
=== 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 0x7f4221098730>

{'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= 10.1562

=== 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: 2.0600 top1= 19.8438
[E 1B20 |  26880/50000 ( 54%) ] Loss: 1.8156 top1= 18.2031
[E 1B30 |  39680/50000 ( 79%) ] Loss: 1.6913 top1= 21.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3105 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1986 top1=  9.9860


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4316 top1= 12.6903

Train epoch 2
[E 2B0  |   1280/50000 (  3%) ] Loss: 1.6341 top1= 21.7969
[E 2B10 |  14080/50000 ( 28%) ] Loss: 1.5972 top1= 24.5312
[E 2B20 |  26880/50000 ( 54%) ] Loss: 1.5834 top1= 26.0156
[E 2B30 |  39680/50000 ( 79%) ] Loss: 1.6369 top1= 22.5781

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3220 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1749 top1= 10.5268


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6736 top1= 19.5212

Train epoch 3
[E 3B0  |   1280/50000 (  3%) ] Loss: 1.5439 top1= 26.5625
[E 3B10 |  14080/50000 ( 28%) ] Loss: 1.5032 top1= 33.1250
[E 3B20 |  26880/50000 ( 54%) ] Loss: 1.4472 top1= 35.7031
[E 3B30 |  39680/50000 ( 79%) ] Loss: 1.4595 top1= 33.3594

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3529 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3660 top1=  9.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7522 top1= 25.4708

Train epoch 4
[E 4B0  |   1280/50000 (  3%) ] Loss: 1.4349 top1= 35.7812
[E 4B10 |  14080/50000 ( 28%) ] Loss: 1.4388 top1= 32.8906
[E 4B20 |  26880/50000 ( 54%) ] Loss: 1.4299 top1= 33.1250
[E 4B30 |  39680/50000 ( 79%) ] Loss: 1.3068 top1= 42.7344

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4156 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5891 top1= 16.8470


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2607 top1= 28.8562

Train epoch 5
[E 5B0  |   1280/50000 (  3%) ] Loss: 1.2985 top1= 44.7656
[E 5B10 |  14080/50000 ( 28%) ] Loss: 1.4318 top1= 37.5000
[E 5B20 |  26880/50000 ( 54%) ] Loss: 1.3858 top1= 39.5312
[E 5B30 |  39680/50000 ( 79%) ] Loss: 1.2816 top1= 41.1719

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4068 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4588 top1= 16.1358


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2754 top1= 30.4487

Train epoch 6
[E 6B0  |   1280/50000 (  3%) ] Loss: 1.2888 top1= 44.2969
[E 6B10 |  14080/50000 ( 28%) ] Loss: 1.2296 top1= 46.1719
[E 6B20 |  26880/50000 ( 54%) ] Loss: 1.2362 top1= 48.4375
[E 6B30 |  39680/50000 ( 79%) ] Loss: 1.2681 top1= 47.2656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3965 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4815 top1= 19.0905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1427 top1= 33.1831

Train epoch 7
[E 7B0  |   1280/50000 (  3%) ] Loss: 1.1432 top1= 52.1875
[E 7B10 |  14080/50000 ( 28%) ] Loss: 1.1513 top1= 50.7812
[E 7B20 |  26880/50000 ( 54%) ] Loss: 1.1187 top1= 53.8281
[E 7B30 |  39680/50000 ( 79%) ] Loss: 1.1023 top1= 52.4219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4224 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6121 top1= 18.9403


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2214 top1= 33.1631

Train epoch 8
[E 8B0  |   1280/50000 (  3%) ] Loss: 1.1763 top1= 53.8281
[E 8B10 |  14080/50000 ( 28%) ] Loss: 1.0562 top1= 56.1719
[E 8B20 |  26880/50000 ( 54%) ] Loss: 1.0094 top1= 57.8125
[E 8B30 |  39680/50000 ( 79%) ] Loss: 1.0793 top1= 54.1406

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4532 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8468 top1= 24.4692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9222 top1= 35.7973

Train epoch 9
[E 9B0  |   1280/50000 (  3%) ] Loss: 1.0332 top1= 58.6719
[E 9B10 |  14080/50000 ( 28%) ] Loss: 0.9628 top1= 61.4844
[E 9B20 |  26880/50000 ( 54%) ] Loss: 0.9558 top1= 61.5625
[E 9B30 |  39680/50000 ( 79%) ] Loss: 0.8290 top1= 66.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4764 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8489 top1= 21.4443


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6481 top1= 39.3830

Train epoch 10
[E10B0  |   1280/50000 (  3%) ] Loss: 0.9738 top1= 61.7188
[E10B10 |  14080/50000 ( 28%) ] Loss: 0.9614 top1= 61.2500
[E10B20 |  26880/50000 ( 54%) ] Loss: 0.8795 top1= 64.8438
[E10B30 |  39680/50000 ( 79%) ] Loss: 0.7945 top1= 68.2031

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4889 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0734 top1= 26.9631


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2050 top1= 38.9323

Train epoch 11
[E11B0  |   1280/50000 (  3%) ] Loss: 0.8862 top1= 66.0156
[E11B10 |  14080/50000 ( 28%) ] Loss: 0.8826 top1= 64.7656
[E11B20 |  26880/50000 ( 54%) ] Loss: 0.7786 top1= 68.7500
[E11B30 |  39680/50000 ( 79%) ] Loss: 0.7877 top1= 68.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4977 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1416 top1= 29.8177


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0252 top1= 39.7135

Train epoch 12
[E12B0  |   1280/50000 (  3%) ] Loss: 0.7567 top1= 69.6875
[E12B10 |  14080/50000 ( 28%) ] Loss: 0.7827 top1= 68.9062
[E12B20 |  26880/50000 ( 54%) ] Loss: 0.7518 top1= 69.6094
[E12B30 |  39680/50000 ( 79%) ] Loss: 0.6984 top1= 72.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5235 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2809 top1= 29.1066


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8134 top1= 42.3478

Train epoch 13
[E13B0  |   1280/50000 (  3%) ] Loss: 0.7431 top1= 70.1562
[E13B10 |  14080/50000 ( 28%) ] Loss: 0.7635 top1= 70.6250
[E13B20 |  26880/50000 ( 54%) ] Loss: 0.7984 top1= 68.2812
[E13B30 |  39680/50000 ( 79%) ] Loss: 0.6723 top1= 74.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5347 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3268 top1= 31.9010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6128 top1= 42.1575

Train epoch 14
[E14B0  |   1280/50000 (  3%) ] Loss: 0.6607 top1= 73.3594
[E14B10 |  14080/50000 ( 28%) ] Loss: 0.7639 top1= 70.0781
[E14B20 |  26880/50000 ( 54%) ] Loss: 0.7236 top1= 72.8125
[E14B30 |  39680/50000 ( 79%) ] Loss: 0.6272 top1= 76.7969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5527 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2352 top1= 33.2232


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8886 top1= 43.3093

Train epoch 15
[E15B0  |   1280/50000 (  3%) ] Loss: 0.6430 top1= 75.0781
[E15B10 |  14080/50000 ( 28%) ] Loss: 0.6499 top1= 75.3906
[E15B20 |  26880/50000 ( 54%) ] Loss: 0.6202 top1= 75.4688
[E15B30 |  39680/50000 ( 79%) ] Loss: 0.5909 top1= 77.4219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5594 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1946 top1= 33.5437


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4793 top1= 43.5497

Train epoch 16
[E16B0  |   1280/50000 (  3%) ] Loss: 0.6082 top1= 76.7188
[E16B10 |  14080/50000 ( 28%) ] Loss: 0.6609 top1= 75.3125
[E16B20 |  26880/50000 ( 54%) ] Loss: 0.6057 top1= 77.3438
[E16B30 |  39680/50000 ( 79%) ] Loss: 0.5576 top1= 80.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5572 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3340 top1= 34.1446


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2497 top1= 43.3594

Train epoch 17
[E17B0  |   1280/50000 (  3%) ] Loss: 0.5879 top1= 78.6719
[E17B10 |  14080/50000 ( 28%) ] Loss: 0.5558 top1= 78.0469
[E17B20 |  26880/50000 ( 54%) ] Loss: 0.5576 top1= 78.2812
[E17B30 |  39680/50000 ( 79%) ] Loss: 0.5470 top1= 77.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5806 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4142 top1= 34.6755


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3800 top1= 43.8802

Train epoch 18
[E18B0  |   1280/50000 (  3%) ] Loss: 0.5403 top1= 80.3125
[E18B10 |  14080/50000 ( 28%) ] Loss: 0.5670 top1= 77.0312
[E18B20 |  26880/50000 ( 54%) ] Loss: 0.5393 top1= 79.5312
[E18B30 |  39680/50000 ( 79%) ] Loss: 0.5019 top1= 81.4844

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5704 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2740 top1= 35.3265


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4584 top1= 43.7300

Train epoch 19
[E19B0  |   1280/50000 (  3%) ] Loss: 0.5405 top1= 80.0781
[E19B10 |  14080/50000 ( 28%) ] Loss: 0.5308 top1= 78.9844
[E19B20 |  26880/50000 ( 54%) ] Loss: 0.5067 top1= 82.0312
[E19B30 |  39680/50000 ( 79%) ] Loss: 0.4672 top1= 82.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.6178 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5740 top1= 36.1178


