
=== 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 BitFlippingWorker
=> Add worker BitFlippingWorker

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f362a0c17f0>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.2959 top1= 10.0000

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([4, 8, 8, 6, 9], device='cuda:0')
Worker 1 has targets: tensor([5, 3, 6, 0, 9], device='cuda:0')
Worker 2 has targets: tensor([2, 9, 9, 3, 1], device='cuda:0')
Worker 3 has targets: tensor([6, 9, 8, 1, 2], device='cuda:0')
Worker 4 has targets: tensor([5, 8, 9, 1, 8], device='cuda:0')
Worker 5 has targets: tensor([6, 7, 5, 2, 3], device='cuda:0')
Worker 6 has targets: tensor([3, 2, 8, 7, 9], device='cuda:0')
Worker 7 has targets: tensor([3, 8, 7, 8, 7], device='cuda:0')
Worker 8 has targets: tensor([8, 0, 2, 4, 8], device='cuda:0')
Worker 9 has targets: tensor([5, 3, 4, 6, 3], device='cuda:0')
Worker 10 has targets: tensor([4, 8, 8, 6, 9], device='cuda:0')
Worker 11 has targets: tensor([5, 3, 6, 0, 9], device='cuda:0')


[E 1B10 |   4224/60000 (  7%) ] Loss: 2.1801 top1= 36.8750
[E 1B20 |   8064/60000 ( 13%) ] Loss: 1.9639 top1= 52.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3057 top1= 73.2372


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3065 top1= 73.0369


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3115 top1= 72.6462

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 1.2920 top1= 68.1250
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.7987 top1= 76.2500
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.7024 top1= 82.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5761 top1= 84.5954


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5824 top1= 84.4251


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5962 top1= 83.4836

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.6646 top1= 80.9375
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.5526 top1= 85.0000
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.5793 top1= 85.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5378 top1= 85.5469


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5517 top1= 84.9760


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5584 top1= 84.6254

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.5879 top1= 84.6875
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.5084 top1= 84.0625
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.5580 top1= 86.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5396 top1= 85.3466


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5582 top1= 84.4752


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5570 top1= 84.7756

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.5812 top1= 83.4375
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.4926 top1= 84.3750
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.5436 top1= 86.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5386 top1= 85.2063


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5596 top1= 84.2248


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5551 top1= 84.7155

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.5719 top1= 83.1250
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.4882 top1= 85.0000
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.5378 top1= 85.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5276 top1= 85.7372


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5507 top1= 84.4651


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5415 top1= 85.3365

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.5574 top1= 84.6875
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.4753 top1= 87.1875
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.5355 top1= 85.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5218 top1= 86.1579


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5503 top1= 84.6454


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5291 top1= 86.0176

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.5437 top1= 84.6875
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.4650 top1= 87.8125
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.5313 top1= 85.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5248 top1= 86.2881


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5520 top1= 84.7356


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5303 top1= 86.2280

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.5322 top1= 85.6250
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.4487 top1= 87.5000
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.5300 top1= 86.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5288 top1= 86.1679


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5569 top1= 84.5753


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5346 top1= 86.1278

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.5243 top1= 85.6250
[E10B10 |   4224/60000 (  7%) ] Loss: 0.4441 top1= 88.1250
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.5213 top1= 86.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5283 top1= 86.2380


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5534 top1= 84.9058


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5366 top1= 86.1378

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.5158 top1= 86.2500
[E11B10 |   4224/60000 (  7%) ] Loss: 0.4368 top1= 88.1250
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.5199 top1= 86.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5301 top1= 86.5885


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5544 top1= 84.9860


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5400 top1= 86.4183

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.5145 top1= 86.5625
[E12B10 |   4224/60000 (  7%) ] Loss: 0.4358 top1= 87.8125
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.5192 top1= 87.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5339 top1= 86.6587


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5553 top1= 85.2764


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5432 top1= 86.3882

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.5103 top1= 85.9375
[E13B10 |   4224/60000 (  7%) ] Loss: 0.4235 top1= 88.7500
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.5188 top1= 86.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5282 top1= 86.9892


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5485 top1= 85.6270


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5391 top1= 86.6687

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.5032 top1= 86.8750
[E14B10 |   4224/60000 (  7%) ] Loss: 0.4221 top1= 89.0625
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.5171 top1= 86.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5295 top1= 86.8990


