
=== 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 0x7fbecc33c490>

{'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: 2.3046 top1= 10.0000

=== 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')


[E 1B10 |  14080/50000 ( 28%) ] Loss: 2.1362 top1= 20.0000
[E 1B20 |  26880/50000 ( 54%) ] Loss: 1.8547 top1= 18.9844
[E 1B30 |  39680/50000 ( 79%) ] Loss: 1.7326 top1= 20.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3071 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9267 top1=  9.9860


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1220 top1= 12.7404

Train epoch 2
[E 2B0  |   1280/50000 (  3%) ] Loss: 1.6557 top1= 22.1094
[E 2B10 |  14080/50000 ( 28%) ] Loss: 1.6504 top1= 21.6406
[E 2B20 |  26880/50000 ( 54%) ] Loss: 1.6151 top1= 23.2812
[E 2B30 |  39680/50000 ( 79%) ] Loss: 1.5672 top1= 27.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2857 top1= 11.8790


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5036 top1= 10.0060


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8084 top1= 18.8802

Train epoch 3
[E 3B0  |   1280/50000 (  3%) ] Loss: 1.5513 top1= 30.0000
[E 3B10 |  14080/50000 ( 28%) ] Loss: 1.5382 top1= 32.1875
[E 3B20 |  26880/50000 ( 54%) ] Loss: 1.5349 top1= 28.7500
[E 3B30 |  39680/50000 ( 79%) ] Loss: 1.5390 top1= 31.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2290 top1= 14.9639


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7085 top1= 16.0557


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8885 top1= 21.9752

Train epoch 4
[E 4B0  |   1280/50000 (  3%) ] Loss: 1.4486 top1= 35.1562
[E 4B10 |  14080/50000 ( 28%) ] Loss: 1.5322 top1= 32.7344
[E 4B20 |  26880/50000 ( 54%) ] Loss: 1.5097 top1= 29.9219
[E 4B30 |  39680/50000 ( 79%) ] Loss: 1.4860 top1= 30.3906

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4667 top1=  9.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9609 top1= 10.0060


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9484 top1= 22.9667

Train epoch 5
[E 5B0  |   1280/50000 (  3%) ] Loss: 1.5193 top1= 29.8438
[E 5B10 |  14080/50000 ( 28%) ] Loss: 1.4351 top1= 35.8594
[E 5B20 |  26880/50000 ( 54%) ] Loss: 1.4270 top1= 33.1250
[E 5B30 |  39680/50000 ( 79%) ] Loss: 1.3791 top1= 35.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3580 top1=  9.3650


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2022 top1= 10.0260


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1896 top1= 23.5377

Train epoch 6
[E 6B0  |   1280/50000 (  3%) ] Loss: 1.4464 top1= 33.9844
[E 6B10 |  14080/50000 ( 28%) ] Loss: 1.4226 top1= 36.9531
[E 6B20 |  26880/50000 ( 54%) ] Loss: 1.3734 top1= 40.7812
[E 6B30 |  39680/50000 ( 79%) ] Loss: 1.2870 top1= 45.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2683 top1= 19.5212


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1235 top1= 15.8854


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0785 top1= 29.3169

Train epoch 7
[E 7B0  |   1280/50000 (  3%) ] Loss: 1.3137 top1= 44.5312
[E 7B10 |  14080/50000 ( 28%) ] Loss: 1.3150 top1= 42.5781
[E 7B20 |  26880/50000 ( 54%) ] Loss: 1.2512 top1= 43.1250
[E 7B30 |  39680/50000 ( 79%) ] Loss: 1.0996 top1= 55.2344

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0722 top1= 20.6931


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7080 top1= 24.7196


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4133 top1= 25.4607

Train epoch 8
[E 8B0  |   1280/50000 (  3%) ] Loss: 1.4444 top1= 46.7188
[E 8B10 |  14080/50000 ( 28%) ] Loss: 1.2419 top1= 48.5156
[E 8B20 |  26880/50000 ( 54%) ] Loss: 1.1482 top1= 52.0312
[E 8B30 |  39680/50000 ( 79%) ] Loss: 1.0220 top1= 57.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9182 top1= 26.1218


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1041 top1= 27.4539


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7980 top1= 32.8526

Train epoch 9
[E 9B0  |   1280/50000 (  3%) ] Loss: 0.9998 top1= 60.2344
[E 9B10 |  14080/50000 ( 28%) ] Loss: 1.0049 top1= 60.4688
[E 9B20 |  26880/50000 ( 54%) ] Loss: 0.9839 top1= 59.6875
[E 9B30 |  39680/50000 ( 79%) ] Loss: 0.9552 top1= 62.7344

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8909 top1= 29.3870


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6699 top1= 30.0481


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3017 top1= 35.4667

Train epoch 10
[E10B0  |   1280/50000 (  3%) ] Loss: 0.8992 top1= 64.9219
[E10B10 |  14080/50000 ( 28%) ] Loss: 0.9193 top1= 63.5938
[E10B20 |  26880/50000 ( 54%) ] Loss: 0.9528 top1= 59.3750
[E10B30 |  39680/50000 ( 79%) ] Loss: 0.8394 top1= 66.4844

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7172 top1= 30.5389


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2064 top1= 31.4804


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9221 top1= 36.7388

Train epoch 11
[E11B0  |   1280/50000 (  3%) ] Loss: 0.8348 top1= 69.7656
[E11B10 |  14080/50000 ( 28%) ] Loss: 0.8154 top1= 67.9688
[E11B20 |  26880/50000 ( 54%) ] Loss: 0.8164 top1= 66.0938
[E11B30 |  39680/50000 ( 79%) ] Loss: 0.7638 top1= 70.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6855 top1= 32.2716


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0451 top1= 32.4018


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6193 top1= 36.0176

Train epoch 12
[E12B0  |   1280/50000 (  3%) ] Loss: 0.8445 top1= 68.2031
[E12B10 |  14080/50000 ( 28%) ] Loss: 0.7688 top1= 70.2344
[E12B20 |  26880/50000 ( 54%) ] Loss: 0.7721 top1= 69.3750
[E12B30 |  39680/50000 ( 79%) ] Loss: 0.7128 top1= 72.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6063 top1= 34.0946


