
=== 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=20,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=20,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=20,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=20,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=20,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=20,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=20,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=20,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=20,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=20,rank=9,shuffle=True)'}
=> Add worker SGDMWorker(index=9, 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=20,rank=10,shuffle=True)'}
=> Add worker SGDMWorker(index=10, 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=20,rank=11,shuffle=True)'}
=> Add worker SGDMWorker(index=11, 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=20,rank=12,shuffle=True)'}
=> Add worker SGDMWorker(index=12, 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=20,rank=13,shuffle=True)'}
=> Add worker SGDMWorker(index=13, 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=20,rank=14,shuffle=True)'}
=> Add worker SGDMWorker(index=14, 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=20,rank=15,shuffle=True)'}
=> Add worker SGDMWorker(index=15, 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=20,rank=16,shuffle=True)'}
=> Add worker SGDMWorker(index=16, 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=20,rank=17,shuffle=True)'}
=> Add worker SGDMWorker(index=17, 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=20,rank=18,shuffle=True)'}
=> Add worker SGDMWorker(index=18, 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=20,rank=19,shuffle=True)'}
=> Add worker SGDMWorker(index=19, momentum=0.9)

=== Start adding graph ===
<codes.graph_utils.Dumbbell object at 0x7fcd916ad730>

{'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  |   1280/50000 (  3%) ] Loss: 2.3045 top1= 10.5469

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([2, 4, 4, 3, 2], device='cuda:0')
Worker 1 has targets: tensor([1, 2, 0, 2, 3], device='cuda:0')
Worker 2 has targets: tensor([4, 4, 2, 4, 3], device='cuda:0')
Worker 3 has targets: tensor([0, 1, 3, 0, 2], device='cuda:0')
Worker 4 has targets: tensor([2, 4, 2, 1, 3], device='cuda:0')
Worker 5 has targets: tensor([2, 1, 4, 1, 4], device='cuda:0')
Worker 6 has targets: tensor([3, 4, 2, 1, 2], device='cuda:0')
Worker 7 has targets: tensor([0, 0, 4, 2, 2], device='cuda:0')
Worker 8 has targets: tensor([0, 4, 3, 0, 2], device='cuda:0')
Worker 9 has targets: tensor([3, 4, 3, 3, 1], device='cuda:0')
Worker 10 has targets: tensor([6, 7, 6, 9, 6], device='cuda:0')
Worker 11 has targets: tensor([9, 8, 6, 8, 8], device='cuda:0')
Worker 12 has targets: tensor([5, 8, 7, 6, 5], device='cuda:0')
Worker 13 has targets: tensor([7, 5, 9, 8, 9], device='cuda:0')
Worker 14 has targets: tensor([5, 9, 7, 7, 5], device='cuda:0')
Worker 15 has targets: tensor([8, 8, 5, 7, 9], device='cuda:0')
Worker 16 has targets: tensor([7, 7, 9, 6, 8], device='cuda:0')
Worker 17 has targets: tensor([5, 6, 9, 9, 5], device='cuda:0')
Worker 18 has targets: tensor([5, 9, 9, 9, 9], device='cuda:0')
Worker 19 has targets: tensor([7, 5, 8, 8, 9], device='cuda:0')



=== Log mixing matrix @ E1B0 ===
[[0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.    0.
  0.    0.    0.    0.    0.    0.    0.    0.091]
 [0.091 0.182 0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.    0.
  0.    0.    0.    0.    0.    0.    0.    0.   ]
 [0.091 0.091 0.182 0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.    0.
  0.    0.    0.    0.    0.    0.    0.    0.   ]
 [0.091 0.091 0.091 0.182 0.091 0.091 0.091 0.091 0.091 0.091 0.    0.
  0.    0.    0.    0.    0.    0.    0.    0.   ]
 [0.091 0.091 0.091 0.091 0.182 0.091 0.091 0.091 0.091 0.091 0.    0.
  0.    0.    0.    0.    0.    0.    0.    0.   ]
 [0.091 0.091 0.091 0.091 0.091 0.182 0.091 0.091 0.091 0.091 0.    0.
  0.    0.    0.    0.    0.    0.    0.    0.   ]
 [0.091 0.091 0.091 0.091 0.091 0.091 0.182 0.091 0.091 0.091 0.    0.
  0.    0.    0.    0.    0.    0.    0.    0.   ]
 [0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.182 0.091 0.091 0.    0.
  0.    0.    0.    0.    0.    0.    0.    0.   ]
 [0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.182 0.091 0.    0.
  0.    0.    0.    0.    0.    0.    0.    0.   ]
 [0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.182 0.    0.
  0.    0.    0.    0.    0.    0.    0.    0.   ]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.182 0.091
  0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.091]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.091 0.182
  0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.091]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.091 0.091
  0.182 0.091 0.091 0.091 0.091 0.091 0.091 0.091]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.091 0.091
  0.091 0.182 0.091 0.091 0.091 0.091 0.091 0.091]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.091 0.091
  0.091 0.091 0.182 0.091 0.091 0.091 0.091 0.091]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.091 0.091
  0.091 0.091 0.091 0.182 0.091 0.091 0.091 0.091]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.091 0.091
  0.091 0.091 0.091 0.091 0.182 0.091 0.091 0.091]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.091 0.091
  0.091 0.091 0.091 0.091 0.091 0.182 0.091 0.091]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.091 0.091
  0.091 0.091 0.091 0.091 0.091 0.091 0.182 0.091]
 [0.091 0.    0.    0.    0.    0.    0.    0.    0.    0.    0.091 0.091
  0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.091]]


[E 1B10 |  14080/50000 ( 28%) ] Loss: 2.0717 top1= 19.8438
[E 1B20 |  26880/50000 ( 54%) ] Loss: 1.8130 top1= 20.5469
[E 1B30 |  39680/50000 ( 79%) ] Loss: 1.6893 top1= 20.3906

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3080 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2658 top1=  9.9860


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4570 top1= 14.3730

Train epoch 2
[E 2B0  |   1280/50000 (  3%) ] Loss: 1.6233 top1= 24.7656
[E 2B10 |  14080/50000 ( 28%) ] Loss: 1.6560 top1= 22.3438
[E 2B20 |  26880/50000 ( 54%) ] Loss: 1.6121 top1= 24.4531
[E 2B30 |  39680/50000 ( 79%) ] Loss: 1.5720 top1= 25.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3232 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9463 top1= 15.6751


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5158 top1= 16.1158

Train epoch 3
[E 3B0  |   1280/50000 (  3%) ] Loss: 1.5606 top1= 28.5938
[E 3B10 |  14080/50000 ( 28%) ] Loss: 1.4859 top1= 32.3438
[E 3B20 |  26880/50000 ( 54%) ] Loss: 1.4938 top1= 32.6562
[E 3B30 |  39680/50000 ( 79%) ] Loss: 1.6464 top1= 23.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3283 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5488 top1= 15.0641


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8848 top1= 14.4131

Train epoch 4
[E 4B0  |   1280/50000 (  3%) ] Loss: 1.5323 top1= 29.1406
[E 4B10 |  14080/50000 ( 28%) ] Loss: 1.4124 top1= 35.4688
[E 4B20 |  26880/50000 ( 54%) ] Loss: 1.5833 top1= 31.0938
[E 4B30 |  39680/50000 ( 79%) ] Loss: 1.3806 top1= 36.7969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3184 top1= 10.0060


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6482 top1= 16.9972


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0904 top1= 23.2572

Train epoch 5
[E 5B0  |   1280/50000 (  3%) ] Loss: 1.3718 top1= 40.6250
[E 5B10 |  14080/50000 ( 28%) ] Loss: 1.3604 top1= 42.1094
[E 5B20 |  26880/50000 ( 54%) ] Loss: 1.3124 top1= 42.5781
[E 5B30 |  39680/50000 ( 79%) ] Loss: 1.2914 top1= 41.4844

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3410 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7675 top1= 17.9287


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0059 top1= 27.1034

Train epoch 6
[E 6B0  |   1280/50000 (  3%) ] Loss: 1.2428 top1= 43.5156
[E 6B10 |  14080/50000 ( 28%) ] Loss: 1.2859 top1= 39.1406
[E 6B20 |  26880/50000 ( 54%) ] Loss: 1.2875 top1= 40.6250
[E 6B30 |  39680/50000 ( 79%) ] Loss: 1.2669 top1= 43.3594

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3479 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4622 top1= 18.6999


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8933 top1= 27.5741

Train epoch 7
[E 7B0  |   1280/50000 (  3%) ] Loss: 1.2508 top1= 45.0781
[E 7B10 |  14080/50000 ( 28%) ] Loss: 1.1916 top1= 49.3750
[E 7B20 |  26880/50000 ( 54%) ] Loss: 1.1619 top1= 49.9219
[E 7B30 |  39680/50000 ( 79%) ] Loss: 1.0756 top1= 54.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3649 top1= 10.0060


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2565 top1= 24.8397


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0341 top1= 30.8193

Train epoch 8
[E 8B0  |   1280/50000 (  3%) ] Loss: 1.1103 top1= 56.7188
[E 8B10 |  14080/50000 ( 28%) ] Loss: 1.0866 top1= 56.7188
[E 8B20 |  26880/50000 ( 54%) ] Loss: 1.0229 top1= 58.7500
[E 8B30 |  39680/50000 ( 79%) ] Loss: 0.9459 top1= 62.4219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3879 top1= 10.0060


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8142 top1= 28.2552


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1141 top1= 36.0777

Train epoch 9
[E 9B0  |   1280/50000 (  3%) ] Loss: 0.9258 top1= 64.4531
[E 9B10 |  14080/50000 ( 28%) ] Loss: 0.9339 top1= 61.7969
[E 9B20 |  26880/50000 ( 54%) ] Loss: 0.9587 top1= 61.9531
[E 9B30 |  39680/50000 ( 79%) ] Loss: 0.9010 top1= 65.0781