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4488 top1= 44.3810

Train epoch 20
[E20B0  |   1280/50000 (  3%) ] Loss: 0.4655 top1= 82.5000
[E20B10 |  14080/50000 ( 28%) ] Loss: 0.4916 top1= 81.4844
[E20B20 |  26880/50000 ( 54%) ] Loss: 0.4842 top1= 82.0312
[E20B30 |  39680/50000 ( 79%) ] Loss: 0.4641 top1= 82.8906

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5909 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3186 top1= 36.8189


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7082 top1= 43.9002

Train epoch 21
[E21B0  |   1280/50000 (  3%) ] Loss: 0.4695 top1= 82.8125
[E21B10 |  14080/50000 ( 28%) ] Loss: 0.5146 top1= 80.2344
[E21B20 |  26880/50000 ( 54%) ] Loss: 0.4730 top1= 83.5156
[E21B30 |  39680/50000 ( 79%) ] Loss: 0.4196 top1= 83.6719

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.6030 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4855 top1= 36.9091


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9759 top1= 43.3193

Train epoch 22
[E22B0  |   1280/50000 (  3%) ] Loss: 0.4760 top1= 82.8125
[E22B10 |  14080/50000 ( 28%) ] Loss: 0.4558 top1= 82.5000
[E22B20 |  26880/50000 ( 54%) ] Loss: 0.4723 top1= 82.1094
[E22B30 |  39680/50000 ( 79%) ] Loss: 0.4528 top1= 82.7344

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.6033 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2685 top1= 36.5785


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5426 top1= 44.8317

Train epoch 23
[E23B0  |   1280/50000 (  3%) ] Loss: 0.4482 top1= 83.5938
[E23B10 |  14080/50000 ( 28%) ] Loss: 0.5323 top1= 80.6250
[E23B20 |  26880/50000 ( 54%) ] Loss: 0.4389 top1= 83.5938
[E23B30 |  39680/50000 ( 79%) ] Loss: 0.4087 top1= 85.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.6233 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7749 top1= 37.6502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2025 top1= 44.6114

Train epoch 24
[E24B0  |   1280/50000 (  3%) ] Loss: 0.4384 top1= 83.9844
[E24B10 |  14080/50000 ( 28%) ] Loss: 0.4825 top1= 81.7969
[E24B20 |  26880/50000 ( 54%) ] Loss: 0.4462 top1= 83.1250
[E24B30 |  39680/50000 ( 79%) ] Loss: 0.4063 top1= 85.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.6218 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4326 top1= 37.9708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1994 top1= 45.2524

Train epoch 25
[E25B0  |   1280/50000 (  3%) ] Loss: 0.4092 top1= 85.3125
[E25B10 |  14080/50000 ( 28%) ] Loss: 0.4693 top1= 82.1094
[E25B20 |  26880/50000 ( 54%) ] Loss: 0.4167 top1= 83.5938
[E25B30 |  39680/50000 ( 79%) ] Loss: 0.3801 top1= 85.8594

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.6274 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5484 top1= 37.7003


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8385 top1= 45.4227

Train epoch 26
[E26B0  |   1280/50000 (  3%) ] Loss: 0.4077 top1= 85.2344
[E26B10 |  14080/50000 ( 28%) ] Loss: 0.4827 top1= 82.8125
[E26B20 |  26880/50000 ( 54%) ] Loss: 0.4268 top1= 84.9219
[E26B30 |  39680/50000 ( 79%) ] Loss: 0.3669 top1= 86.6406

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.6607 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6216 top1= 37.8606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4802 top1= 45.1422

Train epoch 27
[E27B0  |   1280/50000 (  3%) ] Loss: 0.3702 top1= 85.1562
[E27B10 |  14080/50000 ( 28%) ] Loss: 0.4141 top1= 84.8438
[E27B20 |  26880/50000 ( 54%) ] Loss: 0.3446 top1= 87.2656
[E27B30 |  39680/50000 ( 79%) ] Loss: 0.3248 top1= 87.8906

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.6717 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9112 top1= 38.5617


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7390 top1= 45.3926

Train epoch 28
[E28B0  |   1280/50000 (  3%) ] Loss: 0.3618 top1= 86.4844
[E28B10 |  14080/50000 ( 28%) ] Loss: 0.3726 top1= 84.8438
[E28B20 |  26880/50000 ( 54%) ] Loss: 0.3533 top1= 86.4844
[E28B30 |  39680/50000 ( 79%) ] Loss: 0.3532 top1= 87.2656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.6771 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3412 top1= 37.2596


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6824 top1= 45.0421

Train epoch 29
[E29B0  |   1280/50000 (  3%) ] Loss: 0.3713 top1= 86.8750
[E29B10 |  14080/50000 ( 28%) ] Loss: 0.3747 top1= 83.9844
[E29B20 |  26880/50000 ( 54%) ] Loss: 0.3344 top1= 86.5625
[E29B30 |  39680/50000 ( 79%) ] Loss: 0.2959 top1= 89.6094

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.6773 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1955 top1= 38.4115


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6088 top1= 45.0521

Train epoch 30
[E30B0  |   1280/50000 (  3%) ] Loss: 0.3505 top1= 87.6562
[E30B10 |  14080/50000 ( 28%) ] Loss: 0.3052 top1= 88.7500
[E30B20 |  26880/50000 ( 54%) ] Loss: 0.3685 top1= 86.0938
[E30B30 |  39680/50000 ( 79%) ] Loss: 0.3390 top1= 88.2031

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.6657 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0564 top1= 38.2412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2217 top1= 45.0721

Train epoch 31
[E31B0  |   1280/50000 (  3%) ] Loss: 0.3630 top1= 86.7969
[E31B10 |  14080/50000 ( 28%) ] Loss: 0.3533 top1= 86.4062
[E31B20 |  26880/50000 ( 54%) ] Loss: 0.3327 top1= 86.9531
[E31B30 |  39680/50000 ( 79%) ] Loss: 0.3289 top1= 87.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.6841 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0763 top1= 38.7019


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6257 top1= 45.0621

Train epoch 32
[E32B0  |   1280/50000 (  3%) ] Loss: 0.3223 top1= 87.4219
[E32B10 |  14080/50000 ( 28%) ] Loss: 0.2997 top1= 87.9688
[E32B20 |  26880/50000 ( 54%) ] Loss: 0.3447 top1= 87.1875
[E32B30 |  39680/50000 ( 79%) ] Loss: 0.2930 top1= 89.2969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.6875 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8479 top1= 38.6218


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9400 top1= 45.6330

Train epoch 33
[E33B0  |   1280/50000 (  3%) ] Loss: 0.3236 top1= 88.2812
[E33B10 |  14080/50000 ( 28%) ] Loss: 0.3068 top1= 89.2188
[E33B20 |  26880/50000 ( 54%) ] Loss: 0.2786 top1= 89.2188
[E33B30 |  39680/50000 ( 79%) ] Loss: 0.3030 top1= 88.8281

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.6933 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.6767 top1= 37.2396


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1633 top1= 45.6430

Train epoch 34
[E34B0  |   1280/50000 (  3%) ] Loss: 0.3425 top1= 87.1875
[E34B10 |  14080/50000 ( 28%) ] Loss: 0.3575 top1= 86.7969
[E34B20 |  26880/50000 ( 54%) ] Loss: 0.3207 top1= 89.0625
[E34B30 |  39680/50000 ( 79%) ] Loss: 0.2996 top1= 88.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.6671 top1= 10.0461


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8866 top1= 37.4900


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3372 top1= 45.6330

Train epoch 35
[E35B0  |   1280/50000 (  3%) ] Loss: 0.3171 top1= 87.2656
[E35B10 |  14080/50000 ( 28%) ] Loss: 0.2963 top1= 88.9844
[E35B20 |  26880/50000 ( 54%) ] Loss: 0.2907 top1= 88.7500
[E35B30 |  39680/50000 ( 79%) ] Loss: 0.2948 top1= 88.8281

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.7015 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3586 top1= 40.0240


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4925 top1= 45.5228

Train epoch 36
[E36B0  |   1280/50000 (  3%) ] Loss: 0.3060 top1= 89.1406
[E36B10 |  14080/50000 ( 28%) ] Loss: 0.2842 top1= 88.7500
[E36B20 |  26880/50000 ( 54%) ] Loss: 0.2569 top1= 90.0781
[E36B30 |  39680/50000 ( 79%) ] Loss: 0.2899 top1= 89.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.7164 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3214 top1= 39.4331


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9740 top1= 45.4627

Train epoch 37
[E37B0  |   1280/50000 (  3%) ] Loss: 0.2840 top1= 89.2969
[E37B10 |  14080/50000 ( 28%) ] Loss: 0.2978 top1= 89.0625
[E37B20 |  26880/50000 ( 54%) ] Loss: 0.2511 top1= 90.0781
[E37B30 |  39680/50000 ( 79%) ] Loss: 0.2886 top1= 89.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.7334 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3794 top1= 39.4531


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1882 top1= 45.3125

Train epoch 38
[E38B0  |   1280/50000 (  3%) ] Loss: 0.2780 top1= 89.9219
[E38B10 |  14080/50000 ( 28%) ] Loss: 0.3005 top1= 89.1406
[E38B20 |  26880/50000 ( 54%) ] Loss: 0.2566 top1= 90.0000
[E38B30 |  39680/50000 ( 79%) ] Loss: 0.2883 top1= 89.2969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.7390 top1= 10.0260


