
=== 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 0x7f247f07f730>

Train epoch 1
[E 1B0  |    640/60000 (  1%) ] Loss: 2.3066 top1=  9.2188

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


[E 1B10 |   7040/60000 ( 12%) ] Loss: 1.1003 top1= 56.7188
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.6169 top1= 80.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8833 top1= 74.4391


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0002 top1= 45.7432


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4726 top1= 43.2192

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.4689 top1= 86.2500
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.2942 top1= 90.7812
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.2842 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7032 top1= 84.6955


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4347 top1= 49.5994


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8939 top1= 44.8618

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.2383 top1= 92.8125
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.1633 top1= 95.1562
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.2015 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6594 top1= 85.2364


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4772 top1= 49.8097


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0833 top1= 45.5729

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1739 top1= 94.6875
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.1667 top1= 95.4688
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.2129 top1= 93.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5588 top1= 86.8590


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1938 top1= 49.8998


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1014 top1= 45.7432

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.1806 top1= 94.6875
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.1334 top1= 95.9375
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.1756 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5179 top1= 87.8005


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1927 top1= 49.8498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3685 top1= 46.0136

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.1729 top1= 95.0000
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.1426 top1= 95.9375
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.1707 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4887 top1= 87.5701


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9225 top1= 50.0801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7827 top1= 46.2039

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.1659 top1= 95.4688
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.1434 top1= 95.7812
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.1925 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4641 top1= 87.6102


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9850 top1= 50.0801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4157 top1= 46.1338

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.1659 top1= 95.7812
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.1532 top1= 95.9375
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.1950 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4462 top1= 87.9507


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2863 top1= 50.0401


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7078 top1= 46.2039

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.1682 top1= 95.9375
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.1540 top1= 95.6250
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.2060 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4324 top1= 87.9507


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5320 top1= 50.0401


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8802 top1= 46.2440

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.1731 top1= 95.7812
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.1618 top1= 96.2500
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.2045 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4220 top1= 88.0709


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7275 top1= 50.0501


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.0499 top1= 46.2440

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.1730 top1= 96.2500
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.1584 top1= 96.0938
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.2115 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4180 top1= 87.9607


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8928 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2904 top1= 46.2340

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.1796 top1= 96.0938
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.1627 top1= 95.9375
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.2152 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4150 top1= 87.9607


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0300 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4445 top1= 46.2340

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.1830 top1= 95.9375
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.1647 top1= 95.9375
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.2184 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4124 top1= 87.9207


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1509 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5694 top1= 46.2340

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.1855 top1= 95.9375
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.1666 top1= 95.9375
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.2212 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4103 top1= 87.9006


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2542 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6795 top1= 46.2340

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.1878 top1= 95.9375
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.1684 top1= 95.9375
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.2240 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4086 top1= 87.8706


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3531 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7784 top1= 46.2440

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.1900 top1= 95.9375
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.1700 top1= 95.9375
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.2265 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4071 top1= 87.8606


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4376 top1= 50.0701


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8684 top1= 46.2440

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.1919 top1= 95.9375
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.1716 top1= 95.9375
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.2287 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4058 top1= 87.8405


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5146 top1= 50.0701


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9501 top1= 46.2340

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.1937 top1= 96.0938
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.1730 top1= 95.9375
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.2308 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4048 top1= 87.8606


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5868 top1= 50.0701


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0269 top1= 46.2340

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.1953 top1= 96.0938
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.1743 top1= 95.9375
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.2328 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4038 top1= 87.8305


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6552 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0974 top1= 46.2340

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.1969 top1= 96.0938
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.1755 top1= 95.9375
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.2347 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4029 top1= 87.7905


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.7173 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1646 top1= 46.2340

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.1983 top1= 96.0938
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.1767 top1= 95.9375
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.2364 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4021 top1= 87.8105


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.7767 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2270 top1= 46.2440

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.1997 top1= 96.0938
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.1778 top1= 95.9375
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.2380 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4015 top1= 87.7905


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8324 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2858 top1= 46.2440

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.2009 top1= 96.0938
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.1788 top1= 95.7812
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.2396 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4008 top1= 87.7604


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8850 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3418 top1= 46.2340

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.2021 top1= 96.0938
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.1799 top1= 95.7812
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.2411 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4003 top1= 87.7404


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9349 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3947 top1= 46.2340

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.2033 top1= 96.0938
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.1808 top1= 95.7812
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.2425 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3998 top1= 87.7204


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9826 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.4455 top1= 46.2340

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.2044 top1= 96.0938
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.1818 top1= 95.7812
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.2438 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3993 top1= 87.7003


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.0289 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.4941 top1= 46.2340

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.2055 top1= 96.0938
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.1827 top1= 95.7812
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.2451 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3989 top1= 87.6803


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.0718 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5404 top1= 46.2440

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.2065 top1= 96.0938
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.1835 top1= 95.7812
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.2463 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3985 top1= 87.6703


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1136 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5851 top1= 46.2440

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.2075 top1= 96.0938
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.1843 top1= 95.7812
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.2475 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3981 top1= 87.6603


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1538 top1= 50.0701


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.6281 top1= 46.2440

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.2085 top1= 96.0938
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.1851 top1= 95.7812
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.2487 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3978 top1= 87.6502


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1915 top1= 50.0701


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.6691 top1= 46.2440