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3937 top1= 10.0260


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8617 top1= 29.6575


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9836 top1= 36.1178

Train epoch 10
[E10B0  |   1280/50000 (  3%) ] Loss: 0.8828 top1= 65.7812
[E10B10 |  14080/50000 ( 28%) ] Loss: 0.8954 top1= 64.9219
[E10B20 |  26880/50000 ( 54%) ] Loss: 0.8720 top1= 66.2500
[E10B30 |  39680/50000 ( 79%) ] Loss: 0.7687 top1= 71.0156

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4086 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0595 top1= 31.3802


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5031 top1= 37.1494

Train epoch 11
[E11B0  |   1280/50000 (  3%) ] Loss: 0.8876 top1= 68.9844
[E11B10 |  14080/50000 ( 28%) ] Loss: 0.7981 top1= 68.3594
[E11B20 |  26880/50000 ( 54%) ] Loss: 0.7879 top1= 69.0625
[E11B30 |  39680/50000 ( 79%) ] Loss: 0.7078 top1= 72.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3993 top1= 10.0260


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8623 top1= 32.1014


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5018 top1= 39.1026

Train epoch 12
[E12B0  |   1280/50000 (  3%) ] Loss: 0.7601 top1= 71.6406
[E12B10 |  14080/50000 ( 28%) ] Loss: 0.7478 top1= 70.4688
[E12B20 |  26880/50000 ( 54%) ] Loss: 0.7698 top1= 69.5312
[E12B30 |  39680/50000 ( 79%) ] Loss: 0.7362 top1= 71.7969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4099 top1= 10.3165


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3200 top1= 32.9627


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3176 top1= 40.5749

Train epoch 13
[E13B0  |   1280/50000 (  3%) ] Loss: 0.7115 top1= 73.5938
[E13B10 |  14080/50000 ( 28%) ] Loss: 0.7074 top1= 73.4375
[E13B20 |  26880/50000 ( 54%) ] Loss: 0.7128 top1= 72.7344
[E13B30 |  39680/50000 ( 79%) ] Loss: 0.6170 top1= 76.6406

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4045 top1= 10.0661


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3721 top1= 34.2147


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7116 top1= 41.3862

Train epoch 14
[E14B0  |   1280/50000 (  3%) ] Loss: 0.6111 top1= 77.1094
[E14B10 |  14080/50000 ( 28%) ] Loss: 0.6661 top1= 74.4531
[E14B20 |  26880/50000 ( 54%) ] Loss: 0.7107 top1= 74.0625
[E14B30 |  39680/50000 ( 79%) ] Loss: 0.5780 top1= 78.9844

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4146 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2933 top1= 35.4067


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6381 top1= 42.3377

Train epoch 15
[E15B0  |   1280/50000 (  3%) ] Loss: 0.5839 top1= 77.6562
[E15B10 |  14080/50000 ( 28%) ] Loss: 0.7645 top1= 69.3750
[E15B20 |  26880/50000 ( 54%) ] Loss: 0.6405 top1= 75.8594
[E15B30 |  39680/50000 ( 79%) ] Loss: 0.5880 top1= 77.7344

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3952 top1= 10.0260


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0746 top1= 35.2764


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9300 top1= 40.7051

Train epoch 16
[E16B0  |   1280/50000 (  3%) ] Loss: 0.6339 top1= 77.5000
[E16B10 |  14080/50000 ( 28%) ] Loss: 0.6407 top1= 75.1562
[E16B20 |  26880/50000 ( 54%) ] Loss: 0.5984 top1= 76.9531
[E16B30 |  39680/50000 ( 79%) ] Loss: 0.6027 top1= 76.9531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4062 top1= 11.4984


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2108 top1= 36.2280


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1455 top1= 42.4179

Train epoch 17
[E17B0  |   1280/50000 (  3%) ] Loss: 0.5700 top1= 79.0625
[E17B10 |  14080/50000 ( 28%) ] Loss: 0.5617 top1= 78.1250
[E17B20 |  26880/50000 ( 54%) ] Loss: 0.5743 top1= 78.5156
[E17B30 |  39680/50000 ( 79%) ] Loss: 0.5407 top1= 79.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4060 top1= 10.8674


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1992 top1= 36.6787


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1544 top1= 43.5797

Train epoch 18
[E18B0  |   1280/50000 (  3%) ] Loss: 0.4779 top1= 83.5938
[E18B10 |  14080/50000 ( 28%) ] Loss: 0.5162 top1= 80.3125
[E18B20 |  26880/50000 ( 54%) ] Loss: 0.5315 top1= 80.9375
[E18B30 |  39680/50000 ( 79%) ] Loss: 0.5047 top1= 82.4219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4106 top1= 10.1062


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3929 top1= 37.2496


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0802 top1= 43.6699

Train epoch 19
[E19B0  |   1280/50000 (  3%) ] Loss: 0.4764 top1= 81.2500
[E19B10 |  14080/50000 ( 28%) ] Loss: 0.5649 top1= 77.5000
[E19B20 |  26880/50000 ( 54%) ] Loss: 0.5093 top1= 80.4688
[E19B30 |  39680/50000 ( 79%) ] Loss: 0.4665 top1= 81.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4113 top1= 12.4099


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5413 top1= 37.5200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1690 top1= 43.6398

Train epoch 20
[E20B0  |   1280/50000 (  3%) ] Loss: 0.4539 top1= 83.0469
[E20B10 |  14080/50000 ( 28%) ] Loss: 0.5013 top1= 81.0938
[E20B20 |  26880/50000 ( 54%) ] Loss: 0.4852 top1= 81.7969
[E20B30 |  39680/50000 ( 79%) ] Loss: 0.4336 top1= 83.2031

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4150 top1= 11.0377


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5648 top1= 38.1611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1100 top1= 44.4111

Train epoch 21
[E21B0  |   1280/50000 (  3%) ] Loss: 0.4237 top1= 84.2188
[E21B10 |  14080/50000 ( 28%) ] Loss: 0.4571 top1= 81.7188
[E21B20 |  26880/50000 ( 54%) ] Loss: 0.4338 top1= 83.5938
[E21B30 |  39680/50000 ( 79%) ] Loss: 0.4359 top1= 83.3594

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4232 top1= 11.9892


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4443 top1= 38.9423


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2110 top1= 44.5312

Train epoch 22
[E22B0  |   1280/50000 (  3%) ] Loss: 0.4115 top1= 85.9375
[E22B10 |  14080/50000 ( 28%) ] Loss: 0.4425 top1= 83.8281
[E22B20 |  26880/50000 ( 54%) ] Loss: 0.3989 top1= 85.1562
[E22B30 |  39680/50000 ( 79%) ] Loss: 0.3905 top1= 85.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4205 top1= 10.0060


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2860 top1= 38.8321


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1791 top1= 44.4611

Train epoch 23
[E23B0  |   1280/50000 (  3%) ] Loss: 0.3931 top1= 85.3906
[E23B10 |  14080/50000 ( 28%) ] Loss: 0.4248 top1= 84.8438
[E23B20 |  26880/50000 ( 54%) ] Loss: 0.4131 top1= 84.8438
[E23B30 |  39680/50000 ( 79%) ] Loss: 0.3693 top1= 86.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4213 top1= 11.9992


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4144 top1= 37.1094


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5872 top1= 44.5913

Train epoch 24
[E24B0  |   1280/50000 (  3%) ] Loss: 0.4010 top1= 85.0000
[E24B10 |  14080/50000 ( 28%) ] Loss: 0.4454 top1= 83.2031
[E24B20 |  26880/50000 ( 54%) ] Loss: 0.4438 top1= 81.9531
[E24B30 |  39680/50000 ( 79%) ] Loss: 0.4180 top1= 84.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4074 top1= 10.4868


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3844 top1= 38.8822


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.0041 top1= 43.8101

Train epoch 25
[E25B0  |   1280/50000 (  3%) ] Loss: 0.4067 top1= 85.2344
[E25B10 |  14080/50000 ( 28%) ] Loss: 0.4301 top1= 84.2969
[E25B20 |  26880/50000 ( 54%) ] Loss: 0.3908 top1= 85.9375
[E25B30 |  39680/50000 ( 79%) ] Loss: 0.4136 top1= 84.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4328 top1= 13.4315


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4641 top1= 38.7420


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4631 top1= 44.0605

Train epoch 26
[E26B0  |   1280/50000 (  3%) ] Loss: 0.4067 top1= 85.3125
[E26B10 |  14080/50000 ( 28%) ] Loss: 0.3935 top1= 85.3125
[E26B20 |  26880/50000 ( 54%) ] Loss: 0.3872 top1= 85.3125
[E26B30 |  39680/50000 ( 79%) ] Loss: 0.3616 top1= 86.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4238 top1= 12.3698


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6698 top1= 39.3630


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8950 top1= 44.6815

Train epoch 27
[E27B0  |   1280/50000 (  3%) ] Loss: 0.3603 top1= 86.7188
[E27B10 |  14080/50000 ( 28%) ] Loss: 0.3982 top1= 85.5469
[E27B20 |  26880/50000 ( 54%) ] Loss: 0.3694 top1= 86.1719
[E27B30 |  39680/50000 ( 79%) ] Loss: 0.3451 top1= 85.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4330 top1= 10.2464


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3749 top1= 39.3329


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1266 top1= 44.2408

Train epoch 28
[E28B0  |   1280/50000 (  3%) ] Loss: 0.3758 top1= 87.0312
[E28B10 |  14080/50000 ( 28%) ] Loss: 0.4130 top1= 83.6719
[E28B20 |  26880/50000 ( 54%) ] Loss: 0.3362 top1= 87.9688
[E28B30 |  39680/50000 ( 79%) ] Loss: 0.3403 top1= 86.7969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4332 top1= 10.3165


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6679 top1= 39.3730


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8785 top1= 44.7216

Train epoch 29
[E29B0  |   1280/50000 (  3%) ] Loss: 0.3306 top1= 87.5781
[E29B10 |  14080/50000 ( 28%) ] Loss: 0.3548 top1= 86.8750
[E29B20 |  26880/50000 ( 54%) ] Loss: 0.3372 top1= 87.2656
[E29B30 |  39680/50000 ( 79%) ] Loss: 0.3532 top1= 87.2656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4403 top1= 10.8674


