
=== 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 0x7f47993226d0>

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: 2.1287 top1= 32.5000
[E 1B20 |  13440/60000 ( 22%) ] Loss: 1.7901 top1= 52.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2026 top1= 77.5641


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1973 top1= 78.6558


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2196 top1= 75.0300

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 1.2777 top1= 62.9688
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.9388 top1= 73.9062
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.7880 top1= 77.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5272 top1= 87.3097


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5147 top1= 87.5801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5444 top1= 87.0793

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.6251 top1= 80.6250
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.6250 top1= 79.6875
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.5736 top1= 80.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3982 top1= 89.2728


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3948 top1= 89.1627


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4053 top1= 88.9623

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.4467 top1= 86.0938
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.4340 top1= 87.5000
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.4849 top1= 84.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3458 top1= 90.1843


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3514 top1= 89.9339


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3489 top1= 90.0641

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.3885 top1= 87.6562
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.3987 top1= 87.5000
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.3788 top1= 87.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3168 top1= 90.8654


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3222 top1= 90.6350


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3154 top1= 90.8654

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.3168 top1= 89.6875
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.3228 top1= 90.6250
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.3550 top1= 88.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2916 top1= 91.5765


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2950 top1= 91.5765


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2909 top1= 91.5966

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.2631 top1= 92.3438
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.3043 top1= 90.4688
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.3064 top1= 91.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2777 top1= 91.7969


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2827 top1= 91.7568


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2746 top1= 91.8770

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.2525 top1= 93.5938
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.2634 top1= 93.1250
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.2843 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2627 top1= 92.2776


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2668 top1= 92.1875


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2605 top1= 92.3778

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.2371 top1= 92.8125
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.2436 top1= 93.1250
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.2652 top1= 91.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2489 top1= 92.5982


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2489 top1= 92.6282


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2512 top1= 92.4479

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.2153 top1= 93.5938
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.2102 top1= 94.3750
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.2423 top1= 92.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2390 top1= 92.8986


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2422 top1= 92.7384


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2391 top1= 92.7083

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.1892 top1= 93.9062
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.1903 top1= 93.4375
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.2234 top1= 93.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2309 top1= 92.9788


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2362 top1= 92.8686


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2368 top1= 92.8486

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.1989 top1= 93.5938
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.1811 top1= 95.1562
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.1919 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2199 top1= 93.4195


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2221 top1= 93.4896


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2197 top1= 93.2091

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.1647 top1= 95.4688
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.1775 top1= 94.3750
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.1916 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2153 top1= 93.7099


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2231 top1= 93.3994


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2127 top1= 93.4395

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.1391 top1= 97.1875
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.1502 top1= 95.3125
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.1928 top1= 93.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2121 top1= 93.6999


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2103 top1= 93.7500


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2153 top1= 93.4796

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.1433 top1= 96.2500
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.1612 top1= 95.6250
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.1728 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2052 top1= 93.8702


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2053 top1= 93.8301


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2076 top1= 93.5797

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.1426 top1= 96.2500
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.1285 top1= 96.7188
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.1367 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2004 top1= 93.9704


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2023 top1= 93.8702


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2005 top1= 93.8001

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.1138 top1= 97.0312
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0975 top1= 97.3438
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.1359 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1960 top1= 94.2408


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1957 top1= 94.2308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1988 top1= 94.0104

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.1616 top1= 95.7812
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.1166 top1= 96.2500
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.1292 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1922 top1= 94.1807


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1919 top1= 94.1506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1947 top1= 94.0304

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.1207 top1= 97.0312
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.1058 top1= 97.1875
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0979 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1879 top1= 94.3510


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1865 top1= 94.3910


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1892 top1= 94.2708

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0942 top1= 97.9688
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0812 top1= 97.9688
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0859 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1892 top1= 94.3810


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1868 top1= 94.3309


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1920 top1= 94.0204

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.1023 top1= 97.5000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0926 top1= 97.3438
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0952 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1822 top1= 94.6214


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1831 top1= 94.4712


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1816 top1= 94.5212

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0939 top1= 97.8125
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0862 top1= 98.2812
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0991 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1816 top1= 94.4111


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1821 top1= 94.5713


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1826 top1= 94.3810

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0890 top1= 97.9688
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0712 top1= 98.2812
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0749 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1784 top1= 94.6314


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1747 top1= 94.7316


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1839 top1= 94.2608

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0902 top1= 97.8125
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0809 top1= 98.1250
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0732 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1769 top1= 94.8317


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1761 top1= 94.7516


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1791 top1= 94.6314

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0911 top1= 97.6562
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0687 top1= 98.7500
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0866 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1745 top1= 94.8317


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1734 top1= 94.8217


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1751 top1= 94.6514

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0866 top1= 97.9688
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0449 top1= 98.9062
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0563 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1764 top1= 94.7216


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1747 top1= 94.9519


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1794 top1= 94.5212

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.1070 top1= 97.5000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0712 top1= 97.5000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0802 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1714 top1= 94.9319


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1669 top1= 95.0821


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1767 top1= 94.7216

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0881 top1= 97.8125
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0772 top1= 97.9688
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0649 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1684 top1= 94.9920


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1692 top1= 95.0621


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1680 top1= 94.8718

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0537 top1= 98.9062
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0341 top1= 99.2188
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0398 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1722 top1= 94.9720


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1732 top1= 95.0120


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1757 top1= 94.6715

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.1102 top1= 97.6562
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0962 top1= 97.5000
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0763 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1688 top1= 95.0421


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1652 top1= 95.1823


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1712 top1= 94.9119

