
=== Start adding workers ===
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=10,rank=0,shuffle=True)'}
=> Add worker SGDMWorker(index=0, momentum=0.9)
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=10,rank=1,shuffle=True)'}
=> Add worker SGDMWorker(index=1, momentum=0.9)
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=10,rank=2,shuffle=True)'}
=> Add worker SGDMWorker(index=2, momentum=0.9)
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=10,rank=3,shuffle=True)'}
=> Add worker SGDMWorker(index=3, momentum=0.9)
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=10,rank=4,shuffle=True)'}
=> Add worker SGDMWorker(index=4, momentum=0.9)
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=10,rank=5,shuffle=True)'}
=> Add worker SGDMWorker(index=5, momentum=0.9)
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=10,rank=6,shuffle=True)'}
=> Add worker SGDMWorker(index=6, momentum=0.9)
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=10,rank=7,shuffle=True)'}
=> Add worker SGDMWorker(index=7, momentum=0.9)
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=10,rank=8,shuffle=True)'}
=> Add worker SGDMWorker(index=8, momentum=0.9)
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=10,rank=9,shuffle=True)'}
=> Add worker SGDMWorker(index=9, momentum=0.9)

=== Start adding graph ===
<codes.graph_utils.Dumbbell object at 0x7f8e1b249730>

{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': False, 'download': True, 'batch_size': 128, 'shuffle': False, 'sampler': None}
Train epoch 1
[E 1B0  |    640/50000 (  1%) ] Loss: 2.3038 top1=  9.2188

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([1, 4, 1, 1, 1], device='cuda:0')
Worker 1 has targets: tensor([1, 4, 2, 2, 3], device='cuda:0')
Worker 2 has targets: tensor([1, 2, 4, 2, 3], device='cuda:0')
Worker 3 has targets: tensor([1, 0, 4, 3, 0], device='cuda:0')
Worker 4 has targets: tensor([4, 0, 0, 4, 0], device='cuda:0')
Worker 5 has targets: tensor([9, 6, 8, 9, 9], device='cuda:0')
Worker 6 has targets: tensor([6, 9, 5, 9, 9], device='cuda:0')
Worker 7 has targets: tensor([8, 5, 8, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([9, 7, 5, 5, 8], device='cuda:0')
Worker 9 has targets: tensor([8, 9, 7, 5, 7], device='cuda:0')



=== Log mixing matrix @ E1B0 ===
[[0.167 0.167 0.167 0.167 0.167 0.    0.    0.    0.    0.167]
 [0.167 0.333 0.167 0.167 0.167 0.    0.    0.    0.    0.   ]
 [0.167 0.167 0.333 0.167 0.167 0.    0.    0.    0.    0.   ]
 [0.167 0.167 0.167 0.333 0.167 0.    0.    0.    0.    0.   ]
 [0.167 0.167 0.167 0.167 0.333 0.    0.    0.    0.    0.   ]
 [0.    0.    0.    0.    0.    0.333 0.167 0.167 0.167 0.167]
 [0.    0.    0.    0.    0.    0.167 0.333 0.167 0.167 0.167]
 [0.    0.    0.    0.    0.    0.167 0.167 0.333 0.167 0.167]
 [0.    0.    0.    0.    0.    0.167 0.167 0.167 0.333 0.167]
 [0.167 0.    0.    0.    0.    0.167 0.167 0.167 0.167 0.167]]


[E 1B10 |   7040/50000 ( 14%) ] Loss: 1.8365 top1= 20.1562
[E 1B20 |  13440/50000 ( 27%) ] Loss: 1.6527 top1= 16.5625
[E 1B30 |  19840/50000 ( 40%) ] Loss: 1.6090 top1= 22.3438
[E 1B40 |  26240/50000 ( 52%) ] Loss: 1.6206 top1= 23.9062
[E 1B50 |  32640/50000 ( 65%) ] Loss: 1.5530 top1= 30.1562
[E 1B60 |  39040/50000 ( 78%) ] Loss: 1.5400 top1= 30.7812
[E 1B70 |  45440/50000 ( 91%) ] Loss: 1.4034 top1= 36.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3096 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5407 top1= 16.1058


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9386 top1= 14.1426

Train epoch 2
[E 2B0  |    640/50000 (  1%) ] Loss: 1.4667 top1= 32.3438
[E 2B10 |   7040/50000 ( 14%) ] Loss: 1.4333 top1= 35.7812
[E 2B20 |  13440/50000 ( 27%) ] Loss: 1.4383 top1= 33.5938
[E 2B30 |  19840/50000 ( 40%) ] Loss: 1.4240 top1= 33.5938
[E 2B40 |  26240/50000 ( 52%) ] Loss: 1.3252 top1= 41.7188
[E 2B50 |  32640/50000 ( 65%) ] Loss: 1.3433 top1= 37.5000
[E 2B60 |  39040/50000 ( 78%) ] Loss: 1.3338 top1= 38.5938
[E 2B70 |  45440/50000 ( 91%) ] Loss: 1.3030 top1= 40.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3078 top1= 11.0978