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.6458 top1= 39.1727


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1911 top1= 45.8433

Train epoch 39
[E39B0  |   1280/50000 (  3%) ] Loss: 0.2834 top1= 89.4531
[E39B10 |  14080/50000 ( 28%) ] Loss: 0.2681 top1= 89.7656
[E39B20 |  26880/50000 ( 54%) ] Loss: 0.2909 top1= 89.6875
[E39B30 |  39680/50000 ( 79%) ] Loss: 0.2344 top1= 90.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.7419 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0520 top1= 39.5633


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9605 top1= 45.1022

Train epoch 40
[E40B0  |   1280/50000 (  3%) ] Loss: 0.2920 top1= 88.7500
[E40B10 |  14080/50000 ( 28%) ] Loss: 0.2700 top1= 89.2969
[E40B20 |  26880/50000 ( 54%) ] Loss: 0.2474 top1= 90.8594
[E40B30 |  39680/50000 ( 79%) ] Loss: 0.1978 top1= 92.7344

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.7403 top1= 10.0461


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5492 top1= 39.0425


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1577 top1= 45.6831

Train epoch 41
[E41B0  |   1280/50000 (  3%) ] Loss: 0.2614 top1= 89.8438
[E41B10 |  14080/50000 ( 28%) ] Loss: 0.2436 top1= 90.7812
[E41B20 |  26880/50000 ( 54%) ] Loss: 0.2398 top1= 90.6250
[E41B30 |  39680/50000 ( 79%) ] Loss: 0.2200 top1= 91.0156

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.7502 top1= 10.0661


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3534 top1= 40.1442


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7699 top1= 45.6631

Train epoch 42
[E42B0  |   1280/50000 (  3%) ] Loss: 0.2189 top1= 91.6406
[E42B10 |  14080/50000 ( 28%) ] Loss: 0.2622 top1= 89.2188
[E42B20 |  26880/50000 ( 54%) ] Loss: 0.2565 top1= 89.9219
[E42B30 |  39680/50000 ( 79%) ] Loss: 0.2388 top1= 91.0156

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.7709 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0336 top1= 40.5449


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5560 top1= 45.4127

Train epoch 43
[E43B0  |   1280/50000 (  3%) ] Loss: 0.2169 top1= 91.7969
[E43B10 |  14080/50000 ( 28%) ] Loss: 0.2389 top1= 91.1719
[E43B20 |  26880/50000 ( 54%) ] Loss: 0.2568 top1= 91.0156
[E43B30 |  39680/50000 ( 79%) ] Loss: 0.2111 top1= 91.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.7912 top1= 10.0260


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1463 top1= 40.1142


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.7789 top1= 45.6430

Train epoch 44
[E44B0  |   1280/50000 (  3%) ] Loss: 0.2073 top1= 92.7344
[E44B10 |  14080/50000 ( 28%) ] Loss: 0.2302 top1= 90.8594
[E44B20 |  26880/50000 ( 54%) ] Loss: 0.2117 top1= 91.4844
[E44B30 |  39680/50000 ( 79%) ] Loss: 0.2427 top1= 90.8594

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.7987 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1191 top1= 40.1442


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1743 top1= 45.7031

Train epoch 45
[E45B0  |   1280/50000 (  3%) ] Loss: 0.2311 top1= 91.7188
[E45B10 |  14080/50000 ( 28%) ] Loss: 0.2426 top1= 90.8594
[E45B20 |  26880/50000 ( 54%) ] Loss: 0.2283 top1= 91.3281
[E45B30 |  39680/50000 ( 79%) ] Loss: 0.2166 top1= 91.9531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.8020 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7786 top1= 40.6550


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3213 top1= 45.3125

Train epoch 46
[E46B0  |   1280/50000 (  3%) ] Loss: 0.2213 top1= 92.0312
[E46B10 |  14080/50000 ( 28%) ] Loss: 0.2055 top1= 92.1094
[E46B20 |  26880/50000 ( 54%) ] Loss: 0.2085 top1= 92.1875
[E46B30 |  39680/50000 ( 79%) ] Loss: 0.1755 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.8345 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1203 top1= 40.8654


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.0201 top1= 45.6130

Train epoch 47
[E47B0  |   1280/50000 (  3%) ] Loss: 0.1823 top1= 92.8906
[E47B10 |  14080/50000 ( 28%) ] Loss: 0.2034 top1= 92.7344
[E47B20 |  26880/50000 ( 54%) ] Loss: 0.2015 top1= 92.0312
[E47B30 |  39680/50000 ( 79%) ] Loss: 0.1914 top1= 92.4219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.8402 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.6713 top1= 40.0441


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8511 top1= 46.0337

Train epoch 48
[E48B0  |   1280/50000 (  3%) ] Loss: 0.2258 top1= 92.1094
[E48B10 |  14080/50000 ( 28%) ] Loss: 0.2233 top1= 92.6562
[E48B20 |  26880/50000 ( 54%) ] Loss: 0.2313 top1= 90.9375
[E48B30 |  39680/50000 ( 79%) ] Loss: 0.2361 top1= 91.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.8218 top1= 10.0260


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4812 top1= 40.5849


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7461 top1= 45.6030

Train epoch 49
[E49B0  |   1280/50000 (  3%) ] Loss: 0.2123 top1= 92.1094
[E49B10 |  14080/50000 ( 28%) ] Loss: 0.1947 top1= 93.0469
[E49B20 |  26880/50000 ( 54%) ] Loss: 0.2063 top1= 91.7188
[E49B30 |  39680/50000 ( 79%) ] Loss: 0.1983 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.8514 top1= 10.0260


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9908 top1= 40.2644


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1363 top1= 45.4026

Train epoch 50
[E50B0  |   1280/50000 (  3%) ] Loss: 0.1749 top1= 93.1250
[E50B10 |  14080/50000 ( 28%) ] Loss: 0.1975 top1= 91.7969
[E50B20 |  26880/50000 ( 54%) ] Loss: 0.1839 top1= 93.2812
[E50B30 |  39680/50000 ( 79%) ] Loss: 0.1822 top1= 92.5781

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.8822 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8674 top1= 40.3045


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9375 top1= 45.6931

Train epoch 51
[E51B0  |   1280/50000 (  3%) ] Loss: 0.1883 top1= 92.6562
[E51B10 |  14080/50000 ( 28%) ] Loss: 0.2004 top1= 92.1094
[E51B20 |  26880/50000 ( 54%) ] Loss: 0.1666 top1= 93.6719
[E51B30 |  39680/50000 ( 79%) ] Loss: 0.2050 top1= 91.9531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.8782 top1= 10.0561


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8447 top1= 40.2644


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4551 top1= 45.9535

Train epoch 52
[E52B0  |   1280/50000 (  3%) ] Loss: 0.1993 top1= 93.9844
[E52B10 |  14080/50000 ( 28%) ] Loss: 0.1915 top1= 93.2812
[E52B20 |  26880/50000 ( 54%) ] Loss: 0.1993 top1= 92.6562
[E52B30 |  39680/50000 ( 79%) ] Loss: 0.1646 top1= 94.1406

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.8773 top1= 10.0361


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1058 top1= 41.6266


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5538 top1= 45.4127

Train epoch 53
[E53B0  |   1280/50000 (  3%) ] Loss: 0.1413 top1= 94.5312
[E53B10 |  14080/50000 ( 28%) ] Loss: 0.1774 top1= 93.4375
[E53B20 |  26880/50000 ( 54%) ] Loss: 0.1821 top1= 94.0625
[E53B30 |  39680/50000 ( 79%) ] Loss: 0.1455 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.9198 top1= 10.0361


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7971 top1= 41.7468


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.7480 top1= 45.8233

Train epoch 54
[E54B0  |   1280/50000 (  3%) ] Loss: 0.1707 top1= 93.7500
[E54B10 |  14080/50000 ( 28%) ] Loss: 0.1788 top1= 93.8281
[E54B20 |  26880/50000 ( 54%) ] Loss: 0.1571 top1= 94.3750
[E54B30 |  39680/50000 ( 79%) ] Loss: 0.1364 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.9571 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4247 top1= 41.2660


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.8201 top1= 45.9936

Train epoch 55
[E55B0  |   1280/50000 (  3%) ] Loss: 0.1589 top1= 93.9062
[E55B10 |  14080/50000 ( 28%) ] Loss: 0.1422 top1= 94.2969
[E55B20 |  26880/50000 ( 54%) ] Loss: 0.1748 top1= 92.8906
[E55B30 |  39680/50000 ( 79%) ] Loss: 0.1541 top1= 93.9844

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.9583 top1= 10.0461


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2088 top1= 40.8454


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.4835 top1= 45.7332

Train epoch 56
[E56B0  |   1280/50000 (  3%) ] Loss: 0.1484 top1= 94.3750
[E56B10 |  14080/50000 ( 28%) ] Loss: 0.1722 top1= 93.8281
[E56B20 |  26880/50000 ( 54%) ] Loss: 0.1678 top1= 94.4531
[E56B30 |  39680/50000 ( 79%) ] Loss: 0.2080 top1= 91.7969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.9406 top1= 10.0260


