
=== 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 0x7f639fdee6d0>

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: 2.1254 top1= 32.0312
[E 1B20 |  13440/60000 ( 22%) ] Loss: 1.7713 top1= 53.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1769 top1= 77.7444


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1716 top1= 79.1967


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1939 top1= 74.6294

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 1.2477 top1= 65.1562
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.9416 top1= 73.7500
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.8088 top1= 75.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5253 top1= 87.6302


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5175 top1= 87.8506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5384 top1= 87.0393

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.6247 top1= 80.6250
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.6341 top1= 80.0000
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.5603 top1= 82.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3932 top1= 89.4331


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3927 top1= 89.4732


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3973 top1= 89.2929

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.4611 top1= 87.0312
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.4300 top1= 87.5000
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.4703 top1= 84.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3414 top1= 90.5449


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3435 top1= 90.4247


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3442 top1= 90.3345

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.3992 top1= 88.1250
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.3914 top1= 86.7188
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.3874 top1= 87.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3119 top1= 91.2059


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3130 top1= 91.1759


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3127 top1= 91.1659

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.3131 top1= 90.4688
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.3350 top1= 89.5312
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.3671 top1= 87.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2851 top1= 91.8670


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2865 top1= 91.7668


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2866 top1= 91.9071

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.2802 top1= 90.9375
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.3041 top1= 91.5625
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.3193 top1= 91.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2700 top1= 92.1875


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2718 top1= 92.1875


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2706 top1= 92.2576

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.2745 top1= 91.7188
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.2673 top1= 92.1875
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.2979 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2527 top1= 92.7784


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2537 top1= 92.6783


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2543 top1= 92.6583

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.2483 top1= 92.8125
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.2477 top1= 92.9688
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.2798 top1= 91.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2387 top1= 93.0789


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2386 top1= 93.0889


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2412 top1= 93.0489

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.2345 top1= 93.7500
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.2179 top1= 93.9062
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.2427 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2263 top1= 93.4295


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2283 top1= 93.4095


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2273 top1= 93.3694

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.2060 top1= 93.9062
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.1922 top1= 94.5312
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.2312 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2176 top1= 93.6899


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2196 top1= 93.4796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2209 top1= 93.4796

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.2165 top1= 93.1250
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.1914 top1= 94.8438
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.2115 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2058 top1= 94.0605


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2081 top1= 93.9103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2060 top1= 94.0905

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.1861 top1= 93.9062
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.1931 top1= 94.2188
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.2080 top1= 93.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1987 top1= 94.2308


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2027 top1= 94.0304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1982 top1= 94.2208

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.1564 top1= 96.2500
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.1772 top1= 94.6875
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.1800 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1923 top1= 94.3910


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1919 top1= 94.2508


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1956 top1= 94.3710

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.1524 top1= 96.4062
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.1613 top1= 95.1562
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.1785 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1865 top1= 94.5112


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1876 top1= 94.4111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1882 top1= 94.3910

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.1617 top1= 95.1562
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.1468 top1= 96.8750
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.1586 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1786 top1= 94.6314


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1817 top1= 94.4211


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1785 top1= 94.7015

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.1336 top1= 96.5625
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.1179 top1= 97.0312
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.1493 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1726 top1= 94.8718


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1753 top1= 94.8217


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1737 top1= 94.8117

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.1607 top1= 94.6875
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.1323 top1= 96.4062
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.1398 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1681 top1= 94.8918


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1699 top1= 94.8518


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1693 top1= 94.8518

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.1299 top1= 96.0938
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.1249 top1= 96.5625
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.1239 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1619 top1= 95.0321


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1643 top1= 94.9720


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1622 top1= 95.0521

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.1101 top1= 97.5000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.1208 top1= 96.4062
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.1155 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1598 top1= 95.0821


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1620 top1= 95.0921


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1604 top1= 95.1322

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.1164 top1= 96.8750
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.1085 top1= 96.5625
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.1228 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1532 top1= 95.3125


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1560 top1= 95.1823


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1541 top1= 95.3926

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.1159 top1= 97.0312
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.1005 top1= 96.7188
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.1189 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1508 top1= 95.3526


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1550 top1= 95.1022


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1501 top1= 95.3325

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0988 top1= 97.3438
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0845 top1= 97.6562
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0939 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1468 top1= 95.4627


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1490 top1= 95.4127


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1468 top1= 95.4127

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0907 top1= 97.8125
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0972 top1= 97.1875
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0928 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1443 top1= 95.6130


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1462 top1= 95.4928


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1446 top1= 95.5429

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.1054 top1= 97.1875
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0860 top1= 97.9688
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0918 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1399 top1= 95.5629


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1420 top1= 95.5829


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1404 top1= 95.6130

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0805 top1= 98.1250
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0715 top1= 97.9688
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0760 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1371 top1= 95.7933


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1404 top1= 95.6631


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1363 top1= 95.8033

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0902 top1= 97.8125
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0827 top1= 97.5000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0880 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1344 top1= 95.8133


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1355 top1= 95.7332


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1350 top1= 95.8233

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0845 top1= 98.1250
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0761 top1= 98.1250
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0831 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1305 top1= 95.9535


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1322 top1= 95.7833


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1306 top1= 95.9836

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0526 top1= 99.5312
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0449 top1= 99.8438
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0503 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1294 top1= 96.0337


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1316 top1= 95.9235


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1299 top1= 95.9635

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0973 top1= 97.1875
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.1023 top1= 97.0312
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0775 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1284 top1= 96.0437


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1305 top1= 95.9736


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1280 top1= 96.0337