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3224 top1= 17.1875


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7498 top1= 16.7167

Train epoch 3
[E 3B0  |    640/50000 (  1%) ] Loss: 1.3556 top1= 36.8750
[E 3B10 |   7040/50000 ( 14%) ] Loss: 1.3268 top1= 39.3750
[E 3B20 |  13440/50000 ( 27%) ] Loss: 1.2957 top1= 41.4062
[E 3B30 |  19840/50000 ( 40%) ] Loss: 1.3556 top1= 34.8438
[E 3B40 |  26240/50000 ( 52%) ] Loss: 1.2428 top1= 46.2500
[E 3B50 |  32640/50000 ( 65%) ] Loss: 1.2319 top1= 44.2188
[E 3B60 |  39040/50000 ( 78%) ] Loss: 1.2261 top1= 48.9062
[E 3B70 |  45440/50000 ( 91%) ] Loss: 1.1989 top1= 47.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3068 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1835 top1= 19.5312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3393 top1= 10.5970

Train epoch 4
[E 4B0  |    640/50000 (  1%) ] Loss: 1.2332 top1= 45.7812
[E 4B10 |   7040/50000 ( 14%) ] Loss: 1.2008 top1= 44.3750
[E 4B20 |  13440/50000 ( 27%) ] Loss: 1.2118 top1= 45.4688
[E 4B30 |  19840/50000 ( 40%) ] Loss: 1.2243 top1= 43.2812
[E 4B40 |  26240/50000 ( 52%) ] Loss: 1.1367 top1= 53.7500
[E 4B50 |  32640/50000 ( 65%) ] Loss: 1.2586 top1= 48.1250
[E 4B60 |  39040/50000 ( 78%) ] Loss: 1.1918 top1= 51.0938
[E 4B70 |  45440/50000 ( 91%) ] Loss: 1.1373 top1= 50.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3069 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6141 top1= 21.8349


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4109 top1= 10.1763

Train epoch 5
[E 5B0  |    640/50000 (  1%) ] Loss: 1.1389 top1= 49.6875
[E 5B10 |   7040/50000 ( 14%) ] Loss: 1.1626 top1= 50.1562
[E 5B20 |  13440/50000 ( 27%) ] Loss: 1.1697 top1= 51.0938
[E 5B30 |  19840/50000 ( 40%) ] Loss: 1.1644 top1= 52.5000
[E 5B40 |  26240/50000 ( 52%) ] Loss: 1.1015 top1= 53.9062
[E 5B50 |  32640/50000 ( 65%) ] Loss: 1.1444 top1= 52.3438
[E 5B60 |  39040/50000 ( 78%) ] Loss: 1.1333 top1= 52.5000
[E 5B70 |  45440/50000 ( 91%) ] Loss: 1.0365 top1= 52.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3096 top1= 10.0060


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0271 top1= 15.6751


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5242 top1= 10.1462

Train epoch 6
[E 6B0  |    640/50000 (  1%) ] Loss: 1.1321 top1= 51.7188
[E 6B10 |   7040/50000 ( 14%) ] Loss: 1.1672 top1= 52.9688
[E 6B20 |  13440/50000 ( 27%) ] Loss: 1.1718 top1= 50.1562
[E 6B30 |  19840/50000 ( 40%) ] Loss: 1.1003 top1= 53.7500
[E 6B40 |  26240/50000 ( 52%) ] Loss: 1.0016 top1= 61.5625
[E 6B50 |  32640/50000 ( 65%) ] Loss: 1.0791 top1= 55.6250
[E 6B60 |  39040/50000 ( 78%) ] Loss: 1.0573 top1= 58.4375
[E 6B70 |  45440/50000 ( 91%) ] Loss: 1.0576 top1= 56.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3099 top1= 10.0060


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8244 top1= 14.3930


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4247 top1= 10.0160

Train epoch 7
[E 7B0  |    640/50000 (  1%) ] Loss: 1.2227 top1= 51.7188
[E 7B10 |   7040/50000 ( 14%) ] Loss: 1.1080 top1= 55.7812
[E 7B20 |  13440/50000 ( 27%) ] Loss: 1.1720 top1= 52.3438
[E 7B30 |  19840/50000 ( 40%) ] Loss: 1.1244 top1= 56.2500
[E 7B40 |  26240/50000 ( 52%) ] Loss: 1.1364 top1= 53.4375
[E 7B50 |  32640/50000 ( 65%) ] Loss: 1.1341 top1= 55.1562
[E 7B60 |  39040/50000 ( 78%) ] Loss: 1.0665 top1= 56.0938
[E 7B70 |  45440/50000 ( 91%) ] Loss: 0.9924 top1= 60.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3091 top1= 10.0060