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8296 top1= 38.6418


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9164 top1= 44.4511

Train epoch 30
[E30B0  |   1280/50000 (  3%) ] Loss: 0.3485 top1= 87.4219
[E30B10 |  14080/50000 ( 28%) ] Loss: 0.3345 top1= 86.5625
[E30B20 |  26880/50000 ( 54%) ] Loss: 0.3582 top1= 88.0469
[E30B30 |  39680/50000 ( 79%) ] Loss: 0.3077 top1= 89.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4201 top1= 10.1763


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8669 top1= 39.2328


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3267 top1= 45.1322

Train epoch 31
[E31B0  |   1280/50000 (  3%) ] Loss: 0.2816 top1= 89.5312
[E31B10 |  14080/50000 ( 28%) ] Loss: 0.2964 top1= 88.4375
[E31B20 |  26880/50000 ( 54%) ] Loss: 0.3283 top1= 88.0469
[E31B30 |  39680/50000 ( 79%) ] Loss: 0.3210 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4232 top1= 12.1695


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9735 top1= 39.9539


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7851 top1= 45.0020

Train epoch 32
[E32B0  |   1280/50000 (  3%) ] Loss: 0.3230 top1= 89.0625
[E32B10 |  14080/50000 ( 28%) ] Loss: 0.3490 top1= 87.8906
[E32B20 |  26880/50000 ( 54%) ] Loss: 0.2883 top1= 90.4688
[E32B30 |  39680/50000 ( 79%) ] Loss: 0.2959 top1= 89.2969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4440 top1= 11.1879


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7840 top1= 40.2544


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1383 top1= 45.4227

Train epoch 33
[E33B0  |   1280/50000 (  3%) ] Loss: 0.2712 top1= 89.7656
[E33B10 |  14080/50000 ( 28%) ] Loss: 0.3054 top1= 88.2031
[E33B20 |  26880/50000 ( 54%) ] Loss: 0.2770 top1= 90.3125
[E33B30 |  39680/50000 ( 79%) ] Loss: 0.2536 top1= 90.3906

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4352 top1= 10.1462


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4204 top1= 39.4030


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6808 top1= 45.5329

Train epoch 34
[E34B0  |   1280/50000 (  3%) ] Loss: 0.2924 top1= 89.2188
[E34B10 |  14080/50000 ( 28%) ] Loss: 0.2921 top1= 89.2188
[E34B20 |  26880/50000 ( 54%) ] Loss: 0.2844 top1= 89.6875
[E34B30 |  39680/50000 ( 79%) ] Loss: 0.2369 top1= 90.7031

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4302 top1= 10.0661


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1368 top1= 40.0240


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7930 top1= 45.5629

Train epoch 35
[E35B0  |   1280/50000 (  3%) ] Loss: 0.2627 top1= 90.5469
[E35B10 |  14080/50000 ( 28%) ] Loss: 0.2903 top1= 89.7656
[E35B20 |  26880/50000 ( 54%) ] Loss: 0.2599 top1= 90.2344
[E35B30 |  39680/50000 ( 79%) ] Loss: 0.2810 top1= 89.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4306 top1= 10.1963


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5715 top1= 39.5833


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7328 top1= 45.4327

Train epoch 36
[E36B0  |   1280/50000 (  3%) ] Loss: 0.2627 top1= 90.5469
[E36B10 |  14080/50000 ( 28%) ] Loss: 0.2684 top1= 90.3125
[E36B20 |  26880/50000 ( 54%) ] Loss: 0.3165 top1= 89.2969
[E36B30 |  39680/50000 ( 79%) ] Loss: 0.2525 top1= 90.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4315 top1= 15.1743


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9884 top1= 41.5465


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9342 top1= 45.4327

Train epoch 37
[E37B0  |   1280/50000 (  3%) ] Loss: 0.2538 top1= 91.5625
[E37B10 |  14080/50000 ( 28%) ] Loss: 0.2657 top1= 89.6094
[E37B20 |  26880/50000 ( 54%) ] Loss: 0.2924 top1= 88.4375
[E37B30 |  39680/50000 ( 79%) ] Loss: 0.2505 top1= 90.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4437 top1= 12.8105


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7077 top1= 40.6350


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7256 top1= 45.2724

Train epoch 38
[E38B0  |   1280/50000 (  3%) ] Loss: 0.2508 top1= 90.0781
[E38B10 |  14080/50000 ( 28%) ] Loss: 0.2272 top1= 91.8750
[E38B20 |  26880/50000 ( 54%) ] Loss: 0.2366 top1= 91.8750
[E38B30 |  39680/50000 ( 79%) ] Loss: 0.2672 top1= 88.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4361 top1= 11.9992


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9876 top1= 40.9054


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9962 top1= 45.7632

Train epoch 39
[E39B0  |   1280/50000 (  3%) ] Loss: 0.2232 top1= 91.8750
[E39B10 |  14080/50000 ( 28%) ] Loss: 0.2260 top1= 91.6406
[E39B20 |  26880/50000 ( 54%) ] Loss: 0.2202 top1= 92.7344
[E39B30 |  39680/50000 ( 79%) ] Loss: 0.2445 top1= 90.2344

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4469 top1= 12.8305


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5644 top1= 40.5248


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2354 top1= 45.7732

Train epoch 40
[E40B0  |   1280/50000 (  3%) ] Loss: 0.2348 top1= 91.7969
[E40B10 |  14080/50000 ( 28%) ] Loss: 0.2584 top1= 90.4688
[E40B20 |  26880/50000 ( 54%) ] Loss: 0.2506 top1= 90.6250
[E40B30 |  39680/50000 ( 79%) ] Loss: 0.2786 top1= 88.5156

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4462 top1= 10.4667


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0361 top1= 40.8954


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2814 top1= 45.2324

Train epoch 41
[E41B0  |   1280/50000 (  3%) ] Loss: 0.2802 top1= 89.5312
[E41B10 |  14080/50000 ( 28%) ] Loss: 0.2443 top1= 90.8594
[E41B20 |  26880/50000 ( 54%) ] Loss: 0.2213 top1= 91.9531
[E41B30 |  39680/50000 ( 79%) ] Loss: 0.2038 top1= 92.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4591 top1= 11.3482


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3916 top1= 40.5950


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8905 top1= 45.6030

Train epoch 42
[E42B0  |   1280/50000 (  3%) ] Loss: 0.2656 top1= 90.3906
[E42B10 |  14080/50000 ( 28%) ] Loss: 0.1993 top1= 92.5000
[E42B20 |  26880/50000 ( 54%) ] Loss: 0.1942 top1= 92.8125
[E42B30 |  39680/50000 ( 79%) ] Loss: 0.1983 top1= 92.7344

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4618 top1= 15.8053


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0336 top1= 40.5549


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6625 top1= 45.2324

Train epoch 43
[E43B0  |   1280/50000 (  3%) ] Loss: 0.2423 top1= 91.4062
[E43B10 |  14080/50000 ( 28%) ] Loss: 0.2382 top1= 92.0312
[E43B20 |  26880/50000 ( 54%) ] Loss: 0.2444 top1= 91.8750
[E43B30 |  39680/50000 ( 79%) ] Loss: 0.2354 top1= 90.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4504 top1= 11.8189


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7747 top1= 40.8153


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4426 top1= 45.0321

Train epoch 44
[E44B0  |   1280/50000 (  3%) ] Loss: 0.2341 top1= 91.0156
[E44B10 |  14080/50000 ( 28%) ] Loss: 0.2218 top1= 91.7188
[E44B20 |  26880/50000 ( 54%) ] Loss: 0.2311 top1= 91.4844
[E44B30 |  39680/50000 ( 79%) ] Loss: 0.1803 top1= 93.0469

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4609 top1= 14.8738


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1051 top1= 41.4363


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5745 top1= 44.3510

Train epoch 45
[E45B0  |   1280/50000 (  3%) ] Loss: 0.2417 top1= 92.3438
[E45B10 |  14080/50000 ( 28%) ] Loss: 0.2316 top1= 91.0938
[E45B20 |  26880/50000 ( 54%) ] Loss: 0.2410 top1= 91.5625
[E45B30 |  39680/50000 ( 79%) ] Loss: 0.2062 top1= 92.5781

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4648 top1= 15.0040


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8711 top1= 41.8570


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4129 top1= 45.3526

Train epoch 46
[E46B0  |   1280/50000 (  3%) ] Loss: 0.1778 top1= 93.8281
[E46B10 |  14080/50000 ( 28%) ] Loss: 0.1928 top1= 92.7344
[E46B20 |  26880/50000 ( 54%) ] Loss: 0.2019 top1= 92.8125
[E46B30 |  39680/50000 ( 79%) ] Loss: 0.1716 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4759 top1= 13.1510


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4860 top1= 41.4764


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7386 top1= 45.5128

Train epoch 47
[E47B0  |   1280/50000 (  3%) ] Loss: 0.2005 top1= 92.6562
[E47B10 |  14080/50000 ( 28%) ] Loss: 0.1698 top1= 93.8281
[E47B20 |  26880/50000 ( 54%) ] Loss: 0.2354 top1= 91.4062
[E47B30 |  39680/50000 ( 79%) ] Loss: 0.2034 top1= 93.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4692 top1= 10.1963


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1343 top1= 42.1474


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3245 top1= 45.1823

Train epoch 48
[E48B0  |   1280/50000 (  3%) ] Loss: 0.1848 top1= 93.7500
[E48B10 |  14080/50000 ( 28%) ] Loss: 0.1736 top1= 93.9062
[E48B20 |  26880/50000 ( 54%) ] Loss: 0.2000 top1= 92.9688
[E48B30 |  39680/50000 ( 79%) ] Loss: 0.2101 top1= 92.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4635 top1= 15.7452


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2811 top1= 41.1859


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1235 top1= 45.3526

Train epoch 49
[E49B0  |   1280/50000 (  3%) ] Loss: 0.2577 top1= 91.5625
[E49B10 |  14080/50000 ( 28%) ] Loss: 0.1873 top1= 93.2812
[E49B20 |  26880/50000 ( 54%) ] Loss: 0.1892 top1= 93.0469
[E49B30 |  39680/50000 ( 79%) ] Loss: 0.1523 top1= 93.5156