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0966 top1= 33.7841


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2103 top1= 38.8722

Train epoch 13
[E13B0  |   1280/50000 (  3%) ] Loss: 0.7631 top1= 71.7188
[E13B10 |  14080/50000 ( 28%) ] Loss: 0.7691 top1= 70.0000
[E13B20 |  26880/50000 ( 54%) ] Loss: 0.7689 top1= 70.7031
[E13B30 |  39680/50000 ( 79%) ] Loss: 0.6706 top1= 73.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.5757 top1= 37.8005


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1668 top1= 35.2464


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9642 top1= 40.0841

Train epoch 14
[E14B0  |   1280/50000 (  3%) ] Loss: 0.6359 top1= 75.7031
[E14B10 |  14080/50000 ( 28%) ] Loss: 0.7342 top1= 72.0312
[E14B20 |  26880/50000 ( 54%) ] Loss: 0.7482 top1= 71.0938
[E14B30 |  39680/50000 ( 79%) ] Loss: 0.6391 top1= 74.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.5198 top1= 39.1326


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0841 top1= 35.8574


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9930 top1= 38.7620

Train epoch 15
[E15B0  |   1280/50000 (  3%) ] Loss: 0.6374 top1= 75.7812
[E15B10 |  14080/50000 ( 28%) ] Loss: 0.6452 top1= 75.1562
[E15B20 |  26880/50000 ( 54%) ] Loss: 0.6718 top1= 74.9219
[E15B30 |  39680/50000 ( 79%) ] Loss: 0.5568 top1= 79.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4706 top1= 39.7035


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3341 top1= 36.7188


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7879 top1= 39.9239

Train epoch 16
[E16B0  |   1280/50000 (  3%) ] Loss: 0.5873 top1= 77.7344
[E16B10 |  14080/50000 ( 28%) ] Loss: 0.6114 top1= 76.7188
[E16B20 |  26880/50000 ( 54%) ] Loss: 0.5953 top1= 78.9844
[E16B30 |  39680/50000 ( 79%) ] Loss: 0.5260 top1= 79.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4144 top1= 42.5481


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0979 top1= 37.3898


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1095 top1= 41.6066

Train epoch 17
[E17B0  |   1280/50000 (  3%) ] Loss: 0.5508 top1= 79.4531
[E17B10 |  14080/50000 ( 28%) ] Loss: 0.6015 top1= 77.4219
[E17B20 |  26880/50000 ( 54%) ] Loss: 0.5698 top1= 77.1094
[E17B30 |  39680/50000 ( 79%) ] Loss: 0.5182 top1= 80.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4386 top1= 44.0304


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2445 top1= 37.2696


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3392 top1= 41.2760

Train epoch 18
[E18B0  |   1280/50000 (  3%) ] Loss: 0.5489 top1= 80.8594
[E18B10 |  14080/50000 ( 28%) ] Loss: 0.6519 top1= 75.6250
[E18B20 |  26880/50000 ( 54%) ] Loss: 0.5331 top1= 81.0156
[E18B30 |  39680/50000 ( 79%) ] Loss: 0.4845 top1= 81.9531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3957 top1= 44.2208


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3530 top1= 38.8221


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0190 top1= 41.0056

Train epoch 19
[E19B0  |   1280/50000 (  3%) ] Loss: 0.5507 top1= 80.9375
[E19B10 |  14080/50000 ( 28%) ] Loss: 0.5488 top1= 80.0000
[E19B20 |  26880/50000 ( 54%) ] Loss: 0.5112 top1= 81.0156
[E19B30 |  39680/50000 ( 79%) ] Loss: 0.5160 top1= 79.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3463 top1= 43.4796


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9935 top1= 38.8221


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8052 top1= 40.4046

Train epoch 20
[E20B0  |   1280/50000 (  3%) ] Loss: 0.5439 top1= 79.4531
[E20B10 |  14080/50000 ( 28%) ] Loss: 0.5404 top1= 80.9375
[E20B20 |  26880/50000 ( 54%) ] Loss: 0.5064 top1= 82.2656
[E20B30 |  39680/50000 ( 79%) ] Loss: 0.4837 top1= 81.7969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3613 top1= 45.6330


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1725 top1= 39.0725


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1979 top1= 42.7784

Train epoch 21
[E21B0  |   1280/50000 (  3%) ] Loss: 0.4622 top1= 84.2188
[E21B10 |  14080/50000 ( 28%) ] Loss: 0.4457 top1= 84.0625
[E21B20 |  26880/50000 ( 54%) ] Loss: 0.4328 top1= 83.7500
[E21B30 |  39680/50000 ( 79%) ] Loss: 0.4063 top1= 84.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3115 top1= 47.8466


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5113 top1= 39.6835


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3698 top1= 42.6783

Train epoch 22
[E22B0  |   1280/50000 (  3%) ] Loss: 0.4687 top1= 83.9844
[E22B10 |  14080/50000 ( 28%) ] Loss: 0.4176 top1= 85.0781
[E22B20 |  26880/50000 ( 54%) ] Loss: 0.4057 top1= 84.2188
[E22B30 |  39680/50000 ( 79%) ] Loss: 0.4303 top1= 84.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2337 top1= 48.3874


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5417 top1= 39.8838


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9066 top1= 43.0288

Train epoch 23
[E23B0  |   1280/50000 (  3%) ] Loss: 0.4041 top1= 86.4844
[E23B10 |  14080/50000 ( 28%) ] Loss: 0.4199 top1= 84.7656
[E23B20 |  26880/50000 ( 54%) ] Loss: 0.3921 top1= 85.1562
[E23B30 |  39680/50000 ( 79%) ] Loss: 0.3791 top1= 85.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3030 top1= 47.5060


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5869 top1= 39.5533


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5674 top1= 44.0805

Train epoch 24
[E24B0  |   1280/50000 (  3%) ] Loss: 0.3945 top1= 85.2344
[E24B10 |  14080/50000 ( 28%) ] Loss: 0.3816 top1= 86.3281
[E24B20 |  26880/50000 ( 54%) ] Loss: 0.3660 top1= 86.5625
[E24B30 |  39680/50000 ( 79%) ] Loss: 0.3842 top1= 85.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1952 top1= 51.0517


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8102 top1= 39.3029


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0979 top1= 42.2776

Train epoch 25
[E25B0  |   1280/50000 (  3%) ] Loss: 0.4430 top1= 83.3594
[E25B10 |  14080/50000 ( 28%) ] Loss: 0.4046 top1= 85.7812
[E25B20 |  26880/50000 ( 54%) ] Loss: 0.3505 top1= 86.5625
[E25B30 |  39680/50000 ( 79%) ] Loss: 0.3509 top1= 86.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2573 top1= 49.8698