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5273 top1= 11.8289


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7795 top1= 10.0160

Train epoch 8
[E 8B0  |    640/50000 (  1%) ] Loss: 1.1491 top1= 53.7500
[E 8B10 |   7040/50000 ( 14%) ] Loss: 1.1211 top1= 58.9062
[E 8B20 |  13440/50000 ( 27%) ] Loss: 1.0518 top1= 56.8750
[E 8B30 |  19840/50000 ( 40%) ] Loss: 1.1486 top1= 53.2812
[E 8B40 |  26240/50000 ( 52%) ] Loss: 1.0359 top1= 56.5625
[E 8B50 |  32640/50000 ( 65%) ] Loss: 1.1392 top1= 54.0625
[E 8B60 |  39040/50000 ( 78%) ] Loss: 1.1425 top1= 53.1250
[E 8B70 |  45440/50000 ( 91%) ] Loss: 1.0178 top1= 59.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3059 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9217 top1= 15.5449


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5991 top1= 10.0160

Train epoch 9
[E 9B0  |    640/50000 (  1%) ] Loss: 1.0708 top1= 54.2188
[E 9B10 |   7040/50000 ( 14%) ] Loss: 1.0147 top1= 60.1562
[E 9B20 |  13440/50000 ( 27%) ] Loss: 1.0541 top1= 57.5000
[E 9B30 |  19840/50000 ( 40%) ] Loss: 1.1370 top1= 52.3438
[E 9B40 |  26240/50000 ( 52%) ] Loss: 1.0757 top1= 54.2188
[E 9B50 |  32640/50000 ( 65%) ] Loss: 1.1070 top1= 55.3125
[E 9B60 |  39040/50000 ( 78%) ] Loss: 1.0857 top1= 55.4688
[E 9B70 |  45440/50000 ( 91%) ] Loss: 1.0011 top1= 60.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3069 top1= 10.0060


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7920 top1= 17.0673


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3443 top1= 10.0962

Train epoch 10
[E10B0  |    640/50000 (  1%) ] Loss: 1.0990 top1= 53.2812
[E10B10 |   7040/50000 ( 14%) ] Loss: 1.0934 top1= 55.1562
[E10B20 |  13440/50000 ( 27%) ] Loss: 1.0809 top1= 54.5312
[E10B30 |  19840/50000 ( 40%) ] Loss: 1.0372 top1= 57.9688
[E10B40 |  26240/50000 ( 52%) ] Loss: 1.0249 top1= 60.6250
[E10B50 |  32640/50000 ( 65%) ] Loss: 1.0584 top1= 55.7812
[E10B60 |  39040/50000 ( 78%) ] Loss: 1.0449 top1= 57.6562
[E10B70 |  45440/50000 ( 91%) ] Loss: 1.0259 top1= 58.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3135 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7034 top1= 12.2997


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5998 top1= 10.0160

Train epoch 11
[E11B0  |    640/50000 (  1%) ] Loss: 1.1076 top1= 53.5938
[E11B10 |   7040/50000 ( 14%) ] Loss: 0.9800 top1= 61.0938
[E11B20 |  13440/50000 ( 27%) ] Loss: 1.0370 top1= 57.0312
[E11B30 |  19840/50000 ( 40%) ] Loss: 1.0457 top1= 57.1875
[E11B40 |  26240/50000 ( 52%) ] Loss: 1.0224 top1= 57.9688
[E11B50 |  32640/50000 ( 65%) ] Loss: 1.0115 top1= 60.0000
[E11B60 |  39040/50000 ( 78%) ] Loss: 1.0374 top1= 57.3438
[E11B70 |  45440/50000 ( 91%) ] Loss: 1.0229 top1= 60.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3130 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5950 top1= 10.4367


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5528 top1= 10.1462

Train epoch 12
[E12B0  |    640/50000 (  1%) ] Loss: 1.1138 top1= 54.3750
[E12B10 |   7040/50000 ( 14%) ] Loss: 1.0526 top1= 58.5938
[E12B20 |  13440/50000 ( 27%) ] Loss: 1.0096 top1= 57.3438
[E12B30 |  19840/50000 ( 40%) ] Loss: 1.1131 top1= 54.8438
[E12B40 |  26240/50000 ( 52%) ] Loss: 0.9656 top1= 60.0000
[E12B50 |  32640/50000 ( 65%) ] Loss: 1.0554 top1= 58.2812
[E12B60 |  39040/50000 ( 78%) ] Loss: 1.0427 top1= 55.0000
[E12B70 |  45440/50000 ( 91%) ] Loss: 0.9416 top1= 62.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3160 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4972 top1= 12.6102


