80.47 (76.97) Prec@5 92.19 (91.80) + train[2018-10-25-10:30:50] Epoch: [239][7600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.779 (2.857) Prec@1 82.03 (76.96) Prec@5 92.97 (91.79) + train[2018-10-25-10:32:38] Epoch: [239][7800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.546 (2.858) Prec@1 82.81 (76.95) Prec@5 96.09 (91.79) + train[2018-10-25-10:34:24] Epoch: [239][8000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.891 (2.858) Prec@1 77.34 (76.96) Prec@5 91.41 (91.78) + train[2018-10-25-10:36:10] Epoch: [239][8200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.918 (2.857) Prec@1 73.44 (76.97) Prec@5 91.41 (91.78) + train[2018-10-25-10:37:56] Epoch: [239][8400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.908 (2.857) Prec@1 75.78 (76.98) Prec@5 94.53 (91.79) + train[2018-10-25-10:39:43] Epoch: [239][8600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.864 (2.857) Prec@1 75.00 (76.98) Prec@5 89.84 (91.80) + train[2018-10-25-10:41:30] Epoch: [239][8800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.957 (2.857) Prec@1 75.00 (76.98) Prec@5 90.62 (91.79) + train[2018-10-25-10:43:17] Epoch: [239][9000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.854 (2.857) Prec@1 76.56 (76.98) Prec@5 92.19 (91.80) + train[2018-10-25-10:45:05] Epoch: [239][9200/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 2.971 (2.857) Prec@1 74.22 (76.99) Prec@5 94.53 (91.80) + train[2018-10-25-10:46:51] Epoch: [239][9400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.021 (2.857) Prec@1 75.00 (76.99) Prec@5 89.84 (91.80) + train[2018-10-25-10:48:37] Epoch: [239][9600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.850 (2.856) Prec@1 76.56 (76.99) Prec@5 91.41 (91.80) + train[2018-10-25-10:50:22] Epoch: [239][9800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.852 (2.857) Prec@1 82.03 (76.99) Prec@5 90.62 (91.80) + train[2018-10-25-10:52:10] Epoch: [239][10000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.827 (2.857) Prec@1 77.34 (76.98) Prec@5 91.41 (91.80) + train[2018-10-25-10:52:14] Epoch: [239][10009/10010] Time 0.20 (0.53) Data 0.00 (0.00) Loss 3.228 (2.857) Prec@1 60.00 (76.98) Prec@5 80.00 (91.80) +[2018-10-25-10:52:14] **train** Prec@1 76.98 Prec@5 91.80 Error@1 23.02 Error@5 8.20 Loss:2.857 + test [2018-10-25-10:52:18] Epoch: [239][000/391] Time 3.84 (3.84) Data 3.68 (3.68) Loss 0.576 (0.576) Prec@1 92.97 (92.97) Prec@5 97.66 (97.66) + test [2018-10-25-10:52:47] Epoch: [239][200/391] Time 0.13 (0.16) Data 0.00 (0.03) Loss 1.193 (0.995) Prec@1 67.97 (77.35) Prec@5 92.19 (93.61) + test [2018-10-25-10:53:13] Epoch: [239][390/391] Time 0.09 (0.15) Data 0.00 (0.02) Loss 2.047 (1.161) Prec@1 50.00 (73.90) Prec@5 83.75 (91.47) +[2018-10-25-10:53:13] **test** Prec@1 73.90 Prec@5 91.47 Error@1 26.10 Error@5 8.53 Loss:1.161 +----> Best Accuracy : Acc@1=74.00, Acc@5=91.49, Error@1=26.00, Error@5=8.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-25-10:53:13] [Epoch=240/250] [Need: 15:00:45] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-25-10:53:17] Epoch: [240][000/10010] Time 4.56 (4.56) Data 3.96 (3.96) Loss 2.857 (2.857) Prec@1 78.12 (78.12) Prec@5 91.41 (91.41) + train[2018-10-25-10:55:03] Epoch: [240][200/10010] Time 0.51 (0.55) Data 0.00 (0.02) Loss 3.051 (2.858) Prec@1 75.78 (76.94) Prec@5 91.41 (91.74) + train[2018-10-25-10:56:49] Epoch: [240][400/10010] Time 0.58 (0.54) Data 0.00 (0.01) Loss 2.654 (2.860) Prec@1 80.47 (76.90) Prec@5 94.53 (91.77) + train[2018-10-25-10:58:34] Epoch: [240][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.027 (2.857) Prec@1 70.31 (76.95) Prec@5 88.28 (91.84) + train[2018-10-25-11:00:20] Epoch: [240][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 2.919 (2.852) Prec@1 75.78 (77.05) Prec@5 89.06 (91.87) + train[2018-10-25-11:02:06] Epoch: [240][1000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.765 (2.854) Prec@1 78.91 (77.05) Prec@5 92.19 (91.83) + train[2018-10-25-11:03:51] Epoch: [240][1200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.532 (2.853) Prec@1 84.38 (77.05) Prec@5 95.31 (91.85) + train[2018-10-25-11:05:38] Epoch: [240][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.943 (2.853) Prec@1 76.56 (77.06) Prec@5 92.97 (91.86) + train[2018-10-25-11:07:25] Epoch: [240][1600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.819 (2.855) Prec@1 72.66 (77.05) Prec@5 93.75 (91.84) + train[2018-10-25-11:09:12] Epoch: [240][1800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.995 (2.854) Prec@1 73.44 (77.06) Prec@5 92.97 (91.85) + train[2018-10-25-11:10:58] Epoch: [240][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.503 (2.853) Prec@1 85.16 (77.06) Prec@5 96.88 (91.85) + train[2018-10-25-11:12:44] Epoch: [240][2200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.981 (2.853) Prec@1 78.91 (77.07) Prec@5 86.72 (91.84) + train[2018-10-25-11:14:31] Epoch: [240][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.990 (2.854) Prec@1 75.00 (77.07) Prec@5 89.84 (91.82) + train[2018-10-25-11:16:17] Epoch: [240][2600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.837 (2.853) Prec@1 78.12 (77.08) Prec@5 92.97 (91.83) + train[2018-10-25-11:18:03] Epoch: [240][2800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.082 (2.853) Prec@1 75.78 (77.08) Prec@5 89.06 (91.83) + train[2018-10-25-11:19:51] Epoch: [240][3000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.924 (2.852) Prec@1 76.56 (77.12) Prec@5 89.84 (91.85) + train[2018-10-25-11:21:36] Epoch: [240][3200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.728 (2.854) Prec@1 80.47 (77.08) Prec@5 93.75 (91.83) + train[2018-10-25-11:23:23] Epoch: [240][3400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.963 (2.854) Prec@1 75.78 (77.07) Prec@5 92.19 (91.82) + train[2018-10-25-11:25:09] Epoch: [240][3600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.357 (2.855) Prec@1 84.38 (77.06) Prec@5 96.09 (91.81) + train[2018-10-25-11:26:56] Epoch: [240][3800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.861 (2.855) Prec@1 76.56 (77.06) Prec@5 91.41 (91.81) + train[2018-10-25-11:28:43] Epoch: [240][4000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.623 (2.855) Prec@1 83.59 (77.05) Prec@5 93.75 (91.82) + train[2018-10-25-11:30:31] Epoch: [240][4200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.682 (2.856) Prec@1 82.81 (77.04) Prec@5 94.53 (91.82) + train[2018-10-25-11:32:18] Epoch: [240][4400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.637 (2.854) Prec@1 75.78 (77.06) Prec@5 93.75 (91.83) + train[2018-10-25-11:34:04] Epoch: [240][4600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.783 (2.856) Prec@1 77.34 (77.04) Prec@5 92.19 (91.81) + train[2018-10-25-11:35:51] Epoch: [240][4800/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.950 (2.855) Prec@1 76.56 (77.05) Prec@5 90.62 (91.82) + train[2018-10-25-11:37:38] Epoch: [240][5000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.587 (2.855) Prec@1 83.59 (77.04) Prec@5 92.97 (91.83) + train[2018-10-25-11:39:24] Epoch: [240][5200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.779 (2.856) Prec@1 77.34 (77.03) Prec@5 92.19 (91.82) + train[2018-10-25-11:41:12] Epoch: [240][5400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.879 (2.856) Prec@1 74.22 (77.02) Prec@5 95.31 (91.83) + train[2018-10-25-11:42:59] Epoch: [240][5600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.863 (2.856) Prec@1 77.34 (77.03) Prec@5 93.75 (91.83) + train[2018-10-25-11:44:47] Epoch: [240][5800/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.989 (2.856) Prec@1 75.78 (77.03) Prec@5 87.50 (91.83) + train[2018-10-25-11:46:34] Epoch: [240][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.082 (2.856) Prec@1 74.22 (77.03) Prec@5 86.72 (91.83) + train[2018-10-25-11:48:21] Epoch: [240][6200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.591 (2.856) Prec@1 80.47 (77.03) Prec@5 92.19 (91.83) + train[2018-10-25-11:50:08] Epoch: [240][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.701 (2.856) Prec@1 80.47 (77.02) Prec@5 93.75 (91.83) + train[2018-10-25-11:51:53] Epoch: [240][6600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.703 (2.856) Prec@1 80.47 (77.02) Prec@5 92.19 (91.83) + train[2018-10-25-11:53:39] Epoch: [240][6800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.588 (2.856) Prec@1 83.59 (77.02) Prec@5 93.75 (91.83) + train[2018-10-25-11:55:24] Epoch: [240][7000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.631 (2.856) Prec@1 81.25 (77.02) Prec@5 96.09 (91.83) + train[2018-10-25-11:57:10] Epoch: [240][7200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.087 (2.856) Prec@1 73.44 (77.01) Prec@5 86.72 (91.83) + train[2018-10-25-11:58:57] Epoch: [240][7400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.175 (2.857) Prec@1 71.09 (76.99) Prec@5 87.50 (91.83) + train[2018-10-25-12:00:43] Epoch: [240][7600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.915 (2.858) Prec@1 81.25 (76.98) Prec@5 90.62 (91.81) + train[2018-10-25-12:02:28] Epoch: [240][7800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.702 (2.858) Prec@1 80.47 (76.98) Prec@5 94.53 (91.81) + train[2018-10-25-12:04:14] Epoch: [240][8000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.688 (2.858) Prec@1 82.03 (76.98) Prec@5 93.75 (91.81) + train[2018-10-25-12:06:00] Epoch: [240][8200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.957 (2.857) Prec@1 74.22 (76.99) Prec@5 90.62 (91.81) + train[2018-10-25-12:07:45] Epoch: [240][8400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.139 (2.857) Prec@1 67.19 (76.99) Prec@5 89.06 (91.82) + train[2018-10-25-12:09:31] Epoch: [240][8600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.888 (2.857) Prec@1 75.78 (77.00) Prec@5 92.19 (91.82) + train[2018-10-25-12:11:16] Epoch: [240][8800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.861 (2.857) Prec@1 78.91 (77.00) Prec@5 91.41 (91.82) + train[2018-10-25-12:13:03] Epoch: [240][9000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.917 (2.857) Prec@1 75.00 (77.00) Prec@5 90.62 (91.82) + train[2018-10-25-12:14:49] Epoch: [240][9200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.835 (2.857) Prec@1 76.56 (77.00) Prec@5 92.97 (91.82) + train[2018-10-25-12:16:35] Epoch: [240][9400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.107 (2.857) Prec@1 71.09 (77.00) Prec@5 89.84 (91.82) + train[2018-10-25-12:18:22] Epoch: [240][9600/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.897 (2.857) Prec@1 78.91 (77.00) Prec@5 92.19 (91.82) + train[2018-10-25-12:20:10] Epoch: [240][9800/10010] Time 0.66 (0.53) Data 0.00 (0.00) Loss 2.949 (2.857) Prec@1 77.34 (77.01) Prec@5 92.97 (91.83) + train[2018-10-25-12:21:57] Epoch: [240][10000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.767 (2.857) Prec@1 78.12 (77.00) Prec@5 95.31 (91.83) + train[2018-10-25-12:22:01] Epoch: [240][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 3.261 (2.857) Prec@1 73.33 (77.00) Prec@5 93.33 (91.83) +[2018-10-25-12:22:01] **train** Prec@1 77.00 Prec@5 91.83 Error@1 23.00 Error@5 8.17 Loss:2.857 + test [2018-10-25-12:22:06] Epoch: [240][000/391] Time 4.32 (4.32) Data 4.18 (4.18) Loss 0.541 (0.541) Prec@1 92.97 (92.97) Prec@5 98.44 (98.44) + test [2018-10-25-12:22:35] Epoch: [240][200/391] Time 0.14 (0.17) Data 0.00 (0.04) Loss 1.170 (0.988) Prec@1 66.41 (77.47) Prec@5 92.97 (93.69) + test [2018-10-25-12:23:02] Epoch: [240][390/391] Time 0.09 (0.16) Data 0.00 (0.03) Loss 2.112 (1.160) Prec@1 47.50 (73.85) Prec@5 83.75 (91.41) +[2018-10-25-12:23:03] **test** Prec@1 73.85 Prec@5 91.41 Error@1 26.15 Error@5 8.59 Loss:1.160 +----> Best Accuracy : Acc@1=74.00, Acc@5=91.49, Error@1=26.00, Error@5=8.