
=== 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 0x7f87d64329d0>

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: 1.9726 top1= 35.0000
[E 1B20 |   8064/60000 ( 13%) ] Loss: 1.9018 top1= 36.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2811 top1= 41.7468


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3023 top1= 10.0962


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3493 top1= 41.8470

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 1.7829 top1= 46.5625
[E 2B10 |   4224/60000 (  7%) ] Loss: 1.7416 top1= 47.1875
[E 2B20 |   8064/60000 ( 13%) ] Loss: 1.7204 top1= 46.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2776 top1= 41.7969


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3408 top1= 41.8670

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 1.6668 top1= 51.8750
[E 3B10 |   4224/60000 (  7%) ] Loss: 1.6932 top1= 47.8125
[E 3B20 |   8064/60000 ( 13%) ] Loss: 1.7662 top1= 39.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2729 top1= 42.4079


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3861 top1= 42.4479

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 1.5955 top1= 55.6250
[E 4B10 |   4224/60000 (  7%) ] Loss: 1.6530 top1= 47.8125
[E 4B20 |   8064/60000 ( 13%) ] Loss: 1.7522 top1= 45.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2744 top1= 39.4431


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3084 top1= 40.0140

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 1.6524 top1= 53.7500
[E 5B10 |   4224/60000 (  7%) ] Loss: 1.6397 top1= 50.0000
[E 5B20 |   8064/60000 ( 13%) ] Loss: 1.6876 top1= 46.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2783 top1= 41.2961


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2142 top1= 41.7668

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 1.7060 top1= 51.8750
[E 6B10 |   4224/60000 (  7%) ] Loss: 1.6719 top1= 47.1875
[E 6B20 |   8064/60000 ( 13%) ] Loss: 1.6713 top1= 47.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2805 top1= 42.9287


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2021 top1= 42.3277

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 1.7763 top1= 46.2500
[E 7B10 |   4224/60000 (  7%) ] Loss: 1.6189 top1= 48.1250
[E 7B20 |   8064/60000 ( 13%) ] Loss: 1.7287 top1= 43.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2714 top1= 42.0673


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 10.0962


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3331 top1= 41.8870

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 1.5694 top1= 56.5625
[E 8B10 |   4224/60000 (  7%) ] Loss: 1.7724 top1= 41.2500
[E 8B20 |   8064/60000 ( 13%) ] Loss: 1.6941 top1= 45.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2743 top1= 42.1775


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 10.0962


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2733 top1= 42.7183

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 1.5754 top1= 57.5000
[E 9B10 |   4224/60000 (  7%) ] Loss: 1.6647 top1= 49.3750
[E 9B20 |   8064/60000 ( 13%) ] Loss: 1.6395 top1= 49.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2778 top1= 36.2079


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1907 top1= 38.6418

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 1.6959 top1= 50.3125
[E10B10 |   4224/60000 (  7%) ] Loss: 1.7900 top1= 43.1250
[E10B20 |   8064/60000 ( 13%) ] Loss: 1.7515 top1= 45.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2775 top1= 43.0288


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2321 top1= 41.8470

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 1.8119 top1= 41.2500
[E11B10 |   4224/60000 (  7%) ] Loss: 1.6596 top1= 48.7500
[E11B20 |   8064/60000 ( 13%) ] Loss: 1.7499 top1= 43.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2745 top1= 39.4030


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2556 top1= 41.3662

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 1.6470 top1= 51.8750
[E12B10 |   4224/60000 (  7%) ] Loss: 1.8114 top1= 42.8125
[E12B20 |   8064/60000 ( 13%) ] Loss: 1.7309 top1= 45.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2764 top1= 40.6951


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2371 top1= 42.5581

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 1.6513 top1= 51.8750
[E13B10 |   4224/60000 (  7%) ] Loss: 1.6598 top1= 48.1250
[E13B20 |   8064/60000 ( 13%) ] Loss: 1.6245 top1= 51.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2778 top1= 38.6819


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 10.0962


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1898 top1= 40.4948

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 1.7318 top1= 47.1875
[E14B10 |   4224/60000 (  7%) ] Loss: 1.7433 top1= 47.1875
[E14B20 |   8064/60000 ( 13%) ] Loss: 1.6529 top1= 49.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2794 top1= 36.6587


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2037 top1= 39.4331

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 1.7387 top1= 44.0625
[E15B10 |   4224/60000 (  7%) ] Loss: 1.7113 top1= 49.3750
[E15B20 |   8064/60000 ( 13%) ] Loss: 1.7747 top1= 41.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2794 top1= 42.8285