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2332 top1= 40.8153


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3462 top1= 43.3894

Train epoch 26
[E26B0  |   1280/50000 (  3%) ] Loss: 0.3702 top1= 85.9375
[E26B10 |  14080/50000 ( 28%) ] Loss: 0.3837 top1= 85.8594
[E26B20 |  26880/50000 ( 54%) ] Loss: 0.3337 top1= 87.4219
[E26B30 |  39680/50000 ( 79%) ] Loss: 0.3523 top1= 86.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2576 top1= 51.2220


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6788 top1= 40.3646


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0712 top1= 43.8702

Train epoch 27
[E27B0  |   1280/50000 (  3%) ] Loss: 0.3472 top1= 87.8125
[E27B10 |  14080/50000 ( 28%) ] Loss: 0.3720 top1= 85.9375
[E27B20 |  26880/50000 ( 54%) ] Loss: 0.3669 top1= 85.8594
[E27B30 |  39680/50000 ( 79%) ] Loss: 0.3405 top1= 87.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1898 top1= 53.1951


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6744 top1= 40.3045


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8342 top1= 44.3610

Train epoch 28
[E28B0  |   1280/50000 (  3%) ] Loss: 0.3358 top1= 88.4375
[E28B10 |  14080/50000 ( 28%) ] Loss: 0.3889 top1= 85.4688
[E28B20 |  26880/50000 ( 54%) ] Loss: 0.2866 top1= 90.2344
[E28B30 |  39680/50000 ( 79%) ] Loss: 0.3355 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1985 top1= 52.8746


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5436 top1= 40.9054


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4762 top1= 44.3309

Train epoch 29
[E29B0  |   1280/50000 (  3%) ] Loss: 0.3289 top1= 88.0469
[E29B10 |  14080/50000 ( 28%) ] Loss: 0.3338 top1= 87.4219
[E29B20 |  26880/50000 ( 54%) ] Loss: 0.3274 top1= 87.5000
[E29B30 |  39680/50000 ( 79%) ] Loss: 0.2970 top1= 88.9844

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1387 top1= 54.6474


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7815 top1= 41.7067


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5572 top1= 44.0004

Train epoch 30
[E30B0  |   1280/50000 (  3%) ] Loss: 0.3125 top1= 89.1406
[E30B10 |  14080/50000 ( 28%) ] Loss: 0.2950 top1= 89.5312
[E30B20 |  26880/50000 ( 54%) ] Loss: 0.3405 top1= 88.0469
[E30B30 |  39680/50000 ( 79%) ] Loss: 0.3162 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1672 top1= 56.4103


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4892 top1= 40.7252


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4877 top1= 44.4211

Train epoch 31
[E31B0  |   1280/50000 (  3%) ] Loss: 0.3126 top1= 87.8125
[E31B10 |  14080/50000 ( 28%) ] Loss: 0.2913 top1= 90.2344
[E31B20 |  26880/50000 ( 54%) ] Loss: 0.2890 top1= 88.5156
[E31B30 |  39680/50000 ( 79%) ] Loss: 0.2865 top1= 89.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1566 top1= 56.6206


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1178 top1= 41.4062


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6393 top1= 43.6999

Train epoch 32
[E32B0  |   1280/50000 (  3%) ] Loss: 0.2897 top1= 89.7656
[E32B10 |  14080/50000 ( 28%) ] Loss: 0.3044 top1= 88.7500
[E32B20 |  26880/50000 ( 54%) ] Loss: 0.2933 top1= 90.0000
[E32B30 |  39680/50000 ( 79%) ] Loss: 0.2824 top1= 89.2969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1962 top1= 54.9780


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6983 top1= 40.3846


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5634 top1= 44.9119

Train epoch 33
[E33B0  |   1280/50000 (  3%) ] Loss: 0.3103 top1= 89.4531
[E33B10 |  14080/50000 ( 28%) ] Loss: 0.3286 top1= 87.6562
[E33B20 |  26880/50000 ( 54%) ] Loss: 0.2993 top1= 89.4531
[E33B30 |  39680/50000 ( 79%) ] Loss: 0.2935 top1= 89.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1734 top1= 56.3602


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4412 top1= 41.0457


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5576 top1= 44.8317

Train epoch 34
[E34B0  |   1280/50000 (  3%) ] Loss: 0.2673 top1= 90.5469
[E34B10 |  14080/50000 ( 28%) ] Loss: 0.2993 top1= 89.9219
[E34B20 |  26880/50000 ( 54%) ] Loss: 0.2510 top1= 89.6875
[E34B30 |  39680/50000 ( 79%) ] Loss: 0.2392 top1= 90.3906

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1437 top1= 56.0897


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4249 top1= 39.1126


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8611 top1= 44.9519

Train epoch 35
[E35B0  |   1280/50000 (  3%) ] Loss: 0.3213 top1= 87.5781
[E35B10 |  14080/50000 ( 28%) ] Loss: 0.2808 top1= 88.9062
[E35B20 |  26880/50000 ( 54%) ] Loss: 0.2661 top1= 90.1562
[E35B30 |  39680/50000 ( 79%) ] Loss: 0.2797 top1= 90.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2189 top1= 56.4002


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9139 top1= 40.1743


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9238 top1= 44.9920

Train epoch 36
[E36B0  |   1280/50000 (  3%) ] Loss: 0.2936 top1= 90.5469
[E36B10 |  14080/50000 ( 28%) ] Loss: 0.2877 top1= 89.8438
[E36B20 |  26880/50000 ( 54%) ] Loss: 0.2693 top1= 90.6250
[E36B30 |  39680/50000 ( 79%) ] Loss: 0.2337 top1= 91.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1525 top1= 57.6222


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1063 top1= 42.1575


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8566 top1= 44.8618

Train epoch 37
[E37B0  |   1280/50000 (  3%) ] Loss: 0.2594 top1= 90.3906
[E37B10 |  14080/50000 ( 28%) ] Loss: 0.2886 top1= 89.4531
[E37B20 |  26880/50000 ( 54%) ] Loss: 0.2440 top1= 91.1719
[E37B30 |  39680/50000 ( 79%) ] Loss: 0.2573 top1= 90.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0472 top1= 60.4968