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9937 top1= 41.0657


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1702 top1= 45.7933

Train epoch 57
[E57B0  |   1280/50000 (  3%) ] Loss: 0.1614 top1= 94.0625
[E57B10 |  14080/50000 ( 28%) ] Loss: 0.1761 top1= 93.6719
[E57B20 |  26880/50000 ( 54%) ] Loss: 0.1418 top1= 94.8438
[E57B30 |  39680/50000 ( 79%) ] Loss: 0.1993 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.9525 top1= 10.0260


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1474 top1= 41.1458


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2415 top1= 46.1639

Train epoch 58
[E58B0  |   1280/50000 (  3%) ] Loss: 0.1701 top1= 94.4531
[E58B10 |  14080/50000 ( 28%) ] Loss: 0.1543 top1= 93.9844
[E58B20 |  26880/50000 ( 54%) ] Loss: 0.1544 top1= 93.9844
[E58B30 |  39680/50000 ( 79%) ] Loss: 0.1861 top1= 93.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.9469 top1= 10.0461


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8565 top1= 40.8554


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.9135 top1= 45.8934

Train epoch 59
[E59B0  |   1280/50000 (  3%) ] Loss: 0.1894 top1= 92.7344
[E59B10 |  14080/50000 ( 28%) ] Loss: 0.1813 top1= 93.5938
[E59B20 |  26880/50000 ( 54%) ] Loss: 0.1542 top1= 93.8281
[E59B30 |  39680/50000 ( 79%) ] Loss: 0.1879 top1= 93.2031

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.0068 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4488 top1= 41.4864


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1779 top1= 46.3842

Train epoch 60
[E60B0  |   1280/50000 (  3%) ] Loss: 0.1538 top1= 93.9844
[E60B10 |  14080/50000 ( 28%) ] Loss: 0.1362 top1= 95.0000
[E60B20 |  26880/50000 ( 54%) ] Loss: 0.1491 top1= 94.1406
[E60B30 |  39680/50000 ( 79%) ] Loss: 0.2015 top1= 92.8906

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.9466 top1= 10.0561


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3687 top1= 41.0757


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.6365 top1= 45.8333

Train epoch 61
[E61B0  |   1280/50000 (  3%) ] Loss: 0.1574 top1= 93.5156
[E61B10 |  14080/50000 ( 28%) ] Loss: 0.1364 top1= 94.6875
[E61B20 |  26880/50000 ( 54%) ] Loss: 0.1454 top1= 95.2344
[E61B30 |  39680/50000 ( 79%) ] Loss: 0.1407 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.0039 top1= 10.0361


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3972 top1= 41.2560


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.1925 top1= 46.2340

Train epoch 62
[E62B0  |   1280/50000 (  3%) ] Loss: 0.1446 top1= 94.7656
[E62B10 |  14080/50000 ( 28%) ] Loss: 0.1439 top1= 94.7656
[E62B20 |  26880/50000 ( 54%) ] Loss: 0.1229 top1= 95.3906
[E62B30 |  39680/50000 ( 79%) ] Loss: 0.1633 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.9967 top1= 10.0260


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3069 top1= 41.9371


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.4630 top1= 46.2340

Train epoch 63
[E63B0  |   1280/50000 (  3%) ] Loss: 0.1299 top1= 95.3125
[E63B10 |  14080/50000 ( 28%) ] Loss: 0.1201 top1= 95.7031
[E63B20 |  26880/50000 ( 54%) ] Loss: 0.1360 top1= 94.8438
[E63B30 |  39680/50000 ( 79%) ] Loss: 0.1250 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.0028 top1= 10.0962


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9316 top1= 41.4764


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.8480 top1= 46.1639

Train epoch 64
[E64B0  |   1280/50000 (  3%) ] Loss: 0.1447 top1= 94.3750
[E64B10 |  14080/50000 ( 28%) ] Loss: 0.1439 top1= 95.3125
[E64B20 |  26880/50000 ( 54%) ] Loss: 0.1491 top1= 94.4531
[E64B30 |  39680/50000 ( 79%) ] Loss: 0.1627 top1= 94.2969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.9979 top1= 10.0561


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0737 top1= 41.0056


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.9408 top1= 46.3041

Train epoch 65
[E65B0  |   1280/50000 (  3%) ] Loss: 0.1161 top1= 95.3125
[E65B10 |  14080/50000 ( 28%) ] Loss: 0.1398 top1= 94.6875
[E65B20 |  26880/50000 ( 54%) ] Loss: 0.1708 top1= 93.5156
[E65B30 |  39680/50000 ( 79%) ] Loss: 0.1780 top1= 93.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.9656 top1= 10.1262


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3391 top1= 41.2660


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.4054 top1= 46.1038

Train epoch 66
[E66B0  |   1280/50000 (  3%) ] Loss: 0.1225 top1= 95.5469
[E66B10 |  14080/50000 ( 28%) ] Loss: 0.1383 top1= 94.6094
[E66B20 |  26880/50000 ( 54%) ] Loss: 0.1546 top1= 94.1406
[E66B30 |  39680/50000 ( 79%) ] Loss: 0.1268 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.9920 top1= 10.0561


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3611 top1= 41.4864


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.4239 top1= 45.5629

Train epoch 67
[E67B0  |   1280/50000 (  3%) ] Loss: 0.1559 top1= 94.9219
[E67B10 |  14080/50000 ( 28%) ] Loss: 0.1154 top1= 95.8594
[E67B20 |  26880/50000 ( 54%) ] Loss: 0.1247 top1= 96.0156
[E67B30 |  39680/50000 ( 79%) ] Loss: 0.1301 top1= 95.0781

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.0138 top1= 10.1162


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4251 top1= 41.5365


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.7618 top1= 45.6530

Train epoch 68
[E68B0  |   1280/50000 (  3%) ] Loss: 0.0901 top1= 96.9531
[E68B10 |  14080/50000 ( 28%) ] Loss: 0.1065 top1= 96.0938
[E68B20 |  26880/50000 ( 54%) ] Loss: 0.0944 top1= 96.7969
[E68B30 |  39680/50000 ( 79%) ] Loss: 0.1072 top1= 96.7969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.0500 top1= 10.0461


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5569 top1= 41.6366


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.4217 top1= 45.2424

Train epoch 69
[E69B0  |   1280/50000 (  3%) ] Loss: 0.1182 top1= 95.9375
[E69B10 |  14080/50000 ( 28%) ] Loss: 0.1119 top1= 95.8594
[E69B20 |  26880/50000 ( 54%) ] Loss: 0.0964 top1= 96.2500
[E69B30 |  39680/50000 ( 79%) ] Loss: 0.0950 top1= 96.4844

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.0323 top1= 10.0861


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5906 top1= 41.8570


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.6157 top1= 45.5529

Train epoch 70
[E70B0  |   1280/50000 (  3%) ] Loss: 0.1369 top1= 95.3906
[E70B10 |  14080/50000 ( 28%) ] Loss: 0.1077 top1= 95.7031
[E70B20 |  26880/50000 ( 54%) ] Loss: 0.1059 top1= 96.2500
[E70B30 |  39680/50000 ( 79%) ] Loss: 0.1153 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.0428 top1= 10.0761


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8254 top1= 41.5565


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3828 top1= 45.9936

Train epoch 71
[E71B0  |   1280/50000 (  3%) ] Loss: 0.1179 top1= 95.5469
[E71B10 |  14080/50000 ( 28%) ] Loss: 0.1048 top1= 95.8594
[E71B20 |  26880/50000 ( 54%) ] Loss: 0.1072 top1= 96.1719
[E71B30 |  39680/50000 ( 79%) ] Loss: 0.1018 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.0285 top1= 10.0361


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3071 top1= 41.8870


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.4254 top1= 45.7933

Train epoch 72
[E72B0  |   1280/50000 (  3%) ] Loss: 0.1113 top1= 96.5625
[E72B10 |  14080/50000 ( 28%) ] Loss: 0.0930 top1= 96.6406
[E72B20 |  26880/50000 ( 54%) ] Loss: 0.0995 top1= 97.1094
[E72B30 |  39680/50000 ( 79%) ] Loss: 0.1444 top1= 94.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.0170 top1= 10.1663


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8786 top1= 41.7167


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0612 top1= 46.1438

Train epoch 73
[E73B0  |   1280/50000 (  3%) ] Loss: 0.0884 top1= 96.7969
[E73B10 |  14080/50000 ( 28%) ] Loss: 0.1375 top1= 95.1562
[E73B20 |  26880/50000 ( 54%) ] Loss: 0.1254 top1= 95.7031
[E73B30 |  39680/50000 ( 79%) ] Loss: 0.0884 top1= 96.6406

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.0796 top1= 10.0361


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9846 top1= 41.5365


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.9184 top1= 46.5244

Train epoch 74
[E74B0  |   1280/50000 (  3%) ] Loss: 0.1089 top1= 96.0938
[E74B10 |  14080/50000 ( 28%) ] Loss: 0.1165 top1= 96.0156
[E74B20 |  26880/50000 ( 54%) ] Loss: 0.1138 top1= 95.9375
[E74B30 |  39680/50000 ( 79%) ] Loss: 0.1303 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.0664 top1= 10.0561


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8851 top1= 41.5064


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.8029 top1= 46.1138

Train epoch 75
[E75B0  |   1280/50000 (  3%) ] Loss: 0.1070 top1= 96.2500
[E75B10 |  14080/50000 ( 28%) ] Loss: 0.1245 top1= 95.6250
[E75B20 |  26880/50000 ( 54%) ] Loss: 0.1133 top1= 95.7812
[E75B30 |  39680/50000 ( 79%) ] Loss: 0.1002 top1= 96.3281