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-25-12:23:03] [Epoch=241/250] [Need: 13:28:27] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-25-12:23:07] Epoch: [241][000/10010] Time 4.59 (4.59) Data 4.01 (4.01) Loss 2.880 (2.880) Prec@1 77.34 (77.34) Prec@5 92.19 (92.19) + train[2018-10-25-12:24:55] Epoch: [241][200/10010] Time 0.51 (0.56) Data 0.00 (0.02) Loss 2.754 (2.883) Prec@1 75.00 (76.52) Prec@5 92.19 (91.74) + train[2018-10-25-12:26:44] Epoch: [241][400/10010] Time 0.53 (0.55) Data 0.00 (0.01) Loss 2.737 (2.864) Prec@1 78.12 (76.86) Prec@5 94.53 (91.81) + train[2018-10-25-12:28:33] Epoch: [241][600/10010] Time 0.56 (0.55) Data 0.00 (0.01) Loss 3.047 (2.859) Prec@1 73.44 (77.06) Prec@5 91.41 (91.86) + train[2018-10-25-12:30:21] Epoch: [241][800/10010] Time 0.55 (0.55) Data 0.00 (0.01) Loss 2.800 (2.861) Prec@1 81.25 (77.05) Prec@5 92.97 (91.79) + train[2018-10-25-12:32:09] Epoch: [241][1000/10010] Time 0.55 (0.55) Data 0.00 (0.00) Loss 2.555 (2.858) Prec@1 83.59 (77.10) Prec@5 94.53 (91.84) + train[2018-10-25-12:33:58] Epoch: [241][1200/10010] Time 0.53 (0.55) Data 0.00 (0.00) Loss 2.414 (2.859) Prec@1 82.81 (77.09) Prec@5 97.66 (91.81) + train[2018-10-25-12:35:46] Epoch: [241][1400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.642 (2.857) Prec@1 81.25 (77.12) Prec@5 94.53 (91.83) + train[2018-10-25-12:37:34] Epoch: [241][1600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.585 (2.857) Prec@1 79.69 (77.10) Prec@5 95.31 (91.82) + train[2018-10-25-12:39:21] Epoch: [241][1800/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.728 (2.857) Prec@1 82.81 (77.07) Prec@5 92.19 (91.81) + train[2018-10-25-12:41:09] Epoch: [241][2000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 3.041 (2.859) Prec@1 75.00 (77.03) Prec@5 89.84 (91.79) + train[2018-10-25-12:42:57] Epoch: [241][2200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.857 (2.860) Prec@1 75.78 (77.02) Prec@5 92.19 (91.78) + train[2018-10-25-12:44:45] Epoch: [241][2400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.864 (2.859) Prec@1 74.22 (77.05) Prec@5 92.19 (91.79) + train[2018-10-25-12:46:32] Epoch: [241][2600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.661 (2.858) Prec@1 81.25 (77.07) Prec@5 92.19 (91.79) + train[2018-10-25-12:48:20] Epoch: [241][2800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.861 (2.857) Prec@1 74.22 (77.10) Prec@5 93.75 (91.79) + train[2018-10-25-12:50:08] Epoch: [241][3000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.798 (2.857) Prec@1 75.78 (77.11) Prec@5 92.19 (91.79) + train[2018-10-25-12:51:57] Epoch: [241][3200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.802 (2.858) Prec@1 80.47 (77.10) Prec@5 92.19 (91.79) + train[2018-10-25-12:53:46] Epoch: [241][3400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.795 (2.857) Prec@1 77.34 (77.09) Prec@5 90.62 (91.80) + train[2018-10-25-12:55:34] Epoch: [241][3600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.588 (2.857) Prec@1 82.81 (77.10) Prec@5 94.53 (91.80) + train[2018-10-25-12:57:23] Epoch: [241][3800/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 3.114 (2.856) Prec@1 71.88 (77.12) Prec@5 90.62 (91.82) + train[2018-10-25-12:59:12] Epoch: [241][4000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.900 (2.856) Prec@1 79.69 (77.11) Prec@5 91.41 (91.82) + train[2018-10-25-13:01:00] Epoch: [241][4200/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 3.139 (2.857) Prec@1 72.66 (77.09) Prec@5 89.84 (91.82) + train[2018-10-25-13:02:49] Epoch: [241][4400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.928 (2.856) Prec@1 75.78 (77.09) Prec@5 90.62 (91.82) + train[2018-10-25-13:04:37] Epoch: [241][4600/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.717 (2.856) Prec@1 79.69 (77.09) Prec@5 93.75 (91.83) + train[2018-10-25-13:06:25] Epoch: [241][4800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.732 (2.857) Prec@1 77.34 (77.08) Prec@5 94.53 (91.82) + train[2018-10-25-13:08:14] Epoch: [241][5000/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.484 (2.856) Prec@1 83.59 (77.08) Prec@5 96.09 (91.82) + train[2018-10-25-13:10:02] Epoch: [241][5200/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.924 (2.856) Prec@1 76.56 (77.08) Prec@5 92.97 (91.82) + train[2018-10-25-13:11:51] Epoch: [241][5400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.894 (2.855) Prec@1 76.56 (77.09) Prec@5 91.41 (91.83) + train[2018-10-25-13:13:38] Epoch: [241][5600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.089 (2.856) Prec@1 74.22 (77.08) Prec@5 88.28 (91.83) + train[2018-10-25-13:15:27] Epoch: [241][5800/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.651 (2.857) Prec@1 81.25 (77.06) Prec@5 91.41 (91.82) + train[2018-10-25-13:17:14] Epoch: [241][6000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.623 (2.856) Prec@1 75.78 (77.08) Prec@5 96.09 (91.84) + train[2018-10-25-13:19:02] Epoch: [241][6200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 3.031 (2.856) Prec@1 72.66 (77.08) Prec@5 91.41 (91.84) + train[2018-10-25-13:20:50] Epoch: [241][6400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.060 (2.855) Prec@1 71.88 (77.08) Prec@5 88.28 (91.84) + train[2018-10-25-13:22:37] Epoch: [241][6600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.832 (2.855) Prec@1 77.34 (77.08) Prec@5 94.53 (91.83) + train[2018-10-25-13:24:27] Epoch: [241][6800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.843 (2.855) Prec@1 77.34 (77.07) Prec@5 93.75 (91.84) + train[2018-10-25-13:26:14] Epoch: [241][7000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.703 (2.855) Prec@1 80.47 (77.08) Prec@5 95.31 (91.84) + train[2018-10-25-13:28:02] Epoch: [241][7200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.885 (2.855) Prec@1 76.56 (77.08) Prec@5 90.62 (91.83) + train[2018-10-25-13:29:51] Epoch: [241][7400/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.872 (2.855) Prec@1 75.00 (77.07) Prec@5 92.97 (91.82) + train[2018-10-25-13:31:39] Epoch: [241][7600/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.796 (2.856) Prec@1 79.69 (77.07) Prec@5 89.84 (91.82) + train[2018-10-25-13:33:27] Epoch: [241][7800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.975 (2.856) Prec@1 70.31 (77.06) Prec@5 86.72 (91.82) + train[2018-10-25-13:35:15] Epoch: [241][8000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.959 (2.856) Prec@1 74.22 (77.05) Prec@5 93.75 (91.82) + train[2018-10-25-13:37:04] Epoch: [241][8200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.028 (2.856) Prec@1 71.09 (77.05) Prec@5 91.41 (91.82) + train[2018-10-25-13:38:50] Epoch: [241][8400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.895 (2.856) Prec@1 78.91 (77.05) Prec@5 92.97 (91.82) + train[2018-10-25-13:40:38] Epoch: [241][8600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.890 (2.856) Prec@1 78.91 (77.05) Prec@5 89.84 (91.82) + train[2018-10-25-13:42:26] Epoch: [241][8800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.789 (2.856) Prec@1 78.91 (77.04) Prec@5 92.19 (91.82) + train[2018-10-25-13:44:12] Epoch: [241][9000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.165 (2.856) Prec@1 73.44 (77.04) Prec@5 87.50 (91.82) + train[2018-10-25-13:46:00] Epoch: [241][9200/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.958 (2.856) Prec@1 76.56 (77.04) Prec@5 86.72 (91.81) + train[2018-10-25-13:47:48] Epoch: [241][9400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.814 (2.856) Prec@1 77.34 (77.04) Prec@5 91.41 (91.81) + train[2018-10-25-13:49:36] Epoch: [241][9600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.712 (2.857) Prec@1 78.12 (77.04) Prec@5 93.75 (91.81) + train[2018-10-25-13:51:24] Epoch: [241][9800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.925 (2.857) Prec@1 75.78 (77.04) Prec@5 91.41 (91.80) + train[2018-10-25-13:53:11] Epoch: [241][10000/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.893 (2.857) Prec@1 74.22 (77.03) Prec@5 92.97 (91.80) + train[2018-10-25-13:53:15] Epoch: [241][10009/10010] Time 0.14 (0.54) Data 0.00 (0.00) Loss 3.493 (2.857) Prec@1 60.00 (77.03) Prec@5 86.67 (91.80) +[2018-10-25-13:53:15] **train** Prec@1 77.03 Prec@5 91.80 Error@1 22.97 Error@5 8.20 Loss:2.857 + test [2018-10-25-13:53:19] Epoch: [241][000/391] Time 4.45 (4.45) Data 4.31 (4.31) Loss 0.565 (0.565) Prec@1 92.97 (92.97) Prec@5 97.66 (97.66) + test [2018-10-25-13:53:50] Epoch: [241][200/391] Time 0.12 (0.17) Data 0.00 (0.04) Loss 1.162 (0.998) Prec@1 69.53 (77.57) Prec@5 92.97 (93.76) + test [2018-10-25-13:54:18] Epoch: [241][390/391] Time 0.09 (0.16) Data 0.00 (0.03) Loss 2.127 (1.165) Prec@1 45.00 (73.93) Prec@5 83.75 (91.51) +[2018-10-25-13:54:18] **test** Prec@1 73.93 Prec@5 91.51 Error@1 26.07 Error@5 8.49 Loss:1.165 +----> Best Accuracy : Acc@1=74.00, Acc@5=91.49, Error@1=26.00, Error@5=8.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-25-13:54:18] [Epoch=242/250] [Need: 12:10:04] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-25-13:54:24] Epoch: [242][000/10010] Time 5.90 (5.90) Data 5.30 (5.30) Loss 3.052 (3.052) Prec@1 72.66 (72.66) Prec@5 89.84 (89.84) + train[2018-10-25-13:56:10] Epoch: [242][200/10010] Time 0.57 (0.56) Data 0.00 (0.03) Loss 2.586 (2.872) Prec@1 83.59 (76.73) Prec@5 96.09 (91.56) + train[2018-10-25-13:57:56] Epoch: [242][400/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.925 (2.861) Prec@1 76.56 (77.04) Prec@5 90.62 (91.81) + train[2018-10-25-13:59:41] Epoch: [242][600/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 2.684 (2.860) Prec@1 79.69 (76.99) Prec@5 94.53 (91.79) + train[2018-10-25-14:01:27] Epoch: [242][800/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 3.216 (2.860) Prec@1 74.22 (77.02) Prec@5 87.50 (91.78) + train[2018-10-25-14:03:12] Epoch: [242][1000/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.631 (2.860) Prec@1 78.12 (77.00) Prec@5 92.97 (91.76) + train[2018-10-25-14:04:57] Epoch: [242][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.833 (2.856) Prec@1 76.56 (77.06) Prec@5 91.41 (91.77) + train[2018-10-25-14:06:42] Epoch: [242][1400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.871 (2.856) Prec@1 74.22 (77.11) Prec@5 89.84 (91.78) + train[2018-10-25-14:08:29] Epoch: [242][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.098 (2.856) Prec@1 71.88 (77.09) Prec@5 91.41 (91.79) + train[2018-10-25-14:10:14] Epoch: [242][1800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.911 (2.858) Prec@1 76.56 (77.06) Prec@5 92.97 (91.79) + train[2018-10-25-14:11:59] Epoch: [242][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.470 (2.856) Prec@1 85.16 (77.10) Prec@5 96.09 (91.82) + train[2018-10-25-14:13:45] Epoch: [242][2200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.961 (2.855) Prec@1 73.44 (77.12) Prec@5 92.19 (91.84) + train[2018-10-25-14:15:33] Epoch: [242][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.511 (2.855) Prec@1 82.81 (77.09) Prec@5 92.97 (91.82) + train[2018-10-25-14:17:20] Epoch: [242][2600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.679 (2.854) Prec@1 81.25 (77.10) Prec@5 95.31 (91.84) + train[2018-10-25-14:19:08] Epoch: [242][2800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.075 (2.855) Prec@1 73.44 (77.07) Prec@5 90.62 (91.83) + train[2018-10-25-14:20:56] Epoch: [242][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.638 (2.855) Prec@1 81.25 (77.08) Prec@5 93.75 (91.84) + train[2018-10-25-14:22:45] Epoch: [242][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.838 (2.856) Prec@1 71.88 (77.06) Prec@5 89.06 (91.83) + train[2018-10-25-14:24:32] Epoch: [242][3400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.836 (2.856) Prec@1 79.69 (77.04) Prec@5 91.41 (91.83) + train[2018-10-25-14:26:20] Epoch: [242][3600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.758 (2.856) Prec@1 76.56 (77.03) Prec@5 92.97 (91.85) + train[2018-10-25-14:28:07] Epoch: [242][3800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.625 (2.855) Prec@1 80.47 (77.05) Prec@5 95.31 (91.85) + train[2018-10-25-14:29:54] Epoch: [242][4000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.636 (2.856) Prec@1 81.25 (77.03) Prec@5 93.75 (91.84) + train[2018-10-25-14:31:43] Epoch: [242][4200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.077 (2.856) Prec@1 70.31 (77.03) Prec@5 88.28 (91.83) + train[2018-10-25-14:33:31] Epoch: [242][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.719 (2.856) Prec@1 79.69 (77.04) Prec@5 93.75 (91.84) + train[2018-10-25-14:35:22] Epoch: [242][4600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.834 (2.856) Prec@1 78.12 (77.05) Prec@5 91.41 (91.83) + train[2018-10-25-14:37:10] Epoch: [242][4800/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 2.951 (2.857) Prec@1 70.31 (77.03) Prec@5 89.84 (91.82) + train[2018-10-25-14:38:58] Epoch: [242][5000/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 3.128 (2.858) Prec@1 71.09 (77.02) Prec@5 85.16 (91.80) + train[2018-10-25-14:40:47] Epoch: [242][5200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.987 (2.859) Prec@1 71.09 (77.01) Prec@5 90.62 (91.80) + train[2018-10-25-14:42:36] Epoch: [242][5400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.774 (2.858) Prec@1 78.12 (77.00) Prec@5 92.97 (91.80) + train[2018-10-25-14:44:25] Epoch: [242][5600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.769 (2.859) Prec@1 75.78 (77.00) Prec@5 93.75 (91.80) + train[2018-10-25-14:46:13] Epoch: [242][5800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.811 (2.859) Prec@1 76.56 (76.99) Prec@5 92.19 (91.80) + train[2018-10-25-14:48:03] Epoch: [242][6000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.855 (2.859) Prec@1 72.66 (76.99) Prec@5 92.97 (91.79) + train[2018-10-25-14:49:52] Epoch: [242][6200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.888 (2.859) Prec@1 77.34 (76.98) Prec@5 92.19 (91.79) + train[2018-10-25-14:51:41] Epoch: [242][6400/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 2.733 (2.859) Prec@1 78.12 (77.00) Prec@5 94.53 (91.80) + train[2018-10-25-14:53:29] Epoch: [242][6600/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 3.146 (2.859) Prec@1 75.78 (77.00) Prec@5 87.50 (91.80) + train[2018-10-25-14:55:19] Epoch: [242][6800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.994 (2.859) Prec@1 76.56 (76.99) Prec@5 89.06 (91.80) + train[2018-10-25-14:57:07] Epoch: [242][7000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.380 (2.859) Prec@1 85.94 (76.99) Prec@5 96.88 (91.80) + train[2018-10-25-14:58:55] Epoch: [242][7200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.077 (2.859) Prec@1 75.00 (76.99) Prec@5 85.94 (91.80) + train[2018-10-25-15:00:43] Epoch: [242][7400/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 2.606 (2.859) Prec@1 84.38 (76.99) Prec@5 94.53 (91.80) + train[2018-10-25-15:02:31] Epoch: [242][7600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.584 (2.859) Prec@1 78.91 (77.01) Prec@5 95.31 (91.79) + train[2018-10-25-15:04:20] Epoch: [242][7800/10010] Time 0.59 (0.54) Data 0.00 (0.00) Loss 3.120 (2.860) Prec@1 76.56 (77.00) Prec@5 86.72 (91.79) + train[2018-10-25-15:06:08] Epoch: [242][8000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 3.009 (2.860) Prec@1 74.22 (76.99) Prec@5 88.28 (91.79) + train[2018-10-25-15:07:56] Epoch: [242][8200/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.921 (2.859) Prec@1 76.56 (76.99) Prec@5 91.41 (91.79) + train[2018-10-25-15:09:45] Epoch: [242][8400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.668 (2.859) Prec@1 76.56 (76.99) Prec@5 96.09 (91.79) + train[2018-10-25-15:11:33] Epoch: [242][8600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.732 (2.859) Prec@1 76.56 (77.00) Prec@5 93.75 (91.80) + train[2018-10-25-15:13:23] Epoch: [242][8800/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.672 (2.858) Prec@1 81.25 (77.01) Prec@5 94.53 (91.80) + train[2018-10-25-15:15:11] Epoch: [242][9000/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.741 (2.859) Prec@1 80.47 (77.00) Prec@5 92.97 (91.80) + train[2018-10-25-15:17:01] Epoch: [242][9200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.809 (2.859) Prec@1 77.34 (77.00) Prec@5 92.97 (91.80) + train[2018-10-25-15:18:50] Epoch: [242][9400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 3.075 (2.859) Prec@1 75.00 (77.00) Prec@5 86.72 (91.80) + train[2018-10-25-15:20:38] Epoch: [242][9600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.947 (2.859) Prec@1 76.56 (77.00) Prec@5 92.19 (91.80) + train[2018-10-25-15:22:27] Epoch: [242][9800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 3.015 (2.859) Prec@1 75.78 (77.00) Prec@5 90.62 (91.80) + train[2018-10-25-15:24:15] Epoch: [242][10000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.905 (2.859) Prec@1 74.22 (77.00) Prec@5 90.62 (91.80) + train[2018-10-25-15:24:20] Epoch: [242][10009/10010] Time 0.19 (0.54) Data 0.00 (0.00) Loss 3.074 (2.859) Prec@1 66.67 (77.00) Prec@5 86.67 (91.80) +[2018-10-25-15:24:20] **train** Prec@1 77.00 Prec@5 91.80 Error@1 23.00 Error@5 8.20 Loss:2.859 + test [2018-10-25-15:24:24] Epoch: [242][000/391] Time 3.89 (3.89) Data 3.76 (3.76) Loss 0.562 (0.562) Prec@1 92.97 (92.97) Prec@5 98.44 (98.44) + test [2018-10-25-15:24:54] Epoch: [242][200/391] Time 0.14 (0.17) Data 0.00 (0.04) Loss 1.177 (0.986) Prec@1 67.19 (77.37) Prec@5 91.41 (93.70) + test [2018-10-25-15:25:19] Epoch: [242][390/391] Time 0.08 (0.15) Data 0.00 (0.02) Loss 2.147 (1.157) Prec@1 46.25 (73.79) Prec@5 82.50 (91.46) +[2018-10-25-15:25:19] **test** Prec@1 73.79 Prec@5 91.46 Error@1 26.21 Error@5 8.54 Loss:1.157 +----> Best Accuracy : Acc@1=74.00, Acc@5=91.49, Error@1=26.00, Error@5=8.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-25-15:25:20] [Epoch=243/250] [Need: 10:37:09] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-25-15:25:25] Epoch: [243][000/10010] Time 4.96 (4.96) Data 4.35 (4.35) Loss 2.681 (2.681) Prec@1 80.47 (80.47) Prec@5 89.84 (89.84) + train[2018-10-25-15:27:12] Epoch: [243][200/10010] Time 0.50 (0.56) Data 0.00 (0.02) Loss 2.755 (2.837) Prec@1 75.00 (77.37) Prec@5 94.53 (91.92) + train[2018-10-25-15:28:57] Epoch: [243][400/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.757 (2.835) Prec@1 78.91 (77.36) Prec@5 92.97 (91.97) + train[2018-10-25-15:30:43] Epoch: [243][600/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.832 (2.837) Prec@1 77.34 (77.39) Prec@5 92.97 (91.99) + train[2018-10-25-15:32:28] Epoch: [243][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 3.088 (2.848) Prec@1 72.66 (77.16) Prec@5 89.84 (91.82) + train[2018-10-25-15:34:13] Epoch: [243][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.722 (2.846) Prec@1 78.12 (77.23) Prec@5 92.19 (91.84) + train[2018-10-25-15:35:59] Epoch: [243][1200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.873 (2.848) Prec@1 76.56 (77.16) Prec@5 92.19 (91.85) + train[2018-10-25-15:37:44] Epoch: [243][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.878 (2.851) Prec@1 75.00 (77.10) Prec@5 92.97 (91.83) + train[2018-10-25-15:39:31] Epoch: [243][1600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.975 (2.849) Prec@1 72.66 (77.11) Prec@5 93.75 (91.85) + train[2018-10-25-15:41:17] Epoch: [243][1800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.504 (2.849) Prec@1 84.38 (77.13) Prec@5 93.75 (91.87) + train[2018-10-25-15:43:03] Epoch: [243][2000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.814 (2.850) Prec@1 78.12 (77.11) Prec@5 95.31 (91.87) + train[2018-10-25-15:44:50] Epoch: [243][2200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.067 (2.851) Prec@1 69.53 (77.10) Prec@5 89.06 (91.86) + train[2018-10-25-15:46:37] Epoch: [243][2400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.096 (2.852) Prec@1 73.44 (77.09) Prec@5 89.84 (91.84) + train[2018-10-25-15:48:24] Epoch: [243][2600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.758 (2.853) Prec@1 78.12 (77.07) Prec@5 92.97 (91.84) + train[2018-10-25-15:50:10] Epoch: [243][2800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.804 (2.853) Prec@1 78.91 (77.09) Prec@5 92.97 (91.83) + train[2018-10-25-15:51:56] Epoch: [243][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.828 (2.853) Prec@1 74.22 (77.08) Prec@5 92.97 (91.84) + train[2018-10-25-15:53:43] Epoch: [243][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.885 (2.855) Prec@1 74.22 (77.06) Prec@5 91.41 (91.82) + train[2018-10-25-15:55:30] Epoch: [243][3400/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.809 (2.855) Prec@1 79.69 (77.05) Prec@5 89.06 (91.82) + train[2018-10-25-15:57:17] Epoch: [243][3600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.885 (2.854) Prec@1 75.78 (77.05) Prec@5 89.84 (91.83) + train[2018-10-25-15:59:03] Epoch: [243][3800/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.016 (2.855) Prec@1 72.66 (77.04) Prec@5 89.84 (91.83) + train[2018-10-25-16:00:51] Epoch: [243][4000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.280 (2.855) Prec@1 75.00 (77.05) Prec@5 84.38 (91.83) + train[2018-10-25-16:02:38] Epoch: [243][4200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.766 (2.856) Prec@1 82.81 (77.03) Prec@5 90.62 (91.82) + train[2018-10-25-16:04:25] Epoch: [243][4400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.182 (2.855) Prec@1 71.88 (77.03) Prec@5 86.72 (91.82) + train[2018-10-25-16:06:12] Epoch: [243][4600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.779 (2.855) Prec@1 76.56 (77.02) Prec@5 92.97 (91.82) + train[2018-10-25-16:07:58] Epoch: [243][4800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.759 (2.856) Prec@1 79.69 (77.03) Prec@5 90.62 (91.82) + train[2018-10-25-16:09:46] Epoch: [243][5000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.730 (2.855) Prec@1 75.78 (77.04) Prec@5 92.19 (91.83) + train[2018-10-25-16:11:34] Epoch: [243][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.840 (2.854) Prec@1 74.22 (77.05) Prec@5 92.97 (91.83) + train[2018-10-25-16:13:22] Epoch: [243][5400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.050 (2.855) Prec@1 72.66 (77.06) Prec@5 89.06 (91.82) + train[2018-10-25-16:15:11] Epoch: [243][5600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.928 (2.855) Prec@1 76.56 (77.06) Prec@5 91.41 (91.83) + train[2018-10-25-16:16:59] Epoch: [243][5800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.986 (2.855) Prec@1 75.78 (77.06) Prec@5 92.97 (91.82) + train[2018-10-25-16:18:47] Epoch: [243][6000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.725 (2.855) Prec@1 79.69 (77.06) Prec@5 92.19 (91.82) + train[2018-10-25-16:20:35] Epoch: [243][6200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.878 (2.855) Prec@1 75.00 (77.05) Prec@5 91.41 (91.82) + train[2018-10-25-16:22:23] Epoch: [243][6400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.534 (2.855) Prec@1 84.38 (77.05) Prec@5 95.31 (91.82) + train[2018-10-25-16:24:12] Epoch: [243][6600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.764 (2.855) Prec@1 77.34 (77.05) Prec@5 95.31 (91.82) + train[2018-10-25-16:25:59] Epoch: [243][6800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.687 (2.855) Prec@1 78.12 (77.03) Prec@5 92.19 (91.82) + train[2018-10-25-16:27:47] Epoch: [243][7000/10010] Time 0.60 (0.54) Data 0.00 (0.00) Loss 2.853 (2.855) Prec@1 78.91 (77.04) Prec@5 92.97 (91.82) + train[2018-10-25-16:29:36] Epoch: [243][7200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.569 (2.856) Prec@1 78.91 (77.03) Prec@5 96.09 (91.82) + train[2018-10-25-16:31:24] Epoch: [243][7400/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.971 (2.855) Prec@1 73.44 (77.03) Prec@5 90.62 (91.82) + train[2018-10-25-16:33:11] Epoch: [243][7600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.913 (2.856) Prec@1 77.34 (77.03) Prec@5 91.41 (91.82) + train[2018-10-25-16:34:59] Epoch: [243][7800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.566 (2.855) Prec@1 79.69 (77.04) Prec@5 94.53 (91.82) + train[2018-10-25-16:36:47] Epoch: [243][8000/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.981 (2.855) Prec@1 80.47 (77.04) Prec@5 91.41 (91.81) + train[2018-10-25-16:38:34] Epoch: [243][8200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.828 (2.856) Prec@1 78.12 (77.03) Prec@5 93.75 (91.81) + train[2018-10-25-16:40:22] Epoch: [243][8400/10010] Time 0.64 (0.54) Data 0.00 (0.00) Loss 2.994 (2.856) Prec@1 76.56 (77.02) Prec@5 89.84 (91.80) + train[2018-10-25-16:42:10] Epoch: [243][8600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.964 (2.857) Prec@1 74.22 (77.02) Prec@5 89.84 (91.80) + train[2018-10-25-16:43:57] Epoch: [243][8800/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.701 (2.857) Prec@1 80.47 (77.02) Prec@5 92.97 (91.79) + train[2018-10-25-16:45:44] Epoch: [243][9000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.820 (2.857) Prec@1 79.69 (77.02) Prec@5 92.19 (91.80) + train[2018-10-25-16:47:32] Epoch: [243][9200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.830 (2.857) Prec@1 77.34 (77.01) Prec@5 92.19 (91.80) + train[2018-10-25-16:49:18] Epoch: [243][9400/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.875 (2.857) Prec@1 73.44 (77.01) Prec@5 92.97 (91.79) + train[2018-10-25-16:51:06] Epoch: [243][9600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.961 (2.858) Prec@1 75.00 (77.00) Prec@5 89.06 (91.79) + train[2018-10-25-16:52:53] Epoch: [243][9800/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.905 (2.857) Prec@1 75.78 (77.00) Prec@5 90.62 (91.79) + train[2018-10-25-16:54:40] Epoch: [243][10000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.748 (2.857) Prec@1 78.91 (77.01) Prec@5 92.19 (91.79) + train[2018-10-25-16:54:44] Epoch: [243][10009/10010] Time 0.20 (0.54) Data 0.00 (0.00) Loss 4.401 (2.857) Prec@1 66.67 (77.01) Prec@5 73.33 (91.79) +[2018-10-25-16:54:44] **train** Prec@1 77.01 Prec@5 91.79 Error@1 22.99 Error@5 8.21 Loss:2.857 + test [2018-10-25-16:54:48] Epoch: [243][000/391] Time 4.35 (4.35) Data 4.21 (4.21) Loss 0.573 (0.573) Prec@1 93.75 (93.75) Prec@5 97.66 (97.66) + test [2018-10-25-16:55:18] Epoch: [243][200/391] Time 0.13 (0.17) Data 0.00 (0.04) Loss 1.198 (1.008) Prec@1 68.75 (77.45) Prec@5 91.41 (93.68) + test [2018-10-25-16:55:44] Epoch: [243][390/391] Time 0.09 (0.15) Data 0.00 (0.02) Loss 2.137 (1.177) Prec@1 45.00 (73.85) Prec@5 82.50 (91.48) +[2018-10-25-16:55:44] **test** Prec@1 73.85 Prec@5 91.48 Error@1 26.15 Error@5 8.52 Loss:1.177 +----> Best Accuracy : Acc@1=74.00, Acc@5=91.49, Error@1=26.00, Error@5=8.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-25-16:55:44] [Epoch=244/250] [Need: 09:02:29] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-25-16:55:51] Epoch: [244][000/10010] Time 6.33 (6.33) Data 5.74 (5.74) Loss 2.798 (2.798) Prec@1 77.34 (77.34) Prec@5 92.19 (92.19) + train[2018-10-25-16:57:36] Epoch: [244][200/10010] Time 0.56 (0.56) Data 0.00 (0.03) Loss 2.765 (2.854) Prec@1 77.34 (76.97) Prec@5 91.41 (91.73) + train[2018-10-25-16:59:22] Epoch: [244][400/10010] Time 0.55 (0.54) Data 0.00 (0.01) Loss 2.691 (2.850) Prec@1 78.12 (77.22) Prec@5 93.75 (91.83) + train[2018-10-25-17:01:07] Epoch: [244][600/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 2.893 (2.855) Prec@1 74.22 (77.25) Prec@5 95.31 (91.86) + train[2018-10-25-17:02:52] Epoch: [244][800/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.107 (2.856) Prec@1 70.31 (77.21) Prec@5 89.84 (91.85) + train[2018-10-25-17:04:38] Epoch: [244][1000/10010] Time 0.50 (0.53) Data 0.00 (0.01) Loss 2.864 (2.854) Prec@1 71.88 (77.15) Prec@5 90.62 (91.87) + train[2018-10-25-17:06:24] Epoch: [244][1200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.688 (2.855) Prec@1 77.34 (77.10) Prec@5 94.53 (91.90) + train[2018-10-25-17:08:10] Epoch: [244][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.852 (2.854) Prec@1 71.88 (77.10) Prec@5 90.62 (91.91) + train[2018-10-25-17:09:55] Epoch: [244][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.745 (2.855) Prec@1 75.78 (77.06) Prec@5 91.41 (91.90) + train[2018-10-25-17:11:41] Epoch: [244][1800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.666 (2.855) Prec@1 79.69 (77.08) Prec@5 92.97 (91.88) + train[2018-10-25-17:13:27] Epoch: [244][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.873 (2.855) Prec@1 77.34 (77.09) Prec@5 92.97 (91.87) + train[2018-10-25-17:15:13] Epoch: [244][2200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.980 (2.854) Prec@1 72.66 (77.09) Prec@5 89.84 (91.88) + train[2018-10-25-17:17:00] Epoch: [244][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.787 (2.856) Prec@1 79.69 (77.07) Prec@5 92.19 (91.85) + train[2018-10-25-17:18:45] Epoch: [244][2600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.677 (2.856) Prec@1 82.03 (77.05) Prec@5 92.97 (91.86) + train[2018-10-25-17:20:32] Epoch: [244][2800/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 2.864 (2.857) Prec@1 77.34 (77.04) Prec@5 92.97 (91.84) + train[2018-10-25-17:22:17] Epoch: [244][3000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.752 (2.857) Prec@1 80.47 (77.03) Prec@5 92.97 (91.84) + train[2018-10-25-17:24:04] Epoch: [244][3200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.639 (2.858) Prec@1 80.47 (77.01) Prec@5 94.53 (91.84) + train[2018-10-25-17:25:51] Epoch: [244][3400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.831 (2.857) Prec@1 76.56 (77.00) Prec@5 92.19 (91.84) + train[2018-10-25-17:27:38] Epoch: [244][3600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.901 (2.859) Prec@1 75.78 (76.98) Prec@5 88.28 (91.82) + train[2018-10-25-17:29:26] Epoch: [244][3800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.880 (2.859) Prec@1 75.00 (76.98) Prec@5 93.75 (91.81) + train[2018-10-25-17:31:13] Epoch: [244][4000/10010] Time 0.64 (0.53) Data 0.00 (0.00) Loss 2.900 (2.859) Prec@1 75.00 (76.98) Prec@5 91.41 (91.81) + train[2018-10-25-17:33:01] Epoch: [244][4200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.681 (2.859) Prec@1 82.03 (76.98) Prec@5 92.97 (91.82) + train[2018-10-25-17:34:49] Epoch: [244][4400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.788 (2.859) Prec@1 76.56 (76.97) Prec@5 92.19 (91.82) + train[2018-10-25-17:36:36] Epoch: [244][4600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.855 (2.858) Prec@1 75.78 (76.99) Prec@5 92.97 (91.83) + train[2018-10-25-17:38:24] Epoch: [244][4800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.734 (2.858) Prec@1 78.91 (76.99) Prec@5 89.84 (91.83) + train[2018-10-25-17:40:11] Epoch: [244][5000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.872 (2.859) Prec@1 71.88 (76.98) Prec@5 92.97 (91.81) + train[2018-10-25-17:42:00] Epoch: [244][5200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.941 (2.858) Prec@1 74.22 (76.99) Prec@5 91.41 (91.81) + train[2018-10-25-17:43:48] Epoch: [244][5400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.812 (2.858) Prec@1 74.22 (76.99) Prec@5 93.75 (91.81) + train[2018-10-25-17:45:35] Epoch: [244][5600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.022 (2.859) Prec@1 76.56 (76.97) Prec@5 90.62 (91.81) + train[2018-10-25-17:47:22] Epoch: [244][5800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.516 (2.858) Prec@1 79.69 (76.98) Prec@5 96.09 (91.81) + train[2018-10-25-17:49:10] Epoch: [244][6000/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.630 (2.858) Prec@1 82.81 (76.99) Prec@5 93.75 (91.81) + train[2018-10-25-17:50:58] Epoch: [244][6200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.779 (2.858) Prec@1 75.00 (76.98) Prec@5 92.97 (91.81) + train[2018-10-25-17:52:45] Epoch: [244][6400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.826 (2.858) Prec@1 78.12 (76.97) Prec@5 92.97 (91.81) + train[2018-10-25-17:54:32] Epoch: [244][6600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.785 (2.858) Prec@1 80.47 (76.97) Prec@5 92.97 (91.81) + train[2018-10-25-17:56:19] Epoch: [244][6800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.955 (2.858) Prec@1 78.12 (76.97) Prec@5 91.41 (91.81) + train[2018-10-25-17:58:06] Epoch: [244][7000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.909 (2.858) Prec@1 71.88 (76.98) Prec@5 92.19 (91.82) + train[2018-10-25-17:59:53] Epoch: [244][7200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.919 (2.858) Prec@1 75.78 (76.99) Prec@5 93.75 (91.82) + train[2018-10-25-18:01:41] Epoch: [244][7400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.873 (2.858) Prec@1 78.12 (76.98) Prec@5 92.19 (91.82) + train[2018-10-25-18:03:28] Epoch: [244][7600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.660 (2.857) Prec@1 83.59 (76.98) Prec@5 92.19 (91.83) + train[2018-10-25-18:05:15] Epoch: [244][7800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.892 (2.858) Prec@1 79.69 (76.98) Prec@5 90.62 (91.82) + train[2018-10-25-18:07:01] Epoch: [244][8000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.657 (2.857) Prec@1 80.47 (76.98) Prec@5 93.75 (91.83) + train[2018-10-25-18:08:49] Epoch: [244][8200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.129 (2.858) Prec@1 67.97 (76.98) Prec@5 88.28 (91.82) + train[2018-10-25-18:10:36] Epoch: [244][8400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.818 (2.858) Prec@1 75.78 (76.98) Prec@5 92.97 (91.82) + train[2018-10-25-18:12:23] Epoch: [244][8600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.828 (2.858) Prec@1 77.34 (77.00) Prec@5 92.19 (91.82) + train[2018-10-25-18:14:09] Epoch: [244][8800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.711 (2.858) Prec@1 80.47 (77.00) Prec@5 92.97 (91.82) + train[2018-10-25-18:15:57] Epoch: [244][9000/10010] Time 0.61 (0.53) Data 0.00 (0.00) Loss 2.787 (2.857) Prec@1 80.47 (77.01) Prec@5 91.41 (91.82) + train[2018-10-25-18:17:45] Epoch: [244][9200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.905 (2.857) Prec@1 74.22 (77.01) Prec@5 91.41 (91.82) + train[2018-10-25-18:19:33] Epoch: [244][9400/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.959 (2.857) Prec@1 76.56 (77.02) Prec@5 91.41 (91.83) + train[2018-10-25-18:21:20] Epoch: [244][9600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 3.370 (2.857) Prec@1 67.19 (77.02) Prec@5 82.81 (91.83) + train[2018-10-25-18:23:08] Epoch: [244][9800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.708 (2.857) Prec@1 77.34 (77.02) Prec@5 92.97 (91.83) + train[2018-10-25-18:24:56] Epoch: [244][10000/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.928 (2.857) Prec@1 73.44 (77.01) Prec@5 92.97 (91.82) + train[2018-10-25-18:25:01] Epoch: [244][10009/10010] Time 0.29 (0.54) Data 0.00 (0.00) Loss 4.182 (2.857) Prec@1 60.00 (77.01) Prec@5 80.00 (91.82) +[2018-10-25-18:25:01] **train** Prec@1 77.01 Prec@5 91.82 Error@1 22.99 Error@5 8.18 Loss:2.857 + test [2018-10-25-18:25:06] Epoch: [244][000/391] Time 4.52 (4.52) Data 4.38 (4.38) Loss 0.535 (0.535) Prec@1 93.75 (93.75) Prec@5 97.66 (97.66) + test [2018-10-25-18:25:32] Epoch: [244][200/391] Time 0.14 (0.16) Data 0.00 (0.02) Loss 1.173 (0.997) Prec@1 68.75 (77.53) Prec@5 92.19 (93.68) + test [2018-10-25-18:25:58] Epoch: [244][390/391] Time 0.09 (0.14) Data 0.00 (0.01) Loss 2.131 (1.165) Prec@1 46.25 (73.93) Prec@5 83.75 (91.49) +[2018-10-25-18:25:58] **test** Prec@1 73.93 Prec@5 91.49 Error@1 26.07 Error@5 8.51 Loss:1.165 +----> Best Accuracy : Acc@1=74.00, Acc@5=91.49, Error@1=26.00, Error@5=8.