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3000 top1= 41.5264


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3689 top1= 45.0521

Train epoch 38
[E38B0  |   1280/50000 (  3%) ] Loss: 0.2182 top1= 91.6406
[E38B10 |  14080/50000 ( 28%) ] Loss: 0.2150 top1= 92.5781
[E38B20 |  26880/50000 ( 54%) ] Loss: 0.2405 top1= 90.0781
[E38B30 |  39680/50000 ( 79%) ] Loss: 0.2235 top1= 91.4844

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0747 top1= 60.8273


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1619 top1= 41.2560


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8564 top1= 45.6130

Train epoch 39
[E39B0  |   1280/50000 (  3%) ] Loss: 0.2216 top1= 91.7188
[E39B10 |  14080/50000 ( 28%) ] Loss: 0.2229 top1= 91.9531
[E39B20 |  26880/50000 ( 54%) ] Loss: 0.2342 top1= 91.1719
[E39B30 |  39680/50000 ( 79%) ] Loss: 0.2267 top1= 91.3281

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1431 top1= 60.3866


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4338 top1= 41.3862


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4802 top1= 45.6130

Train epoch 40
[E40B0  |   1280/50000 (  3%) ] Loss: 0.2189 top1= 92.0312
[E40B10 |  14080/50000 ( 28%) ] Loss: 0.2082 top1= 91.6406
[E40B20 |  26880/50000 ( 54%) ] Loss: 0.2494 top1= 89.1406
[E40B30 |  39680/50000 ( 79%) ] Loss: 0.2449 top1= 90.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2196 top1= 60.1162


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6488 top1= 41.8970


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5808 top1= 45.0421

Train epoch 41
[E41B0  |   1280/50000 (  3%) ] Loss: 0.2619 top1= 91.3281
[E41B10 |  14080/50000 ( 28%) ] Loss: 0.2232 top1= 91.8750
[E41B20 |  26880/50000 ( 54%) ] Loss: 0.2372 top1= 91.2500
[E41B30 |  39680/50000 ( 79%) ] Loss: 0.2200 top1= 91.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1078 top1= 60.5068


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8366 top1= 40.8053


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2330 top1= 44.5312

Train epoch 42
[E42B0  |   1280/50000 (  3%) ] Loss: 0.2651 top1= 90.3906
[E42B10 |  14080/50000 ( 28%) ] Loss: 0.2494 top1= 90.8594
[E42B20 |  26880/50000 ( 54%) ] Loss: 0.2058 top1= 92.7344
[E42B30 |  39680/50000 ( 79%) ] Loss: 0.2082 top1= 91.7969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0667 top1= 62.6502


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2967 top1= 41.1158


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8477 top1= 45.3025

Train epoch 43
[E43B0  |   1280/50000 (  3%) ] Loss: 0.1959 top1= 93.0469
[E43B10 |  14080/50000 ( 28%) ] Loss: 0.2304 top1= 92.0312
[E43B20 |  26880/50000 ( 54%) ] Loss: 0.2031 top1= 91.9531
[E43B30 |  39680/50000 ( 79%) ] Loss: 0.2129 top1= 91.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0522 top1= 63.1410


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6273 top1= 41.7668


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2657 top1= 45.5629

Train epoch 44
[E44B0  |   1280/50000 (  3%) ] Loss: 0.2071 top1= 92.1875
[E44B10 |  14080/50000 ( 28%) ] Loss: 0.2326 top1= 91.7969
[E44B20 |  26880/50000 ( 54%) ] Loss: 0.2474 top1= 90.3125
[E44B30 |  39680/50000 ( 79%) ] Loss: 0.2017 top1= 92.5781

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0311 top1= 63.5317


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2726 top1= 42.4980


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4659 top1= 45.3425

Train epoch 45
[E45B0  |   1280/50000 (  3%) ] Loss: 0.1891 top1= 92.8125
[E45B10 |  14080/50000 ( 28%) ] Loss: 0.1697 top1= 94.2969
[E45B20 |  26880/50000 ( 54%) ] Loss: 0.1924 top1= 93.3594
[E45B30 |  39680/50000 ( 79%) ] Loss: 0.2039 top1= 92.2656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1006 top1= 61.7989


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4733 top1= 40.9956


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2464 top1= 45.5929

Train epoch 46
[E46B0  |   1280/50000 (  3%) ] Loss: 0.2189 top1= 92.4219
[E46B10 |  14080/50000 ( 28%) ] Loss: 0.1962 top1= 92.5781
[E46B20 |  26880/50000 ( 54%) ] Loss: 0.1777 top1= 93.1250
[E46B30 |  39680/50000 ( 79%) ] Loss: 0.1485 top1= 94.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9956 top1= 65.4447


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0867 top1= 41.8470


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8048 top1= 45.4227

Train epoch 47
[E47B0  |   1280/50000 (  3%) ] Loss: 0.1729 top1= 92.5781
[E47B10 |  14080/50000 ( 28%) ] Loss: 0.1960 top1= 92.1875
[E47B20 |  26880/50000 ( 54%) ] Loss: 0.1933 top1= 92.6562
[E47B30 |  39680/50000 ( 79%) ] Loss: 0.1546 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2349 top1= 62.5100


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2774 top1= 42.1374


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8568 top1= 45.4627

Train epoch 48
[E48B0  |   1280/50000 (  3%) ] Loss: 0.1796 top1= 94.1406
[E48B10 |  14080/50000 ( 28%) ] Loss: 0.1582 top1= 93.5938
[E48B20 |  26880/50000 ( 54%) ] Loss: 0.2007 top1= 92.9688
[E48B30 |  39680/50000 ( 79%) ] Loss: 0.1394 top1= 94.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0851 top1= 64.6434


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4696 top1= 42.1074


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1417 top1= 45.5929

Train epoch 49
[E49B0  |   1280/50000 (  3%) ] Loss: 0.1706 top1= 94.3750
[E49B10 |  14080/50000 ( 28%) ] Loss: 0.1928 top1= 93.4375
[E49B20 |  26880/50000 ( 54%) ] Loss: 0.2535 top1= 90.8594
[E49B30 |  39680/50000 ( 79%) ] Loss: 0.1926 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2784 top1= 61.6386


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9981 top1= 42.8786


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6734 top1= 44.9119

Train epoch 50
[E50B0  |   1280/50000 (  3%) ] Loss: 0.2039 top1= 93.7500
[E50B10 |  14080/50000 ( 28%) ] Loss: 0.2404 top1= 91.2500
[E50B20 |  26880/50000 ( 54%) ] Loss: 0.2016 top1= 92.2656
[E50B30 |  39680/50000 ( 79%) ] Loss: 0.2331 top1= 91.7969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1225 top1= 63.0108


