
=== 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 0x7f71812346d0>

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: 1.8907 top1= 50.0000
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.8088 top1= 75.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4183 top1= 87.6102


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4457 top1= 86.9291


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4627 top1= 85.9175

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.5093 top1= 83.9062
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.4508 top1= 84.5312
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.3702 top1= 87.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2741 top1= 92.3778


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2794 top1= 91.8570


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2953 top1= 91.5465

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.2639 top1= 92.1875
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.2387 top1= 92.0312
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.2311 top1= 92.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2250 top1= 93.5096


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2265 top1= 93.3293


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2385 top1= 92.8986

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1777 top1= 95.1562
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.1603 top1= 95.4688
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.1570 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1952 top1= 94.1907


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2036 top1= 93.8201


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1974 top1= 94.1206

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.1277 top1= 96.5625
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.1139 top1= 97.0312
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.1131 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1729 top1= 94.7616


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1865 top1= 94.2808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1710 top1= 94.8417

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0926 top1= 97.8125
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0783 top1= 97.9688
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0767 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1603 top1= 95.2023


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1763 top1= 94.7616


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1609 top1= 95.1122

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0669 top1= 98.2812
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0569 top1= 98.5938
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0612 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1587 top1= 95.3025


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1816 top1= 94.7015


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1603 top1= 95.1823

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0504 top1= 98.9062
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0449 top1= 99.0625
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0460 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1547 top1= 95.5028


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1679 top1= 95.1222


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1563 top1= 95.4928

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0357 top1= 99.6875
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0310 top1= 99.5312
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0408 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1533 top1= 95.5829


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1816 top1= 94.9519


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1586 top1= 95.3826

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0300 top1= 99.2188
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0167 top1=100.0000
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0262 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1508 top1= 95.7432


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1788 top1= 95.0521


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1589 top1= 95.5729

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0254 top1= 99.5312
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0213 top1= 99.6875
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0388 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1494 top1= 95.8333


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1646 top1= 95.4127


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1625 top1= 95.4627

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0209 top1= 99.6875
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0228 top1= 99.3750
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0150 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1527 top1= 95.8634


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2030 top1= 94.4712


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1770 top1= 95.4427

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0308 top1= 98.9062
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0305 top1= 99.2188
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0204 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1443 top1= 95.9936


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1957 top1= 94.6615


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1593 top1= 95.6530

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0238 top1= 99.0625
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0213 top1= 99.3750
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0238 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1370 top1= 96.1939


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1509 top1= 95.8734


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1433 top1= 96.1438

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0134 top1= 99.5312
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0122 top1= 99.8438
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0207 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1502 top1= 96.0337


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1726 top1= 95.5429


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1508 top1= 96.1639

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0158 top1= 99.6875
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0116 top1= 99.5312
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0120 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1498 top1= 96.1338


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1566 top1= 96.0537


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1555 top1= 96.1839

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0077 top1= 99.8438
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0058 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0084 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1425 top1= 96.2440


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1472 top1= 96.0537


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1458 top1= 96.2841

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0063 top1= 99.8438
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0034 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0046 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1405 top1= 96.3742


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1425 top1= 96.4243


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1424 top1= 96.3742

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0037 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0030 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1427 top1= 96.4042


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1440 top1= 96.3542


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1450 top1= 96.3642

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0028 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1447 top1= 96.3141


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1460 top1= 96.3141


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1455 top1= 96.3542

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0022 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1458 top1= 96.3742


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1468 top1= 96.2340


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1473 top1= 96.3642

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0017 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1484 top1= 96.3642


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1481 top1= 96.2941


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1528 top1= 96.3442

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0016 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1489 top1= 96.3742


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1494 top1= 96.3341


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1511 top1= 96.3742

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1495 top1= 96.3542


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1508 top1= 96.3542


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1495 top1= 96.3442

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1512 top1= 96.3341


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1523 top1= 96.3442


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1512 top1= 96.3742

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1528 top1= 96.3642


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1537 top1= 96.3241


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1530 top1= 96.3642

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: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1540 top1= 96.3742


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1549 top1= 96.3341


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1541 top1= 96.3542

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=0.1552 top1= 96.3542


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1561 top1= 96.3442


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1553 top1= 96.3742

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0010 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1564 top1= 96.3742


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


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1564 top1= 96.3942

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=0.1575 top1= 96.3742


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1583 top1= 96.3341


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1576 top1= 96.4042