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5341 top1= 10.0160

Train epoch 13
[E13B0  |    640/50000 (  1%) ] Loss: 1.0397 top1= 57.0312
[E13B10 |   7040/50000 ( 14%) ] Loss: 1.0251 top1= 57.1875
[E13B20 |  13440/50000 ( 27%) ] Loss: 1.0526 top1= 55.4688
[E13B30 |  19840/50000 ( 40%) ] Loss: 0.9656 top1= 59.3750
[E13B40 |  26240/50000 ( 52%) ] Loss: 0.9835 top1= 60.6250
[E13B50 |  32640/50000 ( 65%) ] Loss: 1.0074 top1= 58.7500
[E13B60 |  39040/50000 ( 78%) ] Loss: 0.9888 top1= 63.1250
[E13B70 |  45440/50000 ( 91%) ] Loss: 1.0015 top1= 59.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3119 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8798 top1= 13.9323


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0268 top1= 10.0361

Train epoch 14
[E14B0  |    640/50000 (  1%) ] Loss: 1.0719 top1= 59.0625
[E14B10 |   7040/50000 ( 14%) ] Loss: 1.0447 top1= 58.1250
[E14B20 |  13440/50000 ( 27%) ] Loss: 1.0522 top1= 57.0312
[E14B30 |  19840/50000 ( 40%) ] Loss: 1.0503 top1= 58.7500
[E14B40 |  26240/50000 ( 52%) ] Loss: 1.0074 top1= 61.8750
[E14B50 |  32640/50000 ( 65%) ] Loss: 1.0003 top1= 58.7500
[E14B60 |  39040/50000 ( 78%) ] Loss: 1.0006 top1= 61.7188
[E14B70 |  45440/50000 ( 91%) ] Loss: 0.9872 top1= 62.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3174 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3691 top1= 10.1362


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0260 top1= 10.9175

Train epoch 15
[E15B0  |    640/50000 (  1%) ] Loss: 1.0488 top1= 57.3438
[E15B10 |   7040/50000 ( 14%) ] Loss: 1.0724 top1= 58.9062
[E15B20 |  13440/50000 ( 27%) ] Loss: 1.0845 top1= 56.8750
[E15B30 |  19840/50000 ( 40%) ] Loss: 1.0836 top1= 59.6875
[E15B40 |  26240/50000 ( 52%) ] Loss: 1.0389 top1= 60.6250
[E15B50 |  32640/50000 ( 65%) ] Loss: 1.1829 top1= 53.5938
[E15B60 |  39040/50000 ( 78%) ] Loss: 1.0676 top1= 56.7188
[E15B70 |  45440/50000 ( 91%) ] Loss: 1.0078 top1= 60.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3148 top1= 10.0060


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4651 top1= 10.3065


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7737 top1= 10.1763

Train epoch 16
[E16B0  |    640/50000 (  1%) ] Loss: 1.0991 top1= 52.8125
[E16B10 |   7040/50000 ( 14%) ] Loss: 1.0304 top1= 57.9688
[E16B20 |  13440/50000 ( 27%) ] Loss: 1.1239 top1= 56.8750
[E16B30 |  19840/50000 ( 40%) ] Loss: 1.1232 top1= 53.7500
[E16B40 |  26240/50000 ( 52%) ] Loss: 0.9806 top1= 64.0625
[E16B50 |  32640/50000 ( 65%) ] Loss: 1.1166 top1= 58.7500
[E16B60 |  39040/50000 ( 78%) ] Loss: 1.0510 top1= 55.1562
[E16B70 |  45440/50000 ( 91%) ] Loss: 1.0275 top1= 60.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3239 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8387 top1= 10.5869


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8516 top1= 12.4900

Train epoch 17
[E17B0  |    640/50000 (  1%) ] Loss: 1.0546 top1= 54.5312
[E17B10 |   7040/50000 ( 14%) ] Loss: 1.1724 top1= 52.0312
[E17B20 |  13440/50000 ( 27%) ] Loss: 1.1119 top1= 54.5312
[E17B30 |  19840/50000 ( 40%) ] Loss: 1.1722 top1= 55.0000
[E17B40 |  26240/50000 ( 52%) ] Loss: 1.0244 top1= 61.0938
[E17B50 |  32640/50000 ( 65%) ] Loss: 1.0445 top1= 58.7500
[E17B60 |  39040/50000 ( 78%) ] Loss: 1.0954 top1= 57.8125
[E17B70 |  45440/50000 ( 91%) ] Loss: 1.0855 top1= 56.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3284 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7719 top1= 10.0561


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5417 top1= 10.9876

Train epoch 18
[E18B0  |    640/50000 (  1%) ] Loss: 1.1312 top1= 54.5312
[E18B10 |   7040/50000 ( 14%) ] Loss: 1.1013 top1= 57.8125
[E18B20 |  13440/50000 ( 27%) ] Loss: 1.1549 top1= 52.8125
[E18B30 |  19840/50000 ( 40%) ] Loss: 1.0747 top1= 55.3125
[E18B40 |  26240/50000 ( 52%) ] Loss: 1.0208 top1= 58.1250
[E18B50 |  32640/50000 ( 65%) ] Loss: 1.1202 top1= 55.7812
[E18B60 |  39040/50000 ( 78%) ] Loss: 1.0705 top1= 58.1250
[E18B70 |  45440/50000 ( 91%) ] Loss: 1.0356 top1= 56.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3236 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5687 top1= 10.1462


