
=== 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 0x7f5cebe4f250>

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: 1.4210 top1= 51.0938
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.8749 top1= 70.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3734 top1= 77.7845


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1436 top1= 48.4876


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9108 top1= 42.7183

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.5403 top1= 83.4375
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.3889 top1= 88.2812
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.3537 top1= 89.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0338 top1= 81.9511


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8506 top1= 49.4892


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6633 top1= 44.4511

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.2979 top1= 90.6250
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.2350 top1= 93.2812
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.2661 top1= 92.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9169 top1= 82.8726


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1835 top1= 49.6795


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0426 top1= 44.8117

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.2467 top1= 92.6562
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.1802 top1= 94.6875
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.2304 top1= 93.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8198 top1= 83.2432


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6105 top1= 49.8197


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6025 top1= 45.2424

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.2076 top1= 93.5938
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.1738 top1= 94.3750
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.2361 top1= 92.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8034 top1= 83.4836


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5229 top1= 49.8998


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3286 top1= 45.3025

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.2004 top1= 93.7500
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.1484 top1= 95.7812
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.1837 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7787 top1= 83.7139


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5599 top1= 50.0501


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3393 top1= 45.5729

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.1795 top1= 94.2188
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.1381 top1= 95.1562
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.1792 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7339 top1= 84.4451


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7400 top1= 50.1102


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5710 top1= 46.0036

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.1465 top1= 95.6250
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.1193 top1= 96.2500
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.1483 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7273 top1= 84.7155


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6755 top1= 50.1803


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4790 top1= 46.1238

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.1605 top1= 95.6250
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.1168 top1= 96.5625
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.1369 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7064 top1= 85.6971


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7044 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4849 top1= 46.2340

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.1286 top1= 96.2500
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.1011 top1= 97.1875
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.1198 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6812 top1= 85.6270


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8748 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6705 top1= 46.3842

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.1226 top1= 96.5625
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0942 top1= 97.0312
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.1260 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6791 top1= 85.9275


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7972 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5698 top1= 46.3842

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.1065 top1= 97.0312
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0871 top1= 97.3438
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0995 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6650 top1= 86.4483


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8005 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5530 top1= 46.5345

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.1233 top1= 95.9375
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0796 top1= 97.6562
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.1051 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6393 top1= 86.6186


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9525 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6951 top1= 46.5445

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0942 top1= 97.6562
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0788 top1= 97.9688
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0855 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6487 top1= 86.5585


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8607 top1= 50.4307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6453 top1= 46.5946

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0932 top1= 97.9688
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0687 top1= 97.8125
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0945 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6361 top1= 86.8590


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9065 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6636 top1= 46.6647

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0829 top1= 97.5000
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0645 top1= 98.1250
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0775 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6108 top1= 87.0393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0275 top1= 50.4407


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8453 top1= 46.6847

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0864 top1= 97.3438
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0560 top1= 98.1250
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0861 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6097 top1= 87.4900


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9359 top1= 50.4307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7517 top1= 46.7849

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0773 top1= 97.8125
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0529 top1= 98.2812
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0655 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6110 top1= 86.8590


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9842 top1= 50.5108


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7938 top1= 46.8550

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0690 top1= 98.1250
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0456 top1= 98.5938
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0616 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5854 top1= 87.4499


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1004 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9293 top1= 46.9451

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0719 top1= 97.9688
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0526 top1= 98.1250
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0597 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5850 top1= 87.7003


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0488 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8800 top1= 46.9351

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0739 top1= 98.4375
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0461 top1= 98.1250
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0590 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5878 top1= 87.0893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0165 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9454 top1= 46.8349

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0678 top1= 97.9688
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0386 top1= 98.7500
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0480 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5640 top1= 87.6002


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1649 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0276 top1= 47.0353

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0609 top1= 98.5938
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0383 top1= 98.9062
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0567 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5611 top1= 87.8606


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1529 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0408 top1= 47.0052

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0567 top1= 98.9062
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0323 top1= 99.0625
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0534 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5655 top1= 87.2296


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0967 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0233 top1= 47.0553

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0637 top1= 98.7500
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0319 top1= 99.2188
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0405 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5469 top1= 87.7103


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2474 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1846 top1= 47.0853

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0436 top1= 99.0625
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0393 top1= 98.9062
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0374 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5480 top1= 87.6803


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2482 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1852 top1= 47.1154

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0475 top1= 98.9062
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0281 top1= 99.0625
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0402 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5491 top1= 87.3197


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2169 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1557 top1= 47.0954

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0422 top1= 99.3750
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0236 top1= 99.5312
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0322 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5307 top1= 87.8706


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3234 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3073 top1= 47.1454

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0425 top1= 98.9062
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0382 top1= 98.4375
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0531 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5371 top1= 87.6603


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3265 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2728 top1= 47.1454

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0490 top1= 99.0625
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0204 top1= 99.5312
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0349 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5375 top1= 87.6603


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3321 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2790 top1= 47.1955