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.0454 top1= 10.0361


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.7266 top1= 41.1458


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.8676 top1= 46.2240

Train epoch 76
[E76B0  |   1280/50000 (  3%) ] Loss: 0.1030 top1= 96.1719
[E76B10 |  14080/50000 ( 28%) ] Loss: 0.1301 top1= 95.0781
[E76B20 |  26880/50000 ( 54%) ] Loss: 0.1003 top1= 96.4062
[E76B30 |  39680/50000 ( 79%) ] Loss: 0.1093 top1= 96.3281

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.0446 top1= 10.0861


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5326 top1= 41.6366


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0269 top1= 45.7933

Train epoch 77
[E77B0  |   1280/50000 (  3%) ] Loss: 0.1135 top1= 96.0156
[E77B10 |  14080/50000 ( 28%) ] Loss: 0.1175 top1= 96.0938
[E77B20 |  26880/50000 ( 54%) ] Loss: 0.1148 top1= 96.0156
[E77B30 |  39680/50000 ( 79%) ] Loss: 0.0824 top1= 96.7969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.0641 top1= 10.1062


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4683 top1= 41.7869


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.6583 top1= 46.2240

Train epoch 78
[E78B0  |   1280/50000 (  3%) ] Loss: 0.0926 top1= 97.5000
[E78B10 |  14080/50000 ( 28%) ] Loss: 0.1066 top1= 97.1094
[E78B20 |  26880/50000 ( 54%) ] Loss: 0.0897 top1= 97.2656
[E78B30 |  39680/50000 ( 79%) ] Loss: 0.0858 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.0917 top1= 10.1663


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6953 top1= 42.5080


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.1961 top1= 46.3341

Train epoch 79
[E79B0  |   1280/50000 (  3%) ] Loss: 0.0835 top1= 97.1094
[E79B10 |  14080/50000 ( 28%) ] Loss: 0.0810 top1= 97.5000
[E79B20 |  26880/50000 ( 54%) ] Loss: 0.0763 top1= 97.0312
[E79B30 |  39680/50000 ( 79%) ] Loss: 0.0933 top1= 96.6406

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.1321 top1= 10.0761


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8926 top1= 42.4279


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.2665 top1= 46.1739

Train epoch 80
[E80B0  |   1280/50000 (  3%) ] Loss: 0.0784 top1= 97.1875
[E80B10 |  14080/50000 ( 28%) ] Loss: 0.0919 top1= 97.0312
[E80B20 |  26880/50000 ( 54%) ] Loss: 0.0850 top1= 96.8750
[E80B30 |  39680/50000 ( 79%) ] Loss: 0.0780 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.1387 top1= 10.1362


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8292 top1= 41.4062


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.0646 top1= 46.2039

Train epoch 81
[E81B0  |   1280/50000 (  3%) ] Loss: 0.0836 top1= 96.7969
[E81B10 |  14080/50000 ( 28%) ] Loss: 0.0768 top1= 97.1094
[E81B20 |  26880/50000 ( 54%) ] Loss: 0.0570 top1= 97.8906
[E81B30 |  39680/50000 ( 79%) ] Loss: 0.0408 top1= 98.3594

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.1374 top1= 10.1663


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9130 top1= 42.8085


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.2848 top1= 46.6647

Train epoch 82
[E82B0  |   1280/50000 (  3%) ] Loss: 0.0351 top1= 98.8281
[E82B10 |  14080/50000 ( 28%) ] Loss: 0.0483 top1= 98.5938
[E82B20 |  26880/50000 ( 54%) ] Loss: 0.0348 top1= 98.7500
[E82B30 |  39680/50000 ( 79%) ] Loss: 0.0204 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.1423 top1= 10.1863


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.4854 top1= 42.9788


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.5887 top1= 46.6747

Train epoch 83
[E83B0  |   1280/50000 (  3%) ] Loss: 0.0345 top1= 99.1406
[E83B10 |  14080/50000 ( 28%) ] Loss: 0.0372 top1= 98.8281
[E83B20 |  26880/50000 ( 54%) ] Loss: 0.0256 top1= 99.0625
[E83B30 |  39680/50000 ( 79%) ] Loss: 0.0211 top1= 99.2969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.1508 top1= 10.1963


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9050 top1= 43.1591


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.9296 top1= 46.7047

Train epoch 84
[E84B0  |   1280/50000 (  3%) ] Loss: 0.0242 top1= 99.1406
[E84B10 |  14080/50000 ( 28%) ] Loss: 0.0383 top1= 98.5156
[E84B20 |  26880/50000 ( 54%) ] Loss: 0.0338 top1= 98.9844
[E84B30 |  39680/50000 ( 79%) ] Loss: 0.0191 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.1606 top1= 10.1562


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.2360 top1= 43.1490


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.1572 top1= 46.7348

Train epoch 85
[E85B0  |   1280/50000 (  3%) ] Loss: 0.0156 top1= 99.4531
[E85B10 |  14080/50000 ( 28%) ] Loss: 0.0307 top1= 98.9844
[E85B20 |  26880/50000 ( 54%) ] Loss: 0.0212 top1= 99.3750
[E85B30 |  39680/50000 ( 79%) ] Loss: 0.0224 top1= 99.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.1673 top1= 10.1763


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.4928 top1= 43.0389


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.1688 top1= 46.7548

Train epoch 86
[E86B0  |   1280/50000 (  3%) ] Loss: 0.0230 top1= 99.4531
[E86B10 |  14080/50000 ( 28%) ] Loss: 0.0277 top1= 98.9062
[E86B20 |  26880/50000 ( 54%) ] Loss: 0.0191 top1= 99.2969
[E86B30 |  39680/50000 ( 79%) ] Loss: 0.0139 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.1691 top1= 10.1863


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.7286 top1= 43.2292


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.3986 top1= 46.6847

Train epoch 87
[E87B0  |   1280/50000 (  3%) ] Loss: 0.0235 top1= 99.4531
[E87B10 |  14080/50000 ( 28%) ] Loss: 0.0194 top1= 99.4531
[E87B20 |  26880/50000 ( 54%) ] Loss: 0.0141 top1= 99.7656
[E87B30 |  39680/50000 ( 79%) ] Loss: 0.0143 top1= 99.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.1741 top1= 10.1863


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.9258 top1= 43.2392


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.5565 top1= 46.7047

Train epoch 88
[E88B0  |   1280/50000 (  3%) ] Loss: 0.0215 top1= 99.4531
[E88B10 |  14080/50000 ( 28%) ] Loss: 0.0179 top1= 99.1406
[E88B20 |  26880/50000 ( 54%) ] Loss: 0.0175 top1= 99.3750
[E88B30 |  39680/50000 ( 79%) ] Loss: 0.0124 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.1799 top1= 10.2063


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.1604 top1= 43.2192


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.5222 top1= 46.7147

Train epoch 89
[E89B0  |   1280/50000 (  3%) ] Loss: 0.0119 top1= 99.8438
[E89B10 |  14080/50000 ( 28%) ] Loss: 0.0241 top1= 99.2188
[E89B20 |  26880/50000 ( 54%) ] Loss: 0.0130 top1= 99.3750
[E89B30 |  39680/50000 ( 79%) ] Loss: 0.0103 top1= 99.6094

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.1828 top1= 10.2264


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.5310 top1= 43.3293


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.7580 top1= 46.8049

Train epoch 90
[E90B0  |   1280/50000 (  3%) ] Loss: 0.0154 top1= 99.3750
[E90B10 |  14080/50000 ( 28%) ] Loss: 0.0147 top1= 99.3750
[E90B20 |  26880/50000 ( 54%) ] Loss: 0.0197 top1= 99.6094
[E90B30 |  39680/50000 ( 79%) ] Loss: 0.0112 top1= 99.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.1880 top1= 10.2364


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.6349 top1= 43.1591


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.7936 top1= 46.7648

Train epoch 91
[E91B0  |   1280/50000 (  3%) ] Loss: 0.0115 top1= 99.6094
[E91B10 |  14080/50000 ( 28%) ] Loss: 0.0110 top1= 99.8438
[E91B20 |  26880/50000 ( 54%) ] Loss: 0.0077 top1= 99.8438
[E91B30 |  39680/50000 ( 79%) ] Loss: 0.0068 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.1948 top1= 10.2264


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.9673 top1= 43.2192


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.9003 top1= 46.7047

Train epoch 92
[E92B0  |   1280/50000 (  3%) ] Loss: 0.0112 top1= 99.6875
[E92B10 |  14080/50000 ( 28%) ] Loss: 0.0243 top1= 99.0625
[E92B20 |  26880/50000 ( 54%) ] Loss: 0.0083 top1= 99.7656
[E92B30 |  39680/50000 ( 79%) ] Loss: 0.0058 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.1909 top1= 10.2764


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.0325 top1= 43.1490


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.8660 top1= 46.6747

Train epoch 93
[E93B0  |   1280/50000 (  3%) ] Loss: 0.0149 top1= 99.3750
[E93B10 |  14080/50000 ( 28%) ] Loss: 0.0140 top1= 99.5312
[E93B20 |  26880/50000 ( 54%) ] Loss: 0.0087 top1= 99.6875
[E93B30 |  39680/50000 ( 79%) ] Loss: 0.0080 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.1997 top1= 10.2163


