
=== 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)
=> Add worker BitFlippingWorker
=> Add worker BitFlippingWorker

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7fdae3ccd2b0>

Train epoch 1
[E 1B0  |    704/60000 (  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')
Worker 20 has targets: tensor([3, 2, 2, 4, 3], device='cuda:0')
Worker 21 has targets: tensor([8, 9, 7, 7, 9], device='cuda:0')


[E 1B10 |   7744/60000 ( 13%) ] Loss: 1.4178 top1= 51.7188
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.8555 top1= 72.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3728 top1= 77.4639


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1751 top1= 48.4876


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9120 top1= 42.5881

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.5200 top1= 84.3750
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.3860 top1= 87.8125
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.3575 top1= 89.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0329 top1= 81.7508


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8361 top1= 49.4992


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6505 top1= 44.4211

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2926 top1= 91.0938
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.2314 top1= 93.2812
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.2699 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9163 top1= 83.0929


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1855 top1= 49.6595


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0472 top1= 44.8618

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.2472 top1= 91.8750
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1805 top1= 94.3750
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.2242 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8186 top1= 83.4635


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5727 top1= 49.8498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5940 top1= 45.2324

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.2022 top1= 93.9062
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1754 top1= 94.8438
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.2269 top1= 92.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8030 top1= 83.3233


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5165 top1= 49.9199


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3321 top1= 45.3726

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1983 top1= 93.2812
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1457 top1= 95.7812
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1895 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7796 top1= 83.7139


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5598 top1= 50.0801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3396 top1= 45.6530

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1722 top1= 94.8438
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1414 top1= 95.4688
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1769 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7318 top1= 84.6554


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7429 top1= 50.1402


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5852 top1= 46.0236

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1486 top1= 96.0938
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1148 top1= 96.4062
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1463 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7280 top1= 84.8157


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6741 top1= 50.2003


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4827 top1= 46.1038

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1633 top1= 95.1562
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1162 top1= 96.4062
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1393 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7042 top1= 85.8373


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7092 top1= 50.2204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5109 top1= 46.2740

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1304 top1= 96.0938
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.1020 top1= 97.3438
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1238 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6794 top1= 85.8874


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8708 top1= 50.3405


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6763 top1= 46.3542

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1239 top1= 96.7188
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0938 top1= 97.0312
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1228 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6786 top1= 86.1278


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7727 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5640 top1= 46.3341

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1064 top1= 97.1875
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0861 top1= 97.3438
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1038 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6637 top1= 86.4583


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8098 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5366 top1= 46.5545

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1284 top1= 96.0938
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0817 top1= 97.3438
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1010 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6399 top1= 86.8590


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9238 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6929 top1= 46.5244

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0978 top1= 97.8125
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0764 top1= 97.6562
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0820 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6446 top1= 86.7688


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8644 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6664 top1= 46.5445

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0941 top1= 97.3438
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0663 top1= 97.8125
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0910 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6332 top1= 87.0192


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9147 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6770 top1= 46.7147

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0820 top1= 97.5000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0656 top1= 98.1250
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0745 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6129 top1= 87.1094


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0260 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8523 top1= 46.6947

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0870 top1= 97.5000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0553 top1= 98.1250
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0819 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6096 top1= 87.5100


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9224 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7623 top1= 46.7748

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0789 top1= 97.6562
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0515 top1= 98.4375
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0644 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6125 top1= 86.8690


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9653 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8113 top1= 46.8550

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0720 top1= 97.5000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0456 top1= 98.2812
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0585 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5874 top1= 87.3698


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0691 top1= 50.5108


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9189 top1= 46.9050

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0686 top1= 98.4375
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0515 top1= 97.9688
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0565 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5847 top1= 87.9908


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0589 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8873 top1= 46.9451

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0767 top1= 97.8125
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0510 top1= 98.4375
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0592 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5887 top1= 86.8790


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0041 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9361 top1= 46.8249

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0688 top1= 97.9688
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0398 top1= 98.2812
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0447 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5640 top1= 87.6502


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1474 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0286 top1= 46.9752

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0617 top1= 98.5938
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0454 top1= 98.7500
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0541 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5638 top1= 87.8305


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1416 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0518 top1= 47.0453

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0583 top1= 98.7500
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0321 top1= 98.9062
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0545 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5679 top1= 87.1094


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1046 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0128 top1= 47.0252

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0629 top1= 98.5938
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0284 top1= 99.3750
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0388 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5490 top1= 87.7704


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2316 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1803 top1= 47.0453

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0426 top1= 99.2188
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0392 top1= 98.9062
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0358 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5476 top1= 87.7905


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2729 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1654 top1= 47.1054

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0465 top1= 99.0625
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0295 top1= 98.7500
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0381 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5492 top1= 87.4499


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2372 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1334 top1= 47.1454

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0434 top1= 99.2188
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0238 top1= 99.5312
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0297 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5302 top1= 87.9908


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3295 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3123 top1= 47.1154

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0422 top1= 99.2188
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0371 top1= 98.9062
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0556 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5339 top1= 87.8305


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3573 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2999 top1= 47.1554

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0510 top1= 98.5938
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0208 top1= 99.3750
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0346 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5361 top1= 87.4900


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3428 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2771 top1= 47.2456