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7270 top1= 10.4367

Train epoch 19
[E19B0  |    640/50000 (  1%) ] Loss: 1.1836 top1= 50.0000
[E19B10 |   7040/50000 ( 14%) ] Loss: 1.1157 top1= 55.9375
[E19B20 |  13440/50000 ( 27%) ] Loss: 1.2018 top1= 52.0312
[E19B30 |  19840/50000 ( 40%) ] Loss: 1.0991 top1= 54.8438
[E19B40 |  26240/50000 ( 52%) ] Loss: 1.0889 top1= 53.7500
[E19B50 |  32640/50000 ( 65%) ] Loss: 1.2115 top1= 50.6250
[E19B60 |  39040/50000 ( 78%) ] Loss: 1.1084 top1= 53.4375
[E19B70 |  45440/50000 ( 91%) ] Loss: 1.1489 top1= 52.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3167 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4825 top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6810 top1= 13.0008

Train epoch 20
[E20B0  |    640/50000 (  1%) ] Loss: 1.2697 top1= 45.0000
[E20B10 |   7040/50000 ( 14%) ] Loss: 1.3017 top1= 50.0000
[E20B20 |  13440/50000 ( 27%) ] Loss: 1.2303 top1= 49.6875
[E20B30 |  19840/50000 ( 40%) ] Loss: 1.2452 top1= 49.6875
[E20B40 |  26240/50000 ( 52%) ] Loss: 1.1562 top1= 49.6875
[E20B50 |  32640/50000 ( 65%) ] Loss: 1.1855 top1= 48.4375
[E20B60 |  39040/50000 ( 78%) ] Loss: 1.1790 top1= 48.7500
[E20B70 |  45440/50000 ( 91%) ] Loss: 1.2414 top1= 50.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3339 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5627 top1= 13.7119


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3051 top1= 10.4968

Train epoch 21
[E21B0  |    640/50000 (  1%) ] Loss: 1.2503 top1= 45.3125
[E21B10 |   7040/50000 ( 14%) ] Loss: 1.2622 top1= 45.4688
[E21B20 |  13440/50000 ( 27%) ] Loss: 1.3650 top1= 39.8438
[E21B30 |  19840/50000 ( 40%) ] Loss: 1.4140 top1= 35.1562
[E21B40 |  26240/50000 ( 52%) ] Loss: 1.3510 top1= 43.5938
[E21B50 |  32640/50000 ( 65%) ] Loss: 1.4227 top1= 41.8750
[E21B60 |  39040/50000 ( 78%) ] Loss: 1.2960 top1= 45.9375
[E21B70 |  45440/50000 ( 91%) ] Loss: 1.2696 top1= 45.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3377 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6303 top1= 10.2063


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7459 top1=  9.9860

Train epoch 22
[E22B0  |    640/50000 (  1%) ] Loss: 1.3530 top1= 39.0625
[E22B10 |   7040/50000 ( 14%) ] Loss: 1.3146 top1= 40.9375
[E22B20 |  13440/50000 ( 27%) ] Loss: 1.3077 top1= 42.1875
[E22B30 |  19840/50000 ( 40%) ] Loss: 1.3729 top1= 38.5938
[E22B40 |  26240/50000 ( 52%) ] Loss: 1.3609 top1= 41.0938
[E22B50 |  32640/50000 ( 65%) ] Loss: 1.4026 top1= 39.8438
[E22B60 |  39040/50000 ( 78%) ] Loss: 1.4292 top1= 37.5000
[E22B70 |  45440/50000 ( 91%) ] Loss: 1.3864 top1= 36.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3192 top1=  7.2716


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5479 top1= 12.4700


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3194 top1= 10.0661

Train epoch 23
[E23B0  |    640/50000 (  1%) ] Loss: 1.4192 top1= 35.9375
[E23B10 |   7040/50000 ( 14%) ] Loss: 1.4151 top1= 39.5312
[E23B20 |  13440/50000 ( 27%) ] Loss: 1.3606 top1= 33.5938
[E23B30 |  19840/50000 ( 40%) ] Loss: 1.4574 top1= 33.5938
[E23B40 |  26240/50000 ( 52%) ] Loss: 1.5055 top1= 35.6250
[E23B50 |  32640/50000 ( 65%) ] Loss: 1.4114 top1= 37.3438
[E23B60 |  39040/50000 ( 78%) ] Loss: 1.4519 top1= 31.0938
[E23B70 |  45440/50000 ( 91%) ] Loss: 1.4152 top1= 35.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3219 top1=  9.7957


