
=== 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 0x7fcf480999d0>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.3109 top1=  9.6875

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


[E 1B10 |   4224/60000 (  7%) ] Loss: 2.0524 top1= 31.2500
[E 1B20 |   8064/60000 ( 13%) ] Loss: 1.9591 top1= 25.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2964 top1= 34.2248


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3033 top1= 10.0962


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7173 top1= 33.2933

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 1.7133 top1= 37.8125
[E 2B10 |   4224/60000 (  7%) ] Loss: 1.5164 top1= 51.8750
[E 2B20 |   8064/60000 ( 13%) ] Loss: 1.4439 top1= 50.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.1475 top1= 43.2893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3019 top1= 19.5413


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6741 top1= 43.5697

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 1.3758 top1= 56.5625
[E 3B10 |   4224/60000 (  7%) ] Loss: 1.4156 top1= 55.3125
[E 3B20 |   8064/60000 ( 13%) ] Loss: 1.3969 top1= 53.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.1183 top1= 44.0304


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2992 top1= 10.8273


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7150 top1= 44.0905

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 1.3389 top1= 54.6875
[E 4B10 |   4224/60000 (  7%) ] Loss: 1.3954 top1= 52.5000
[E 4B20 |   8064/60000 ( 13%) ] Loss: 1.3622 top1= 51.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0386 top1= 43.8001


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2958 top1= 10.8674


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6413 top1= 44.2808

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 1.2553 top1= 51.8750
[E 5B10 |   4224/60000 (  7%) ] Loss: 1.0999 top1= 55.0000
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.8072 top1= 81.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4874 top1= 63.2312


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4515 top1= 46.1639


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4846 top1= 43.8702

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.6314 top1= 83.4375
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.6064 top1= 88.7500
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.5040 top1= 90.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3284 top1= 68.9103


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2357 top1= 48.1571


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2992 top1= 43.9804

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.5276 top1= 86.8750
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.5607 top1= 88.7500
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.4831 top1= 91.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3192 top1= 70.8634


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1742 top1= 48.1070


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2524 top1= 44.1306

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.5328 top1= 87.8125
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.5670 top1= 88.4375
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.4871 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3239 top1= 71.7849


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0739 top1= 47.7764


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2603 top1= 44.2208

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.5614 top1= 86.8750
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.5803 top1= 87.5000
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.4909 top1= 91.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3213 top1= 71.9151


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0433 top1= 47.7063


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2842 top1= 44.2808

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.5628 top1= 87.1875
[E10B10 |   4224/60000 (  7%) ] Loss: 0.5706 top1= 87.5000
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.4823 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3200 top1= 72.0954


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0390 top1= 47.8065


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2836 top1= 44.3810

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.5614 top1= 86.8750
[E11B10 |   4224/60000 (  7%) ] Loss: 0.5633 top1= 87.5000
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.4745 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3177 top1= 71.2841


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0384 top1= 47.8766


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2473 top1= 44.3510

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.5564 top1= 86.8750
[E12B10 |   4224/60000 (  7%) ] Loss: 0.5627 top1= 87.5000
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.4698 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3134 top1= 71.2841


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0369 top1= 47.8766


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2459 top1= 44.2808

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.5513 top1= 86.5625
[E13B10 |   4224/60000 (  7%) ] Loss: 0.5684 top1= 87.1875
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.4710 top1= 91.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3103 top1= 72.0052


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0335 top1= 47.9067


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2614 top1= 44.4511

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.5438 top1= 87.5000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.5647 top1= 87.1875
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.4740 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3125 top1= 71.5745


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0328 top1= 47.8866


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2537 top1= 44.3109

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.5472 top1= 87.5000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.5598 top1= 87.5000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.4710 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3127 top1= 72.0553


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0293 top1= 47.9067


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2525 top1= 44.4211

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.5466 top1= 86.8750
[E16B10 |   4224/60000 (  7%) ] Loss: 0.5637 top1= 87.8125
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.4690 top1= 91.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3115 top1= 72.0954


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0299 top1= 47.9167


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2409 top1= 44.5112

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.5447 top1= 87.1875
[E17B10 |   4224/60000 (  7%) ] Loss: 0.5592 top1= 87.5000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.4688 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3100 top1= 72.1655


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0292 top1= 47.8766


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2402 top1= 44.5312

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.5416 top1= 86.8750
[E18B10 |   4224/60000 (  7%) ] Loss: 0.5575 top1= 87.5000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.4690 top1= 91.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3092 top1= 72.3958


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0284 top1= 47.9267


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2214 top1= 44.6314

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.5352 top1= 87.5000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.5559 top1= 87.8125
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.4644 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3110 top1= 72.4459


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0292 top1= 47.9467


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2107 top1= 44.5713

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.5413 top1= 86.5625
[E20B10 |   4224/60000 (  7%) ] Loss: 0.5569 top1= 88.1250
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.4676 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3072 top1= 72.9868


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0304 top1= 47.9467


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2434 top1= 44.4912

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.5383 top1= 86.5625
[E21B10 |   4224/60000 (  7%) ] Loss: 0.5556 top1= 87.8125
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.4602 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3059 top1= 73.0569


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0319 top1= 48.0168


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2381 top1= 44.6715

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.5354 top1= 87.1875
[E22B10 |   4224/60000 (  7%) ] Loss: 0.5511 top1= 88.1250
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.4573 top1= 91.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3089 top1= 73.2272


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0312 top1= 48.0168


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2310 top1= 44.6514

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.5386 top1= 86.8750
[E23B10 |   4224/60000 (  7%) ] Loss: 0.5395 top1= 87.8125
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.4537 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3079 top1= 72.3357


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0339 top1= 47.9868


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2146 top1= 44.5212

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.5390 top1= 87.1875
[E24B10 |   4224/60000 (  7%) ] Loss: 0.5426 top1= 88.4375
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.4506 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3056 top1= 72.1254


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0345 top1= 48.0068


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2161 top1= 44.4712

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.5425 top1= 86.8750
[E25B10 |   4224/60000 (  7%) ] Loss: 0.5456 top1= 87.8125
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.4487 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3066 top1= 73.0970


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0335 top1= 48.0469


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2359 top1= 44.5413

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.5367 top1= 87.1875
[E26B10 |   4224/60000 (  7%) ] Loss: 0.5423 top1= 88.1250
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.4476 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3049 top1= 72.8265


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0337 top1= 48.0469


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2416 top1= 44.5212

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.5410 top1= 87.1875
[E27B10 |   4224/60000 (  7%) ] Loss: 0.5340 top1= 88.4375
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.4468 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3059 top1= 72.3458


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0337 top1= 48.0268


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2313 top1= 44.3309

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.5448 top1= 86.2500
[E28B10 |   4224/60000 (  7%) ] Loss: 0.5346 top1= 88.4375
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.4467 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3059 top1= 72.7664


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0336 top1= 48.0669


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2371 top1= 44.4211

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.5402 top1= 87.8125
[E29B10 |   4224/60000 (  7%) ] Loss: 0.5337 top1= 87.8125
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.4475 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3046 top1= 72.1254


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0351 top1= 48.0669


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2172 top1= 44.3610

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.5474 top1= 85.6250
[E30B10 |   4224/60000 (  7%) ] Loss: 0.5398 top1= 88.1250
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.4521 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3006 top1= 73.6078


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0347 top1= 48.0469


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2438 top1= 44.6514