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5458 top1= 85.9876


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5434 top1= 86.3882

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.5028 top1= 86.5625
[E15B10 |   4224/60000 (  7%) ] Loss: 0.4285 top1= 89.6875
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.5142 top1= 86.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5291 top1= 87.0593


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5474 top1= 85.8373


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5413 top1= 86.7788

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.4957 top1= 86.2500
[E16B10 |   4224/60000 (  7%) ] Loss: 0.4258 top1= 90.6250
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.5121 top1= 87.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5294 top1= 86.7788


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5492 top1= 85.9175


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5383 top1= 86.4683

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.4955 top1= 86.5625
[E17B10 |   4224/60000 (  7%) ] Loss: 0.4258 top1= 90.3125
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.5097 top1= 86.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5305 top1= 86.8490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5507 top1= 85.7973


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5414 top1= 86.4183

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.4927 top1= 86.8750
[E18B10 |   4224/60000 (  7%) ] Loss: 0.4285 top1= 90.3125
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.5052 top1= 86.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5311 top1= 86.8890


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5545 top1= 85.7672


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5372 top1= 86.6587

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.4952 top1= 86.5625
[E19B10 |   4224/60000 (  7%) ] Loss: 0.4216 top1= 90.3125
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.4988 top1= 86.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5323 top1= 86.6386


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5536 top1= 85.4567


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5404 top1= 86.3081

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.4961 top1= 85.9375
[E20B10 |   4224/60000 (  7%) ] Loss: 0.4268 top1= 90.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.4927 top1= 86.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5310 top1= 86.7788


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5527 top1= 85.4067


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5392 top1= 86.4884

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.4892 top1= 86.2500
[E21B10 |   4224/60000 (  7%) ] Loss: 0.4251 top1= 89.3750
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.4959 top1= 87.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5347 top1= 86.5485


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5593 top1= 85.3566


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5398 top1= 86.4283

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.4941 top1= 85.9375
[E22B10 |   4224/60000 (  7%) ] Loss: 0.4234 top1= 90.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.4896 top1= 87.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5317 top1= 86.6987


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5546 top1= 85.4968


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5386 top1= 86.7288

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.4899 top1= 85.6250
[E23B10 |   4224/60000 (  7%) ] Loss: 0.4183 top1= 89.3750
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.4873 top1= 87.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5323 top1= 86.8089


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5560 top1= 85.6170


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5397 top1= 86.5485

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.4908 top1= 86.2500
[E24B10 |   4224/60000 (  7%) ] Loss: 0.4204 top1= 88.7500
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.4844 top1= 87.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5332 top1= 86.4283


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5540 top1= 85.4267


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5436 top1= 86.1178

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.4909 top1= 86.2500
[E25B10 |   4224/60000 (  7%) ] Loss: 0.4130 top1= 90.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.4821 top1= 88.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5313 top1= 86.6587


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5544 top1= 85.4367


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5389 top1= 86.4683

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.4838 top1= 85.9375
[E26B10 |   4224/60000 (  7%) ] Loss: 0.4102 top1= 90.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.4820 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5301 top1= 86.6186


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5528 top1= 85.4267


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5396 top1= 86.6086

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.4892 top1= 86.2500
[E27B10 |   4224/60000 (  7%) ] Loss: 0.4063 top1= 90.6250
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.4797 top1= 87.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5274 top1= 86.5885


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5513 top1= 85.4567


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5365 top1= 86.5184

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.4873 top1= 85.9375
[E28B10 |   4224/60000 (  7%) ] Loss: 0.4085 top1= 89.3750
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.4806 top1= 88.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5294 top1= 86.5986


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5508 top1= 85.4868


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5402 top1= 86.3782

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.4881 top1= 85.9375
[E29B10 |   4224/60000 (  7%) ] Loss: 0.4092 top1= 90.6250
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.4845 top1= 87.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5326 top1= 86.2881


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5550 top1= 85.0561


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5475 top1= 85.8674

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.4960 top1= 85.6250
[E30B10 |   4224/60000 (  7%) ] Loss: 0.4091 top1= 89.3750
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.4842 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5300 top1= 86.5485


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5454 top1= 85.8173


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5470 top1= 86.0176