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-25-18:25:58] [Epoch=245/250] [Need: 07:31:06] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-25-18:26:04] Epoch: [245][000/10010] Time 5.97 (5.97) Data 5.38 (5.38) Loss 2.930 (2.930) Prec@1 76.56 (76.56) Prec@5 88.28 (88.28) + train[2018-10-25-18:27:50] Epoch: [245][200/10010] Time 0.54 (0.56) Data 0.00 (0.03) Loss 2.905 (2.866) Prec@1 74.22 (76.57) Prec@5 90.62 (91.81) + train[2018-10-25-18:29:35] Epoch: [245][400/10010] Time 0.51 (0.54) Data 0.00 (0.01) Loss 3.069 (2.872) Prec@1 74.22 (76.60) Prec@5 93.75 (91.73) + train[2018-10-25-18:31:21] Epoch: [245][600/10010] Time 0.54 (0.54) Data 0.00 (0.01) Loss 2.898 (2.871) Prec@1 76.56 (76.72) Prec@5 90.62 (91.72) + train[2018-10-25-18:33:06] Epoch: [245][800/10010] Time 0.54 (0.53) Data 0.00 (0.01) Loss 2.852 (2.869) Prec@1 76.56 (76.76) Prec@5 92.19 (91.77) + train[2018-10-25-18:34:52] Epoch: [245][1000/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.036 (2.866) Prec@1 75.00 (76.75) Prec@5 85.94 (91.74) + train[2018-10-25-18:36:38] Epoch: [245][1200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.891 (2.862) Prec@1 79.69 (76.78) Prec@5 89.84 (91.77) + train[2018-10-25-18:38:24] Epoch: [245][1400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.883 (2.863) Prec@1 72.66 (76.79) Prec@5 91.41 (91.75) + train[2018-10-25-18:40:10] Epoch: [245][1600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.694 (2.862) Prec@1 79.69 (76.81) Prec@5 92.19 (91.77) + train[2018-10-25-18:41:55] Epoch: [245][1800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.943 (2.864) Prec@1 76.56 (76.80) Prec@5 89.84 (91.75) + train[2018-10-25-18:43:40] Epoch: [245][2000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.825 (2.862) Prec@1 76.56 (76.88) Prec@5 93.75 (91.79) + train[2018-10-25-18:45:26] Epoch: [245][2200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.896 (2.861) Prec@1 82.81 (76.91) Prec@5 88.28 (91.78) + train[2018-10-25-18:47:12] Epoch: [245][2400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.730 (2.858) Prec@1 78.12 (76.97) Prec@5 96.09 (91.81) + train[2018-10-25-18:48:59] Epoch: [245][2600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.667 (2.859) Prec@1 82.81 (76.97) Prec@5 93.75 (91.81) + train[2018-10-25-18:50:45] Epoch: [245][2800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.561 (2.857) Prec@1 82.03 (76.98) Prec@5 94.53 (91.84) + train[2018-10-25-18:52:32] Epoch: [245][3000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.120 (2.857) Prec@1 71.88 (76.98) Prec@5 87.50 (91.84) + train[2018-10-25-18:54:19] Epoch: [245][3200/10010] Time 0.60 (0.53) Data 0.00 (0.00) Loss 2.963 (2.857) Prec@1 78.12 (76.99) Prec@5 91.41 (91.84) + train[2018-10-25-18:56:06] Epoch: [245][3400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.860 (2.857) Prec@1 80.47 (76.98) Prec@5 92.97 (91.84) + train[2018-10-25-18:57:53] Epoch: [245][3600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.846 (2.857) Prec@1 75.00 (76.99) Prec@5 92.19 (91.85) + train[2018-10-25-18:59:39] Epoch: [245][3800/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 3.035 (2.857) Prec@1 73.44 (76.99) Prec@5 90.62 (91.85) + train[2018-10-25-19:01:26] Epoch: [245][4000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.041 (2.857) Prec@1 76.56 (76.99) Prec@5 91.41 (91.84) + train[2018-10-25-19:03:12] Epoch: [245][4200/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.722 (2.856) Prec@1 80.47 (77.01) Prec@5 92.19 (91.85) + train[2018-10-25-19:04:59] Epoch: [245][4400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.183 (2.856) Prec@1 67.97 (77.01) Prec@5 87.50 (91.84) + train[2018-10-25-19:06:45] Epoch: [245][4600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.743 (2.857) Prec@1 75.00 (77.01) Prec@5 93.75 (91.83) + train[2018-10-25-19:08:32] Epoch: [245][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.950 (2.857) Prec@1 78.12 (77.02) Prec@5 90.62 (91.83) + train[2018-10-25-19:10:21] Epoch: [245][5000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.136 (2.856) Prec@1 69.53 (77.02) Prec@5 90.62 (91.84) + train[2018-10-25-19:12:08] Epoch: [245][5200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.771 (2.856) Prec@1 78.12 (77.01) Prec@5 93.75 (91.83) + train[2018-10-25-19:13:55] Epoch: [245][5400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.116 (2.857) Prec@1 75.00 (77.00) Prec@5 88.28 (91.82) + train[2018-10-25-19:15:42] Epoch: [245][5600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.624 (2.857) Prec@1 79.69 (77.00) Prec@5 94.53 (91.83) + train[2018-10-25-19:17:30] Epoch: [245][5800/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.943 (2.857) Prec@1 75.78 (77.01) Prec@5 92.97 (91.82) + train[2018-10-25-19:19:17] Epoch: [245][6000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.684 (2.857) Prec@1 75.78 (76.99) Prec@5 94.53 (91.82) + train[2018-10-25-19:21:04] Epoch: [245][6200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.684 (2.857) Prec@1 82.03 (77.00) Prec@5 96.88 (91.83) + train[2018-10-25-19:22:53] Epoch: [245][6400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.693 (2.858) Prec@1 82.03 (77.00) Prec@5 94.53 (91.83) + train[2018-10-25-19:24:41] Epoch: [245][6600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.010 (2.858) Prec@1 74.22 (77.00) Prec@5 89.06 (91.83) + train[2018-10-25-19:26:27] Epoch: [245][6800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.983 (2.857) Prec@1 68.75 (77.01) Prec@5 89.84 (91.83) + train[2018-10-25-19:28:13] Epoch: [245][7000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.676 (2.858) Prec@1 79.69 (77.01) Prec@5 94.53 (91.82) + train[2018-10-25-19:29:59] Epoch: [245][7200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.931 (2.857) Prec@1 72.66 (77.02) Prec@5 92.97 (91.83) + train[2018-10-25-19:31:46] Epoch: [245][7400/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.074 (2.857) Prec@1 71.88 (77.01) Prec@5 89.84 (91.82) + train[2018-10-25-19:33:32] Epoch: [245][7600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.771 (2.858) Prec@1 79.69 (77.00) Prec@5 90.62 (91.82) + train[2018-10-25-19:35:19] Epoch: [245][7800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.773 (2.858) Prec@1 78.12 (77.00) Prec@5 93.75 (91.82) + train[2018-10-25-19:37:06] Epoch: [245][8000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.157 (2.858) Prec@1 71.09 (77.00) Prec@5 88.28 (91.81) + train[2018-10-25-19:38:53] Epoch: [245][8200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.795 (2.858) Prec@1 78.12 (77.00) Prec@5 92.19 (91.81) + train[2018-10-25-19:40:40] Epoch: [245][8400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.577 (2.858) Prec@1 79.69 (77.00) Prec@5 97.66 (91.82) + train[2018-10-25-19:42:26] Epoch: [245][8600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.898 (2.858) Prec@1 75.78 (77.01) Prec@5 89.84 (91.82) + train[2018-10-25-19:44:14] Epoch: [245][8800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.841 (2.858) Prec@1 75.00 (77.00) Prec@5 94.53 (91.81) + train[2018-10-25-19:46:02] Epoch: [245][9000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.617 (2.858) Prec@1 76.56 (77.00) Prec@5 95.31 (91.81) + train[2018-10-25-19:47:48] Epoch: [245][9200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.934 (2.858) Prec@1 71.88 (77.00) Prec@5 89.84 (91.81) + train[2018-10-25-19:49:35] Epoch: [245][9400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.934 (2.858) Prec@1 74.22 (77.00) Prec@5 92.97 (91.81) + train[2018-10-25-19:51:21] Epoch: [245][9600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.308 (2.858) Prec@1 71.09 (77.00) Prec@5 84.38 (91.82) + train[2018-10-25-19:53:09] Epoch: [245][9800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.937 (2.858) Prec@1 76.56 (77.01) Prec@5 89.84 (91.82) + train[2018-10-25-19:54:54] Epoch: [245][10000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.926 (2.857) Prec@1 78.91 (77.01) Prec@5 91.41 (91.82) + train[2018-10-25-19:54:59] Epoch: [245][10009/10010] Time 0.19 (0.53) Data 0.00 (0.00) Loss 2.923 (2.858) Prec@1 80.00 (77.01) Prec@5 93.33 (91.81) +[2018-10-25-19:54:59] **train** Prec@1 77.01 Prec@5 91.81 Error@1 22.99 Error@5 8.19 Loss:2.858 + test [2018-10-25-19:55:03] Epoch: [245][000/391] Time 4.55 (4.55) Data 4.41 (4.41) Loss 0.513 (0.513) Prec@1 92.97 (92.97) Prec@5 99.22 (99.22) + test [2018-10-25-19:55:33] Epoch: [245][200/391] Time 0.12 (0.17) Data 0.00 (0.04) Loss 1.193 (0.992) Prec@1 71.09 (77.35) Prec@5 92.19 (93.68) + test [2018-10-25-19:55:59] Epoch: [245][390/391] Time 0.08 (0.15) Data 0.00 (0.02) Loss 2.138 (1.162) Prec@1 45.00 (73.76) Prec@5 83.75 (91.46) +[2018-10-25-19:55:59] **test** Prec@1 73.76 Prec@5 91.46 Error@1 26.24 Error@5 8.54 Loss:1.162 +----> Best Accuracy : Acc@1=74.00, Acc@5=91.49, Error@1=26.00, Error@5=8.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-25-19:55:59] [Epoch=246/250] [Need: 06:00:04] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-25-19:56:04] Epoch: [246][000/10010] Time 4.79 (4.79) Data 4.16 (4.16) Loss 2.876 (2.876) Prec@1 75.00 (75.00) Prec@5 92.19 (92.19) + train[2018-10-25-19:57:51] Epoch: [246][200/10010] Time 0.54 (0.56) Data 0.00 (0.02) Loss 2.607 (2.864) Prec@1 81.25 (76.88) Prec@5 94.53 (91.78) + train[2018-10-25-19:59:39] Epoch: [246][400/10010] Time 0.57 (0.55) Data 0.00 (0.01) Loss 3.069 (2.864) Prec@1 74.22 (76.88) Prec@5 87.50 (91.73) + train[2018-10-25-20:01:27] Epoch: [246][600/10010] Time 0.53 (0.55) Data 0.00 (0.01) Loss 2.658 (2.864) Prec@1 79.69 (76.81) Prec@5 92.97 (91.75) + train[2018-10-25-20:03:15] Epoch: [246][800/10010] Time 0.50 (0.54) Data 0.00 (0.01) Loss 2.536 (2.863) Prec@1 82.03 (76.84) Prec@5 94.53 (91.78) + train[2018-10-25-20:05:02] Epoch: [246][1000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.852 (2.863) Prec@1 73.44 (76.82) Prec@5 91.41 (91.78) + train[2018-10-25-20:06:50] Epoch: [246][1200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.751 (2.863) Prec@1 78.12 (76.83) Prec@5 94.53 (91.76) + train[2018-10-25-20:08:37] Epoch: [246][1400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.863 (2.861) Prec@1 80.47 (76.88) Prec@5 89.06 (91.76) + train[2018-10-25-20:10:25] Epoch: [246][1600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.921 (2.861) Prec@1 72.66 (76.87) Prec@5 91.41 (91.76) + train[2018-10-25-20:12:13] Epoch: [246][1800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.327 (2.860) Prec@1 71.88 (76.88) Prec@5 85.16 (91.78) + train[2018-10-25-20:13:59] Epoch: [246][2000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.899 (2.860) Prec@1 76.56 (76.89) Prec@5 91.41 (91.78) + train[2018-10-25-20:15:45] Epoch: [246][2200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.932 (2.861) Prec@1 74.22 (76.86) Prec@5 89.84 (91.78) + train[2018-10-25-20:17:32] Epoch: [246][2400/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.828 (2.860) Prec@1 78.91 (76.88) Prec@5 90.62 (91.78) + train[2018-10-25-20:19:18] Epoch: [246][2600/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.729 (2.861) Prec@1 80.47 (76.86) Prec@5 92.19 (91.76) + train[2018-10-25-20:21:05] Epoch: [246][2800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.813 (2.860) Prec@1 78.12 (76.90) Prec@5 93.75 (91.78) + train[2018-10-25-20:22:52] Epoch: [246][3000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.943 (2.859) Prec@1 76.56 (76.93) Prec@5 91.41 (91.79) + train[2018-10-25-20:24:39] Epoch: [246][3200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.095 (2.859) Prec@1 75.00 (76.91) Prec@5 89.06 (91.78) + train[2018-10-25-20:26:27] Epoch: [246][3400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.778 (2.859) Prec@1 78.91 (76.91) Prec@5 91.41 (91.79) + train[2018-10-25-20:28:13] Epoch: [246][3600/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.849 (2.858) Prec@1 75.78 (76.93) Prec@5 92.19 (91.79) + train[2018-10-25-20:30:01] Epoch: [246][3800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.757 (2.858) Prec@1 79.69 (76.93) Prec@5 91.41 (91.79) + train[2018-10-25-20:31:48] Epoch: [246][4000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.034 (2.858) Prec@1 73.44 (76.95) Prec@5 88.28 (91.79) + train[2018-10-25-20:33:35] Epoch: [246][4200/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 3.010 (2.858) Prec@1 75.00 (76.96) Prec@5 89.06 (91.79) + train[2018-10-25-20:35:22] Epoch: [246][4400/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.117 (2.856) Prec@1 75.00 (76.98) Prec@5 87.50 (91.81) + train[2018-10-25-20:37:09] Epoch: [246][4600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.758 (2.856) Prec@1 75.78 (76.99) Prec@5 91.41 (91.82) + train[2018-10-25-20:38:56] Epoch: [246][4800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.819 (2.856) Prec@1 78.91 (77.00) Prec@5 92.19 (91.81) + train[2018-10-25-20:40:44] Epoch: [246][5000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 3.105 (2.857) Prec@1 75.00 (77.00) Prec@5 83.59 (91.80) + train[2018-10-25-20:42:30] Epoch: [246][5200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.860 (2.856) Prec@1 75.00 (77.01) Prec@5 92.97 (91.80) + train[2018-10-25-20:44:17] Epoch: [246][5400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.737 (2.856) Prec@1 79.69 (77.02) Prec@5 93.75 (91.80) + train[2018-10-25-20:46:06] Epoch: [246][5600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.996 (2.857) Prec@1 73.44 (77.01) Prec@5 91.41 (91.80) + train[2018-10-25-20:47:53] Epoch: [246][5800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.949 (2.856) Prec@1 73.44 (77.02) Prec@5 89.84 (91.80) + train[2018-10-25-20:49:40] Epoch: [246][6000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.584 (2.856) Prec@1 83.59 (77.03) Prec@5 96.88 (91.80) + train[2018-10-25-20:51:27] Epoch: [246][6200/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.873 (2.856) Prec@1 77.34 (77.01) Prec@5 89.06 (91.80) + train[2018-10-25-20:53:14] Epoch: [246][6400/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.970 (2.856) Prec@1 73.44 (77.02) Prec@5 91.41 (91.80) + train[2018-10-25-20:55:02] Epoch: [246][6600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.883 (2.857) Prec@1 75.00 (77.01) Prec@5 93.75 (91.80) + train[2018-10-25-20:56:50] Epoch: [246][6800/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 3.248 (2.857) Prec@1 68.75 (77.01) Prec@5 87.50 (91.79) + train[2018-10-25-20:58:37] Epoch: [246][7000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.151 (2.857) Prec@1 74.22 (77.00) Prec@5 89.84 (91.79) + train[2018-10-25-21:00:25] Epoch: [246][7200/10010] Time 0.49 (0.54) Data 0.00 (0.00) Loss 2.785 (2.858) Prec@1 78.12 (77.00) Prec@5 92.97 (91.79) + train[2018-10-25-21:02:13] Epoch: [246][7400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.693 (2.857) Prec@1 81.25 (77.00) Prec@5 96.09 (91.79) + train[2018-10-25-21:04:00] Epoch: [246][7600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.184 (2.858) Prec@1 67.19 (76.99) Prec@5 87.50 (91.78) + train[2018-10-25-21:05:47] Epoch: [246][7800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.627 (2.858) Prec@1 81.25 (76.99) Prec@5 94.53 (91.78) + train[2018-10-25-21:07:34] Epoch: [246][8000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.867 (2.858) Prec@1 75.00 (77.00) Prec@5 94.53 (91.78) + train[2018-10-25-21:09:20] Epoch: [246][8200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.427 (2.858) Prec@1 71.09 (76.99) Prec@5 85.94 (91.78) + train[2018-10-25-21:11:07] Epoch: [246][8400/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.963 (2.858) Prec@1 73.44 (76.99) Prec@5 90.62 (91.78) + train[2018-10-25-21:12:53] Epoch: [246][8600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.941 (2.858) Prec@1 76.56 (76.99) Prec@5 92.97 (91.78) + train[2018-10-25-21:14:40] Epoch: [246][8800/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.960 (2.858) Prec@1 75.00 (76.99) Prec@5 91.41 (91.78) + train[2018-10-25-21:16:27] Epoch: [246][9000/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.103 (2.858) Prec@1 72.66 (77.00) Prec@5 89.06 (91.78) + train[2018-10-25-21:18:15] Epoch: [246][9200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.879 (2.857) Prec@1 82.81 (77.00) Prec@5 92.19 (91.79) + train[2018-10-25-21:20:03] Epoch: [246][9400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.741 (2.857) Prec@1 82.03 (77.00) Prec@5 95.31 (91.79) + train[2018-10-25-21:21:49] Epoch: [246][9600/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.618 (2.858) Prec@1 81.25 (76.99) Prec@5 94.53 (91.78) + train[2018-10-25-21:23:35] Epoch: [246][9800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.784 (2.858) Prec@1 81.25 (76.99) Prec@5 92.97 (91.77) + train[2018-10-25-21:25:22] Epoch: [246][10000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.691 (2.859) Prec@1 78.12 (76.98) Prec@5 96.09 (91.77) + train[2018-10-25-21:25:27] Epoch: [246][10009/10010] Time 0.20 (0.54) Data 0.00 (0.00) Loss 3.587 (2.859) Prec@1 73.33 (76.98) Prec@5 93.33 (91.77) +[2018-10-25-21:25:27] **train** Prec@1 76.98 Prec@5 91.77 Error@1 23.02 Error@5 8.23 Loss:2.859 + test [2018-10-25-21:25:31] Epoch: [246][000/391] Time 4.19 (4.19) Data 4.06 (4.06) Loss 0.510 (0.510) Prec@1 93.75 (93.75) Prec@5 99.22 (99.22) + test [2018-10-25-21:25:58] Epoch: [246][200/391] Time 0.15 (0.16) Data 0.00 (0.03) Loss 1.193 (0.979) Prec@1 67.19 (77.55) Prec@5 92.19 (93.64) + test [2018-10-25-21:26:24] Epoch: [246][390/391] Time 0.09 (0.15) Data 0.00 (0.01) Loss 2.132 (1.148) Prec@1 48.75 (73.93) Prec@5 83.75 (91.46) +[2018-10-25-21:26:24] **test** Prec@1 73.93 Prec@5 91.46 Error@1 26.07 Error@5 8.54 Loss:1.148 +----> Best Accuracy : Acc@1=74.00, Acc@5=91.49, Error@1=26.00, Error@5=8.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-25-21:26:24] [Epoch=247/250] [Need: 04:31:15] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-25-21:26:29] Epoch: [247][000/10010] Time 5.03 (5.03) Data 4.43 (4.43) Loss 2.797 (2.797) Prec@1 72.66 (72.66) Prec@5 94.53 (94.53) + train[2018-10-25-21:28:15] Epoch: [247][200/10010] Time 0.50 (0.55) Data 0.00 (0.02) Loss 2.872 (2.837) Prec@1 78.12 (77.57) Prec@5 91.41 (91.86) + train[2018-10-25-21:30:01] Epoch: [247][400/10010] Time 0.54 (0.54) Data 0.00 (0.01) Loss 2.726 (2.843) Prec@1 76.56 (77.32) Prec@5 93.75 (91.86) + train[2018-10-25-21:31:47] Epoch: [247][600/10010] Time 0.52 (0.54) Data 0.00 (0.01) Loss 3.227 (2.854) Prec@1 71.09 (77.10) Prec@5 89.06 (91.79) + train[2018-10-25-21:33:33] Epoch: [247][800/10010] Time 0.57 (0.54) Data 0.00 (0.01) Loss 2.941 (2.857) Prec@1 72.66 (77.03) Prec@5 93.75 (91.81) + train[2018-10-25-21:35:19] Epoch: [247][1000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.829 (2.857) Prec@1 81.25 (77.01) Prec@5 92.19 (91.84) + train[2018-10-25-21:37:05] Epoch: [247][1200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.672 (2.856) Prec@1 81.25 (77.02) Prec@5 95.31 (91.84) + train[2018-10-25-21:38:51] Epoch: [247][1400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.750 (2.857) Prec@1 78.12 (76.99) Prec@5 92.19 (91.82) + train[2018-10-25-21:40:37] Epoch: [247][1600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.975 (2.857) Prec@1 72.66 (77.00) Prec@5 93.75 (91.82) + train[2018-10-25-21:42:22] Epoch: [247][1800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.783 (2.856) Prec@1 77.34 (77.03) Prec@5 92.19 (91.83) + train[2018-10-25-21:44:08] Epoch: [247][2000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.932 (2.855) Prec@1 75.00 (77.05) Prec@5 89.84 (91.83) + train[2018-10-25-21:45:54] Epoch: [247][2200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.801 (2.854) Prec@1 72.66 (77.07) Prec@5 93.75 (91.84) + train[2018-10-25-21:47:40] Epoch: [247][2400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.750 (2.854) Prec@1 78.91 (77.07) Prec@5 91.41 (91.83) + train[2018-10-25-21:49:25] Epoch: [247][2600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.906 (2.855) Prec@1 75.78 (77.05) Prec@5 89.84 (91.82) + train[2018-10-25-21:51:11] Epoch: [247][2800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.052 (2.857) Prec@1 76.56 (77.03) Prec@5 87.50 (91.80) + train[2018-10-25-21:52:57] Epoch: [247][3000/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.872 (2.856) Prec@1 79.69 (77.05) Prec@5 89.84 (91.80) + train[2018-10-25-21:54:44] Epoch: [247][3200/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.043 (2.857) Prec@1 69.53 (77.01) Prec@5 89.84 (91.79) + train[2018-10-25-21:56:29] Epoch: [247][3400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.624 (2.856) Prec@1 79.69 (77.04) Prec@5 95.31 (91.80) + train[2018-10-25-21:58:15] Epoch: [247][3600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.768 (2.855) Prec@1 77.34 (77.04) Prec@5 92.19 (91.81) + train[2018-10-25-22:00:01] Epoch: [247][3800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.022 (2.856) Prec@1 73.44 (77.03) Prec@5 89.84 (91.80) + train[2018-10-25-22:01:47] Epoch: [247][4000/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.871 (2.857) Prec@1 78.91 (77.01) Prec@5 90.62 (91.78) + train[2018-10-25-22:03:32] Epoch: [247][4200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.262 (2.858) Prec@1 67.19 (77.01) Prec@5 86.72 (91.77) + train[2018-10-25-22:05:19] Epoch: [247][4400/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.663 (2.858) Prec@1 77.34 (76.99) Prec@5 94.53 (91.77) + train[2018-10-25-22:07:05] Epoch: [247][4600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.879 (2.858) Prec@1 74.22 (76.99) Prec@5 92.19 (91.77) + train[2018-10-25-22:08:51] Epoch: [247][4800/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.851 (2.859) Prec@1 82.81 (76.98) Prec@5 92.97 (91.76) + train[2018-10-25-22:10:36] Epoch: [247][5000/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.897 (2.859) Prec@1 79.69 (76.97) Prec@5 88.28 (91.76) + train[2018-10-25-22:12:24] Epoch: [247][5200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.344 (2.859) Prec@1 70.31 (76.98) Prec@5 85.16 (91.76) + train[2018-10-25-22:14:11] Epoch: [247][5400/10010] Time 0.59 (0.53) Data 0.00 (0.00) Loss 2.918 (2.858) Prec@1 74.22 (77.00) Prec@5 90.62 (91.76) + train[2018-10-25-22:15:59] Epoch: [247][5600/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.805 (2.858) Prec@1 79.69 (77.00) Prec@5 92.19 (91.76) + train[2018-10-25-22:17:47] Epoch: [247][5800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.926 (2.859) Prec@1 74.22 (76.97) Prec@5 89.84 (91.75) + train[2018-10-25-22:19:34] Epoch: [247][6000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.778 (2.859) Prec@1 76.56 (76.97) Prec@5 91.41 (91.76) + train[2018-10-25-22:21:21] Epoch: [247][6200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.963 (2.860) Prec@1 76.56 (76.96) Prec@5 88.28 (91.75) + train[2018-10-25-22:23:09] Epoch: [247][6400/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 3.112 (2.860) Prec@1 75.78 (76.96) Prec@5 86.72 (91.75) + train[2018-10-25-22:24:57] Epoch: [247][6600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.674 (2.859) Prec@1 76.56 (76.97) Prec@5 93.75 (91.76) + train[2018-10-25-22:26:45] Epoch: [247][6800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.908 (2.859) Prec@1 75.00 (76.97) Prec@5 92.19 (91.77) + train[2018-10-25-22:28:33] Epoch: [247][7000/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.933 (2.859) Prec@1 75.00 (76.96) Prec@5 92.19 (91.77) + train[2018-10-25-22:30:21] Epoch: [247][7200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.999 (2.859) Prec@1 77.34 (76.98) Prec@5 89.06 (91.78) + train[2018-10-25-22:32:09] Epoch: [247][7400/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.550 (2.859) Prec@1 82.03 (76.98) Prec@5 95.31 (91.77) + train[2018-10-25-22:33:56] Epoch: [247][7600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.874 (2.859) Prec@1 73.44 (76.98) Prec@5 91.41 (91.78) + train[2018-10-25-22:35:45] Epoch: [247][7800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.665 (2.858) Prec@1 79.69 (76.99) Prec@5 92.97 (91.78) + train[2018-10-25-22:37:33] Epoch: [247][8000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.122 (2.858) Prec@1 73.44 (77.00) Prec@5 92.97 (91.79) + train[2018-10-25-22:39:22] Epoch: [247][8200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.202 (2.858) Prec@1 74.22 (77.00) Prec@5 86.72 (91.79) + train[2018-10-25-22:41:11] Epoch: [247][8400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.352 (2.858) Prec@1 69.53 (77.00) Prec@5 85.94 (91.79) + train[2018-10-25-22:42:59] Epoch: [247][8600/10010] Time 0.62 (0.53) Data 0.00 (0.00) Loss 2.599 (2.858) Prec@1 82.03 (76.99) Prec@5 95.31 (91.79) + train[2018-10-25-22:44:48] Epoch: [247][8800/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.722 (2.858) Prec@1 77.34 (77.00) Prec@5 93.75 (91.78) + train[2018-10-25-22:46:37] Epoch: [247][9000/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.965 (2.858) Prec@1 77.34 (77.00) Prec@5 91.41 (91.78) + train[2018-10-25-22:48:25] Epoch: [247][9200/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.764 (2.857) Prec@1 79.69 (77.01) Prec@5 92.97 (91.79) + train[2018-10-25-22:50:13] Epoch: [247][9400/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.731 (2.858) Prec@1 78.12 (77.01) Prec@5 92.97 (91.79) + train[2018-10-25-22:52:01] Epoch: [247][9600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.908 (2.858) Prec@1 70.31 (77.01) Prec@5 92.19 (91.79) + train[2018-10-25-22:53:51] Epoch: [247][9800/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.980 (2.858) Prec@1 75.00 (77.00) Prec@5 89.06 (91.78) + train[2018-10-25-22:55:38] Epoch: [247][10000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.842 (2.858) Prec@1 76.56 (77.00) Prec@5 90.62 (91.79) + train[2018-10-25-22:55:43] Epoch: [247][10009/10010] Time 0.19 (0.54) Data 0.00 (0.00) Loss 3.674 (2.858) Prec@1 53.33 (77.00) Prec@5 80.00 (91.79) +[2018-10-25-22:55:43] **train** Prec@1 77.00 Prec@5 91.79 Error@1 23.00 Error@5 8.21 Loss:2.858 + test [2018-10-25-22:55:47] Epoch: [247][000/391] Time 4.23 (4.23) Data 4.09 (4.09) Loss 0.544 (0.544) Prec@1 93.75 (93.75) Prec@5 98.44 (98.44) + test [2018-10-25-22:56:16] Epoch: [247][200/391] Time 0.14 (0.17) Data 0.02 (0.03) Loss 1.204 (0.997) Prec@1 68.75 (77.54) Prec@5 92.19 (93.67) + test [2018-10-25-22:56:42] Epoch: [247][390/391] Time 0.08 (0.15) Data 0.00 (0.02) Loss 2.183 (1.167) Prec@1 46.25 (73.88) Prec@5 83.75 (91.44) +[2018-10-25-22:56:42] **test** Prec@1 73.88 Prec@5 91.44 Error@1 26.12 Error@5 8.56 Loss:1.167 +----> Best Accuracy : Acc@1=74.00, Acc@5=91.49, Error@1=26.00, Error@5=8.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-25-22:56:42] [Epoch=248/250] [Need: 03:00:35] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-25-22:56:48] Epoch: [248][000/10010] Time 5.61 (5.61) Data 5.04 (5.04) Loss 2.906 (2.906) Prec@1 74.22 (74.22) Prec@5 89.06 (89.06) + train[2018-10-25-22:58:37] Epoch: [248][200/10010] Time 0.58 (0.57) Data 0.00 (0.03) Loss 2.390 (2.852) Prec@1 85.94 (76.74) Prec@5 97.66 (91.71) + train[2018-10-25-23:00:27] Epoch: [248][400/10010] Time 0.50 (0.56) Data 0.00 (0.01) Loss 2.780 (2.851) Prec@1 74.22 (76.85) Prec@5 92.97 (91.78) + train[2018-10-25-23:02:15] Epoch: [248][600/10010] Time 0.53 (0.55) Data 0.00 (0.01) Loss 2.928 (2.848) Prec@1 73.44 (76.97) Prec@5 92.97 (91.84) + train[2018-10-25-23:04:05] Epoch: [248][800/10010] Time 0.55 (0.55) Data 0.00 (0.01) Loss 2.596 (2.854) Prec@1 81.25 (76.89) Prec@5 96.09 (91.79) + train[2018-10-25-23:05:54] Epoch: [248][1000/10010] Time 0.52 (0.55) Data 0.00 (0.01) Loss 3.003 (2.849) Prec@1 78.91 (77.05) Prec@5 90.62 (91.84) + train[2018-10-25-23:07:44] Epoch: [248][1200/10010] Time 0.56 (0.55) Data 0.00 (0.00) Loss 2.800 (2.851) Prec@1 78.91 (77.01) Prec@5 92.19 (91.81) + train[2018-10-25-23:09:33] Epoch: [248][1400/10010] Time 0.51 (0.55) Data 0.00 (0.00) Loss 3.077 (2.849) Prec@1 73.44 (77.04) Prec@5 90.62 (91.84) + train[2018-10-25-23:11:21] Epoch: [248][1600/10010] Time 0.54 (0.55) Data 0.00 (0.00) Loss 3.007 (2.849) Prec@1 70.31 (77.03) Prec@5 92.97 (91.85) + train[2018-10-25-23:13:09] Epoch: [248][1800/10010] Time 0.52 (0.55) Data 0.00 (0.00) Loss 2.770 (2.850) Prec@1 81.25 (77.04) Prec@5 94.53 (91.84) + train[2018-10-25-23:14:57] Epoch: [248][2000/10010] Time 0.50 (0.55) Data 0.00 (0.00) Loss 2.866 (2.852) Prec@1 74.22 (77.04) Prec@5 92.19 (91.83) + train[2018-10-25-23:16:47] Epoch: [248][2200/10010] Time 0.57 (0.55) Data 0.00 (0.00) Loss 3.040 (2.853) Prec@1 72.66 (77.02) Prec@5 89.84 (91.83) + train[2018-10-25-23:18:35] Epoch: [248][2400/10010] Time 0.52 (0.55) Data 0.00 (0.00) Loss 2.807 (2.854) Prec@1 75.78 (77.00) Prec@5 95.31 (91.83) + train[2018-10-25-23:20:23] Epoch: [248][2600/10010] Time 0.57 (0.55) Data 0.00 (0.00) Loss 2.704 (2.852) Prec@1 81.25 (77.02) Prec@5 92.97 (91.84) + train[2018-10-25-23:22:12] Epoch: [248][2800/10010] Time 0.54 (0.55) Data 0.00 (0.00) Loss 2.706 (2.853) Prec@1 80.47 (77.04) Prec@5 90.62 (91.84) + train[2018-10-25-23:24:01] Epoch: [248][3000/10010] Time 0.52 (0.55) Data 0.00 (0.00) Loss 2.737 (2.852) Prec@1 78.12 (77.04) Prec@5 92.97 (91.84) + train[2018-10-25-23:25:49] Epoch: [248][3200/10010] Time 0.51 (0.55) Data 0.00 (0.00) Loss 2.893 (2.851) Prec@1 81.25 (77.05) Prec@5 91.41 (91.85) + train[2018-10-25-23:27:37] Epoch: [248][3400/10010] Time 0.52 (0.55) Data 0.00 (0.00) Loss 2.690 (2.851) Prec@1 78.12 (77.07) Prec@5 94.53 (91.85) + train[2018-10-25-23:29:24] Epoch: [248][3600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.871 (2.850) Prec@1 71.88 (77.07) Prec@5 92.97 (91.86) + train[2018-10-25-23:31:12] Epoch: [248][3800/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.938 (2.851) Prec@1 74.22 (77.06) Prec@5 94.53 (91.85) + train[2018-10-25-23:33:00] Epoch: [248][4000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.834 (2.851) Prec@1 78.91 (77.07) Prec@5 91.41 (91.85) + train[2018-10-25-23:34:48] Epoch: [248][4200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.764 (2.851) Prec@1 78.12 (77.06) Prec@5 92.97 (91.85) + train[2018-10-25-23:36:37] Epoch: [248][4400/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.897 (2.851) Prec@1 72.66 (77.06) Prec@5 89.84 (91.85) + train[2018-10-25-23:38:27] Epoch: [248][4600/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.735 (2.852) Prec@1 84.38 (77.06) Prec@5 93.75 (91.85) + train[2018-10-25-23:40:15] Epoch: [248][4800/10010] Time 0.61 (0.54) Data 0.00 (0.00) Loss 2.715 (2.852) Prec@1 78.12 (77.06) Prec@5 91.41 (91.85) + train[2018-10-25-23:42:04] Epoch: [248][5000/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 2.939 (2.852) Prec@1 75.78 (77.04) Prec@5 92.97 (91.85) + train[2018-10-25-23:43:53] Epoch: [248][5200/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.630 (2.852) Prec@1 80.47 (77.05) Prec@5 92.97 (91.86) + train[2018-10-25-23:45:42] Epoch: [248][5400/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.880 (2.851) Prec@1 78.91 (77.07) Prec@5 89.84 (91.87) + train[2018-10-25-23:47:32] Epoch: [248][5600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.036 (2.851) Prec@1 75.00 (77.06) Prec@5 91.41 (91.86) + train[2018-10-25-23:49:21] Epoch: [248][5800/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 3.242 (2.852) Prec@1 69.53 (77.04) Prec@5 88.28 (91.86) + train[2018-10-25-23:51:10] Epoch: [248][6000/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.029 (2.852) Prec@1 75.78 (77.03) Prec@5 89.06 (91.87) + train[2018-10-25-23:52:58] Epoch: [248][6200/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.012 (2.852) Prec@1 74.22 (77.03) Prec@5 89.06 (91.87) + train[2018-10-25-23:54:47] Epoch: [248][6400/10010] Time 0.57 (0.54) Data 0.00 (0.00) Loss 3.131 (2.852) Prec@1 69.53 (77.03) Prec@5 89.84 (91.87) + train[2018-10-25-23:56:35] Epoch: [248][6600/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.638 (2.852) Prec@1 81.25 (77.04) Prec@5 92.97 (91.87) + train[2018-10-25-23:58:24] Epoch: [248][6800/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.807 (2.853) Prec@1 77.34 (77.03) Prec@5 90.62 (91.87) + train[2018-10-26-00:00:11] Epoch: [248][7000/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.594 (2.853) Prec@1 80.47 (77.03) Prec@5 93.75 (91.87) + train[2018-10-26-00:01:59] Epoch: [248][7200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.862 (2.853) Prec@1 75.00 (77.02) Prec@5 90.62 (91.86) + train[2018-10-26-00:03:47] Epoch: [248][7400/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 3.007 (2.854) Prec@1 73.44 (77.01) Prec@5 91.41 (91.86) + train[2018-10-26-00:05:35] Epoch: [248][7600/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.942 (2.854) Prec@1 74.22 (77.01) Prec@5 90.62 (91.86) + train[2018-10-26-00:07:23] Epoch: [248][7800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.672 (2.854) Prec@1 79.69 (77.00) Prec@5 96.09 (91.86) + train[2018-10-26-00:09:13] Epoch: [248][8000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.585 (2.853) Prec@1 76.56 (77.01) Prec@5 96.88 (91.86) + train[2018-10-26-00:11:02] Epoch: [248][8200/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 2.681 (2.853) Prec@1 81.25 (77.01) Prec@5 96.88 (91.87) + train[2018-10-26-00:12:51] Epoch: [248][8400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.877 (2.853) Prec@1 77.34 (77.01) Prec@5 91.41 (91.87) + train[2018-10-26-00:14:41] Epoch: [248][8600/10010] Time 0.64 (0.54) Data 0.00 (0.00) Loss 2.884 (2.854) Prec@1 75.78 (77.01) Prec@5 94.53 (91.87) + train[2018-10-26-00:16:30] Epoch: [248][8800/10010] Time 0.51 (0.54) Data 0.00 (0.00) Loss 3.051 (2.854) Prec@1 75.00 (77.01) Prec@5 87.50 (91.87) + train[2018-10-26-00:18:18] Epoch: [248][9000/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.774 (2.854) Prec@1 81.25 (77.01) Prec@5 92.19 (91.87) + train[2018-10-26-00:20:08] Epoch: [248][9200/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.003 (2.854) Prec@1 75.00 (77.01) Prec@5 89.84 (91.86) + train[2018-10-26-00:21:55] Epoch: [248][9400/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.982 (2.854) Prec@1 72.66 (77.00) Prec@5 89.06 (91.86) + train[2018-10-26-00:23:45] Epoch: [248][9600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.748 (2.854) Prec@1 75.78 (77.00) Prec@5 90.62 (91.86) + train[2018-10-26-00:25:34] Epoch: [248][9800/10010] Time 0.56 (0.54) Data 0.00 (0.00) Loss 2.676 (2.855) Prec@1 82.03 (76.99) Prec@5 92.97 (91.85) + train[2018-10-26-00:27:23] Epoch: [248][10000/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.981 (2.854) Prec@1 75.00 (77.00) Prec@5 91.41 (91.85) + train[2018-10-26-00:27:27] Epoch: [248][10009/10010] Time 0.19 (0.54) Data 0.00 (0.00) Loss 3.543 (2.854) Prec@1 66.67 (77.00) Prec@5 86.67 (91.85) +[2018-10-26-00:27:27] **train** Prec@1 77.00 Prec@5 91.85 Error@1 23.00 Error@5 8.15 Loss:2.854 + test [2018-10-26-00:27:31] Epoch: [248][000/391] Time 3.91 (3.91) Data 3.77 (3.77) Loss 0.545 (0.545) Prec@1 92.97 (92.97) Prec@5 97.66 (97.66) + test [2018-10-26-00:28:00] Epoch: [248][200/391] Time 0.12 (0.16) Data 0.00 (0.03) Loss 1.174 (0.987) Prec@1 69.53 (77.40) Prec@5 92.19 (93.71) + test [2018-10-26-00:28:27] Epoch: [248][390/391] Time 0.09 (0.15) Data 0.00 (0.02) Loss 2.111 (1.153) Prec@1 45.00 (73.89) Prec@5 85.00 (91.52) +[2018-10-26-00:28:27] **test** Prec@1 73.89 Prec@5 91.52 Error@1 26.11 Error@5 8.48 Loss:1.153 +----> Best Accuracy : Acc@1=74.00, Acc@5=91.49, Error@1=26.00, Error@5=8.