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.1763 top1= 43.1891


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.9624 top1= 46.7348

Train epoch 94
[E94B0  |   1280/50000 (  3%) ] Loss: 0.0088 top1= 99.8438
[E94B10 |  14080/50000 ( 28%) ] Loss: 0.0163 top1= 99.6094
[E94B20 |  26880/50000 ( 54%) ] Loss: 0.0064 top1= 99.9219
[E94B30 |  39680/50000 ( 79%) ] Loss: 0.0167 top1= 99.6094

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.1981 top1= 10.2664


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.1282 top1= 43.1891


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.0800 top1= 46.6546

Train epoch 95
[E95B0  |   1280/50000 (  3%) ] Loss: 0.0104 top1= 99.7656
[E95B10 |  14080/50000 ( 28%) ] Loss: 0.0101 top1= 99.6875
[E95B20 |  26880/50000 ( 54%) ] Loss: 0.0147 top1= 99.4531
[E95B30 |  39680/50000 ( 79%) ] Loss: 0.0080 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2020 top1= 10.3265


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.3833 top1= 43.3494


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.2737 top1= 46.6747

Train epoch 96
[E96B0  |   1280/50000 (  3%) ] Loss: 0.0074 top1= 99.7656
[E96B10 |  14080/50000 ( 28%) ] Loss: 0.0154 top1= 99.6094
[E96B20 |  26880/50000 ( 54%) ] Loss: 0.0115 top1= 99.6875
[E96B30 |  39680/50000 ( 79%) ] Loss: 0.0103 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2043 top1= 10.2965


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.4756 top1= 43.2993


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.4961 top1= 46.6346

Train epoch 97
[E97B0  |   1280/50000 (  3%) ] Loss: 0.0185 top1= 99.5312
[E97B10 |  14080/50000 ( 28%) ] Loss: 0.0138 top1= 99.4531
[E97B20 |  26880/50000 ( 54%) ] Loss: 0.0081 top1= 99.7656
[E97B30 |  39680/50000 ( 79%) ] Loss: 0.0170 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2097 top1= 10.3466


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.5667 top1= 43.3193


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.4054 top1= 46.6947

Train epoch 98
[E98B0  |   1280/50000 (  3%) ] Loss: 0.0122 top1= 99.4531
[E98B10 |  14080/50000 ( 28%) ] Loss: 0.0105 top1= 99.7656
[E98B20 |  26880/50000 ( 54%) ] Loss: 0.0102 top1= 99.6094
[E98B30 |  39680/50000 ( 79%) ] Loss: 0.0048 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2112 top1= 10.2764


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.9027 top1= 43.2993


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.4097 top1= 46.7047

Train epoch 99
[E99B0  |   1280/50000 (  3%) ] Loss: 0.0104 top1= 99.6094
[E99B10 |  14080/50000 ( 28%) ] Loss: 0.0050 top1= 99.9219
[E99B20 |  26880/50000 ( 54%) ] Loss: 0.0079 top1= 99.6875
[E99B30 |  39680/50000 ( 79%) ] Loss: 0.0077 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2132 top1= 10.2965


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.6811 top1= 43.1791


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.4287 top1= 46.7248

Train epoch 100
[E100B0  |   1280/50000 (  3%) ] Loss: 0.0062 top1= 99.8438
[E100B10 |  14080/50000 ( 28%) ] Loss: 0.0146 top1= 99.6094
[E100B20 |  26880/50000 ( 54%) ] Loss: 0.0139 top1= 99.6875
[E100B30 |  39680/50000 ( 79%) ] Loss: 0.0153 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2166 top1= 10.3065


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.8469 top1= 43.1691


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.4112 top1= 46.7147

Train epoch 101
[E101B0  |   1280/50000 (  3%) ] Loss: 0.0096 top1= 99.5312
[E101B10 |  14080/50000 ( 28%) ] Loss: 0.0119 top1= 99.7656
[E101B20 |  26880/50000 ( 54%) ] Loss: 0.0069 top1= 99.6094
[E101B30 |  39680/50000 ( 79%) ] Loss: 0.0077 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2173 top1= 10.3466


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.1827 top1= 43.2692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.4500 top1= 46.7248

Train epoch 102
[E102B0  |   1280/50000 (  3%) ] Loss: 0.0042 top1= 99.9219
[E102B10 |  14080/50000 ( 28%) ] Loss: 0.0054 top1= 99.8438
[E102B20 |  26880/50000 ( 54%) ] Loss: 0.0079 top1= 99.6875
[E102B30 |  39680/50000 ( 79%) ] Loss: 0.0062 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2205 top1= 10.3666


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.1526 top1= 43.2993


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.4909 top1= 46.7448

Train epoch 103
[E103B0  |   1280/50000 (  3%) ] Loss: 0.0052 top1= 99.8438
[E103B10 |  14080/50000 ( 28%) ] Loss: 0.0060 top1= 99.8438
[E103B20 |  26880/50000 ( 54%) ] Loss: 0.0059 top1= 99.7656
[E103B30 |  39680/50000 ( 79%) ] Loss: 0.0047 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2220 top1= 10.3466


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.2984 top1= 43.3293


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.4868 top1= 46.7047

Train epoch 104
[E104B0  |   1280/50000 (  3%) ] Loss: 0.0067 top1= 99.9219
[E104B10 |  14080/50000 ( 28%) ] Loss: 0.0055 top1= 99.8438
[E104B20 |  26880/50000 ( 54%) ] Loss: 0.0055 top1= 99.8438
[E104B30 |  39680/50000 ( 79%) ] Loss: 0.0069 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2240 top1= 10.4267


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.5138 top1= 43.2592


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.5231 top1= 46.7548

Train epoch 105
[E105B0  |   1280/50000 (  3%) ] Loss: 0.0056 top1= 99.9219
[E105B10 |  14080/50000 ( 28%) ] Loss: 0.0135 top1= 99.3750
[E105B20 |  26880/50000 ( 54%) ] Loss: 0.0085 top1= 99.5312
[E105B30 |  39680/50000 ( 79%) ] Loss: 0.0047 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2261 top1= 10.4167


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.6539 top1= 43.3293


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.5653 top1= 46.6847

Train epoch 106
[E106B0  |   1280/50000 (  3%) ] Loss: 0.0049 top1= 99.8438
[E106B10 |  14080/50000 ( 28%) ] Loss: 0.0044 top1= 99.9219
[E106B20 |  26880/50000 ( 54%) ] Loss: 0.0050 top1= 99.9219
[E106B30 |  39680/50000 ( 79%) ] Loss: 0.0203 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2275 top1= 10.4367


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.6519 top1= 43.2893


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7172 top1= 46.7147

Train epoch 107
[E107B0  |   1280/50000 (  3%) ] Loss: 0.0054 top1= 99.8438
[E107B10 |  14080/50000 ( 28%) ] Loss: 0.0092 top1= 99.6875
[E107B20 |  26880/50000 ( 54%) ] Loss: 0.0065 top1= 99.6875
[E107B30 |  39680/50000 ( 79%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2315 top1= 10.4367


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.7269 top1= 43.3794


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.6504 top1= 46.7648

Train epoch 108
[E108B0  |   1280/50000 (  3%) ] Loss: 0.0134 top1= 99.6094
[E108B10 |  14080/50000 ( 28%) ] Loss: 0.0097 top1= 99.5312
[E108B20 |  26880/50000 ( 54%) ] Loss: 0.0114 top1= 99.3750
[E108B30 |  39680/50000 ( 79%) ] Loss: 0.0050 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2341 top1= 10.4467


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.8261 top1= 43.2592


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7283 top1= 46.7248

Train epoch 109
[E109B0  |   1280/50000 (  3%) ] Loss: 0.0047 top1= 99.8438
[E109B10 |  14080/50000 ( 28%) ] Loss: 0.0092 top1= 99.5312
[E109B20 |  26880/50000 ( 54%) ] Loss: 0.0051 top1= 99.8438
[E109B30 |  39680/50000 ( 79%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2350 top1= 10.3966


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.8054 top1= 43.1591


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8079 top1= 46.7448

Train epoch 110
[E110B0  |   1280/50000 (  3%) ] Loss: 0.0061 top1= 99.7656
[E110B10 |  14080/50000 ( 28%) ] Loss: 0.0064 top1= 99.7656
[E110B20 |  26880/50000 ( 54%) ] Loss: 0.0070 top1= 99.9219
[E110B30 |  39680/50000 ( 79%) ] Loss: 0.0097 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2429 top1= 10.3966


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.0099 top1= 43.2993


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8004 top1= 46.6747

Train epoch 111
[E111B0  |   1280/50000 (  3%) ] Loss: 0.0102 top1= 99.7656
[E111B10 |  14080/50000 ( 28%) ] Loss: 0.0046 top1= 99.9219
[E111B20 |  26880/50000 ( 54%) ] Loss: 0.0041 top1= 99.9219
[E111B30 |  39680/50000 ( 79%) ] Loss: 0.0086 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2373 top1= 10.4267


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.8567 top1= 43.2893


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.9346 top1= 46.6947

Train epoch 112
[E112B0  |   1280/50000 (  3%) ] Loss: 0.0050 top1= 99.9219
[E112B10 |  14080/50000 ( 28%) ] Loss: 0.0080 top1= 99.6875
[E112B20 |  26880/50000 ( 54%) ] Loss: 0.0063 top1= 99.8438
[E112B30 |  39680/50000 ( 79%) ] Loss: 0.0083 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2471 top1= 10.4167