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4761 top1= 12.8105


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0225 top1= 41.0357


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2968 top1= 45.7732

Train epoch 50
[E50B0  |   1280/50000 (  3%) ] Loss: 0.2047 top1= 92.8125
[E50B10 |  14080/50000 ( 28%) ] Loss: 0.1757 top1= 93.2031
[E50B20 |  26880/50000 ( 54%) ] Loss: 0.1782 top1= 93.0469
[E50B30 |  39680/50000 ( 79%) ] Loss: 0.1798 top1= 92.7344

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4760 top1= 14.4331


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2157 top1= 41.2460


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2792 top1= 45.6931

Train epoch 51
[E51B0  |   1280/50000 (  3%) ] Loss: 0.2064 top1= 92.9688
[E51B10 |  14080/50000 ( 28%) ] Loss: 0.2000 top1= 92.5000
[E51B20 |  26880/50000 ( 54%) ] Loss: 0.1950 top1= 93.7500
[E51B30 |  39680/50000 ( 79%) ] Loss: 0.2037 top1= 91.7969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4664 top1= 15.7452


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3105 top1= 41.8169


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7847 top1= 45.8934

Train epoch 52
[E52B0  |   1280/50000 (  3%) ] Loss: 0.1674 top1= 93.7500
[E52B10 |  14080/50000 ( 28%) ] Loss: 0.1422 top1= 94.6094
[E52B20 |  26880/50000 ( 54%) ] Loss: 0.1838 top1= 92.9688
[E52B30 |  39680/50000 ( 79%) ] Loss: 0.1890 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4738 top1= 14.9239


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1236 top1= 41.4864


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2610 top1= 45.6931

Train epoch 53
[E53B0  |   1280/50000 (  3%) ] Loss: 0.1774 top1= 94.5312
[E53B10 |  14080/50000 ( 28%) ] Loss: 0.1889 top1= 92.4219
[E53B20 |  26880/50000 ( 54%) ] Loss: 0.1682 top1= 94.3750
[E53B30 |  39680/50000 ( 79%) ] Loss: 0.1875 top1= 93.0469

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4751 top1= 10.5970


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.6252 top1= 41.8069


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8477 top1= 45.5228

Train epoch 54
[E54B0  |   1280/50000 (  3%) ] Loss: 0.1837 top1= 93.6719
[E54B10 |  14080/50000 ( 28%) ] Loss: 0.1452 top1= 93.9062
[E54B20 |  26880/50000 ( 54%) ] Loss: 0.2033 top1= 92.1875
[E54B30 |  39680/50000 ( 79%) ] Loss: 0.2163 top1= 91.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4698 top1= 16.5865


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0934 top1= 42.0272


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4450 top1= 45.5929

Train epoch 55
[E55B0  |   1280/50000 (  3%) ] Loss: 0.1753 top1= 93.3594
[E55B10 |  14080/50000 ( 28%) ] Loss: 0.1468 top1= 95.0781
[E55B20 |  26880/50000 ( 54%) ] Loss: 0.1940 top1= 92.7344
[E55B30 |  39680/50000 ( 79%) ] Loss: 0.2126 top1= 92.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4775 top1= 16.6466


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2334 top1= 41.7768


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3596 top1= 45.4627

Train epoch 56
[E56B0  |   1280/50000 (  3%) ] Loss: 0.1812 top1= 93.5156
[E56B10 |  14080/50000 ( 28%) ] Loss: 0.1524 top1= 93.6719
[E56B20 |  26880/50000 ( 54%) ] Loss: 0.2055 top1= 92.6562
[E56B30 |  39680/50000 ( 79%) ] Loss: 0.1579 top1= 94.1406

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4703 top1= 15.6851


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0348 top1= 41.9171


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.4230 top1= 45.9535

Train epoch 57
[E57B0  |   1280/50000 (  3%) ] Loss: 0.1594 top1= 94.1406
[E57B10 |  14080/50000 ( 28%) ] Loss: 0.1466 top1= 94.7656
[E57B20 |  26880/50000 ( 54%) ] Loss: 0.1883 top1= 92.9688
[E57B30 |  39680/50000 ( 79%) ] Loss: 0.1626 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4864 top1= 13.9223


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1693 top1= 42.2075


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.7235 top1= 45.7532

Train epoch 58
[E58B0  |   1280/50000 (  3%) ] Loss: 0.1505 top1= 94.3750
[E58B10 |  14080/50000 ( 28%) ] Loss: 0.1336 top1= 95.2344
[E58B20 |  26880/50000 ( 54%) ] Loss: 0.1613 top1= 94.2969
[E58B30 |  39680/50000 ( 79%) ] Loss: 0.1361 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4966 top1= 19.5913


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1494 top1= 41.7067


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3546 top1= 45.5929

Train epoch 59
[E59B0  |   1280/50000 (  3%) ] Loss: 0.1480 top1= 94.9219
[E59B10 |  14080/50000 ( 28%) ] Loss: 0.1413 top1= 95.2344
[E59B20 |  26880/50000 ( 54%) ] Loss: 0.1784 top1= 93.6719
[E59B30 |  39680/50000 ( 79%) ] Loss: 0.1210 top1= 95.2344

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5082 top1= 11.2680


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5879 top1= 42.1775


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.9183 top1= 45.5729

Train epoch 60
[E60B0  |   1280/50000 (  3%) ] Loss: 0.1268 top1= 95.3125
[E60B10 |  14080/50000 ( 28%) ] Loss: 0.1585 top1= 93.6719
[E60B20 |  26880/50000 ( 54%) ] Loss: 0.1530 top1= 94.9219
[E60B30 |  39680/50000 ( 79%) ] Loss: 0.1525 top1= 94.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5083 top1= 10.6871


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0905 top1= 42.3978


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6931 top1= 45.3125

Train epoch 61
[E61B0  |   1280/50000 (  3%) ] Loss: 0.1353 top1= 95.3125
[E61B10 |  14080/50000 ( 28%) ] Loss: 0.1610 top1= 94.3750
[E61B20 |  26880/50000 ( 54%) ] Loss: 0.1609 top1= 94.6875
[E61B30 |  39680/50000 ( 79%) ] Loss: 0.1505 top1= 95.0781

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5171 top1= 13.0409


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2557 top1= 41.9772


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.4889 top1= 46.0938

Train epoch 62
[E62B0  |   1280/50000 (  3%) ] Loss: 0.1204 top1= 95.7812
[E62B10 |  14080/50000 ( 28%) ] Loss: 0.1489 top1= 94.2969
[E62B20 |  26880/50000 ( 54%) ] Loss: 0.1399 top1= 95.3125
[E62B30 |  39680/50000 ( 79%) ] Loss: 0.1245 top1= 95.2344

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5197 top1= 15.9455


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4105 top1= 41.6266


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.4402 top1= 45.9836

Train epoch 63
[E63B0  |   1280/50000 (  3%) ] Loss: 0.1161 top1= 95.3906
[E63B10 |  14080/50000 ( 28%) ] Loss: 0.1345 top1= 94.1406
[E63B20 |  26880/50000 ( 54%) ] Loss: 0.1346 top1= 94.9219
[E63B30 |  39680/50000 ( 79%) ] Loss: 0.1676 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5123 top1= 16.9071


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8950 top1= 41.7468


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0896 top1= 45.4828

Train epoch 64
[E64B0  |   1280/50000 (  3%) ] Loss: 0.1238 top1= 95.3125
[E64B10 |  14080/50000 ( 28%) ] Loss: 0.1547 top1= 94.4531
[E64B20 |  26880/50000 ( 54%) ] Loss: 0.1490 top1= 94.5312
[E64B30 |  39680/50000 ( 79%) ] Loss: 0.1280 top1= 95.8594

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5179 top1= 10.6671


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0751 top1= 41.6867


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1345 top1= 45.7232

Train epoch 65
[E65B0  |   1280/50000 (  3%) ] Loss: 0.1088 top1= 96.1719
[E65B10 |  14080/50000 ( 28%) ] Loss: 0.1237 top1= 95.5469
[E65B20 |  26880/50000 ( 54%) ] Loss: 0.1381 top1= 95.9375
[E65B30 |  39680/50000 ( 79%) ] Loss: 0.1324 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5180 top1= 15.4247


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6968 top1= 42.3578


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4958 top1= 45.5629

Train epoch 66
[E66B0  |   1280/50000 (  3%) ] Loss: 0.1307 top1= 95.2344
[E66B10 |  14080/50000 ( 28%) ] Loss: 0.1203 top1= 95.6250
[E66B20 |  26880/50000 ( 54%) ] Loss: 0.1013 top1= 96.3281
[E66B30 |  39680/50000 ( 79%) ] Loss: 0.1137 top1= 95.3906

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5227 top1= 17.7083


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8441 top1= 42.1474


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3288 top1= 45.6530

Train epoch 67
[E67B0  |   1280/50000 (  3%) ] Loss: 0.1317 top1= 95.3906
[E67B10 |  14080/50000 ( 28%) ] Loss: 0.1443 top1= 95.4688
[E67B20 |  26880/50000 ( 54%) ] Loss: 0.1033 top1= 96.0938
[E67B30 |  39680/50000 ( 79%) ] Loss: 0.0980 top1= 96.6406

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5098 top1= 14.3630


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3238 top1= 42.5681


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5921 top1= 46.2841

Train epoch 68
[E68B0  |   1280/50000 (  3%) ] Loss: 0.1050 top1= 95.7031
[E68B10 |  14080/50000 ( 28%) ] Loss: 0.1219 top1= 95.6250
[E68B20 |  26880/50000 ( 54%) ] Loss: 0.1136 top1= 96.0156
[E68B30 |  39680/50000 ( 79%) ] Loss: 0.1130 top1= 95.5469

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5083 top1= 17.8486


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4563 top1= 41.6466


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.7008 top1= 45.9135

Train epoch 69
[E69B0  |   1280/50000 (  3%) ] Loss: 0.1067 top1= 96.2500
[E69B10 |  14080/50000 ( 28%) ] Loss: 0.0918 top1= 96.5625
[E69B20 |  26880/50000 ( 54%) ] Loss: 0.1205 top1= 95.7812
[E69B30 |  39680/50000 ( 79%) ] Loss: 0.1326 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5083 top1= 13.8922