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2203 top1= 42.3077

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 1.6404 top1= 54.6875
[E16B10 |   4224/60000 (  7%) ] Loss: 1.7040 top1= 45.3125
[E16B20 |   8064/60000 ( 13%) ] Loss: 1.7254 top1= 41.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2753 top1= 43.1891


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2274 top1= 42.8085

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 1.5832 top1= 58.4375
[E17B10 |   4224/60000 (  7%) ] Loss: 1.8189 top1= 40.3125
[E17B20 |   8064/60000 ( 13%) ] Loss: 1.6578 top1= 48.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2715 top1= 37.6803


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2655 top1= 39.4431

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 1.6159 top1= 52.5000
[E18B10 |   4224/60000 (  7%) ] Loss: 1.6943 top1= 48.1250
[E18B20 |   8064/60000 ( 13%) ] Loss: 1.6943 top1= 45.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2758 top1= 37.4599


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2207 top1= 39.6334

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 1.6701 top1= 49.6875
[E19B10 |   4224/60000 (  7%) ] Loss: 1.6414 top1= 49.3750
[E19B20 |   8064/60000 ( 13%) ] Loss: 1.7492 top1= 42.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2814 top1= 34.1246


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1724 top1= 35.2464

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 1.7300 top1= 48.7500
[E20B10 |   4224/60000 (  7%) ] Loss: 1.6235 top1= 49.3750
[E20B20 |   8064/60000 ( 13%) ] Loss: 1.6615 top1= 46.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2790 top1= 40.7352


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1819 top1= 40.1943

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 1.6739 top1= 52.1875
[E21B10 |   4224/60000 (  7%) ] Loss: 1.6852 top1= 48.7500
[E21B20 |   8064/60000 ( 13%) ] Loss: 1.6451 top1= 47.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2744 top1= 42.5982


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2120 top1= 42.7384

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 1.6041 top1= 54.0625
[E22B10 |   4224/60000 (  7%) ] Loss: 1.7168 top1= 47.1875
[E22B20 |   8064/60000 ( 13%) ] Loss: 1.6333 top1= 49.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2781 top1= 42.5681


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1934 top1= 41.1258

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 1.7389 top1= 45.6250
[E23B10 |   4224/60000 (  7%) ] Loss: 1.7113 top1= 44.0625
[E23B20 |   8064/60000 ( 13%) ] Loss: 1.6657 top1= 46.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2763 top1= 39.2528


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1881 top1= 40.8253

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 1.6866 top1= 47.5000
[E24B10 |   4224/60000 (  7%) ] Loss: 1.6604 top1= 46.2500
[E24B20 |   8064/60000 ( 13%) ] Loss: 1.6473 top1= 50.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2779 top1= 42.5781


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2012 top1= 43.1290

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 1.5970 top1= 58.1250
[E25B10 |   4224/60000 (  7%) ] Loss: 1.6593 top1= 49.6875
[E25B20 |   8064/60000 ( 13%) ] Loss: 1.7788 top1= 43.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2796 top1= 33.3233


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1534 top1= 33.0228

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 1.7895 top1= 44.3750
[E26B10 |   4224/60000 (  7%) ] Loss: 1.7771 top1= 40.9375
[E26B20 |   8064/60000 ( 13%) ] Loss: 1.8744 top1= 36.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2776 top1= 38.5317


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 10.0962


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2178 top1= 40.8854

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 1.6185 top1= 51.8750
[E27B10 |   4224/60000 (  7%) ] Loss: 1.6517 top1= 46.5625
[E27B20 |   8064/60000 ( 13%) ] Loss: 1.6951 top1= 46.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2832 top1= 35.8974


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1507 top1= 38.3914

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 1.7488 top1= 50.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 1.6204 top1= 50.6250
[E28B20 |   8064/60000 ( 13%) ] Loss: 1.6927 top1= 45.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2779 top1= 39.2127


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1687 top1= 41.5865

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 1.6151 top1= 54.6875
[E29B10 |   4224/60000 (  7%) ] Loss: 1.7623 top1= 40.6250
[E29B20 |   8064/60000 ( 13%) ] Loss: 1.7298 top1= 45.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2750 top1= 43.0589


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2522 top1= 42.8686

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 1.6026 top1= 50.6250
[E30B10 |   4224/60000 (  7%) ] Loss: 1.6345 top1= 50.6250
[E30B20 |   8064/60000 ( 13%) ] Loss: 1.7983 top1= 41.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2815 top1= 42.2776


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3022 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1895 top1= 42.1975