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6478 top1= 10.7973


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4131 top1= 10.0661

Train epoch 24
[E24B0  |    640/50000 (  1%) ] Loss: 1.4561 top1= 31.8750
[E24B10 |   7040/50000 ( 14%) ] Loss: 1.4894 top1= 31.5625
[E24B20 |  13440/50000 ( 27%) ] Loss: 1.4907 top1= 30.0000
[E24B30 |  19840/50000 ( 40%) ] Loss: 1.4547 top1= 31.0938
[E24B40 |  26240/50000 ( 52%) ] Loss: 1.3658 top1= 38.7500
[E24B50 |  32640/50000 ( 65%) ] Loss: 1.4362 top1= 35.7812
[E24B60 |  39040/50000 ( 78%) ] Loss: 1.4315 top1= 36.8750
[E24B70 |  45440/50000 ( 91%) ] Loss: 1.3875 top1= 37.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3161 top1=  7.6322


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7575 top1= 10.7572


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4938 top1= 10.0160

Train epoch 25
[E25B0  |    640/50000 (  1%) ] Loss: 1.4267 top1= 36.2500
[E25B10 |   7040/50000 ( 14%) ] Loss: nan top1= 31.8750
[E25B20 |  13440/50000 ( 27%) ] Loss: nan top1= 27.6562
[E25B30 |  19840/50000 ( 40%) ] Loss: nan top1= 26.0938
[E25B40 |  26240/50000 ( 52%) ] Loss: nan top1= 32.0312
[E25B50 |  32640/50000 ( 65%) ] Loss: nan top1= 28.9062
[E25B60 |  39040/50000 ( 78%) ] Loss: nan top1= 27.8125
[E25B70 |  45440/50000 ( 91%) ] Loss: nan top1= 26.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 26
[E26B0  |    640/50000 (  1%) ] Loss: nan top1= 25.7812
[E26B10 |   7040/50000 ( 14%) ] Loss: nan top1= 24.2188
[E26B20 |  13440/50000 ( 27%) ] Loss: nan top1= 27.8125
[E26B30 |  19840/50000 ( 40%) ] Loss: nan top1= 27.6562
[E26B40 |  26240/50000 ( 52%) ] Loss: nan top1= 31.5625
[E26B50 |  32640/50000 ( 65%) ] Loss: nan top1= 27.3438
[E26B60 |  39040/50000 ( 78%) ] Loss: nan top1= 26.5625
[E26B70 |  45440/50000 ( 91%) ] Loss: nan top1= 22.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 27
[E27B0  |    640/50000 (  1%) ] Loss: nan top1= 20.4688
[E27B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E27B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E27B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E27B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E27B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E27B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E27B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 28
[E28B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E28B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E28B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E28B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E28B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E28B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E28B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E28B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 29
[E29B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E29B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E29B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E29B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E29B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E29B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E29B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E29B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 30
[E30B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E30B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E30B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E30B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E30B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E30B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E30B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E30B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 31
[E31B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E31B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E31B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E31B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E31B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E31B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E31B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E31B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 32
[E32B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E32B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E32B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E32B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E32B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E32B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E32B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E32B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 33
[E33B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E33B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E33B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E33B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E33B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E33B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E33B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E33B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 34
[E34B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E34B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E34B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E34B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E34B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E34B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E34B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E34B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 35
[E35B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E35B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E35B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E35B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E35B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E35B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E35B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E35B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 36
[E36B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E36B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E36B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E36B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E36B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E36B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E36B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E36B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 37
[E37B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E37B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E37B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E37B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E37B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E37B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E37B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E37B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 38
[E38B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E38B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E38B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E38B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E38B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E38B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E38B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E38B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 39
[E39B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E39B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E39B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E39B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E39B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E39B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E39B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E39B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 40
[E40B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E40B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E40B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E40B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E40B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E40B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E40B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E40B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 41
[E41B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E41B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E41B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E41B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E41B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E41B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E41B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E41B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 42
[E42B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E42B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E42B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E42B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E42B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E42B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E42B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E42B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 43
[E43B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E43B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E43B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E43B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E43B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E43B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E43B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E43B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 44
[E44B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E44B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E44B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E44B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E44B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E44B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E44B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E44B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 45
[E45B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E45B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E45B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E45B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E45B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E45B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E45B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E45B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 46
[E46B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E46B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E46B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E46B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E46B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E46B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E46B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E46B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 47
[E47B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E47B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E47B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E47B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E47B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E47B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E47B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E47B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 48
[E48B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E48B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E48B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E48B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E48B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E48B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E48B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E48B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 49
[E49B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E49B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E49B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E49B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E49B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E49B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E49B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E49B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 50
[E50B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E50B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E50B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E50B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E50B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E50B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E50B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E50B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 51
[E51B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E51B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E51B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E51B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E51B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E51B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E51B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E51B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 52
[E52B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E52B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E52B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E52B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E52B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E52B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E52B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E52B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 53
[E53B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E53B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E53B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E53B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E53B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E53B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E53B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E53B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 54
[E54B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E54B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E54B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E54B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E54B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E54B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E54B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E54B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 55
[E55B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E55B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E55B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E55B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E55B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E55B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E55B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E55B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 56
[E56B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E56B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E56B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E56B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E56B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E56B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E56B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E56B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 57
[E57B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E57B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E57B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E57B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E57B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E57B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E57B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E57B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 58
[E58B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E58B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E58B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E58B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E58B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E58B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E58B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E58B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 59
[E59B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E59B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E59B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E59B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E59B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E59B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E59B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E59B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 60
[E60B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E60B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E60B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E60B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E60B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E60B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E60B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E60B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 61
[E61B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E61B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E61B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E61B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E61B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E61B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E61B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E61B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 62
[E62B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E62B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E62B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E62B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E62B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E62B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E62B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E62B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 63
[E63B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E63B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E63B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E63B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E63B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E63B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E63B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E63B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 64
[E64B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E64B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E64B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E64B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E64B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E64B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E64B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E64B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 65
[E65B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E65B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E65B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E65B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E65B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E65B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E65B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E65B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 66