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth + +==>>[2018-10-26-00:28:27] [Epoch=249/250] [Need: 01:31:44] LR=0.0001 ~ 0.0001, Batch=128 + train[2018-10-26-00:28:31] Epoch: [249][000/10010] Time 4.29 (4.29) Data 3.66 (3.66) Loss 2.643 (2.643) Prec@1 81.25 (81.25) Prec@5 94.53 (94.53) + train[2018-10-26-00:30:17] Epoch: [249][200/10010] Time 0.51 (0.55) Data 0.00 (0.02) Loss 2.732 (2.845) Prec@1 80.47 (77.25) Prec@5 91.41 (92.08) + train[2018-10-26-00:32:02] Epoch: [249][400/10010] Time 0.53 (0.54) Data 0.00 (0.01) Loss 2.911 (2.849) Prec@1 75.00 (77.26) Prec@5 92.97 (91.95) + train[2018-10-26-00:33:47] Epoch: [249][600/10010] Time 0.52 (0.53) Data 0.00 (0.01) Loss 3.060 (2.848) Prec@1 73.44 (77.30) Prec@5 89.84 (92.01) + train[2018-10-26-00:35:33] Epoch: [249][800/10010] Time 0.51 (0.53) Data 0.00 (0.01) Loss 2.800 (2.849) Prec@1 75.00 (77.27) Prec@5 92.19 (91.97) + train[2018-10-26-00:37:19] Epoch: [249][1000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.860 (2.851) Prec@1 76.56 (77.22) Prec@5 92.97 (91.93) + train[2018-10-26-00:39:04] Epoch: [249][1200/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.794 (2.851) Prec@1 73.44 (77.21) Prec@5 91.41 (91.92) + train[2018-10-26-00:40:49] Epoch: [249][1400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.811 (2.848) Prec@1 75.00 (77.24) Prec@5 93.75 (91.96) + train[2018-10-26-00:42:36] Epoch: [249][1600/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 3.166 (2.849) Prec@1 78.12 (77.19) Prec@5 89.84 (91.95) + train[2018-10-26-00:44:21] Epoch: [249][1800/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.521 (2.851) Prec@1 82.81 (77.17) Prec@5 93.75 (91.92) + train[2018-10-26-00:46:07] Epoch: [249][2000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 3.112 (2.852) Prec@1 75.78 (77.14) Prec@5 89.06 (91.90) + train[2018-10-26-00:47:52] Epoch: [249][2200/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.889 (2.853) Prec@1 71.09 (77.14) Prec@5 90.62 (91.91) + train[2018-10-26-00:49:38] Epoch: [249][2400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.958 (2.852) Prec@1 76.56 (77.18) Prec@5 91.41 (91.90) + train[2018-10-26-00:51:24] Epoch: [249][2600/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.748 (2.853) Prec@1 80.47 (77.17) Prec@5 92.97 (91.90) + train[2018-10-26-00:53:11] Epoch: [249][2800/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.488 (2.854) Prec@1 85.16 (77.12) Prec@5 94.53 (91.88) + train[2018-10-26-00:54:58] Epoch: [249][3000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 3.067 (2.853) Prec@1 75.00 (77.11) Prec@5 88.28 (91.90) + train[2018-10-26-00:56:45] Epoch: [249][3200/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.778 (2.854) Prec@1 80.47 (77.07) Prec@5 92.19 (91.89) + train[2018-10-26-00:58:31] Epoch: [249][3400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.784 (2.853) Prec@1 74.22 (77.09) Prec@5 93.75 (91.90) + train[2018-10-26-01:00:19] Epoch: [249][3600/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.847 (2.853) Prec@1 75.78 (77.08) Prec@5 91.41 (91.89) + train[2018-10-26-01:02:06] Epoch: [249][3800/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.035 (2.854) Prec@1 76.56 (77.07) Prec@5 88.28 (91.88) + train[2018-10-26-01:03:55] Epoch: [249][4000/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.924 (2.854) Prec@1 74.22 (77.08) Prec@5 92.97 (91.88) + train[2018-10-26-01:05:42] Epoch: [249][4200/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.784 (2.854) Prec@1 77.34 (77.08) Prec@5 92.97 (91.87) + train[2018-10-26-01:07:30] Epoch: [249][4400/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 3.018 (2.853) Prec@1 75.78 (77.09) Prec@5 91.41 (91.88) + train[2018-10-26-01:09:17] Epoch: [249][4600/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.669 (2.853) Prec@1 82.81 (77.08) Prec@5 93.75 (91.88) + train[2018-10-26-01:11:03] Epoch: [249][4800/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 2.943 (2.852) Prec@1 75.78 (77.09) Prec@5 89.84 (91.90) + train[2018-10-26-01:12:51] Epoch: [249][5000/10010] Time 0.52 (0.53) Data 0.00 (0.00) Loss 2.670 (2.852) Prec@1 78.12 (77.09) Prec@5 92.97 (91.90) + train[2018-10-26-01:14:37] Epoch: [249][5200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.606 (2.851) Prec@1 85.94 (77.09) Prec@5 94.53 (91.91) + train[2018-10-26-01:16:25] Epoch: [249][5400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.008 (2.852) Prec@1 74.22 (77.08) Prec@5 89.84 (91.91) + train[2018-10-26-01:18:12] Epoch: [249][5600/10010] Time 0.58 (0.53) Data 0.00 (0.00) Loss 2.653 (2.852) Prec@1 77.34 (77.07) Prec@5 92.97 (91.90) + train[2018-10-26-01:20:00] Epoch: [249][5800/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.770 (2.853) Prec@1 77.34 (77.06) Prec@5 92.19 (91.89) + train[2018-10-26-01:21:48] Epoch: [249][6000/10010] Time 0.51 (0.53) Data 0.00 (0.00) Loss 2.645 (2.853) Prec@1 78.12 (77.06) Prec@5 96.88 (91.89) + train[2018-10-26-01:23:36] Epoch: [249][6200/10010] Time 0.56 (0.53) Data 0.00 (0.00) Loss 2.903 (2.853) Prec@1 78.91 (77.05) Prec@5 88.28 (91.89) + train[2018-10-26-01:25:25] Epoch: [249][6400/10010] Time 0.50 (0.53) Data 0.00 (0.00) Loss 3.142 (2.853) Prec@1 67.97 (77.05) Prec@5 88.28 (91.89) + train[2018-10-26-01:27:14] Epoch: [249][6600/10010] Time 0.54 (0.53) Data 0.00 (0.00) Loss 2.775 (2.853) Prec@1 76.56 (77.05) Prec@5 92.97 (91.89) + train[2018-10-26-01:29:01] Epoch: [249][6800/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 2.841 (2.854) Prec@1 76.56 (77.04) Prec@5 93.75 (91.89) + train[2018-10-26-01:30:50] Epoch: [249][7000/10010] Time 0.53 (0.53) Data 0.00 (0.00) Loss 2.546 (2.854) Prec@1 84.38 (77.05) Prec@5 96.88 (91.88) + train[2018-10-26-01:32:38] Epoch: [249][7200/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 3.018 (2.854) Prec@1 76.56 (77.05) Prec@5 89.84 (91.88) + train[2018-10-26-01:34:25] Epoch: [249][7400/10010] Time 0.55 (0.53) Data 0.00 (0.00) Loss 3.146 (2.854) Prec@1 73.44 (77.05) Prec@5 90.62 (91.87) + train[2018-10-26-01:36:13] Epoch: [249][7600/10010] Time 0.57 (0.53) Data 0.00 (0.00) Loss 2.607 (2.854) Prec@1 80.47 (77.05) Prec@5 95.31 (91.88) + train[2018-10-26-01:38:01] Epoch: [249][7800/10010] Time 0.58 (0.54) Data 0.00 (0.00) Loss 2.828 (2.853) Prec@1 80.47 (77.05) Prec@5 92.19 (91.88) + train[2018-10-26-01:39:48] Epoch: [249][8000/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.605 (2.854) Prec@1 82.03 (77.05) Prec@5 94.53 (91.87) + train[2018-10-26-01:41:36] Epoch: [249][8200/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.795 (2.854) Prec@1 75.78 (77.05) Prec@5 93.75 (91.87) + train[2018-10-26-01:43:22] Epoch: [249][8400/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.693 (2.854) Prec@1 83.59 (77.05) Prec@5 94.53 (91.87) + train[2018-10-26-01:45:09] Epoch: [249][8600/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.912 (2.853) Prec@1 73.44 (77.06) Prec@5 95.31 (91.88) + train[2018-10-26-01:46:57] Epoch: [249][8800/10010] Time 0.53 (0.54) Data 0.00 (0.00) Loss 2.653 (2.854) Prec@1 80.47 (77.05) Prec@5 92.97 (91.87) + train[2018-10-26-01:48:45] Epoch: [249][9000/10010] Time 0.55 (0.54) Data 0.00 (0.00) Loss 2.919 (2.854) Prec@1 77.34 (77.05) Prec@5 92.19 (91.87) + train[2018-10-26-01:50:32] Epoch: [249][9200/10010] Time 0.52 (0.54) Data 0.00 (0.00) Loss 2.806 (2.854) Prec@1 79.69 (77.04) Prec@5 92.19 (91.87) + train[2018-10-26-01:52:20] Epoch: [249][9400/10010] Time 0.50 (0.54) Data 0.00 (0.00) Loss 2.797 (2.854) Prec@1 80.47 (77.04) Prec@5 91.41 (91.86) + train[2018-10-26-01:54:08] Epoch: [249][9600/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.789 (2.854) Prec@1 76.56 (77.05) Prec@5 92.19 (91.87) + train[2018-10-26-01:55:56] Epoch: [249][9800/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 2.631 (2.853) Prec@1 79.69 (77.06) Prec@5 95.31 (91.87) + train[2018-10-26-01:57:44] Epoch: [249][10000/10010] Time 0.54 (0.54) Data 0.00 (0.00) Loss 3.023 (2.853) Prec@1 70.31 (77.05) Prec@5 91.41 (91.87) + train[2018-10-26-01:57:48] Epoch: [249][10009/10010] Time 0.19 (0.54) Data 0.00 (0.00) Loss 2.848 (2.853) Prec@1 73.33 (77.05) Prec@5 86.67 (91.87) +[2018-10-26-01:57:48] **train** Prec@1 77.05 Prec@5 91.87 Error@1 22.95 Error@5 8.13 Loss:2.853 + test [2018-10-26-01:57:52] Epoch: [249][000/391] Time 4.44 (4.44) Data 4.30 (4.30) Loss 0.554 (0.554) Prec@1 91.41 (91.41) Prec@5 98.44 (98.44) + test [2018-10-26-01:58:23] Epoch: [249][200/391] Time 0.12 (0.18) Data 0.00 (0.04) Loss 1.190 (0.988) Prec@1 67.19 (77.41) Prec@5 92.19 (93.73) + test [2018-10-26-01:58:50] Epoch: [249][390/391] Time 0.08 (0.16) Data 0.00 (0.03) Loss 2.108 (1.156) Prec@1 46.25 (73.85) Prec@5 83.75 (91.47) +[2018-10-26-01:58:50] **test** Prec@1 73.85 Prec@5 91.47 Error@1 26.15 Error@5 8.53 Loss:1.156 +----> Best Accuracy : Acc@1=74.00, Acc@5=91.49, Error@1=26.00, Error@5=8.51 +----> Save into ./snapshots/NAS/DMS_V1-imagenet-C50-L14-E250/seed-3993/checkpoint-imagenet-model.pth diff --git a/scripts-cluster/job-script.sh b/scripts-cluster/job-script.sh index 79b40ac..172f563 100644 --- a/scripts-cluster/job-script.sh +++ b/scripts-cluster/job-script.sh @@ -1,13 +1,15 @@ #!/bin/bash # echo "CHECK-DATA-DIR START" -sh /home/HGCP_Program/software-install/afs_mount/bin/afs_mount.sh \ - COMM_KM_Data COMM_km_2018 \ - `pwd`/hadoop-data \ - afs://xingtian.afs.baidu.com:9902/user/COMM_KM_Data/dongxuanyi/datasets +#sh /home/HGCP_Program/software-install/afs_mount/bin/afs_mount.sh \ +# COMM_KM_Data COMM_km_2018 \ +# `pwd`/hadoop-data \ +# afs://xingtian.afs.baidu.com:9902/user/COMM_KM_Data/dongxuanyi/datasets export TORCH_HOME="./data/data/" -tar xvf ./hadoop-data/cifar.python.tar -C ${TORCH_HOME} +wget -q http://10.127.2.44:8000/cifar.python.tar --directory-prefix=${TORCH_HOME} +tar xvf ${TORCH_HOME}/cifar.python.tar -C ${TORCH_HOME} +rm ${TORCH_HOME}/cifar.python.tar #tar xvf ./hadoop-data/ILSVRC2012.tar -C ${TORCH_HOME} cifar_dir="${TORCH_HOME}/cifar.python" diff --git a/scripts-cnn/train-imagenet.sh b/scripts-cnn/train-imagenet.sh index 8a1e05a..d934ebd 100644 --- a/scripts-cnn/train-imagenet.sh +++ b/scripts-cnn/train-imagenet.sh @@ -29,22 +29,35 @@ else tar --version #tar xf ./hadoop-data/ILSVRC2012.tar -C ${TORCH_HOME} commands="./data/data/get_imagenet.sh" - ${PY_C} ./data/decompress.py ./hadoop-data/ILSVRC2012-TAR ./data/data/ILSVRC2012 tar > ${commands} + #${PY_C} ./data/decompress.py ./hadoop-data/ILSVRC2012-TAR ./data/data/ILSVRC2012 tar > ${commands} #${PY_C} ./data/decompress.py ./hadoop-data/ILSVRC2012-ZIP ./data/data/ILSVRC2012 zip > ./data/data/get_imagenet.sh #bash ./data/data/get_imagenet.sh + #count=0 + #while read -r line; do + # temp_file="./data/data/TEMP-${count}.sh" + # echo "${line}" > ${temp_file} + # bash ${temp_file} + # count=$((count+1)) + #${PY_C} ./data/ps_mem.py -p $$ + # free -g + #done < "${commands}" + #wget http://10.127.2.44:8000/ILSVRC2012.tar --directory-prefix=${TORCH_HOME} + ${PY_C} ./data/decompress.py ./data/classes.txt ${TORCH_HOME}/ILSVRC2012 wget > ${commands} count=0 while read -r line; do temp_file="./data/data/TEMP-${count}.sh" echo "${line}" > ${temp_file} bash ${temp_file} count=$((count+1)) + #${PY_C} ./data/ps_mem.py -p $$ + # free -g done < "${commands}" + #echo "Copy ILSVRC2012 done" + #tar -xvf ${TORCH_HOME}/ILSVRC2012.tar -C ${TORCH_HOME} + #rm ${TORCH_HOME}/ILSVRC2012.tar echo "Unzip ILSVRC2012 done" fi -exit 1 - - ${PY_C} --version ${PY_C} ./exps-cnn/train_base.py \