
=== 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 0x7f85fcac7250>

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: 1.4695 top1= 48.1250
[E 1B20 |  13440/60000 ( 22%) ] Loss: 1.0865 top1= 62.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4594 top1= 80.2384


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7121 top1= 48.3073


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5526 top1= 43.1791

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.6743 top1= 79.3750
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.5812 top1= 80.1562
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.4431 top1= 85.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0850 top1= 82.3017


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3537 top1= 49.3790


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1389 top1= 44.1907

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.3531 top1= 88.9062
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.2981 top1= 90.1562
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.3401 top1= 89.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9625 top1= 82.3618


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7573 top1= 49.5793


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4518 top1= 44.7416

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.2701 top1= 92.3438
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.2242 top1= 92.9688
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.2631 top1= 92.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8804 top1= 82.5321


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1158 top1= 49.7496


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7302 top1= 45.1923

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.2098 top1= 94.2188
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.1708 top1= 95.1562
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.2267 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8417 top1= 82.7724


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1259 top1= 49.8898


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8954 top1= 45.4327

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.1789 top1= 95.0000
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.1517 top1= 95.4688
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.1948 top1= 93.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8074 top1= 84.1947


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1820 top1= 50.0401


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0045 top1= 45.7632

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.1699 top1= 95.3125
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.2022 top1= 92.8125
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.2034 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8148 top1= 83.9744


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2179 top1= 50.1102


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6505 top1= 45.9535

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.1559 top1= 95.4688
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.1223 top1= 96.5625
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.1376 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7788 top1= 83.4135


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2595 top1= 50.2103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9537 top1= 46.0837

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.1494 top1= 95.7812
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.1665 top1= 95.3125
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.1591 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7576 top1= 84.5252


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0488 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1071 top1= 46.2139

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.1167 top1= 97.5000
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.1007 top1= 97.5000
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.1234 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7252 top1= 84.7857


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2974 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3054 top1= 46.3542

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.1116 top1= 97.3438
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0890 top1= 97.3438
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.1174 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7169 top1= 85.3866


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3314 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2688 top1= 46.4243

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.1014 top1= 97.6562
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0852 top1= 97.5000
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0970 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6972 top1= 85.6771


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4030 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2939 top1= 46.5144

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.1077 top1= 96.8750
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0786 top1= 97.5000
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0984 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6797 top1= 86.1278


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5284 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3863 top1= 46.6046

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0930 top1= 97.6562
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0745 top1= 98.1250
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0794 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6785 top1= 86.2680


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5205 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3565 top1= 46.6346

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0889 top1= 97.8125
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0664 top1= 98.1250
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0801 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6665 top1= 86.0276


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5512 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4208 top1= 46.7248

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0802 top1= 98.1250
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0662 top1= 97.6562
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0744 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6453 top1= 86.3281


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6888 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5631 top1= 46.7748

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0719 top1= 98.4375
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0534 top1= 98.2812
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0725 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6443 top1= 86.6386


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6380 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5089 top1= 46.8249

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0743 top1= 98.1250
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0590 top1= 97.8125
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0651 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6410 top1= 86.2179


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6645 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5917 top1= 46.9551

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0724 top1= 98.2812
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0523 top1= 98.5938
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0599 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6175 top1= 86.8389


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8195 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6973 top1= 46.9551

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0683 top1= 98.5938
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0528 top1= 98.1250
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0545 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6172 top1= 87.1595


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7736 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6480 top1= 47.0052

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0662 top1= 98.4375
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0443 top1= 98.1250
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0541 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6188 top1= 86.2981


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7663 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6804 top1= 47.0453

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0588 top1= 98.2812
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0398 top1= 99.0625
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0495 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5954 top1= 86.9892


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9154 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8246 top1= 47.0553

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0538 top1= 98.5938
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0377 top1= 99.0625
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0534 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5979 top1= 87.1494


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9136 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8200 top1= 47.1154

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0518 top1= 98.9062
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0354 top1= 98.9062
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0487 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5952 top1= 86.6286


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9054 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8026 top1= 47.1655

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0571 top1= 98.7500
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0329 top1= 99.2188
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0418 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5770 top1= 87.0192


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0460 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9830 top1= 47.1354

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0425 top1= 98.7500
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0341 top1= 99.0625
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0379 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5790 top1= 87.0893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0412 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9716 top1= 47.1755

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0432 top1= 98.7500
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0279 top1= 99.3750
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0377 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5746 top1= 87.0893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0376 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9647 top1= 47.2656

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0401 top1= 99.0625
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0279 top1= 99.2188
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0329 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5603 top1= 87.2596


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1331 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1155 top1= 47.2155

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0350 top1= 99.2188
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0284 top1= 98.9062
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0434 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5646 top1= 87.3297


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1077 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1249 top1= 47.1755

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0368 top1= 99.0625
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0234 top1= 99.3750
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0342 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5625 top1= 87.1194


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1171 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1109 top1= 47.3157