[E66B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E66B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E66B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E66B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E66B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E66B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E66B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E66B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 67
[E67B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E67B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E67B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E67B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E67B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E67B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E67B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E67B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 68
[E68B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E68B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E68B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E68B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E68B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E68B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E68B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E68B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 69
[E69B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E69B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E69B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E69B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E69B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E69B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E69B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E69B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 70
[E70B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E70B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E70B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E70B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E70B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E70B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E70B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E70B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 71
[E71B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E71B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E71B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E71B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E71B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E71B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E71B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E71B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 72
[E72B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E72B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E72B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E72B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E72B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E72B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E72B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E72B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 73
[E73B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E73B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E73B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E73B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E73B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E73B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E73B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E73B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 74
[E74B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E74B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E74B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E74B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E74B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E74B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E74B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E74B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 75
[E75B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E75B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E75B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E75B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E75B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E75B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E75B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E75B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 76
[E76B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E76B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E76B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E76B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E76B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E76B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E76B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E76B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 77
[E77B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E77B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E77B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E77B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E77B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E77B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E77B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E77B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 78
[E78B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E78B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E78B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E78B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E78B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E78B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E78B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E78B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 79
[E79B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E79B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E79B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E79B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E79B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E79B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E79B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E79B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 80
[E80B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E80B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E80B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E80B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E80B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E80B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E80B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E80B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 81
[E81B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E81B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E81B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E81B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E81B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E81B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E81B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E81B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 82
[E82B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E82B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E82B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E82B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E82B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E82B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E82B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E82B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 83
[E83B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E83B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E83B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E83B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E83B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E83B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E83B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E83B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 84
[E84B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E84B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E84B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E84B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E84B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E84B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E84B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E84B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 85
[E85B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E85B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E85B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E85B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E85B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E85B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E85B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E85B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 86
[E86B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E86B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E86B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E86B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E86B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E86B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E86B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E86B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 87
[E87B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E87B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E87B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E87B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E87B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E87B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E87B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E87B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 88
[E88B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E88B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E88B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E88B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E88B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E88B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E88B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E88B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 89
[E89B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E89B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E89B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E89B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E89B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E89B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E89B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E89B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 90
[E90B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E90B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E90B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E90B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E90B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E90B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E90B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E90B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 91
[E91B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E91B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E91B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E91B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E91B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E91B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E91B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E91B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 92
[E92B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E92B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E92B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E92B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E92B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E92B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E92B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E92B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 93
[E93B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E93B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E93B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E93B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E93B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E93B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E93B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E93B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 94
[E94B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E94B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E94B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E94B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E94B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E94B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E94B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E94B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 95
[E95B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E95B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E95B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E95B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E95B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E95B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E95B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E95B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 96
[E96B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E96B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E96B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E96B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E96B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E96B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E96B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E96B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 97
[E97B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E97B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E97B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E97B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E97B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E97B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E97B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E97B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 98
[E98B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E98B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E98B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E98B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E98B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E98B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E98B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E98B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 99
[E99B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E99B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E99B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E99B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E99B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E99B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E99B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E99B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 100
[E100B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E100B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E100B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E100B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E100B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E100B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E100B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E100B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 101
[E101B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E101B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E101B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E101B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E101B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E101B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E101B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E101B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 102
[E102B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E102B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E102B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E102B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E102B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E102B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E102B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E102B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 103
[E103B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E103B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E103B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E103B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E103B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E103B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E103B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E103B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 104
[E104B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E104B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E104B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E104B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E104B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E104B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E104B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E104B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 105
[E105B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E105B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E105B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E105B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E105B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E105B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E105B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E105B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 106
[E106B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E106B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E106B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E106B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E106B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E106B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E106B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E106B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 107
[E107B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E107B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E107B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E107B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E107B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E107B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E107B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E107B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 108
[E108B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E108B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E108B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E108B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E108B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E108B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E108B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E108B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 109