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2485 top1= 42.5781


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5787 top1= 45.9635

Train epoch 51
[E51B0  |   1280/50000 (  3%) ] Loss: 0.1949 top1= 93.2812
[E51B10 |  14080/50000 ( 28%) ] Loss: 0.1694 top1= 93.1250
[E51B20 |  26880/50000 ( 54%) ] Loss: 0.1620 top1= 94.2188
[E51B30 |  39680/50000 ( 79%) ] Loss: 0.1667 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0674 top1= 64.8938


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3572 top1= 43.1591


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8655 top1= 45.9335

Train epoch 52
[E52B0  |   1280/50000 (  3%) ] Loss: 0.1574 top1= 94.2969
[E52B10 |  14080/50000 ( 28%) ] Loss: 0.1419 top1= 94.6875
[E52B20 |  26880/50000 ( 54%) ] Loss: 0.1378 top1= 94.4531
[E52B30 |  39680/50000 ( 79%) ] Loss: 0.1536 top1= 94.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1590 top1= 62.7003


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4321 top1= 42.2576


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8777 top1= 45.5829

Train epoch 53
[E53B0  |   1280/50000 (  3%) ] Loss: 0.1445 top1= 95.0781
[E53B10 |  14080/50000 ( 28%) ] Loss: 0.1758 top1= 93.6719
[E53B20 |  26880/50000 ( 54%) ] Loss: 0.1505 top1= 94.2188
[E53B30 |  39680/50000 ( 79%) ] Loss: 0.1837 top1= 93.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2307 top1= 62.7804


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4948 top1= 43.2692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9087 top1= 45.5028

Train epoch 54
[E54B0  |   1280/50000 (  3%) ] Loss: 0.1615 top1= 93.9844
[E54B10 |  14080/50000 ( 28%) ] Loss: 0.1458 top1= 94.7656
[E54B20 |  26880/50000 ( 54%) ] Loss: 0.1423 top1= 94.9219
[E54B30 |  39680/50000 ( 79%) ] Loss: 0.1725 top1= 93.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1301 top1= 63.4515


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0063 top1= 42.3778


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3487 top1= 45.8333

Train epoch 55
[E55B0  |   1280/50000 (  3%) ] Loss: 0.1779 top1= 93.7500
[E55B10 |  14080/50000 ( 28%) ] Loss: 0.1595 top1= 94.3750
[E55B20 |  26880/50000 ( 54%) ] Loss: 0.1728 top1= 94.0625
[E55B30 |  39680/50000 ( 79%) ] Loss: 0.1521 top1= 93.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1113 top1= 65.4447


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2637 top1= 42.0673


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9470 top1= 46.2340

Train epoch 56
[E56B0  |   1280/50000 (  3%) ] Loss: 0.1557 top1= 94.0625
[E56B10 |  14080/50000 ( 28%) ] Loss: 0.1534 top1= 94.2188
[E56B20 |  26880/50000 ( 54%) ] Loss: 0.1350 top1= 94.7656
[E56B30 |  39680/50000 ( 79%) ] Loss: 0.1296 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9682 top1= 67.6583


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0141 top1= 42.3077


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7935 top1= 45.7732

Train epoch 57
[E57B0  |   1280/50000 (  3%) ] Loss: 0.1677 top1= 93.8281
[E57B10 |  14080/50000 ( 28%) ] Loss: 0.1233 top1= 96.2500
[E57B20 |  26880/50000 ( 54%) ] Loss: 0.1191 top1= 96.0938
[E57B30 |  39680/50000 ( 79%) ] Loss: 0.1808 top1= 92.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2162 top1= 64.4631


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8764 top1= 42.4679


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8183 top1= 46.1538

Train epoch 58
[E58B0  |   1280/50000 (  3%) ] Loss: 0.1604 top1= 94.3750
[E58B10 |  14080/50000 ( 28%) ] Loss: 0.1287 top1= 95.7812
[E58B20 |  26880/50000 ( 54%) ] Loss: 0.1304 top1= 95.5469
[E58B30 |  39680/50000 ( 79%) ] Loss: 0.1472 top1= 94.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1148 top1= 65.6951


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4683 top1= 42.0773


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7119 top1= 45.8934

Train epoch 59
[E59B0  |   1280/50000 (  3%) ] Loss: 0.1692 top1= 94.4531
[E59B10 |  14080/50000 ( 28%) ] Loss: 0.1498 top1= 94.6875
[E59B20 |  26880/50000 ( 54%) ] Loss: 0.1161 top1= 95.5469
[E59B30 |  39680/50000 ( 79%) ] Loss: 0.1440 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1275 top1= 65.7552


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0879 top1= 42.5781


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8753 top1= 45.7532

Train epoch 60
[E60B0  |   1280/50000 (  3%) ] Loss: 0.1546 top1= 94.5312
[E60B10 |  14080/50000 ( 28%) ] Loss: 0.1605 top1= 93.9062
[E60B20 |  26880/50000 ( 54%) ] Loss: 0.1583 top1= 94.6094
[E60B30 |  39680/50000 ( 79%) ] Loss: 0.1331 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2372 top1= 65.4948


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0576 top1= 42.5581


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6860 top1= 45.9135

Train epoch 61
[E61B0  |   1280/50000 (  3%) ] Loss: 0.1332 top1= 95.3906
[E61B10 |  14080/50000 ( 28%) ] Loss: 0.1159 top1= 95.5469
[E61B20 |  26880/50000 ( 54%) ] Loss: 0.1359 top1= 95.4688
[E61B30 |  39680/50000 ( 79%) ] Loss: 0.1547 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2151 top1= 64.5633


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0654 top1= 42.2476


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9376 top1= 45.8233

Train epoch 62
[E62B0  |   1280/50000 (  3%) ] Loss: 0.1390 top1= 94.7656
[E62B10 |  14080/50000 ( 28%) ] Loss: 0.1457 top1= 95.1562
[E62B20 |  26880/50000 ( 54%) ] Loss: 0.1469 top1= 95.2344
[E62B30 |  39680/50000 ( 79%) ] Loss: 0.1317 top1= 95.2344

