
=== Start adding workers ===
=> Add worker SGDMWorker(index=0, momentum=0.9)
=> Add worker SGDMWorker(index=1, momentum=0.9)
=> Add worker SGDMWorker(index=2, momentum=0.9)
=> Add worker SGDMWorker(index=3, momentum=0.9)
=> Add worker SGDMWorker(index=4, momentum=0.9)
=> Add worker SGDMWorker(index=5, momentum=0.9)
=> Add worker SGDMWorker(index=6, momentum=0.9)
=> Add worker SGDMWorker(index=7, momentum=0.9)
=> Add worker SGDMWorker(index=8, momentum=0.9)
=> Add worker SGDMWorker(index=9, momentum=0.9)

=== Start adding graph ===
<codes.graph_utils.Dumbbell object at 0x7f293806f6d0>

Train epoch 1
[E 1B0  |    320/60000 (  1%) ] Loss: 2.3027 top1= 10.3125

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


[E 1B10 |   3520/60000 (  6%) ] Loss: 1.0548 top1= 63.1250
[E 1B20 |   6720/60000 ( 11%) ] Loss: 0.3872 top1= 87.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5928 top1= 82.4619


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4667 top1= 49.3389


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7384 top1= 44.4211

Train epoch 2
[E 2B0  |    320/60000 (  1%) ] Loss: 0.3257 top1= 90.0000
[E 2B10 |   3520/60000 (  6%) ] Loss: 0.2359 top1= 92.5000
[E 2B20 |   6720/60000 ( 11%) ] Loss: 0.2521 top1= 91.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4399 top1= 87.0693


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1078 top1= 53.2452


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2822 top1= 48.5677

Train epoch 3
[E 3B0  |    320/60000 (  1%) ] Loss: 0.1937 top1= 95.3125
[E 3B10 |   3520/60000 (  6%) ] Loss: 0.1372 top1= 95.3125
[E 3B20 |   6720/60000 ( 11%) ] Loss: 0.1246 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3675 top1= 88.5917


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7679 top1= 58.1430


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0022 top1= 52.6442

Train epoch 4
[E 4B0  |    320/60000 (  1%) ] Loss: 0.1366 top1= 97.1875
[E 4B10 |   3520/60000 (  6%) ] Loss: 0.0782 top1= 98.1250
[E 4B20 |   6720/60000 ( 11%) ] Loss: 0.0821 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3436 top1= 89.3129


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7061 top1= 60.2464


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7379 top1= 55.8894

Train epoch 5
[E 5B0  |    320/60000 (  1%) ] Loss: 0.1033 top1= 98.1250
[E 5B10 |   3520/60000 (  6%) ] Loss: 0.0443 top1= 98.7500
[E 5B20 |   6720/60000 ( 11%) ] Loss: 0.0536 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3256 top1= 89.9239


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6070 top1= 62.4299


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6355 top1= 58.3133

Train epoch 6
[E 6B0  |    320/60000 (  1%) ] Loss: 0.0803 top1= 97.8125
[E 6B10 |   3520/60000 (  6%) ] Loss: 0.0549 top1= 98.1250
[E 6B20 |   6720/60000 ( 11%) ] Loss: 0.0863 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3518 top1= 88.7420


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6113 top1= 64.1727


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6480 top1= 58.8942

Train epoch 7
[E 7B0  |    320/60000 (  1%) ] Loss: 0.1018 top1= 95.9375
[E 7B10 |   3520/60000 (  6%) ] Loss: 0.0774 top1= 97.1875
[E 7B20 |   6720/60000 ( 11%) ] Loss: 0.0458 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3068 top1= 90.5248


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5752 top1= 65.3345


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6548 top1= 56.6306

Train epoch 8
[E 8B0  |    320/60000 (  1%) ] Loss: 0.0443 top1= 99.0625
[E 8B10 |   3520/60000 (  6%) ] Loss: 0.0383 top1= 99.0625
[E 8B20 |   6720/60000 ( 11%) ] Loss: 0.0295 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3011 top1= 90.6350


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4860 top1= 67.3177


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6200 top1= 59.5853

Train epoch 9
[E 9B0  |    320/60000 (  1%) ] Loss: 0.0374 top1= 98.7500
[E 9B10 |   3520/60000 (  6%) ] Loss: 0.0318 top1= 99.3750
[E 9B20 |   6720/60000 ( 11%) ] Loss: 0.0274 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3082 top1= 90.2644


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5849 top1= 67.3377


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1427 top1= 68.1791

Train epoch 10
[E10B0  |    320/60000 (  1%) ] Loss: 0.0283 top1= 99.6875
[E10B10 |   3520/60000 (  6%) ] Loss: 0.0175 top1= 99.6875
[E10B20 |   6720/60000 ( 11%) ] Loss: 0.0183 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2912 top1= 91.2159


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4756 top1= 68.0288


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0997 top1= 70.2224

Train epoch 11
[E11B0  |    320/60000 (  1%) ] Loss: 0.0149 top1=100.0000
[E11B10 |   3520/60000 (  6%) ] Loss: 0.0099 top1=100.0000
[E11B20 |   6720/60000 ( 11%) ] Loss: 0.0195 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2804 top1= 91.6266


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2314 top1= 70.8233


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1006 top1= 71.2640

Train epoch 12
[E12B0  |    320/60000 (  1%) ] Loss: 0.0079 top1=100.0000
[E12B10 |   3520/60000 (  6%) ] Loss: 0.0222 top1= 98.7500
[E12B20 |   6720/60000 ( 11%) ] Loss: 0.0145 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2831 top1= 91.6767


