
=== 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 0x7f8e2960e9d0>

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: 1.3865 top1= 50.6250
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.9225 top1= 69.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4043 top1= 79.5172


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8861 top1= 48.2873


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7715 top1= 42.5681

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.5841 top1= 84.6875
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.4433 top1= 86.8750
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.2298 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0446 top1= 81.3301


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7178 top1= 49.3790


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4775 top1= 44.3510

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.2681 top1= 93.1250
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.3089 top1= 89.3750
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1715 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9237 top1= 83.7039


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9832 top1= 49.6595


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7225 top1= 44.9119

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.2574 top1= 91.5625
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.2295 top1= 92.5000
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.1492 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8660 top1= 84.3550


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0745 top1= 49.8297


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9140 top1= 45.3425

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.1708 top1= 95.0000
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.1737 top1= 93.4375
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.1219 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8177 top1= 84.2248


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2224 top1= 50.0100


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0333 top1= 45.5228

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.1483 top1= 95.3125
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.1645 top1= 93.1250
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.1063 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7785 top1= 85.4768


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2851 top1= 50.0801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1701 top1= 45.7031

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.1355 top1= 96.2500
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.1265 top1= 94.6875
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.1013 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7389 top1= 85.7372


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4914 top1= 50.1402


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3700 top1= 45.8433

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.1193 top1= 96.2500
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.1074 top1= 96.5625
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.1028 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7404 top1= 85.5669


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5409 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1059 top1= 45.9635

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.1125 top1= 97.1875
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.1128 top1= 95.9375
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0723 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7220 top1= 85.3866


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5195 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1963 top1= 46.1338

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0888 top1= 97.1875
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0847 top1= 96.8750
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0598 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7114 top1= 85.8874


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5570 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3260 top1= 46.1939

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0894 top1= 97.5000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0723 top1= 96.8750
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0689 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6977 top1= 86.1478


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5858 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4136 top1= 46.3041

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0814 top1= 96.8750
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0718 top1= 97.5000
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0545 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6770 top1= 86.4884


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6092 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4491 top1= 46.4042

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0656 top1= 98.1250
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0703 top1= 98.1250
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0442 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6603 top1= 86.3782


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7748 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7100 top1= 46.4543

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0595 top1= 97.8125
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0567 top1= 98.1250
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0446 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6432 top1= 86.9792


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7929 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6760 top1= 46.4643

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0571 top1= 98.4375
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0553 top1= 97.5000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0383 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6494 top1= 86.9291


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8074 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6844 top1= 46.5845

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0622 top1= 98.1250
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0526 top1= 98.4375
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0326 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6298 top1= 87.6302


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8639 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5566 top1= 46.6246

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0467 top1= 99.3750
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0475 top1= 98.7500
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0288 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6314 top1= 87.3598


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7187 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6399 top1= 46.7548

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0433 top1= 99.6875
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0408 top1= 99.0625
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0322 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6264 top1= 87.5100


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8036 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7543 top1= 46.8450

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0553 top1= 99.0625
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0415 top1= 98.7500
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0216 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6029 top1= 87.1494


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9342 top1= 50.5308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9589 top1= 46.8750

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0346 top1= 99.3750
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0345 top1= 99.3750
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0225 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5992 top1= 87.1795


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9467 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0166 top1= 46.8349

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0380 top1= 99.3750
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0396 top1= 98.7500
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0210 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5916 top1= 87.4700


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0078 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9799 top1= 46.9852

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0338 top1= 99.3750
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0326 top1= 99.3750
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0224 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5932 top1= 87.5501


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0303 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9039 top1= 47.0453

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0355 top1= 99.6875
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0323 top1= 99.3750
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0162 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5944 top1= 87.4599


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0022 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8671 top1= 47.0653

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0351 top1= 99.3750
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0266 top1= 99.3750
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0180 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5905 top1= 87.0693


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9142 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9274 top1= 47.1554

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0293 top1= 99.6875
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0281 top1= 99.6875
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0152 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5650 top1= 87.6302


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0507 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0959 top1= 47.0853

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0203 top1= 99.6875
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0170 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0123 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5618 top1= 87.1995


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1198 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1593 top1= 47.0853

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0267 top1= 99.3750
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0221 top1= 99.6875
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0187 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5521 top1= 88.1110


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0703 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1293 top1= 47.1955

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0213 top1= 99.6875
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0202 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0110 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5505 top1= 88.1210


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1245 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0823 top1= 47.1955

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0217 top1= 99.3750
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0263 top1= 99.3750
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0129 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5594 top1= 88.4215


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2121 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0857 top1= 47.2256

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0239 top1= 99.6875
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0189 top1= 99.6875
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0110 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5506 top1= 88.3914


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0341 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1043 top1= 47.2256

