
=== 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 0x7fcfe87ef6d0>

Train epoch 1
[E 1B0  |    640/60000 (  1%) ] Loss: 2.3007 top1=  9.6875

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


[E 1B10 |   7040/60000 ( 12%) ] Loss: 1.3825 top1= 54.8438
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.8196 top1= 76.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3655 top1= 77.7143


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1203 top1= 48.7079


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9864 top1= 43.2792

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.5061 top1= 84.0625
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.3439 top1= 89.0625
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.3089 top1= 91.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0385 top1= 81.9111


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8535 top1= 49.4491


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6324 top1= 44.5513

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.2769 top1= 90.9375
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.2487 top1= 91.4062
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.2480 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9138 top1= 82.4720


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1321 top1= 49.7596


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9384 top1= 44.8518

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.2297 top1= 92.6562
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.1700 top1= 94.2188
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.1901 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8267 top1= 83.4135


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5611 top1= 49.8798


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4733 top1= 45.1222

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.1736 top1= 94.5312
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.1849 top1= 93.9062
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.1725 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8196 top1= 83.1931


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5115 top1= 49.9800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2798 top1= 45.3626

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.1675 top1= 95.3125
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.1507 top1= 94.5312
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.1661 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7797 top1= 84.5453


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5054 top1= 50.0701


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2746 top1= 45.7632

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.1635 top1= 95.7812
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.1389 top1= 95.0000
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.1464 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7455 top1= 84.8658


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6917 top1= 50.1502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4704 top1= 45.8734

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.1481 top1= 95.6250
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.1267 top1= 95.9375
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.1316 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7352 top1= 85.0761


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6793 top1= 50.2003


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3764 top1= 46.0337

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.1419 top1= 95.6250
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.1126 top1= 96.0938
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.1395 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7188 top1= 85.5068


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6513 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3925 top1= 46.1438

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.1298 top1= 96.0938
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.1059 top1= 96.7188
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.1058 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6935 top1= 86.0877


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8218 top1= 50.3005


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5438 top1= 46.2941

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.1054 top1= 96.8750
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0992 top1= 96.8750
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0911 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6928 top1= 85.9075


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7751 top1= 50.3405


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5023 top1= 46.2941

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.1014 top1= 97.0312
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.1154 top1= 96.7188
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.1012 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6843 top1= 86.2580


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7482 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5649 top1= 46.5044

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0933 top1= 97.9688
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0888 top1= 96.7188
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0867 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6670 top1= 86.1879


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8796 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6826 top1= 46.4443

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.1068 top1= 97.1875
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0802 top1= 97.3438
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0765 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6653 top1= 86.1979


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8219 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5944 top1= 46.5345

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0920 top1= 96.8750
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0759 top1= 97.3438
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0735 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6598 top1= 86.4884


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7864 top1= 50.4407


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6559 top1= 46.6346

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0845 top1= 97.9688
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0670 top1= 97.8125
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0639 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6393 top1= 86.8990


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9438 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7624 top1= 46.6747

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0852 top1= 97.8125
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0672 top1= 97.3438
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0673 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6498 top1= 86.1579


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9047 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7647 top1= 46.7548

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0808 top1= 98.1250
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0741 top1= 97.1875
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0547 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6355 top1= 86.8890


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8664 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7711 top1= 46.8450

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0758 top1= 97.5000
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0567 top1= 97.8125
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0479 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6229 top1= 86.2981


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0415 top1= 50.5108


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9543 top1= 46.7949

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0671 top1= 98.4375
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0475 top1= 98.2812
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0475 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6215 top1= 86.6486


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0017 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8310 top1= 46.9351

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0726 top1= 98.1250
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0545 top1= 98.2812
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0497 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6194 top1= 87.0793


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9581 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8332 top1= 46.9752

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0622 top1= 98.1250
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0530 top1= 97.9688
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0402 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6033 top1= 86.7087


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0896 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0377 top1= 47.0353

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0562 top1= 98.2812
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0445 top1= 98.2812
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0353 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5996 top1= 87.0393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1082 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0017 top1= 47.0553

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0607 top1= 97.9688
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0459 top1= 98.2812
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0499 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6070 top1= 86.7588


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0728 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9686 top1= 47.0553

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0532 top1= 98.5938
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0365 top1= 98.9062
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0310 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5898 top1= 86.8490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2155 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1502 top1= 47.1054

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0480 top1= 98.7500
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0330 top1= 98.9062
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0284 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5883 top1= 86.2380


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1478 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1340 top1= 47.1655

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0521 top1= 98.1250
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0281 top1= 99.0625
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0256 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5936 top1= 86.8790


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2077 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0934 top1= 47.1955

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0509 top1= 98.1250
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0328 top1= 99.0625
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0228 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5856 top1= 85.9776


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2725 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3189 top1= 47.2155

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0394 top1= 99.0625
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0302 top1= 99.0625
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0240 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5887 top1= 85.5469


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2456 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3175 top1= 47.2456

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0408 top1= 99.0625
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0265 top1= 99.2188
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0228 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5826 top1= 86.2380


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2725 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2793 top1= 47.2356

