
=== 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 0x7fbebe9329d0>

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: 1.3792 top1= 52.8125
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.8066 top1= 75.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3737 top1= 71.9050


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9825 top1= 48.0769


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0590 top1= 40.0240

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.5056 top1= 84.6875
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3732 top1= 90.0000
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.2525 top1= 90.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0298 top1= 81.0096


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8679 top1= 49.4892


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5865 top1= 44.4111

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.2503 top1= 94.3750
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.3097 top1= 91.2500
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1904 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9062 top1= 83.4335


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1392 top1= 49.6494


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8385 top1= 44.8818

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.2348 top1= 92.8125
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.2263 top1= 91.8750
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.1683 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8485 top1= 84.0244


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3335 top1= 49.8097


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1103 top1= 45.3826

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.1780 top1= 95.0000
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.1771 top1= 93.4375
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.1374 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8045 top1= 84.0645


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3977 top1= 49.9599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2024 top1= 45.5128

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.1462 top1= 95.3125
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.1453 top1= 94.3750
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.1086 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7601 top1= 85.0561


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5134 top1= 50.0701


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3295 top1= 45.6530

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.1432 top1= 96.2500
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.1428 top1= 94.6875
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.1165 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7323 top1= 85.0060


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6641 top1= 50.1302


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5450 top1= 45.6430

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.1288 top1= 96.5625
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.1196 top1= 95.6250
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0965 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7285 top1= 85.0361


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6470 top1= 50.1903


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4224 top1= 45.9135

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.1279 top1= 96.5625
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.1243 top1= 95.9375
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0700 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7099 top1= 85.5068


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6357 top1= 50.1502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4373 top1= 46.1438

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.1081 top1= 95.9375
[E10B10 |   4224/60000 (  7%) ] Loss: 0.1024 top1= 95.9375
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0705 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7111 top1= 85.2063


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6560 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4758 top1= 46.2039

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.1007 top1= 96.2500
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0884 top1= 96.8750
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0752 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6866 top1= 86.0777


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6508 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5439 top1= 46.2841

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0899 top1= 96.8750
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0771 top1= 97.1875
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0603 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6642 top1= 86.9992


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6986 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5620 top1= 46.3642

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0689 top1= 97.5000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0815 top1= 96.2500
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0606 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6529 top1= 86.3582


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8690 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7829 top1= 46.4343

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0674 top1= 98.1250
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0637 top1= 97.5000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0638 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6275 top1= 87.3998


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9313 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7063 top1= 46.3942

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0691 top1= 98.1250
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0729 top1= 97.5000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0401 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6374 top1= 87.0192


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9325 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7180 top1= 46.5845

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0745 top1= 97.5000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0623 top1= 98.4375
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0325 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6256 top1= 87.0994


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9769 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7967 top1= 46.5946

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0532 top1= 99.0625
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0517 top1= 98.4375
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0328 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6167 top1= 87.2796


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8794 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8194 top1= 46.6847

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0515 top1= 98.4375
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0460 top1= 98.1250
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0418 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6155 top1= 87.2897


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9754 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8862 top1= 46.7248

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0560 top1= 98.1250
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0399 top1= 99.3750
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0251 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5911 top1= 87.8806


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0873 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0390 top1= 46.8550

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0417 top1= 98.7500
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0395 top1= 99.6875
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0235 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5823 top1= 88.0409


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1499 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0878 top1= 46.8450

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0504 top1= 98.4375
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0367 top1= 99.3750
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0240 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5811 top1= 88.0308


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1809 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0762 top1= 46.8550

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0426 top1= 98.4375
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0352 top1= 99.0625
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0189 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5795 top1= 87.9407


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1628 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0211 top1= 46.9952

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0479 top1= 99.0625
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0424 top1= 98.1250
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0196 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5820 top1= 87.6002


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1291 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0442 top1= 47.0453

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0437 top1= 99.3750
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0289 top1= 99.3750
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0219 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5773 top1= 87.4900


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0827 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1418 top1= 47.0453

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0346 top1= 99.6875
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0296 top1= 99.3750
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0152 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5548 top1= 88.0609


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2278 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3026 top1= 47.0853

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0233 top1= 99.6875
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0177 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0139 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5565 top1= 87.6502


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3019 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3392 top1= 47.0252

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0357 top1= 99.3750
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0288 top1= 99.3750
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0129 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5454 top1= 88.7320


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2623 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2643 top1= 47.1955

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0264 top1= 99.3750
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0231 top1= 99.3750
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0118 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5377 top1= 88.1811


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2570 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2567 top1= 47.0052

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0295 top1= 99.0625
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0181 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0148 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5461 top1= 88.5116


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3716 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2546 top1= 47.1855

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0271 top1= 99.6875
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0165 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0122 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5321 top1= 88.9724


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2515 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2654 top1= 47.1755