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.8976 top1= 43.2592


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.0013 top1= 46.7748

Train epoch 113
[E113B0  |   1280/50000 (  3%) ] Loss: 0.0045 top1= 99.8438
[E113B10 |  14080/50000 ( 28%) ] Loss: 0.0118 top1= 99.7656
[E113B20 |  26880/50000 ( 54%) ] Loss: 0.0050 top1= 99.8438
[E113B30 |  39680/50000 ( 79%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2479 top1= 10.4067


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.7223 top1= 43.4395


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.1229 top1= 46.6947

Train epoch 114
[E114B0  |   1280/50000 (  3%) ] Loss: 0.0057 top1= 99.8438
[E114B10 |  14080/50000 ( 28%) ] Loss: 0.0069 top1= 99.7656
[E114B20 |  26880/50000 ( 54%) ] Loss: 0.0054 top1= 99.7656
[E114B30 |  39680/50000 ( 79%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2425 top1= 10.3966


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.9052 top1= 43.4395


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.3129 top1= 46.7047

Train epoch 115
[E115B0  |   1280/50000 (  3%) ] Loss: 0.0075 top1= 99.8438
[E115B10 |  14080/50000 ( 28%) ] Loss: 0.0066 top1= 99.8438
[E115B20 |  26880/50000 ( 54%) ] Loss: 0.0035 top1= 99.9219
[E115B30 |  39680/50000 ( 79%) ] Loss: 0.0048 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2495 top1= 10.4667


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.7559 top1= 43.3694


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.9928 top1= 46.6847

Train epoch 116
[E116B0  |   1280/50000 (  3%) ] Loss: 0.0024 top1=100.0000
[E116B10 |  14080/50000 ( 28%) ] Loss: 0.0038 top1= 99.8438
[E116B20 |  26880/50000 ( 54%) ] Loss: 0.0127 top1= 99.8438
[E116B30 |  39680/50000 ( 79%) ] Loss: 0.0019 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2505 top1= 10.4267


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.2161 top1= 43.2492


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8964 top1= 46.6847

Train epoch 117
[E117B0  |   1280/50000 (  3%) ] Loss: 0.0019 top1=100.0000
[E117B10 |  14080/50000 ( 28%) ] Loss: 0.0051 top1= 99.7656
[E117B20 |  26880/50000 ( 54%) ] Loss: 0.0028 top1= 99.9219
[E117B30 |  39680/50000 ( 79%) ] Loss: 0.0035 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2474 top1= 10.4467


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.1520 top1= 43.3293


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.1965 top1= 46.6947

Train epoch 118
[E118B0  |   1280/50000 (  3%) ] Loss: 0.0032 top1=100.0000
[E118B10 |  14080/50000 ( 28%) ] Loss: 0.0025 top1=100.0000
[E118B20 |  26880/50000 ( 54%) ] Loss: 0.0037 top1= 99.9219
[E118B30 |  39680/50000 ( 79%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2464 top1= 10.4768


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.3187 top1= 43.3794


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.1332 top1= 46.6546

Train epoch 119
[E119B0  |   1280/50000 (  3%) ] Loss: 0.0021 top1=100.0000
[E119B10 |  14080/50000 ( 28%) ] Loss: 0.0106 top1= 99.6875
[E119B20 |  26880/50000 ( 54%) ] Loss: 0.0047 top1= 99.9219
[E119B30 |  39680/50000 ( 79%) ] Loss: 0.0111 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2432 top1= 10.5168


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.2666 top1= 43.3694


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.2004 top1= 46.7748

Train epoch 120
[E120B0  |   1280/50000 (  3%) ] Loss: 0.0049 top1= 99.7656
[E120B10 |  14080/50000 ( 28%) ] Loss: 0.0049 top1= 99.8438
[E120B20 |  26880/50000 ( 54%) ] Loss: 0.0052 top1= 99.8438
[E120B30 |  39680/50000 ( 79%) ] Loss: 0.0056 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2488 top1= 10.4567


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.2953 top1= 43.2692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.2271 top1= 46.7548

Train epoch 121
[E121B0  |   1280/50000 (  3%) ] Loss: 0.0054 top1= 99.7656
[E121B10 |  14080/50000 ( 28%) ] Loss: 0.0038 top1= 99.9219
[E121B20 |  26880/50000 ( 54%) ] Loss: 0.0023 top1= 99.9219
[E121B30 |  39680/50000 ( 79%) ] Loss: 0.0081 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2493 top1= 10.4567


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.2522 top1= 43.2993


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.1575 top1= 46.7548

Train epoch 122
[E122B0  |   1280/50000 (  3%) ] Loss: 0.0073 top1= 99.7656
[E122B10 |  14080/50000 ( 28%) ] Loss: 0.0032 top1= 99.9219
[E122B20 |  26880/50000 ( 54%) ] Loss: 0.0044 top1= 99.8438
[E122B30 |  39680/50000 ( 79%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2496 top1= 10.4567


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.1986 top1= 43.2592


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.0754 top1= 46.7248

Train epoch 123
[E123B0  |   1280/50000 (  3%) ] Loss: 0.0035 top1= 99.9219
[E123B10 |  14080/50000 ( 28%) ] Loss: 0.0117 top1= 99.7656
[E123B20 |  26880/50000 ( 54%) ] Loss: 0.0015 top1=100.0000
[E123B30 |  39680/50000 ( 79%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2497 top1= 10.4567


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.1464 top1= 43.2392


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.9936 top1= 46.7147

Train epoch 124
[E124B0  |   1280/50000 (  3%) ] Loss: 0.0060 top1= 99.9219
[E124B10 |  14080/50000 ( 28%) ] Loss: 0.0062 top1= 99.7656
[E124B20 |  26880/50000 ( 54%) ] Loss: 0.0028 top1=100.0000
[E124B30 |  39680/50000 ( 79%) ] Loss: 0.0041 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2498 top1= 10.4667


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.0736 top1= 43.2893


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.9288 top1= 46.7348

Train epoch 125
[E125B0  |   1280/50000 (  3%) ] Loss: 0.0032 top1=100.0000
[E125B10 |  14080/50000 ( 28%) ] Loss: 0.0102 top1= 99.6875
[E125B20 |  26880/50000 ( 54%) ] Loss: 0.0029 top1= 99.9219
[E125B30 |  39680/50000 ( 79%) ] Loss: 0.0023 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2495 top1= 10.4667


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=13.0548 top1= 43.2492


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8780 top1= 46.7348

Train epoch 126
[E126B0  |   1280/50000 (  3%) ] Loss: 0.0028 top1=100.0000
[E126B10 |  14080/50000 ( 28%) ] Loss: 0.0049 top1= 99.8438
[E126B20 |  26880/50000 ( 54%) ] Loss: 0.0032 top1= 99.9219
[E126B30 |  39680/50000 ( 79%) ] Loss: 0.0030 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2502 top1= 10.4667


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.9839 top1= 43.2792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8037 top1= 46.7348

Train epoch 127
[E127B0  |   1280/50000 (  3%) ] Loss: 0.0033 top1= 99.9219
[E127B10 |  14080/50000 ( 28%) ] Loss: 0.0020 top1=100.0000
[E127B20 |  26880/50000 ( 54%) ] Loss: 0.0036 top1= 99.9219
[E127B30 |  39680/50000 ( 79%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2508 top1= 10.4567


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.9187 top1= 43.2592


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7524 top1= 46.7348

Train epoch 128
[E128B0  |   1280/50000 (  3%) ] Loss: 0.0072 top1= 99.9219
[E128B10 |  14080/50000 ( 28%) ] Loss: 0.0036 top1= 99.9219
[E128B20 |  26880/50000 ( 54%) ] Loss: 0.0036 top1= 99.9219
[E128B30 |  39680/50000 ( 79%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2508 top1= 10.4567


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.8633 top1= 43.2692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7066 top1= 46.7248

Train epoch 129
[E129B0  |   1280/50000 (  3%) ] Loss: 0.0018 top1=100.0000
[E129B10 |  14080/50000 ( 28%) ] Loss: 0.0026 top1= 99.9219
[E129B20 |  26880/50000 ( 54%) ] Loss: 0.0012 top1=100.0000
[E129B30 |  39680/50000 ( 79%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2510 top1= 10.4567


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.8311 top1= 43.2592


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.6366 top1= 46.7448

Train epoch 130
[E130B0  |   1280/50000 (  3%) ] Loss: 0.0063 top1= 99.8438
[E130B10 |  14080/50000 ( 28%) ] Loss: 0.0044 top1= 99.9219
[E130B20 |  26880/50000 ( 54%) ] Loss: 0.0030 top1= 99.9219
[E130B30 |  39680/50000 ( 79%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2506 top1= 10.4667


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.7896 top1= 43.2893


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.5780 top1= 46.7147

Train epoch 131
[E131B0  |   1280/50000 (  3%) ] Loss: 0.0033 top1= 99.9219
[E131B10 |  14080/50000 ( 28%) ] Loss: 0.0059 top1= 99.6875
[E131B20 |  26880/50000 ( 54%) ] Loss: 0.0009 top1=100.0000
[E131B30 |  39680/50000 ( 79%) ] Loss: 0.0062 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2510 top1= 10.4667