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4824 top1= 41.3862


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2706 top1= 45.8133

Train epoch 70
[E70B0  |   1280/50000 (  3%) ] Loss: 0.1010 top1= 96.3281
[E70B10 |  14080/50000 ( 28%) ] Loss: 0.1481 top1= 94.5312
[E70B20 |  26880/50000 ( 54%) ] Loss: 0.1303 top1= 95.7031
[E70B30 |  39680/50000 ( 79%) ] Loss: 0.1007 top1= 96.4844

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5112 top1= 12.1194


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6239 top1= 41.7568


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1047 top1= 45.9535

Train epoch 71
[E71B0  |   1280/50000 (  3%) ] Loss: 0.0802 top1= 96.6406
[E71B10 |  14080/50000 ( 28%) ] Loss: 0.1059 top1= 96.4062
[E71B20 |  26880/50000 ( 54%) ] Loss: 0.1042 top1= 96.7969
[E71B30 |  39680/50000 ( 79%) ] Loss: 0.0863 top1= 96.7969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5209 top1= 11.2179


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1134 top1= 40.6550


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2497 top1= 45.8333

Train epoch 72
[E72B0  |   1280/50000 (  3%) ] Loss: 0.1231 top1= 95.0000
[E72B10 |  14080/50000 ( 28%) ] Loss: 0.1139 top1= 96.0156
[E72B20 |  26880/50000 ( 54%) ] Loss: 0.1120 top1= 96.0938
[E72B30 |  39680/50000 ( 79%) ] Loss: 0.1222 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5282 top1= 15.7452


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4942 top1= 41.6266


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3930 top1= 45.4728

Train epoch 73
[E73B0  |   1280/50000 (  3%) ] Loss: 0.1156 top1= 95.7812
[E73B10 |  14080/50000 ( 28%) ] Loss: 0.1039 top1= 96.0938
[E73B20 |  26880/50000 ( 54%) ] Loss: 0.0934 top1= 96.2500
[E73B30 |  39680/50000 ( 79%) ] Loss: 0.1073 top1= 96.4844

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5417 top1= 15.3646


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8162 top1= 42.2476


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.9599 top1= 45.8433

Train epoch 74
[E74B0  |   1280/50000 (  3%) ] Loss: 0.1150 top1= 95.7812
[E74B10 |  14080/50000 ( 28%) ] Loss: 0.0998 top1= 96.4844
[E74B20 |  26880/50000 ( 54%) ] Loss: 0.1285 top1= 95.0781
[E74B30 |  39680/50000 ( 79%) ] Loss: 0.0955 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5363 top1= 14.2528


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4449 top1= 41.8870


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0201 top1= 45.8634

Train epoch 75
[E75B0  |   1280/50000 (  3%) ] Loss: 0.0841 top1= 96.9531
[E75B10 |  14080/50000 ( 28%) ] Loss: 0.1104 top1= 95.7812
[E75B20 |  26880/50000 ( 54%) ] Loss: 0.0960 top1= 96.7969
[E75B30 |  39680/50000 ( 79%) ] Loss: 0.0931 top1= 97.1094

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5318 top1= 13.7320


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2446 top1= 42.2676


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.1167 top1= 45.9836

Train epoch 76
[E76B0  |   1280/50000 (  3%) ] Loss: 0.1010 top1= 96.2500
[E76B10 |  14080/50000 ( 28%) ] Loss: 0.1234 top1= 95.8594
[E76B20 |  26880/50000 ( 54%) ] Loss: 0.1299 top1= 95.4688
[E76B30 |  39680/50000 ( 79%) ] Loss: 0.1251 top1= 96.0156

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5348 top1= 15.6050


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1021 top1= 42.3377


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0021 top1= 46.0837

Train epoch 77
[E77B0  |   1280/50000 (  3%) ] Loss: 0.0933 top1= 96.7188
[E77B10 |  14080/50000 ( 28%) ] Loss: 0.0962 top1= 96.8750
[E77B20 |  26880/50000 ( 54%) ] Loss: 0.1342 top1= 94.9219
[E77B30 |  39680/50000 ( 79%) ] Loss: 0.1125 top1= 96.1719

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5382 top1= 15.5148


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1132 top1= 41.6567


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8983 top1= 45.9635

Train epoch 78
[E78B0  |   1280/50000 (  3%) ] Loss: 0.1008 top1= 96.4844
[E78B10 |  14080/50000 ( 28%) ] Loss: 0.0879 top1= 96.7969
[E78B20 |  26880/50000 ( 54%) ] Loss: 0.1111 top1= 95.7031
[E78B30 |  39680/50000 ( 79%) ] Loss: 0.1249 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5495 top1= 15.5248


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8357 top1= 41.3462


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7534 top1= 45.9635

Train epoch 79
[E79B0  |   1280/50000 (  3%) ] Loss: 0.1081 top1= 96.0156
[E79B10 |  14080/50000 ( 28%) ] Loss: 0.1024 top1= 96.8750
[E79B20 |  26880/50000 ( 54%) ] Loss: 0.0768 top1= 97.0312
[E79B30 |  39680/50000 ( 79%) ] Loss: 0.0925 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5256 top1= 14.3630


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5831 top1= 42.0974


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8838 top1= 45.6931

Train epoch 80
[E80B0  |   1280/50000 (  3%) ] Loss: 0.1030 top1= 96.5625
[E80B10 |  14080/50000 ( 28%) ] Loss: 0.0501 top1= 98.4375
[E80B20 |  26880/50000 ( 54%) ] Loss: 0.0815 top1= 97.1875
[E80B30 |  39680/50000 ( 79%) ] Loss: 0.0746 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5196 top1= 13.1611


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1118 top1= 41.8470


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6465 top1= 45.9736

Train epoch 81
[E81B0  |   1280/50000 (  3%) ] Loss: 0.0718 top1= 97.5000
[E81B10 |  14080/50000 ( 28%) ] Loss: 0.0584 top1= 98.2812
[E81B20 |  26880/50000 ( 54%) ] Loss: 0.0436 top1= 98.3594
[E81B30 |  39680/50000 ( 79%) ] Loss: 0.0403 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5249 top1= 14.0425


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6361 top1= 43.4595


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9640 top1= 46.4543

Train epoch 82
[E82B0  |   1280/50000 (  3%) ] Loss: 0.0427 top1= 98.5156
[E82B10 |  14080/50000 ( 28%) ] Loss: 0.0329 top1= 98.9844
[E82B20 |  26880/50000 ( 54%) ] Loss: 0.0419 top1= 98.7500
[E82B30 |  39680/50000 ( 79%) ] Loss: 0.0262 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5280 top1= 15.1342


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2293 top1= 43.5196


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2103 top1= 46.4143

Train epoch 83
[E83B0  |   1280/50000 (  3%) ] Loss: 0.0255 top1= 98.9844
[E83B10 |  14080/50000 ( 28%) ] Loss: 0.0356 top1= 98.4375
[E83B20 |  26880/50000 ( 54%) ] Loss: 0.0206 top1= 99.3750
[E83B30 |  39680/50000 ( 79%) ] Loss: 0.0310 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5292 top1= 14.8337


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.7893 top1= 43.5998


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5904 top1= 46.4643

Train epoch 84
[E84B0  |   1280/50000 (  3%) ] Loss: 0.0137 top1= 99.6094
[E84B10 |  14080/50000 ( 28%) ] Loss: 0.0250 top1= 99.3750
[E84B20 |  26880/50000 ( 54%) ] Loss: 0.0211 top1= 99.3750
[E84B30 |  39680/50000 ( 79%) ] Loss: 0.0209 top1= 99.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5324 top1= 14.4531


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.0544 top1= 43.5998


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.9029 top1= 46.4844

Train epoch 85
[E85B0  |   1280/50000 (  3%) ] Loss: 0.0211 top1= 99.3750
[E85B10 |  14080/50000 ( 28%) ] Loss: 0.0284 top1= 99.2188
[E85B20 |  26880/50000 ( 54%) ] Loss: 0.0190 top1= 99.3750
[E85B30 |  39680/50000 ( 79%) ] Loss: 0.0210 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5378 top1= 14.9139


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.2675 top1= 43.7200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.0583 top1= 46.5345

Train epoch 86
[E86B0  |   1280/50000 (  3%) ] Loss: 0.0266 top1= 98.9844
[E86B10 |  14080/50000 ( 28%) ] Loss: 0.0183 top1= 99.2969
[E86B20 |  26880/50000 ( 54%) ] Loss: 0.0261 top1= 99.2188
[E86B30 |  39680/50000 ( 79%) ] Loss: 0.0187 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5395 top1= 14.5933


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.3790 top1= 43.4796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.1305 top1= 46.5645

Train epoch 87
[E87B0  |   1280/50000 (  3%) ] Loss: 0.0141 top1= 99.3750
[E87B10 |  14080/50000 ( 28%) ] Loss: 0.0142 top1= 99.6875
[E87B20 |  26880/50000 ( 54%) ] Loss: 0.0200 top1= 99.4531
[E87B30 |  39680/50000 ( 79%) ] Loss: 0.0145 top1= 99.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5419 top1= 14.0725


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.7123 top1= 43.7700


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.3947 top1= 46.5445

Train epoch 88
[E88B0  |   1280/50000 (  3%) ] Loss: 0.0213 top1= 99.3750
[E88B10 |  14080/50000 ( 28%) ] Loss: 0.0149 top1= 99.5312
[E88B20 |  26880/50000 ( 54%) ] Loss: 0.0098 top1= 99.6094
[E88B30 |  39680/50000 ( 79%) ] Loss: 0.0149 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5450 top1= 13.9423


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.0624 top1= 43.6899


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.6810 top1= 46.5745

Train epoch 89
[E89B0  |   1280/50000 (  3%) ] Loss: 0.0133 top1= 99.4531
[E89B10 |  14080/50000 ( 28%) ] Loss: 0.0231 top1= 99.1406
[E89B20 |  26880/50000 ( 54%) ] Loss: 0.0160 top1= 99.6094
[E89B30 |  39680/50000 ( 79%) ] Loss: 0.0156 top1= 99.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5473 top1= 13.6619


