
=== 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 0x7f4bcd0dc2b0>

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: 1.4208 top1= 51.0938
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.8669 top1= 70.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3710 top1= 77.2736


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1485 top1= 48.4776


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9550 top1= 42.3678

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.5379 top1= 83.2812
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.3809 top1= 87.8125
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.3570 top1= 89.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0300 top1= 81.7808


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8315 top1= 49.4992


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6707 top1= 44.4611

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2966 top1= 90.6250
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.2366 top1= 93.2812
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.2751 top1= 91.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9162 top1= 82.8526


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1713 top1= 49.6695


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0483 top1= 44.8217

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.2500 top1= 92.1875
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1781 top1= 94.3750
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.2267 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8173 top1= 83.3634


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5426 top1= 49.7997


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5973 top1= 45.1923

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1981 top1= 94.0625
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1732 top1= 94.6875
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.2270 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8050 top1= 83.5537


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5164 top1= 49.9399


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2852 top1= 45.3025

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.2003 top1= 93.4375
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1440 top1= 96.0938
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1901 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7797 top1= 83.9944


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5518 top1= 50.0801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3183 top1= 45.7833

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1686 top1= 94.8438
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1428 top1= 95.0000
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1754 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7329 top1= 84.6454


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7240 top1= 50.1502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5812 top1= 46.0537

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1448 top1= 96.2500
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1182 top1= 96.2500
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1468 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7289 top1= 84.7957


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6622 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4862 top1= 46.1038

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1593 top1= 95.4688
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1157 top1= 96.0938
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1395 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7064 top1= 85.8574


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7184 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5036 top1= 46.2540

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1289 top1= 96.4062
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.1032 top1= 97.3438
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1236 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6819 top1= 85.7873


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8654 top1= 50.3005


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6736 top1= 46.3642

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1247 top1= 96.7188
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0941 top1= 96.8750
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1236 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6796 top1= 86.0477


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7637 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5630 top1= 46.3442

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1074 top1= 97.3438
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0865 top1= 97.1875
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1026 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6655 top1= 86.4583


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8098 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5315 top1= 46.5645

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1269 top1= 95.9375
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0799 top1= 97.3438
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1002 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6422 top1= 86.7087


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9322 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6869 top1= 46.5144

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0973 top1= 97.9688
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0780 top1= 97.6562
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0797 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6475 top1= 86.6687


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8612 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6426 top1= 46.6146

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0920 top1= 97.6562
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0666 top1= 97.6562
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0936 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6345 top1= 86.9391


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9108 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6715 top1= 46.7248

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0828 top1= 97.8125
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0647 top1= 98.1250
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0762 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6161 top1= 86.8990


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0152 top1= 50.4307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8459 top1= 46.6947

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0851 top1= 97.8125
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0551 top1= 98.1250
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0728 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6129 top1= 87.4399


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9121 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7508 top1= 46.7748

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0797 top1= 97.8125
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0515 top1= 98.4375
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0665 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6143 top1= 86.8189


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9671 top1= 50.5108


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8207 top1= 46.8550

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0721 top1= 98.1250
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0456 top1= 98.5938
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0589 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5899 top1= 87.2997


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0791 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9325 top1= 46.9151

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0673 top1= 98.1250
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0528 top1= 97.8125
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0590 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5884 top1= 87.7504


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0459 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8827 top1= 46.9451

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0731 top1= 97.9688
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0490 top1= 98.2812
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0610 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5927 top1= 86.6787


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0112 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9405 top1= 46.8650

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0711 top1= 97.8125
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0388 top1= 98.5938
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0449 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5687 top1= 87.5601


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1677 top1= 50.5308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0190 top1= 46.9952

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0617 top1= 98.2812
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0400 top1= 98.7500
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0549 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5677 top1= 87.8405


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1380 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0433 top1= 46.9952

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0597 top1= 98.5938
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0318 top1= 98.9062
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0533 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5716 top1= 87.0092


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1098 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0152 top1= 47.0252

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0612 top1= 98.5938
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0294 top1= 99.3750
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0397 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5517 top1= 87.5701


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2632 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1783 top1= 47.0252

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0435 top1= 99.0625
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0400 top1= 98.9062
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0372 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5529 top1= 87.5601


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2626 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1769 top1= 47.0853

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0449 top1= 98.9062
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0301 top1= 98.7500
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0370 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5536 top1= 87.2095


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2284 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1229 top1= 47.1254

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0415 top1= 99.3750
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0256 top1= 99.5312
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0303 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5361 top1= 87.7404


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3391 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3000 top1= 47.1054

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0402 top1= 99.0625
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0363 top1= 98.5938
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0511 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5393 top1= 87.4900


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3488 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3132 top1= 47.1354

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0524 top1= 98.5938
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0206 top1= 99.5312
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0331 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5414 top1= 87.2596


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3475 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2927 top1= 47.2155