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9679 top1= 75.8013


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1765 top1= 71.0537

Train epoch 13
[E13B0  |    320/60000 (  1%) ] Loss: 0.0084 top1= 99.6875
[E13B10 |   3520/60000 (  6%) ] Loss: 0.0056 top1=100.0000
[E13B20 |   6720/60000 ( 11%) ] Loss: 0.0045 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2740 top1= 92.0172


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9294 top1= 76.8329


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0206 top1= 75.0000

Train epoch 14
[E14B0  |    320/60000 (  1%) ] Loss: 0.0042 top1=100.0000
[E14B10 |   3520/60000 (  6%) ] Loss: 0.0168 top1= 99.3750
[E14B20 |   6720/60000 ( 11%) ] Loss: 0.0038 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2716 top1= 92.4179


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8516 top1= 78.4655


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9317 top1= 76.4724

Train epoch 15
[E15B0  |    320/60000 (  1%) ] Loss: 0.0044 top1=100.0000
[E15B10 |   3520/60000 (  6%) ] Loss: 0.0091 top1= 99.6875
[E15B20 |   6720/60000 ( 11%) ] Loss: 0.0132 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2674 top1= 92.6482


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8309 top1= 79.3269


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6939 top1= 81.6907

Train epoch 16
[E16B0  |    320/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E16B10 |   3520/60000 (  6%) ] Loss: 0.0032 top1=100.0000
[E16B20 |   6720/60000 ( 11%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2667 top1= 92.8085


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8000 top1= 80.1382


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7246 top1= 81.8409

Train epoch 17
[E17B0  |    320/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E17B10 |   3520/60000 (  6%) ] Loss: 0.0034 top1=100.0000
[E17B20 |   6720/60000 ( 11%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2693 top1= 92.7384


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7543 top1= 81.4303


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7965 top1= 80.8393

Train epoch 18
[E18B0  |    320/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E18B10 |   3520/60000 (  6%) ] Loss: 0.0028 top1=100.0000
[E18B20 |   6720/60000 ( 11%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2727 top1= 92.7484


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7194 top1= 82.6022


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8101 top1= 80.8093

Train epoch 19
[E19B0  |    320/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E19B10 |   3520/60000 (  6%) ] Loss: 0.0021 top1=100.0000
[E19B20 |   6720/60000 ( 11%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2745 top1= 92.8486


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7055 top1= 83.1530


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7716 top1= 81.6707

Train epoch 20
[E20B0  |    320/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E20B10 |   3520/60000 (  6%) ] Loss: 0.0018 top1=100.0000
[E20B20 |   6720/60000 ( 11%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2755 top1= 92.9587


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7057 top1= 83.3634


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7253 top1= 82.6623

Train epoch 21
[E21B0  |    320/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E21B10 |   3520/60000 (  6%) ] Loss: 0.0017 top1=100.0000
[E21B20 |   6720/60000 ( 11%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2768 top1= 92.9988


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6992 top1= 83.7139


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6945 top1= 83.4135

Train epoch 22
[E22B0  |    320/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E22B10 |   3520/60000 (  6%) ] Loss: 0.0015 top1=100.0000
[E22B20 |   6720/60000 ( 11%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2783 top1= 93.0589


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6842 top1= 84.1747


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6796 top1= 83.8742

Train epoch 23
[E23B0  |    320/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E23B10 |   3520/60000 (  6%) ] Loss: 0.0014 top1=100.0000
[E23B20 |   6720/60000 ( 11%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2797 top1= 93.0489


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6687 top1= 84.6254


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6693 top1= 84.2849

Train epoch 24
[E24B0  |    320/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E24B10 |   3520/60000 (  6%) ] Loss: 0.0013 top1=100.0000
[E24B20 |   6720/60000 ( 11%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2812 top1= 93.0889


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6554 top1= 84.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6580 top1= 84.7356

Train epoch 25
[E25B0  |    320/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E25B10 |   3520/60000 (  6%) ] Loss: 0.0013 top1=100.0000
[E25B20 |   6720/60000 ( 11%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2825 top1= 93.1390


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6450 top1= 85.2664


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6465 top1= 85.0962

Train epoch 26
[E26B0  |    320/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E26B10 |   3520/60000 (  6%) ] Loss: 0.0012 top1=100.0000
[E26B20 |   6720/60000 ( 11%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2837 top1= 93.1791


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6348 top1= 85.6170


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6369 top1= 85.3666

Train epoch 27
[E27B0  |    320/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E27B10 |   3520/60000 (  6%) ] Loss: 0.0011 top1=100.0000
[E27B20 |   6720/60000 ( 11%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2850 top1= 93.2091


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6257 top1= 85.8874


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6277 top1= 85.6370

Train epoch 28
[E28B0  |    320/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E28B10 |   3520/60000 (  6%) ] Loss: 0.0011 top1=100.0000
[E28B20 |   6720/60000 ( 11%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2862 top1= 93.2192


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6166 top1= 86.2179


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6186 top1= 85.9375

Train epoch 29
[E29B0  |    320/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E29B10 |   3520/60000 (  6%) ] Loss: 0.0010 top1=100.0000
[E29B20 |   6720/60000 ( 11%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2874 top1= 93.2392


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6084 top1= 86.4784


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6113 top1= 86.1579

Train epoch 30
[E30B0  |    320/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E30B10 |   3520/60000 (  6%) ] Loss: 0.0010 top1=100.0000
[E30B20 |   6720/60000 ( 11%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2885 top1= 93.2392


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6007 top1= 86.6486


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6038 top1= 86.3482

