
=== 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 0x7f7772dee6d0>

Train epoch 1
[E 1B0  |    640/60000 (  1%) ] Loss: 2.3080 top1=  8.4375

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


[E 1B10 |   7040/60000 ( 12%) ] Loss: 1.8915 top1= 50.1562
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.8095 top1= 75.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4195 top1= 87.6502


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4508 top1= 86.7288


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4585 top1= 86.0076

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.5127 top1= 84.5312
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.4494 top1= 83.7500
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.3702 top1= 87.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2739 top1= 92.2877


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2796 top1= 91.7368


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2944 top1= 91.5865

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.2610 top1= 92.0312
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.2384 top1= 92.3438
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.2283 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2261 top1= 93.4896


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2267 top1= 93.3093


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2419 top1= 92.7784

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1772 top1= 95.1562
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.1605 top1= 95.6250
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.1574 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1981 top1= 94.1106


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2073 top1= 93.5797


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1998 top1= 94.0004

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.1271 top1= 96.5625
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.1118 top1= 96.4062
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.1106 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1734 top1= 94.8017


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1870 top1= 94.3710


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1727 top1= 94.8618

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0949 top1= 97.5000
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0799 top1= 98.1250
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0774 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1628 top1= 95.0821


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1797 top1= 94.7616


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1649 top1= 94.9720

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0686 top1= 98.2812
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0549 top1= 98.5938
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0639 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1601 top1= 95.2825


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1762 top1= 94.9018


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1642 top1= 95.1723

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0499 top1= 99.0625
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0413 top1= 99.0625
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0453 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1541 top1= 95.6430


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1687 top1= 95.1122


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1568 top1= 95.4327

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0393 top1= 99.2188
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0281 top1= 99.5312
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0382 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1524 top1= 95.6130


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1746 top1= 95.1623


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1618 top1= 95.3926

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0310 top1= 99.3750
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0178 top1=100.0000
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0277 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1574 top1= 95.5228


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1709 top1= 95.1623


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1676 top1= 95.4728

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0289 top1= 99.2188
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0219 top1= 99.8438
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0263 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1542 top1= 95.7432


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1904 top1= 94.8618


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1569 top1= 95.8534

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0249 top1= 99.5312
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0196 top1= 99.5312
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0165 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1499 top1= 95.9335


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1936 top1= 94.7115


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1706 top1= 95.5829

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0283 top1= 99.3750
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0143 top1= 99.6875
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0198 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1434 top1= 95.9435


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1781 top1= 95.1723


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1489 top1= 95.9034

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0160 top1= 99.8438
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0215 top1= 99.5312
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0276 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1405 top1= 96.1138


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1464 top1= 95.8734


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1516 top1= 95.9535

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0167 top1= 99.6875
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0150 top1= 99.6875
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0250 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1542 top1= 95.9635


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1729 top1= 95.4427


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1502 top1= 96.2340

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0238 top1= 99.2188
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0120 top1= 99.6875
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0077 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1436 top1= 96.2340


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1479 top1= 96.1839


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1508 top1= 96.2540

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0064 top1=100.0000
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0066 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0057 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1426 top1= 96.2240


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1437 top1= 96.1038


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1478 top1= 96.1839

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0078 top1= 99.6875
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0033 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0065 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1411 top1= 96.3041


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1432 top1= 96.2740


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1436 top1= 96.3542

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0028 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0034 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1426 top1= 96.3041


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1444 top1= 96.3141


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1468 top1= 96.2841

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0028 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1455 top1= 96.3742


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1469 top1= 96.2440


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1468 top1= 96.3241

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0023 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1477 top1= 96.3842


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1484 top1= 96.2139


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1499 top1= 96.3341

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0020 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1495 top1= 96.3442


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1492 top1= 96.2640


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1533 top1= 96.3642

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0019 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1502 top1= 96.3642


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1507 top1= 96.2841


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1526 top1= 96.3742

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0018 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1507 top1= 96.3742


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1521 top1= 96.2841


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1510 top1= 96.3942

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0017 top1=100.0000
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1521 top1= 96.4243


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1534 top1= 96.2841


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1522 top1= 96.4243

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0014 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1536 top1= 96.4143


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1547 top1= 96.2941


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1539 top1= 96.4243

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0013 top1=100.0000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1550 top1= 96.4042


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1561 top1= 96.3041


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1552 top1= 96.4343

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0012 top1=100.0000
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1562 top1= 96.3942


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1572 top1= 96.3041


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1563 top1= 96.4143

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0011 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1574 top1= 96.4042


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1585 top1= 96.3041


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1575 top1= 96.4143

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0011 top1=100.0000
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1585 top1= 96.4042


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1595 top1= 96.3041


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1585 top1= 96.4343