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.0151 top1= 43.6098


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.7811 top1= 46.6246

Train epoch 90
[E90B0  |   1280/50000 (  3%) ] Loss: 0.0165 top1= 99.4531
[E90B10 |  14080/50000 ( 28%) ] Loss: 0.0092 top1= 99.7656
[E90B20 |  26880/50000 ( 54%) ] Loss: 0.0115 top1= 99.6094
[E90B30 |  39680/50000 ( 79%) ] Loss: 0.0148 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5492 top1= 13.7019


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.3508 top1= 43.6098


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.8661 top1= 46.5044

Train epoch 91
[E91B0  |   1280/50000 (  3%) ] Loss: 0.0094 top1= 99.6875
[E91B10 |  14080/50000 ( 28%) ] Loss: 0.0102 top1= 99.6875
[E91B20 |  26880/50000 ( 54%) ] Loss: 0.0134 top1= 99.3750
[E91B30 |  39680/50000 ( 79%) ] Loss: 0.0141 top1= 99.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5512 top1= 13.5417


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.3519 top1= 43.5597


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.8376 top1= 46.4944

Train epoch 92
[E92B0  |   1280/50000 (  3%) ] Loss: 0.0112 top1= 99.5312
[E92B10 |  14080/50000 ( 28%) ] Loss: 0.0104 top1= 99.6094
[E92B20 |  26880/50000 ( 54%) ] Loss: 0.0098 top1= 99.7656
[E92B30 |  39680/50000 ( 79%) ] Loss: 0.0078 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5529 top1= 13.7720


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.6246 top1= 43.5597


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.9902 top1= 46.5445

Train epoch 93
[E93B0  |   1280/50000 (  3%) ] Loss: 0.0117 top1= 99.4531
[E93B10 |  14080/50000 ( 28%) ] Loss: 0.0125 top1= 99.4531
[E93B20 |  26880/50000 ( 54%) ] Loss: 0.0116 top1= 99.6094
[E93B30 |  39680/50000 ( 79%) ] Loss: 0.0144 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5533 top1= 13.7620


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.7461 top1= 43.5597


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.0374 top1= 46.5946

Train epoch 94
[E94B0  |   1280/50000 (  3%) ] Loss: 0.0132 top1= 99.5312
[E94B10 |  14080/50000 ( 28%) ] Loss: 0.0105 top1= 99.7656
[E94B20 |  26880/50000 ( 54%) ] Loss: 0.0110 top1= 99.7656
[E94B30 |  39680/50000 ( 79%) ] Loss: 0.0065 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5525 top1= 12.9607


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.9363 top1= 43.5096


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.2183 top1= 46.6346

Train epoch 95
[E95B0  |   1280/50000 (  3%) ] Loss: 0.0105 top1= 99.4531
[E95B10 |  14080/50000 ( 28%) ] Loss: 0.0201 top1= 99.3750
[E95B20 |  26880/50000 ( 54%) ] Loss: 0.0062 top1= 99.6875
[E95B30 |  39680/50000 ( 79%) ] Loss: 0.0154 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5536 top1= 13.4415


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.0972 top1= 43.7500


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.3268 top1= 46.5845

Train epoch 96
[E96B0  |   1280/50000 (  3%) ] Loss: 0.0087 top1= 99.7656
[E96B10 |  14080/50000 ( 28%) ] Loss: 0.0109 top1= 99.7656
[E96B20 |  26880/50000 ( 54%) ] Loss: 0.0087 top1= 99.6875
[E96B30 |  39680/50000 ( 79%) ] Loss: 0.0097 top1= 99.6094

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5544 top1= 13.3313


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.3447 top1= 43.6699


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.4154 top1= 46.6046

Train epoch 97
[E97B0  |   1280/50000 (  3%) ] Loss: 0.0092 top1= 99.6094
[E97B10 |  14080/50000 ( 28%) ] Loss: 0.0105 top1= 99.6875
[E97B20 |  26880/50000 ( 54%) ] Loss: 0.0098 top1= 99.6094
[E97B30 |  39680/50000 ( 79%) ] Loss: 0.0125 top1= 99.6094

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5563 top1= 13.4615


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.1960 top1= 43.5897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.4347 top1= 46.6046

Train epoch 98
[E98B0  |   1280/50000 (  3%) ] Loss: 0.0049 top1= 99.7656
[E98B10 |  14080/50000 ( 28%) ] Loss: 0.0092 top1= 99.6094
[E98B20 |  26880/50000 ( 54%) ] Loss: 0.0047 top1= 99.8438
[E98B30 |  39680/50000 ( 79%) ] Loss: 0.0118 top1= 99.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5565 top1= 12.9507


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.6217 top1= 43.7099


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.4344 top1= 46.5745

Train epoch 99
[E99B0  |   1280/50000 (  3%) ] Loss: 0.0091 top1= 99.8438
[E99B10 |  14080/50000 ( 28%) ] Loss: 0.0123 top1= 99.6875
[E99B20 |  26880/50000 ( 54%) ] Loss: 0.0084 top1= 99.6094
[E99B30 |  39680/50000 ( 79%) ] Loss: 0.0062 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5584 top1= 13.3313


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.6524 top1= 43.6298


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.6098 top1= 46.5946

Train epoch 100
[E100B0  |   1280/50000 (  3%) ] Loss: 0.0086 top1= 99.6094
[E100B10 |  14080/50000 ( 28%) ] Loss: 0.0108 top1= 99.6094
[E100B20 |  26880/50000 ( 54%) ] Loss: 0.0085 top1= 99.9219
[E100B30 |  39680/50000 ( 79%) ] Loss: 0.0073 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5590 top1= 13.2913


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.7140 top1= 43.5998


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.6440 top1= 46.6146

Train epoch 101
[E101B0  |   1280/50000 (  3%) ] Loss: 0.0152 top1= 99.9219
[E101B10 |  14080/50000 ( 28%) ] Loss: 0.0119 top1= 99.4531
[E101B20 |  26880/50000 ( 54%) ] Loss: 0.0094 top1= 99.7656
[E101B30 |  39680/50000 ( 79%) ] Loss: 0.0067 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5607 top1= 12.9006


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.8260 top1= 43.6999


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.6371 top1= 46.5745

Train epoch 102
[E102B0  |   1280/50000 (  3%) ] Loss: 0.0094 top1= 99.6094
[E102B10 |  14080/50000 ( 28%) ] Loss: 0.0100 top1= 99.4531
[E102B20 |  26880/50000 ( 54%) ] Loss: 0.0080 top1= 99.7656
[E102B30 |  39680/50000 ( 79%) ] Loss: 0.0082 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5636 top1= 12.8305


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.9100 top1= 43.7300


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.8459 top1= 46.6647

Train epoch 103
[E103B0  |   1280/50000 (  3%) ] Loss: 0.0064 top1= 99.7656
[E103B10 |  14080/50000 ( 28%) ] Loss: 0.0154 top1= 99.5312
[E103B20 |  26880/50000 ( 54%) ] Loss: 0.0071 top1= 99.6875
[E103B30 |  39680/50000 ( 79%) ] Loss: 0.0120 top1= 99.6094

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5624 top1= 12.8806


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.9547 top1= 43.5397


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.7501 top1= 46.5745

Train epoch 104
[E104B0  |   1280/50000 (  3%) ] Loss: 0.0064 top1= 99.8438
[E104B10 |  14080/50000 ( 28%) ] Loss: 0.0059 top1= 99.7656
[E104B20 |  26880/50000 ( 54%) ] Loss: 0.0053 top1= 99.6875
[E104B30 |  39680/50000 ( 79%) ] Loss: 0.0103 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5617 top1= 12.8506


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.0555 top1= 43.6398


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.8510 top1= 46.6346

Train epoch 105
[E105B0  |   1280/50000 (  3%) ] Loss: 0.0079 top1= 99.7656
[E105B10 |  14080/50000 ( 28%) ] Loss: 0.0026 top1=100.0000
[E105B20 |  26880/50000 ( 54%) ] Loss: 0.0090 top1= 99.6875
[E105B30 |  39680/50000 ( 79%) ] Loss: 0.0073 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5663 top1= 12.9908


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.1771 top1= 43.6498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.9470 top1= 46.6346

Train epoch 106
[E106B0  |   1280/50000 (  3%) ] Loss: 0.0135 top1= 99.5312
[E106B10 |  14080/50000 ( 28%) ] Loss: 0.0067 top1= 99.7656
[E106B20 |  26880/50000 ( 54%) ] Loss: 0.0076 top1= 99.6094
[E106B30 |  39680/50000 ( 79%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5666 top1= 12.9908


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.3580 top1= 43.6498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.9220 top1= 46.6546

Train epoch 107
[E107B0  |   1280/50000 (  3%) ] Loss: 0.0083 top1= 99.6094
[E107B10 |  14080/50000 ( 28%) ] Loss: 0.0031 top1= 99.9219
[E107B20 |  26880/50000 ( 54%) ] Loss: 0.0069 top1= 99.7656
[E107B30 |  39680/50000 ( 79%) ] Loss: 0.0133 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5702 top1= 12.8105


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.4090 top1= 43.6498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.1413 top1= 46.6246

Train epoch 108
[E108B0  |   1280/50000 (  3%) ] Loss: 0.0046 top1= 99.8438
[E108B10 |  14080/50000 ( 28%) ] Loss: 0.0046 top1= 99.9219
[E108B20 |  26880/50000 ( 54%) ] Loss: 0.0063 top1= 99.8438
[E108B30 |  39680/50000 ( 79%) ] Loss: 0.0046 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5693 top1= 12.9507


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.5257 top1= 43.6298


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.1581 top1= 46.7047

Train epoch 109
[E109B0  |   1280/50000 (  3%) ] Loss: 0.0074 top1= 99.8438
[E109B10 |  14080/50000 ( 28%) ] Loss: 0.0058 top1= 99.8438
[E109B20 |  26880/50000 ( 54%) ] Loss: 0.0036 top1= 99.9219
[E109B30 |  39680/50000 ( 79%) ] Loss: 0.0044 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5699 top1= 12.8005