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0508 top1= 68.0188


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4749 top1= 42.8185


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8726 top1= 45.8534

Train epoch 63
[E63B0  |   1280/50000 (  3%) ] Loss: 0.1035 top1= 96.3281
[E63B10 |  14080/50000 ( 28%) ] Loss: 0.1497 top1= 95.0781
[E63B20 |  26880/50000 ( 54%) ] Loss: 0.1413 top1= 94.7656
[E63B30 |  39680/50000 ( 79%) ] Loss: 0.1220 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0586 top1= 68.0689


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3700 top1= 43.0589


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4901 top1= 45.6430

Train epoch 64
[E64B0  |   1280/50000 (  3%) ] Loss: 0.1086 top1= 95.5469
[E64B10 |  14080/50000 ( 28%) ] Loss: 0.1448 top1= 95.0000
[E64B20 |  26880/50000 ( 54%) ] Loss: 0.1360 top1= 95.4688
[E64B30 |  39680/50000 ( 79%) ] Loss: 0.1603 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0725 top1= 67.8886


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5235 top1= 43.0489


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9566 top1= 45.5929

Train epoch 65
[E65B0  |   1280/50000 (  3%) ] Loss: 0.1249 top1= 95.5469
[E65B10 |  14080/50000 ( 28%) ] Loss: 0.1635 top1= 94.8438
[E65B20 |  26880/50000 ( 54%) ] Loss: 0.1195 top1= 95.7031
[E65B30 |  39680/50000 ( 79%) ] Loss: 0.1352 top1= 95.3906

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1016 top1= 66.9271


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1178 top1= 43.1991


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.8410 top1= 45.1422

Train epoch 66
[E66B0  |   1280/50000 (  3%) ] Loss: 0.1717 top1= 93.9844
[E66B10 |  14080/50000 ( 28%) ] Loss: 0.0925 top1= 96.7969
[E66B20 |  26880/50000 ( 54%) ] Loss: 0.0987 top1= 96.4062
[E66B30 |  39680/50000 ( 79%) ] Loss: 0.1295 top1= 95.2344

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2258 top1= 63.8321


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2776 top1= 43.2692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3094 top1= 45.7532

Train epoch 67
[E67B0  |   1280/50000 (  3%) ] Loss: 0.0833 top1= 97.1875
[E67B10 |  14080/50000 ( 28%) ] Loss: 0.1028 top1= 96.0156
[E67B20 |  26880/50000 ( 54%) ] Loss: 0.0991 top1= 96.2500
[E67B30 |  39680/50000 ( 79%) ] Loss: 0.1102 top1= 96.4844

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1109 top1= 67.5881


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.6980 top1= 43.2993


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1061 top1= 45.8133

Train epoch 68
[E68B0  |   1280/50000 (  3%) ] Loss: 0.0996 top1= 96.6406
[E68B10 |  14080/50000 ( 28%) ] Loss: 0.1281 top1= 95.2344
[E68B20 |  26880/50000 ( 54%) ] Loss: 0.0832 top1= 97.2656
[E68B30 |  39680/50000 ( 79%) ] Loss: 0.1108 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0348 top1= 69.0104


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8177 top1= 42.7885


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.6106 top1= 45.4026

Train epoch 69
[E69B0  |   1280/50000 (  3%) ] Loss: 0.1311 top1= 95.2344
[E69B10 |  14080/50000 ( 28%) ] Loss: 0.0991 top1= 96.0156
[E69B20 |  26880/50000 ( 54%) ] Loss: 0.0963 top1= 96.5625
[E69B30 |  39680/50000 ( 79%) ] Loss: 0.0793 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2567 top1= 64.6034


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2679 top1= 42.5681


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.7790 top1= 45.3526

Train epoch 70
[E70B0  |   1280/50000 (  3%) ] Loss: 0.1011 top1= 96.0156
[E70B10 |  14080/50000 ( 28%) ] Loss: 0.1236 top1= 95.3906
[E70B20 |  26880/50000 ( 54%) ] Loss: 0.1158 top1= 95.4688
[E70B30 |  39680/50000 ( 79%) ] Loss: 0.0857 top1= 96.7969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1398 top1= 67.6082


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9068 top1= 42.8185


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.0412 top1= 45.8333

Train epoch 71
[E71B0  |   1280/50000 (  3%) ] Loss: 0.0926 top1= 96.8750
[E71B10 |  14080/50000 ( 28%) ] Loss: 0.1176 top1= 96.5625
[E71B20 |  26880/50000 ( 54%) ] Loss: 0.0942 top1= 96.8750
[E71B30 |  39680/50000 ( 79%) ] Loss: 0.0738 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1561 top1= 66.3962


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3671 top1= 42.5280


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.6725 top1= 46.0837

Train epoch 72
[E72B0  |   1280/50000 (  3%) ] Loss: 0.1095 top1= 96.0938
[E72B10 |  14080/50000 ( 28%) ] Loss: 0.1021 top1= 95.8594
[E72B20 |  26880/50000 ( 54%) ] Loss: 0.1044 top1= 96.4062
[E72B30 |  39680/50000 ( 79%) ] Loss: 0.0821 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3355 top1= 64.5333


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5254 top1= 43.3794


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.3363 top1= 46.1839

Train epoch 73
[E73B0  |   1280/50000 (  3%) ] Loss: 0.0837 top1= 97.1875
[E73B10 |  14080/50000 ( 28%) ] Loss: 0.1188 top1= 96.4062
[E73B20 |  26880/50000 ( 54%) ] Loss: 0.0998 top1= 96.4062
[E73B30 |  39680/50000 ( 79%) ] Loss: 0.1092 top1= 95.7031

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0950 top1= 67.8385


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1689 top1= 43.1190


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.0914 top1= 45.6430

Train epoch 74
[E74B0  |   1280/50000 (  3%) ] Loss: 0.1033 top1= 96.3281
[E74B10 |  14080/50000 ( 28%) ] Loss: 0.0770 top1= 96.9531
[E74B20 |  26880/50000 ( 54%) ] Loss: 0.1097 top1= 96.3281
[E74B30 |  39680/50000 ( 79%) ] Loss: 0.1199 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1703 top1= 66.5365


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5778 top1= 43.1090


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.0316 top1= 46.0637

Train epoch 75
[E75B0  |   1280/50000 (  3%) ] Loss: 0.0780 top1= 97.4219
[E75B10 |  14080/50000 ( 28%) ] Loss: 0.0750 top1= 97.2656
[E75B20 |  26880/50000 ( 54%) ] Loss: 0.1135 top1= 95.9375
[E75B30 |  39680/50000 ( 79%) ] Loss: 0.1204 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1115 top1= 67.3578


