
=== 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)
=> Add worker SGDMWorker(index=10, momentum=0.9)
=> Add worker SGDMWorker(index=11, momentum=0.9)
=> Add worker SGDMWorker(index=12, momentum=0.9)
=> Add worker SGDMWorker(index=13, momentum=0.9)
=> Add worker SGDMWorker(index=14, momentum=0.9)
=> Add worker SGDMWorker(index=15, momentum=0.9)
=> Add worker SGDMWorker(index=16, momentum=0.9)
=> Add worker SGDMWorker(index=17, momentum=0.9)
=> Add worker SGDMWorker(index=18, momentum=0.9)
=> Add worker SGDMWorker(index=19, momentum=0.9)

=== Start adding graph ===
<codes.graph_utils.Dumbbell object at 0x7f3aba34c250>

Train epoch 1
[E 1B0  |    640/60000 (  1%) ] Loss: 2.3066 top1=  9.2188

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


[E 1B10 |   7040/60000 ( 12%) ] Loss: 1.0381 top1= 61.7188
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.3998 top1= 87.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7381 top1= 78.0148


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9986 top1= 49.2788


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6615 top1= 44.1506

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.2856 top1= 90.9375
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.1928 top1= 93.9062
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.1981 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6872 top1= 83.9443


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5641 top1= 49.8798


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3537 top1= 45.7532

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.1606 top1= 94.5312
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.1088 top1= 97.0312
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.1258 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6252 top1= 84.6554


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4688 top1= 50.1502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4735 top1= 46.1038

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1191 top1= 96.7188
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.0796 top1= 98.1250
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.0834 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5746 top1= 85.3966


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5903 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4647 top1= 46.3942

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.0837 top1= 97.9688
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.0642 top1= 98.1250
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.0587 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5390 top1= 85.6470


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7318 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4933 top1= 46.6146

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0602 top1= 98.9062
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0462 top1= 98.7500
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0478 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5007 top1= 86.3482


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8274 top1= 50.5108


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5778 top1= 46.7248

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0444 top1= 99.2188
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0323 top1= 99.2188
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0421 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4722 top1= 87.0793


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9807 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5368 top1= 46.8049

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0351 top1= 99.2188
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0241 top1= 99.5312
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0277 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4549 top1= 86.5986


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9903 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8618 top1= 46.8249

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0334 top1= 98.9062
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0189 top1= 99.6875
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0188 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4409 top1= 86.6787


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9923 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1987 top1= 46.9050

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0183 top1= 99.5312
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0129 top1=100.0000
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0210 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4614 top1= 85.2664


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8737 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4658 top1= 46.9151

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0209 top1= 99.3750
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0122 top1= 99.8438
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0109 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4414 top1= 85.8173


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9711 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6655 top1= 46.9651

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0071 top1= 99.8438
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0086 top1=100.0000
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0110 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4277 top1= 86.6987


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0981 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6842 top1= 47.1554

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0052 top1=100.0000
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0049 top1=100.0000
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0192 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4176 top1= 86.7989


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3354 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4609 top1= 47.1454

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0040 top1=100.0000
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0036 top1=100.0000
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0079 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3836 top1= 88.3514


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.6420 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5476 top1= 46.7849

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0145 top1= 99.5312
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0035 top1=100.0000
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0082 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3866 top1= 88.0208


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8493 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1626 top1= 46.9651

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0033 top1=100.0000
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0089 top1= 99.6875
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0087 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4079 top1= 86.6286


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0037 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4725 top1= 47.0653

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0058 top1= 99.8438
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0034 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4050 top1= 86.7087


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1495 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6151 top1= 47.2356

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0019 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4070 top1= 86.5284


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2663 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8364 top1= 47.2356

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0014 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3974 top1= 86.8690


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3800 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.0324 top1= 47.2356

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0012 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3840 top1= 87.4199


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4902 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1717 top1= 47.2256

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0011 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3783 top1= 87.6302


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5956 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2610 top1= 47.2756

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0011 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3780 top1= 87.6102


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6903 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3533 top1= 47.2957

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0009 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3775 top1= 87.6302


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.7741 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4665 top1= 47.2957

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0007 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3771 top1= 87.6102


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8566 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5806 top1= 47.3057

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0007 top1=100.0000
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3772 top1= 87.6302


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9365 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6712 top1= 47.2957

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0006 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3774 top1= 87.6302


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.0105 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7542 top1= 47.2857

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0006 top1=100.0000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3773 top1= 87.6402


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.0785 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8302 top1= 47.2857

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0005 top1=100.0000
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3775 top1= 87.6102


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1441 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9020 top1= 47.2857

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0005 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3773 top1= 87.6202


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2071 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9684 top1= 47.2857

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0005 top1=100.0000
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3778 top1= 87.5901


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2649 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0323 top1= 47.2857