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.7460 top1= 43.5697


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.2388 top1= 46.6546

Train epoch 110
[E110B0  |   1280/50000 (  3%) ] Loss: 0.0049 top1= 99.8438
[E110B10 |  14080/50000 ( 28%) ] Loss: 0.0080 top1= 99.8438
[E110B20 |  26880/50000 ( 54%) ] Loss: 0.0120 top1= 99.6094
[E110B30 |  39680/50000 ( 79%) ] Loss: 0.0049 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5722 top1= 12.9407


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.7980 top1= 43.6599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.2635 top1= 46.6546

Train epoch 111
[E111B0  |   1280/50000 (  3%) ] Loss: 0.0088 top1= 99.8438
[E111B10 |  14080/50000 ( 28%) ] Loss: 0.0108 top1= 99.5312
[E111B20 |  26880/50000 ( 54%) ] Loss: 0.0064 top1= 99.8438
[E111B30 |  39680/50000 ( 79%) ] Loss: 0.0019 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5721 top1= 13.0008


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.7246 top1= 43.6699


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.2754 top1= 46.6446

Train epoch 112
[E112B0  |   1280/50000 (  3%) ] Loss: 0.0031 top1= 99.9219
[E112B10 |  14080/50000 ( 28%) ] Loss: 0.0035 top1=100.0000
[E112B20 |  26880/50000 ( 54%) ] Loss: 0.0087 top1= 99.6875
[E112B30 |  39680/50000 ( 79%) ] Loss: 0.0039 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5719 top1= 13.0909


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.9015 top1= 43.6098


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.3497 top1= 46.6146

Train epoch 113
[E113B0  |   1280/50000 (  3%) ] Loss: 0.0035 top1= 99.8438
[E113B10 |  14080/50000 ( 28%) ] Loss: 0.0069 top1= 99.8438
[E113B20 |  26880/50000 ( 54%) ] Loss: 0.0080 top1= 99.6875
[E113B30 |  39680/50000 ( 79%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5712 top1= 12.9708


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.1018 top1= 43.6899


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.3893 top1= 46.6046

Train epoch 114
[E114B0  |   1280/50000 (  3%) ] Loss: 0.0027 top1= 99.9219
[E114B10 |  14080/50000 ( 28%) ] Loss: 0.0016 top1= 99.9219
[E114B20 |  26880/50000 ( 54%) ] Loss: 0.0040 top1= 99.9219
[E114B30 |  39680/50000 ( 79%) ] Loss: 0.0087 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5730 top1= 13.1010


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.0699 top1= 43.6498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.3394 top1= 46.6546

Train epoch 115
[E115B0  |   1280/50000 (  3%) ] Loss: 0.0061 top1= 99.7656
[E115B10 |  14080/50000 ( 28%) ] Loss: 0.0042 top1= 99.9219
[E115B20 |  26880/50000 ( 54%) ] Loss: 0.0037 top1= 99.7656
[E115B30 |  39680/50000 ( 79%) ] Loss: 0.0019 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5758 top1= 13.0609


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.8301 top1= 43.8401


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.4612 top1= 46.6446

Train epoch 116
[E116B0  |   1280/50000 (  3%) ] Loss: 0.0080 top1= 99.7656
[E116B10 |  14080/50000 ( 28%) ] Loss: 0.0047 top1= 99.6875
[E116B20 |  26880/50000 ( 54%) ] Loss: 0.0020 top1=100.0000
[E116B30 |  39680/50000 ( 79%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5732 top1= 12.9808


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.1302 top1= 43.7200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.4825 top1= 46.6947

Train epoch 117
[E117B0  |   1280/50000 (  3%) ] Loss: 0.0023 top1= 99.9219
[E117B10 |  14080/50000 ( 28%) ] Loss: 0.0043 top1= 99.8438
[E117B20 |  26880/50000 ( 54%) ] Loss: 0.0069 top1= 99.7656
[E117B30 |  39680/50000 ( 79%) ] Loss: 0.0084 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5750 top1= 12.9407


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.1436 top1= 43.7200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.5886 top1= 46.6246

Train epoch 118
[E118B0  |   1280/50000 (  3%) ] Loss: 0.0051 top1= 99.7656
[E118B10 |  14080/50000 ( 28%) ] Loss: 0.0021 top1=100.0000
[E118B20 |  26880/50000 ( 54%) ] Loss: 0.0094 top1= 99.6875
[E118B30 |  39680/50000 ( 79%) ] Loss: 0.0062 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5771 top1= 12.8906


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.0922 top1= 43.6799


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.5844 top1= 46.6346

Train epoch 119
[E119B0  |   1280/50000 (  3%) ] Loss: 0.0028 top1= 99.9219
[E119B10 |  14080/50000 ( 28%) ] Loss: 0.0043 top1= 99.7656
[E119B20 |  26880/50000 ( 54%) ] Loss: 0.0034 top1= 99.9219
[E119B30 |  39680/50000 ( 79%) ] Loss: 0.0018 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5777 top1= 13.0208


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.3480 top1= 43.7400


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7032 top1= 46.5345

Train epoch 120
[E120B0  |   1280/50000 (  3%) ] Loss: 0.0143 top1= 99.5312
[E120B10 |  14080/50000 ( 28%) ] Loss: 0.0041 top1= 99.8438
[E120B20 |  26880/50000 ( 54%) ] Loss: 0.0036 top1= 99.7656
[E120B30 |  39680/50000 ( 79%) ] Loss: 0.0030 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5780 top1= 13.0308


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.3506 top1= 43.6599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8372 top1= 46.6546

Train epoch 121
[E121B0  |   1280/50000 (  3%) ] Loss: 0.0024 top1= 99.9219
[E121B10 |  14080/50000 ( 28%) ] Loss: 0.0029 top1= 99.9219
[E121B20 |  26880/50000 ( 54%) ] Loss: 0.0050 top1= 99.8438
[E121B30 |  39680/50000 ( 79%) ] Loss: 0.0057 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5777 top1= 13.0609


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.3414 top1= 43.6799


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8187 top1= 46.6647

Train epoch 122
[E122B0  |   1280/50000 (  3%) ] Loss: 0.0067 top1= 99.8438
[E122B10 |  14080/50000 ( 28%) ] Loss: 0.0012 top1=100.0000
[E122B20 |  26880/50000 ( 54%) ] Loss: 0.0053 top1= 99.7656
[E122B30 |  39680/50000 ( 79%) ] Loss: 0.0101 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5775 top1= 13.0108


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.3706 top1= 43.6799


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8174 top1= 46.6146

Train epoch 123
[E123B0  |   1280/50000 (  3%) ] Loss: 0.0019 top1=100.0000
[E123B10 |  14080/50000 ( 28%) ] Loss: 0.0039 top1= 99.9219
[E123B20 |  26880/50000 ( 54%) ] Loss: 0.0034 top1= 99.9219
[E123B30 |  39680/50000 ( 79%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5776 top1= 13.0208


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.3719 top1= 43.6699


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7993 top1= 46.6046

Train epoch 124
[E124B0  |   1280/50000 (  3%) ] Loss: 0.0041 top1= 99.9219
[E124B10 |  14080/50000 ( 28%) ] Loss: 0.0011 top1=100.0000
[E124B20 |  26880/50000 ( 54%) ] Loss: 0.0079 top1= 99.7656
[E124B30 |  39680/50000 ( 79%) ] Loss: 0.0044 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5776 top1= 13.0308


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.3698 top1= 43.6599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7836 top1= 46.6246

Train epoch 125
[E125B0  |   1280/50000 (  3%) ] Loss: 0.0028 top1= 99.9219
[E125B10 |  14080/50000 ( 28%) ] Loss: 0.0049 top1= 99.6875
[E125B20 |  26880/50000 ( 54%) ] Loss: 0.0027 top1= 99.9219
[E125B30 |  39680/50000 ( 79%) ] Loss: 0.0023 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5779 top1= 12.9708


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.3901 top1= 43.6599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7844 top1= 46.6246

Train epoch 126
[E126B0  |   1280/50000 (  3%) ] Loss: 0.0031 top1= 99.8438
[E126B10 |  14080/50000 ( 28%) ] Loss: 0.0042 top1= 99.8438
[E126B20 |  26880/50000 ( 54%) ] Loss: 0.0026 top1= 99.9219
[E126B30 |  39680/50000 ( 79%) ] Loss: 0.0063 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5780 top1= 12.9708


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.4016 top1= 43.6699


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7803 top1= 46.6146

Train epoch 127
[E127B0  |   1280/50000 (  3%) ] Loss: 0.0024 top1= 99.9219
[E127B10 |  14080/50000 ( 28%) ] Loss: 0.0029 top1= 99.9219
[E127B20 |  26880/50000 ( 54%) ] Loss: 0.0036 top1= 99.9219
[E127B30 |  39680/50000 ( 79%) ] Loss: 0.0029 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5777 top1= 13.0509


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.4006 top1= 43.6699


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7949 top1= 46.6246

Train epoch 128
[E128B0  |   1280/50000 (  3%) ] Loss: 0.0015 top1=100.0000
[E128B10 |  14080/50000 ( 28%) ] Loss: 0.0022 top1=100.0000
[E128B20 |  26880/50000 ( 54%) ] Loss: 0.0048 top1= 99.7656
[E128B30 |  39680/50000 ( 79%) ] Loss: 0.0064 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5778 top1= 13.0809


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.4349 top1= 43.6899


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8007 top1= 46.6246

Train epoch 129
[E129B0  |   1280/50000 (  3%) ] Loss: 0.0027 top1= 99.9219
[E129B10 |  14080/50000 ( 28%) ] Loss: 0.0031 top1= 99.9219
[E129B20 |  26880/50000 ( 54%) ] Loss: 0.0081 top1= 99.6094
[E129B30 |  39680/50000 ( 79%) ] Loss: 0.0058 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5780 top1= 13.0809