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1093 top1= 43.2692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5400 top1= 46.0737

Train epoch 76
[E76B0  |   1280/50000 (  3%) ] Loss: 0.0992 top1= 96.3281
[E76B10 |  14080/50000 ( 28%) ] Loss: 0.0981 top1= 95.9375
[E76B20 |  26880/50000 ( 54%) ] Loss: 0.0936 top1= 96.7969
[E76B30 |  39680/50000 ( 79%) ] Loss: 0.0804 top1= 97.4219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2246 top1= 66.0357


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8814 top1= 43.0088


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6907 top1= 45.9335

Train epoch 77
[E77B0  |   1280/50000 (  3%) ] Loss: 0.1000 top1= 95.9375
[E77B10 |  14080/50000 ( 28%) ] Loss: 0.0873 top1= 97.0312
[E77B20 |  26880/50000 ( 54%) ] Loss: 0.0759 top1= 97.1094
[E77B30 |  39680/50000 ( 79%) ] Loss: 0.0967 top1= 96.7969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1632 top1= 68.3894


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7558 top1= 43.0990


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.0559 top1= 46.2139

Train epoch 78
[E78B0  |   1280/50000 (  3%) ] Loss: 0.0745 top1= 97.4219
[E78B10 |  14080/50000 ( 28%) ] Loss: 0.1066 top1= 96.4062
[E78B20 |  26880/50000 ( 54%) ] Loss: 0.0753 top1= 97.6562
[E78B30 |  39680/50000 ( 79%) ] Loss: 0.0933 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2964 top1= 67.0072


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3304 top1= 43.0288


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.5210 top1= 46.0236

Train epoch 79
[E79B0  |   1280/50000 (  3%) ] Loss: 0.0639 top1= 97.6562
[E79B10 |  14080/50000 ( 28%) ] Loss: 0.0504 top1= 98.5156
[E79B20 |  26880/50000 ( 54%) ] Loss: 0.0675 top1= 97.0312
[E79B30 |  39680/50000 ( 79%) ] Loss: 0.0913 top1= 96.7969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2489 top1= 66.5865


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0960 top1= 42.2476


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.7786 top1= 46.1138

Train epoch 80
[E80B0  |   1280/50000 (  3%) ] Loss: 0.1087 top1= 96.1719
[E80B10 |  14080/50000 ( 28%) ] Loss: 0.0978 top1= 96.8750
[E80B20 |  26880/50000 ( 54%) ] Loss: 0.0944 top1= 97.5000
[E80B30 |  39680/50000 ( 79%) ] Loss: 0.1043 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1862 top1= 67.9387


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0026 top1= 43.6198


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.5151 top1= 45.7532

Train epoch 81
[E81B0  |   1280/50000 (  3%) ] Loss: 0.0693 top1= 97.5781
[E81B10 |  14080/50000 ( 28%) ] Loss: 0.0600 top1= 98.2031
[E81B20 |  26880/50000 ( 54%) ] Loss: 0.0525 top1= 98.2812
[E81B30 |  39680/50000 ( 79%) ] Loss: 0.0340 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0688 top1= 70.6631


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6986 top1= 44.6715


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2473 top1= 47.4760

Train epoch 82
[E82B0  |   1280/50000 (  3%) ] Loss: 0.0404 top1= 98.6719
[E82B10 |  14080/50000 ( 28%) ] Loss: 0.0353 top1= 98.7500
[E82B20 |  26880/50000 ( 54%) ] Loss: 0.0294 top1= 98.9062
[E82B30 |  39680/50000 ( 79%) ] Loss: 0.0212 top1= 99.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1548 top1= 70.8233


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6595 top1= 45.5228


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6434 top1= 47.8666

Train epoch 83
[E83B0  |   1280/50000 (  3%) ] Loss: 0.0298 top1= 99.0625
[E83B10 |  14080/50000 ( 28%) ] Loss: 0.0315 top1= 98.9844
[E83B20 |  26880/50000 ( 54%) ] Loss: 0.0266 top1= 99.1406
[E83B30 |  39680/50000 ( 79%) ] Loss: 0.0160 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1695 top1= 71.6647


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7969 top1= 45.5429


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8330 top1= 47.7865

Train epoch 84
[E84B0  |   1280/50000 (  3%) ] Loss: 0.0217 top1= 99.1406
[E84B10 |  14080/50000 ( 28%) ] Loss: 0.0366 top1= 98.8281
[E84B20 |  26880/50000 ( 54%) ] Loss: 0.0228 top1= 99.4531
[E84B30 |  39680/50000 ( 79%) ] Loss: 0.0197 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2204 top1= 71.5946


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9589 top1= 46.0837


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8135 top1= 48.0869

Train epoch 85
[E85B0  |   1280/50000 (  3%) ] Loss: 0.0189 top1= 99.5312
[E85B10 |  14080/50000 ( 28%) ] Loss: 0.0283 top1= 99.1406
[E85B20 |  26880/50000 ( 54%) ] Loss: 0.0209 top1= 99.2188
[E85B30 |  39680/50000 ( 79%) ] Loss: 0.0186 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2421 top1= 71.9351


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8694 top1= 46.1739


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2647 top1= 47.9968

Train epoch 86
[E86B0  |   1280/50000 (  3%) ] Loss: 0.0159 top1= 99.4531
[E86B10 |  14080/50000 ( 28%) ] Loss: 0.0307 top1= 99.0625
[E86B20 |  26880/50000 ( 54%) ] Loss: 0.0174 top1= 99.5312
[E86B30 |  39680/50000 ( 79%) ] Loss: 0.0167 top1= 99.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2740 top1= 71.8650


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4366 top1= 45.6530


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3775 top1= 48.0569

Train epoch 87
[E87B0  |   1280/50000 (  3%) ] Loss: 0.0212 top1= 99.4531
[E87B10 |  14080/50000 ( 28%) ] Loss: 0.0243 top1= 99.2969
[E87B20 |  26880/50000 ( 54%) ] Loss: 0.0171 top1= 99.4531
[E87B30 |  39680/50000 ( 79%) ] Loss: 0.0213 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3173 top1= 71.7648


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.6275 top1= 46.0337


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2954 top1= 48.0970

Train epoch 88
[E88B0  |   1280/50000 (  3%) ] Loss: 0.0197 top1= 99.1406
[E88B10 |  14080/50000 ( 28%) ] Loss: 0.0214 top1= 99.2969
[E88B20 |  26880/50000 ( 54%) ] Loss: 0.0223 top1= 99.1406
[E88B30 |  39680/50000 ( 79%) ] Loss: 0.0169 top1= 99.2969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2947 top1= 72.4459