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.7534 top1= 43.3093


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.5001 top1= 46.7147

Train epoch 132
[E132B0  |   1280/50000 (  3%) ] Loss: 0.0070 top1= 99.7656
[E132B10 |  14080/50000 ( 28%) ] Loss: 0.0036 top1= 99.8438
[E132B20 |  26880/50000 ( 54%) ] Loss: 0.0020 top1=100.0000
[E132B30 |  39680/50000 ( 79%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2512 top1= 10.4667


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.6928 top1= 43.3093


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.4548 top1= 46.7147

Train epoch 133
[E133B0  |   1280/50000 (  3%) ] Loss: 0.0026 top1=100.0000
[E133B10 |  14080/50000 ( 28%) ] Loss: 0.0045 top1= 99.8438
[E133B20 |  26880/50000 ( 54%) ] Loss: 0.0019 top1=100.0000
[E133B30 |  39680/50000 ( 79%) ] Loss: 0.0040 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2513 top1= 10.4768


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.6444 top1= 43.3193


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.4164 top1= 46.6847

Train epoch 134
[E134B0  |   1280/50000 (  3%) ] Loss: 0.0056 top1= 99.6875
[E134B10 |  14080/50000 ( 28%) ] Loss: 0.0039 top1= 99.8438
[E134B20 |  26880/50000 ( 54%) ] Loss: 0.0012 top1=100.0000
[E134B30 |  39680/50000 ( 79%) ] Loss: 0.0034 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2504 top1= 10.4768


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.6473 top1= 43.3494


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.3767 top1= 46.6947

Train epoch 135
[E135B0  |   1280/50000 (  3%) ] Loss: 0.0039 top1= 99.9219
[E135B10 |  14080/50000 ( 28%) ] Loss: 0.0044 top1= 99.9219
[E135B20 |  26880/50000 ( 54%) ] Loss: 0.0032 top1= 99.9219
[E135B30 |  39680/50000 ( 79%) ] Loss: 0.0054 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2498 top1= 10.4868


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.6327 top1= 43.2893


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.3391 top1= 46.6747

Train epoch 136
[E136B0  |   1280/50000 (  3%) ] Loss: 0.0095 top1= 99.7656
[E136B10 |  14080/50000 ( 28%) ] Loss: 0.0018 top1=100.0000
[E136B20 |  26880/50000 ( 54%) ] Loss: 0.0035 top1= 99.9219
[E136B30 |  39680/50000 ( 79%) ] Loss: 0.0048 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2491 top1= 10.4868


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.6223 top1= 43.2893


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.2805 top1= 46.6947

Train epoch 137
[E137B0  |   1280/50000 (  3%) ] Loss: 0.0036 top1= 99.8438
[E137B10 |  14080/50000 ( 28%) ] Loss: 0.0041 top1= 99.8438
[E137B20 |  26880/50000 ( 54%) ] Loss: 0.0018 top1=100.0000
[E137B30 |  39680/50000 ( 79%) ] Loss: 0.0040 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2493 top1= 10.4868


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.5655 top1= 43.3093


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.2004 top1= 46.6947

Train epoch 138
[E138B0  |   1280/50000 (  3%) ] Loss: 0.0080 top1= 99.7656
[E138B10 |  14080/50000 ( 28%) ] Loss: 0.0025 top1= 99.9219
[E138B20 |  26880/50000 ( 54%) ] Loss: 0.0017 top1=100.0000
[E138B30 |  39680/50000 ( 79%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2499 top1= 10.4768


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.5039 top1= 43.2993


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.1410 top1= 46.7047

Train epoch 139
[E139B0  |   1280/50000 (  3%) ] Loss: 0.0025 top1= 99.9219
[E139B10 |  14080/50000 ( 28%) ] Loss: 0.0014 top1=100.0000
[E139B20 |  26880/50000 ( 54%) ] Loss: 0.0038 top1= 99.8438
[E139B30 |  39680/50000 ( 79%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2501 top1= 10.4968


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.4383 top1= 43.3594


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.0604 top1= 46.6947

Train epoch 140
[E140B0  |   1280/50000 (  3%) ] Loss: 0.0054 top1= 99.9219
[E140B10 |  14080/50000 ( 28%) ] Loss: 0.0026 top1= 99.9219
[E140B20 |  26880/50000 ( 54%) ] Loss: 0.0020 top1= 99.9219
[E140B30 |  39680/50000 ( 79%) ] Loss: 0.0040 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2500 top1= 10.5068


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.4141 top1= 43.3393


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.0044 top1= 46.7047

Train epoch 141
[E141B0  |   1280/50000 (  3%) ] Loss: 0.0042 top1= 99.9219
[E141B10 |  14080/50000 ( 28%) ] Loss: 0.0032 top1= 99.9219
[E141B20 |  26880/50000 ( 54%) ] Loss: 0.0031 top1= 99.8438
[E141B30 |  39680/50000 ( 79%) ] Loss: 0.0039 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2497 top1= 10.5168


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.3791 top1= 43.3393


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.9563 top1= 46.6947

Train epoch 142
[E142B0  |   1280/50000 (  3%) ] Loss: 0.0052 top1= 99.7656
[E142B10 |  14080/50000 ( 28%) ] Loss: 0.0054 top1= 99.7656
[E142B20 |  26880/50000 ( 54%) ] Loss: 0.0037 top1=100.0000
[E142B30 |  39680/50000 ( 79%) ] Loss: 0.0041 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2489 top1= 10.5268


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.3220 top1= 43.3293


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.9073 top1= 46.6947

Train epoch 143
[E143B0  |   1280/50000 (  3%) ] Loss: 0.0034 top1= 99.8438
[E143B10 |  14080/50000 ( 28%) ] Loss: 0.0055 top1= 99.6875
[E143B20 |  26880/50000 ( 54%) ] Loss: 0.0019 top1=100.0000
[E143B30 |  39680/50000 ( 79%) ] Loss: 0.0049 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2488 top1= 10.5168


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.3113 top1= 43.3293


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.8696 top1= 46.6947

Train epoch 144
[E144B0  |   1280/50000 (  3%) ] Loss: 0.0034 top1= 99.9219
[E144B10 |  14080/50000 ( 28%) ] Loss: 0.0025 top1= 99.9219
[E144B20 |  26880/50000 ( 54%) ] Loss: 0.0017 top1=100.0000
[E144B30 |  39680/50000 ( 79%) ] Loss: 0.0052 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2479 top1= 10.5268


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.2717 top1= 43.3293


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.8162 top1= 46.6747

Train epoch 145
[E145B0  |   1280/50000 (  3%) ] Loss: 0.0023 top1=100.0000
[E145B10 |  14080/50000 ( 28%) ] Loss: 0.0027 top1=100.0000
[E145B20 |  26880/50000 ( 54%) ] Loss: 0.0022 top1=100.0000
[E145B30 |  39680/50000 ( 79%) ] Loss: 0.0018 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2471 top1= 10.5369


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.2580 top1= 43.3393


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.7919 top1= 46.6847

Train epoch 146
[E146B0  |   1280/50000 (  3%) ] Loss: 0.0031 top1=100.0000
[E146B10 |  14080/50000 ( 28%) ] Loss: 0.0037 top1= 99.8438
[E146B20 |  26880/50000 ( 54%) ] Loss: 0.0031 top1= 99.9219
[E146B30 |  39680/50000 ( 79%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2472 top1= 10.5268


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.2413 top1= 43.3293


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.7506 top1= 46.6847

Train epoch 147
[E147B0  |   1280/50000 (  3%) ] Loss: 0.0023 top1=100.0000
[E147B10 |  14080/50000 ( 28%) ] Loss: 0.0018 top1=100.0000
[E147B20 |  26880/50000 ( 54%) ] Loss: 0.0062 top1= 99.8438
[E147B30 |  39680/50000 ( 79%) ] Loss: 0.0041 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2475 top1= 10.5369


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.1799 top1= 43.3293


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.7272 top1= 46.6847

Train epoch 148
[E148B0  |   1280/50000 (  3%) ] Loss: 0.0044 top1= 99.8438
[E148B10 |  14080/50000 ( 28%) ] Loss: 0.0024 top1= 99.9219
[E148B20 |  26880/50000 ( 54%) ] Loss: 0.0038 top1= 99.8438
[E148B30 |  39680/50000 ( 79%) ] Loss: 0.0033 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2474 top1= 10.5369


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.1099 top1= 43.3193


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.6776 top1= 46.6847

Train epoch 149
[E149B0  |   1280/50000 (  3%) ] Loss: 0.0062 top1= 99.9219
[E149B10 |  14080/50000 ( 28%) ] Loss: 0.0036 top1= 99.8438
[E149B20 |  26880/50000 ( 54%) ] Loss: 0.0036 top1= 99.9219
[E149B30 |  39680/50000 ( 79%) ] Loss: 0.0060 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2474 top1= 10.5369


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.0709 top1= 43.3093


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.6204 top1= 46.6546

Train epoch 150
[E150B0  |   1280/50000 (  3%) ] Loss: 0.0034 top1= 99.9219
[E150B10 |  14080/50000 ( 28%) ] Loss: 0.0024 top1= 99.9219
[E150B20 |  26880/50000 ( 54%) ] Loss: 0.0057 top1= 99.9219
[E150B30 |  39680/50000 ( 79%) ] Loss: 0.0026 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2469 top1= 10.5369


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=12.0493 top1= 43.3193


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.5814 top1= 46.6747