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.4366 top1= 43.7099


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7802 top1= 46.6146

Train epoch 130
[E130B0  |   1280/50000 (  3%) ] Loss: 0.0079 top1= 99.8438
[E130B10 |  14080/50000 ( 28%) ] Loss: 0.0049 top1= 99.7656
[E130B20 |  26880/50000 ( 54%) ] Loss: 0.0029 top1= 99.9219
[E130B30 |  39680/50000 ( 79%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5780 top1= 13.0509


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.4287 top1= 43.7099


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7575 top1= 46.6046

Train epoch 131
[E131B0  |   1280/50000 (  3%) ] Loss: 0.0082 top1= 99.6094
[E131B10 |  14080/50000 ( 28%) ] Loss: 0.0049 top1= 99.7656
[E131B20 |  26880/50000 ( 54%) ] Loss: 0.0037 top1= 99.8438
[E131B30 |  39680/50000 ( 79%) ] Loss: 0.0056 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5780 top1= 13.0609


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.4422 top1= 43.7099


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7589 top1= 46.6146

Train epoch 132
[E132B0  |   1280/50000 (  3%) ] Loss: 0.0030 top1= 99.9219
[E132B10 |  14080/50000 ( 28%) ] Loss: 0.0027 top1= 99.9219
[E132B20 |  26880/50000 ( 54%) ] Loss: 0.0033 top1= 99.9219
[E132B30 |  39680/50000 ( 79%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5780 top1= 12.9808


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.4570 top1= 43.7200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7523 top1= 46.6346

Train epoch 133
[E133B0  |   1280/50000 (  3%) ] Loss: 0.0026 top1= 99.9219
[E133B10 |  14080/50000 ( 28%) ] Loss: 0.0022 top1=100.0000
[E133B20 |  26880/50000 ( 54%) ] Loss: 0.0028 top1= 99.9219
[E133B30 |  39680/50000 ( 79%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5780 top1= 12.9808


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.4634 top1= 43.7200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7561 top1= 46.6346

Train epoch 134
[E134B0  |   1280/50000 (  3%) ] Loss: 0.0013 top1=100.0000
[E134B10 |  14080/50000 ( 28%) ] Loss: 0.0047 top1= 99.9219
[E134B20 |  26880/50000 ( 54%) ] Loss: 0.0062 top1= 99.6094
[E134B30 |  39680/50000 ( 79%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5782 top1= 12.9607


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.4789 top1= 43.6799


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7556 top1= 46.6346

Train epoch 135
[E135B0  |   1280/50000 (  3%) ] Loss: 0.0020 top1= 99.9219
[E135B10 |  14080/50000 ( 28%) ] Loss: 0.0035 top1= 99.9219
[E135B20 |  26880/50000 ( 54%) ] Loss: 0.0014 top1=100.0000
[E135B30 |  39680/50000 ( 79%) ] Loss: 0.0042 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5781 top1= 12.9607


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.4983 top1= 43.6699


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7533 top1= 46.6546

Train epoch 136
[E136B0  |   1280/50000 (  3%) ] Loss: 0.0037 top1= 99.9219
[E136B10 |  14080/50000 ( 28%) ] Loss: 0.0032 top1= 99.8438
[E136B20 |  26880/50000 ( 54%) ] Loss: 0.0009 top1=100.0000
[E136B30 |  39680/50000 ( 79%) ] Loss: 0.0029 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5782 top1= 12.9407


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.5035 top1= 43.6799


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7618 top1= 46.6446

Train epoch 137
[E137B0  |   1280/50000 (  3%) ] Loss: 0.0038 top1= 99.9219
[E137B10 |  14080/50000 ( 28%) ] Loss: 0.0022 top1= 99.9219
[E137B20 |  26880/50000 ( 54%) ] Loss: 0.0041 top1= 99.8438
[E137B30 |  39680/50000 ( 79%) ] Loss: 0.0033 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5781 top1= 12.9407


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.5252 top1= 43.6699


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7797 top1= 46.6346

Train epoch 138
[E138B0  |   1280/50000 (  3%) ] Loss: 0.0036 top1= 99.8438
[E138B10 |  14080/50000 ( 28%) ] Loss: 0.0027 top1=100.0000
[E138B20 |  26880/50000 ( 54%) ] Loss: 0.0038 top1= 99.8438
[E138B30 |  39680/50000 ( 79%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5782 top1= 12.9407


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.5189 top1= 43.6699


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8006 top1= 46.6446

Train epoch 139
[E139B0  |   1280/50000 (  3%) ] Loss: 0.0019 top1=100.0000
[E139B10 |  14080/50000 ( 28%) ] Loss: 0.0051 top1= 99.8438
[E139B20 |  26880/50000 ( 54%) ] Loss: 0.0045 top1= 99.8438
[E139B30 |  39680/50000 ( 79%) ] Loss: 0.0042 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5782 top1= 12.9507


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.5006 top1= 43.6899


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8176 top1= 46.6346

Train epoch 140
[E140B0  |   1280/50000 (  3%) ] Loss: 0.0014 top1=100.0000
[E140B10 |  14080/50000 ( 28%) ] Loss: 0.0063 top1= 99.9219
[E140B20 |  26880/50000 ( 54%) ] Loss: 0.0029 top1= 99.9219
[E140B30 |  39680/50000 ( 79%) ] Loss: 0.0050 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5784 top1= 12.9307


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.4995 top1= 43.6899


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8176 top1= 46.6346

Train epoch 141
[E141B0  |   1280/50000 (  3%) ] Loss: 0.0044 top1= 99.8438
[E141B10 |  14080/50000 ( 28%) ] Loss: 0.0058 top1= 99.8438
[E141B20 |  26880/50000 ( 54%) ] Loss: 0.0067 top1= 99.6875
[E141B30 |  39680/50000 ( 79%) ] Loss: 0.0039 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5783 top1= 12.9307


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.5231 top1= 43.7400


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8114 top1= 46.6246

Train epoch 142
[E142B0  |   1280/50000 (  3%) ] Loss: 0.0019 top1=100.0000
[E142B10 |  14080/50000 ( 28%) ] Loss: 0.0015 top1=100.0000
[E142B20 |  26880/50000 ( 54%) ] Loss: 0.0026 top1= 99.9219
[E142B30 |  39680/50000 ( 79%) ] Loss: 0.0082 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5783 top1= 12.9307


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.5270 top1= 43.7200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8161 top1= 46.6546

Train epoch 143
[E143B0  |   1280/50000 (  3%) ] Loss: 0.0065 top1= 99.6875
[E143B10 |  14080/50000 ( 28%) ] Loss: 0.0016 top1=100.0000
[E143B20 |  26880/50000 ( 54%) ] Loss: 0.0098 top1= 99.6094
[E143B30 |  39680/50000 ( 79%) ] Loss: 0.0017 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5783 top1= 12.9307


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.5366 top1= 43.7300


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8146 top1= 46.6446

Train epoch 144
[E144B0  |   1280/50000 (  3%) ] Loss: 0.0077 top1= 99.8438
[E144B10 |  14080/50000 ( 28%) ] Loss: 0.0067 top1= 99.7656
[E144B20 |  26880/50000 ( 54%) ] Loss: 0.0026 top1= 99.8438
[E144B30 |  39680/50000 ( 79%) ] Loss: 0.0051 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5785 top1= 12.9307


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.5089 top1= 43.7200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7987 top1= 46.6246

Train epoch 145
[E145B0  |   1280/50000 (  3%) ] Loss: 0.0028 top1= 99.9219
[E145B10 |  14080/50000 ( 28%) ] Loss: 0.0018 top1=100.0000
[E145B20 |  26880/50000 ( 54%) ] Loss: 0.0018 top1= 99.9219
[E145B30 |  39680/50000 ( 79%) ] Loss: 0.0027 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5785 top1= 12.9407


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.5148 top1= 43.7200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8055 top1= 46.6246

Train epoch 146
[E146B0  |   1280/50000 (  3%) ] Loss: 0.0021 top1= 99.9219
[E146B10 |  14080/50000 ( 28%) ] Loss: 0.0011 top1=100.0000
[E146B20 |  26880/50000 ( 54%) ] Loss: 0.0032 top1= 99.8438
[E146B30 |  39680/50000 ( 79%) ] Loss: 0.0066 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5784 top1= 12.9407


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.5351 top1= 43.7400


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8196 top1= 46.6446

Train epoch 147
[E147B0  |   1280/50000 (  3%) ] Loss: 0.0062 top1= 99.7656
[E147B10 |  14080/50000 ( 28%) ] Loss: 0.0025 top1=100.0000
[E147B20 |  26880/50000 ( 54%) ] Loss: 0.0050 top1= 99.7656
[E147B30 |  39680/50000 ( 79%) ] Loss: 0.0033 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5782 top1= 12.9808


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.5451 top1= 43.7400


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8358 top1= 46.6847

Train epoch 148
[E148B0  |   1280/50000 (  3%) ] Loss: 0.0043 top1= 99.8438
[E148B10 |  14080/50000 ( 28%) ] Loss: 0.0018 top1=100.0000
[E148B20 |  26880/50000 ( 54%) ] Loss: 0.0007 top1=100.0000
[E148B30 |  39680/50000 ( 79%) ] Loss: 0.0049 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5784 top1= 12.9407


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.5424 top1= 43.7800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8407 top1= 46.6647

Train epoch 149
[E149B0  |   1280/50000 (  3%) ] Loss: 0.0035 top1= 99.9219
[E149B10 |  14080/50000 ( 28%) ] Loss: 0.0017 top1=100.0000
[E149B20 |  26880/50000 ( 54%) ] Loss: 0.0024 top1= 99.9219
[E149B30 |  39680/50000 ( 79%) ] Loss: 0.0019 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5788 top1= 12.9006


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.5605 top1= 43.6999


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8519 top1= 46.6647

Train epoch 150
[E150B0  |   1280/50000 (  3%) ] Loss: 0.0040 top1= 99.8438
[E150B10 |  14080/50000 ( 28%) ] Loss: 0.0007 top1=100.0000
[E150B20 |  26880/50000 ( 54%) ] Loss: 0.0048 top1= 99.7656
[E150B30 |  39680/50000 ( 79%) ] Loss: 0.0021 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5789 top1= 12.8906


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.5874 top1= 43.6599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8615 top1= 46.6747