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.6970 top1= 45.6430


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5265 top1= 48.1671

Train epoch 89
[E89B0  |   1280/50000 (  3%) ] Loss: 0.0209 top1= 99.4531
[E89B10 |  14080/50000 ( 28%) ] Loss: 0.0243 top1= 99.1406
[E89B20 |  26880/50000 ( 54%) ] Loss: 0.0224 top1= 99.0625
[E89B30 |  39680/50000 ( 79%) ] Loss: 0.0133 top1= 99.6094

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3355 top1= 72.3958


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5183 top1= 46.0236


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9422 top1= 47.8265

Train epoch 90
[E90B0  |   1280/50000 (  3%) ] Loss: 0.0135 top1= 99.6875
[E90B10 |  14080/50000 ( 28%) ] Loss: 0.0208 top1= 99.2969
[E90B20 |  26880/50000 ( 54%) ] Loss: 0.0216 top1= 99.2969
[E90B30 |  39680/50000 ( 79%) ] Loss: 0.0180 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3944 top1= 71.7448


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3779 top1= 45.6430


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9318 top1= 48.2472

Train epoch 91
[E91B0  |   1280/50000 (  3%) ] Loss: 0.0101 top1= 99.6875
[E91B10 |  14080/50000 ( 28%) ] Loss: 0.0151 top1= 99.5312
[E91B20 |  26880/50000 ( 54%) ] Loss: 0.0196 top1= 99.4531
[E91B30 |  39680/50000 ( 79%) ] Loss: 0.0155 top1= 99.2969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4109 top1= 71.7248


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7348 top1= 46.0337


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2075 top1= 47.7163

Train epoch 92
[E92B0  |   1280/50000 (  3%) ] Loss: 0.0098 top1= 99.8438
[E92B10 |  14080/50000 ( 28%) ] Loss: 0.0235 top1= 99.2969
[E92B20 |  26880/50000 ( 54%) ] Loss: 0.0166 top1= 99.6094
[E92B30 |  39680/50000 ( 79%) ] Loss: 0.0267 top1= 99.2969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4228 top1= 72.2456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8919 top1= 46.1939


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.8046 top1= 48.2272

Train epoch 93
[E93B0  |   1280/50000 (  3%) ] Loss: 0.0116 top1= 99.7656
[E93B10 |  14080/50000 ( 28%) ] Loss: 0.0197 top1= 99.4531
[E93B20 |  26880/50000 ( 54%) ] Loss: 0.0139 top1= 99.3750
[E93B30 |  39680/50000 ( 79%) ] Loss: 0.0143 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4464 top1= 72.1354


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4873 top1= 46.5946


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5371 top1= 48.0970

Train epoch 94
[E94B0  |   1280/50000 (  3%) ] Loss: 0.0276 top1= 99.1406
[E94B10 |  14080/50000 ( 28%) ] Loss: 0.0237 top1= 99.0625
[E94B20 |  26880/50000 ( 54%) ] Loss: 0.0157 top1= 99.6094
[E94B30 |  39680/50000 ( 79%) ] Loss: 0.0133 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4128 top1= 72.6162


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7083 top1= 46.2540


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2998 top1= 48.3373

Train epoch 95
[E95B0  |   1280/50000 (  3%) ] Loss: 0.0151 top1= 99.5312
[E95B10 |  14080/50000 ( 28%) ] Loss: 0.0162 top1= 99.4531
[E95B20 |  26880/50000 ( 54%) ] Loss: 0.0153 top1= 99.6875
[E95B30 |  39680/50000 ( 79%) ] Loss: 0.0122 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4309 top1= 72.7764


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0353 top1= 46.1538


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.4878 top1= 48.7881

Train epoch 96
[E96B0  |   1280/50000 (  3%) ] Loss: 0.0110 top1= 99.6094
[E96B10 |  14080/50000 ( 28%) ] Loss: 0.0213 top1= 99.1406
[E96B20 |  26880/50000 ( 54%) ] Loss: 0.0152 top1= 99.3750
[E96B30 |  39680/50000 ( 79%) ] Loss: 0.0115 top1= 99.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4655 top1= 72.6562


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7780 top1= 46.7348


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5499 top1= 48.5477

Train epoch 97
[E97B0  |   1280/50000 (  3%) ] Loss: 0.0115 top1= 99.6094
[E97B10 |  14080/50000 ( 28%) ] Loss: 0.0148 top1= 99.6094
[E97B20 |  26880/50000 ( 54%) ] Loss: 0.0115 top1= 99.5312
[E97B30 |  39680/50000 ( 79%) ] Loss: 0.0109 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.5123 top1= 72.2857


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9778 top1= 46.7348


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.9119 top1= 48.4375

Train epoch 98
[E98B0  |   1280/50000 (  3%) ] Loss: 0.0192 top1= 99.5312
[E98B10 |  14080/50000 ( 28%) ] Loss: 0.0125 top1= 99.6094
[E98B20 |  26880/50000 ( 54%) ] Loss: 0.0114 top1= 99.7656
[E98B30 |  39680/50000 ( 79%) ] Loss: 0.0063 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4803 top1= 72.5260


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5876 top1= 46.0737


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.8455 top1= 48.3474

Train epoch 99
[E99B0  |   1280/50000 (  3%) ] Loss: 0.0067 top1= 99.6875
[E99B10 |  14080/50000 ( 28%) ] Loss: 0.0143 top1= 99.6094
[E99B20 |  26880/50000 ( 54%) ] Loss: 0.0204 top1= 99.3750
[E99B30 |  39680/50000 ( 79%) ] Loss: 0.0056 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.5336 top1= 72.5461


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3540 top1= 46.4443


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.9852 top1= 48.7079

Train epoch 100
[E100B0  |   1280/50000 (  3%) ] Loss: 0.0082 top1= 99.6875
[E100B10 |  14080/50000 ( 28%) ] Loss: 0.0080 top1= 99.8438
[E100B20 |  26880/50000 ( 54%) ] Loss: 0.0110 top1= 99.6875
[E100B30 |  39680/50000 ( 79%) ] Loss: 0.0051 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.5256 top1= 72.5661


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6175 top1= 46.2841


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.6059 top1= 49.0785