[E109B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E109B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E109B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E109B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E109B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E109B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E109B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E109B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 110
[E110B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E110B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E110B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E110B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E110B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E110B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E110B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E110B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 111
[E111B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E111B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E111B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E111B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E111B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E111B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E111B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E111B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 112
[E112B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E112B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E112B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E112B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E112B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E112B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E112B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E112B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 113
[E113B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E113B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E113B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E113B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E113B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E113B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E113B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E113B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 114
[E114B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E114B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E114B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E114B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E114B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E114B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E114B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E114B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 115
[E115B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E115B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E115B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E115B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E115B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E115B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E115B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E115B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 116
[E116B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E116B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E116B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E116B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E116B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E116B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E116B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E116B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 117
[E117B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E117B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E117B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E117B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E117B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E117B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E117B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E117B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 118
[E118B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E118B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E118B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E118B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E118B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E118B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E118B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E118B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 119
[E119B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E119B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E119B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E119B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E119B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E119B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E119B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E119B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 120
[E120B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E120B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E120B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E120B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E120B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E120B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E120B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E120B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 121
[E121B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E121B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E121B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E121B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E121B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E121B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E121B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E121B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 122
[E122B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E122B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E122B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E122B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E122B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E122B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E122B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E122B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 123
[E123B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E123B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E123B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E123B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E123B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E123B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E123B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E123B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 124
[E124B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E124B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E124B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E124B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E124B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E124B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E124B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E124B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 125
[E125B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E125B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E125B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E125B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E125B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E125B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E125B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E125B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 126
[E126B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E126B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E126B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E126B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E126B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E126B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E126B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E126B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 127
[E127B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E127B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E127B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E127B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E127B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E127B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E127B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E127B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 128
[E128B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E128B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E128B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E128B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E128B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E128B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E128B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E128B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 129
[E129B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E129B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E129B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E129B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E129B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E129B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E129B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E129B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 130
[E130B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E130B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E130B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E130B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E130B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E130B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E130B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E130B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 131
[E131B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E131B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E131B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E131B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E131B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E131B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E131B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E131B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 132
[E132B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E132B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E132B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E132B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E132B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E132B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E132B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E132B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 133
[E133B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E133B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E133B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E133B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E133B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E133B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E133B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E133B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 134
[E134B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E134B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E134B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E134B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E134B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E134B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E134B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E134B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 135
[E135B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E135B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E135B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E135B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E135B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E135B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E135B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E135B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 136
[E136B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E136B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E136B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E136B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E136B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E136B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E136B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E136B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 137
[E137B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E137B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E137B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E137B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E137B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E137B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E137B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E137B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 138
[E138B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E138B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E138B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E138B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E138B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E138B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E138B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E138B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 139
[E139B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E139B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E139B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E139B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E139B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E139B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E139B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E139B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 140
[E140B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E140B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E140B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E140B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E140B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E140B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E140B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E140B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 141
[E141B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E141B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E141B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E141B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E141B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E141B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E141B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E141B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 142
[E142B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E142B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E142B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E142B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E142B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E142B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E142B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E142B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 143
[E143B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E143B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E143B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E143B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E143B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E143B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E143B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E143B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 144
[E144B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E144B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E144B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E144B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E144B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E144B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E144B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E144B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 145
[E145B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E145B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E145B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E145B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E145B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E145B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E145B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E145B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 146
[E146B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E146B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E146B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E146B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E146B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E146B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E146B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E146B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 147
[E147B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E147B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E147B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E147B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E147B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E147B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E147B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E147B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 148
[E148B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E148B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E148B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E148B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E148B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E148B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E148B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E148B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 149
[E149B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E149B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E149B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E149B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E149B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E149B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E149B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E149B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

Train epoch 150
[E150B0  |    640/50000 (  1%) ] Loss: nan top1=  9.0625
[E150B10 |   7040/50000 ( 14%) ] Loss: nan top1=  9.8438
[E150B20 |  13440/50000 ( 27%) ] Loss: nan top1= 10.3125
[E150B30 |  19840/50000 ( 40%) ] Loss: nan top1=  9.5312
[E150B40 |  26240/50000 ( 52%) ] Loss: nan top1= 11.8750
[E150B50 |  32640/50000 ( 65%) ] Loss: nan top1= 12.8125
[E150B60 |  39040/50000 ( 78%) ] Loss: nan top1= 10.1562
[E150B70 |  45440/50000 ( 91%) ] Loss: nan top1=  9.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=nan top1=  9.9960

