
=== 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 0x7f190bcbe7f0>

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: 1.0021 top1= 63.1250
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2621 top1= 90.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6835 top1= 78.9163


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.7801 top1= 48.6478


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5461 top1= 43.5296

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3906 top1= 90.3125
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.2581 top1= 92.5000
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1568 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7271 top1= 84.3950


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1181 top1= 49.7696


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0704 top1= 45.5329

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1466 top1= 95.3125
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1276 top1= 95.3125
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0822 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6094 top1= 85.2664


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7096 top1= 50.0100


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1399 top1= 45.9836

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0839 top1= 97.1875
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0661 top1= 97.1875
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0553 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5321 top1= 86.8289


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6990 top1= 50.1803


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2444 top1= 46.0637

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0522 top1= 98.4375
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0477 top1= 99.0625
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0301 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4700 top1= 88.0609


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7472 top1= 50.2103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5614 top1= 46.3241

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0278 top1= 99.0625
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0332 top1= 99.3750
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0211 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4434 top1= 87.7003


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7047 top1= 50.2404


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8015 top1= 46.3141

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0163 top1=100.0000
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0210 top1=100.0000
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0157 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4397 top1= 87.0292


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7242 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8049 top1= 45.9235

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0137 top1=100.0000
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0153 top1=100.0000
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0133 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4120 top1= 87.6202


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6653 top1= 50.2704


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5742 top1= 46.2841

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0112 top1=100.0000
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0177 top1=100.0000
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0089 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3997 top1= 87.4299


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5499 top1= 50.3405


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5559 top1= 46.4744

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0086 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0130 top1=100.0000
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0081 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3778 top1= 88.1911


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4422 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4763 top1= 46.6346

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0115 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0167 top1= 99.6875
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0115 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3782 top1= 87.9407


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2805 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2960 top1= 46.3041

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0112 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0182 top1=100.0000
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0101 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3813 top1= 88.2111


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1203 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8439 top1= 46.3742

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0095 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0307 top1= 99.6875
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0077 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3805 top1= 87.6102


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9175 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8680 top1= 46.7448

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0071 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0071 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0063 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3792 top1= 87.6703


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7292 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7191 top1= 46.7147

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0067 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0071 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0056 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3649 top1= 88.1310


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5732 top1= 50.4307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6363 top1= 46.8950

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0068 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0091 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0058 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3537 top1= 88.4615


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4381 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4672 top1= 47.3257

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0059 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0066 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0060 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3465 top1= 88.7720


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3119 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3344 top1= 47.8065

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0057 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0066 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0057 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3423 top1= 88.8421


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2040 top1= 51.0116


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2352 top1= 48.2071

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0061 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0067 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0058 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3373 top1= 89.0124


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0832 top1= 51.4523


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1170 top1= 48.5777

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0059 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0070 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0057 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3336 top1= 89.0825


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9930 top1= 51.8029


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9986 top1= 49.0986

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0060 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0074 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0057 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3311 top1= 89.2428


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9197 top1= 52.1334


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9245 top1= 49.6394

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0060 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0072 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0058 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3279 top1= 89.3329


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8304 top1= 52.7444


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8431 top1= 50.0801

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0059 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0076 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0058 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3260 top1= 89.4431


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7762 top1= 53.3353


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7560 top1= 50.6110

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0058 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0073 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0059 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3227 top1= 89.4531


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6855 top1= 54.0264


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6866 top1= 51.0016

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0057 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0070 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0059 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3205 top1= 89.4732


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6246 top1= 54.5773


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6239 top1= 51.6126

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0059 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0069 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0061 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3162 top1= 89.6334


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5433 top1= 55.2083


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5544 top1= 52.0833

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0056 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0068 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0056 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3146 top1= 89.8137


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4924 top1= 55.9195


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4527 top1= 52.7644

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0053 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0075 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0057 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3128 top1= 89.9038


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4295 top1= 56.2901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4042 top1= 53.0248

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0054 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0083 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0056 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3128 top1= 89.9038


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3722 top1= 56.8109


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3632 top1= 53.4155

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0052 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0089 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0065 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3115 top1= 89.9840


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3351 top1= 57.1414


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3739 top1= 53.4856

