
=== 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 0x7f9a741dd6d0>

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=0.4194 top1= 87.6202


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4504 top1= 86.7288


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4586 top1= 85.9776

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.5127 top1= 84.5312
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.4492 top1= 83.9062
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.3690 top1= 87.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2739 top1= 92.1775


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2787 top1= 91.7368


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2949 top1= 91.5865

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.2613 top1= 92.3438
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.2378 top1= 92.3438
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.2298 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2276 top1= 93.4095


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2273 top1= 93.2792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2436 top1= 92.6983

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1791 top1= 95.0000
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.1636 top1= 95.6250
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.1567 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1973 top1= 94.1206


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2067 top1= 93.6098


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1990 top1= 93.9904

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.1271 top1= 96.4062
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.1137 top1= 96.7188
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.1111 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1731 top1= 94.7716


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1870 top1= 94.3910


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1728 top1= 94.8317

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0924 top1= 97.3438
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0808 top1= 97.9688
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0774 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1627 top1= 95.1022


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1794 top1= 94.7115


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1656 top1= 95.0621

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0679 top1= 98.1250
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0546 top1= 98.7500
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0645 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1604 top1= 95.3125


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1778 top1= 94.8117


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1656 top1= 95.1222

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0497 top1= 99.0625
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0388 top1= 99.3750
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0483 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1531 top1= 95.6931


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1657 top1= 95.2424


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1549 top1= 95.5729

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0379 top1= 99.5312
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0269 top1= 99.8438
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0377 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1533 top1= 95.6430


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1895 top1= 94.7416


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1586 top1= 95.4227

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0353 top1= 99.3750
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0178 top1= 99.8438
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0271 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1568 top1= 95.6030


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1823 top1= 95.0321


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1651 top1= 95.4427

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0274 top1= 99.6875
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0202 top1= 99.8438
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0287 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1516 top1= 95.8233


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1829 top1= 95.0921


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1739 top1= 95.2925

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0251 top1= 99.5312
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0147 top1= 99.8438
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0176 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1518 top1= 95.8834


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2008 top1= 94.6915


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1643 top1= 95.6631

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0250 top1= 99.0625
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0243 top1= 99.2188
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0224 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1460 top1= 95.9034


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1782 top1= 95.0621


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1514 top1= 95.9335

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0212 top1= 99.5312
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0203 top1= 99.5312
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0187 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1437 top1= 96.0637


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1482 top1= 95.9635


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1560 top1= 95.8534

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0178 top1= 99.5312
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0116 top1= 99.6875
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0188 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1590 top1= 95.9435


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1857 top1= 95.2524


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1498 top1= 96.1839

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0206 top1= 99.2188
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0146 top1= 99.8438
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0095 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1408 top1= 96.3241


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1449 top1= 96.1238


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1533 top1= 96.1338

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0078 top1= 99.8438
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0049 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0059 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1421 top1= 96.3442


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1424 top1= 96.3241


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1507 top1= 96.1038

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0061 top1=100.0000
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0034 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0047 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1408 top1= 96.4042


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1403 top1= 96.3642


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1456 top1= 96.3642

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0034 top1=100.0000
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0029 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1448 top1= 96.3241


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1454 top1= 96.3241


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1499 top1= 96.2340

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0028 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1465 top1= 96.3742


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1472 top1= 96.3442


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1493 top1= 96.2640

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0027 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0024 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1476 top1= 96.3942


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1480 top1= 96.2941


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1496 top1= 96.2640

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0018 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1491 top1= 96.3542


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1491 top1= 96.3341


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1522 top1= 96.3041

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0018 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1509 top1= 96.3542


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1507 top1= 96.3642


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1556 top1= 96.3241

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0016 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1511 top1= 96.3942


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1521 top1= 96.3542


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1530 top1= 96.4042

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0016 top1=100.0000
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1523 top1= 96.4443


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1536 top1= 96.3742


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1524 top1= 96.4744

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1545 top1= 96.4443


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1549 top1= 96.3542


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1554 top1= 96.4443

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1554 top1= 96.4543


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1559 top1= 96.3542


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1559 top1= 96.4143

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1566 top1= 96.4343


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1572 top1= 96.3542


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1570 top1= 96.4343

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=0.1578 top1= 96.4243


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1583 top1= 96.3742


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1581 top1= 96.4443

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1589 top1= 96.4343


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1595 top1= 96.3642


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1591 top1= 96.4443

