
=== 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 ByzantineWorker(index=10)
=> Add worker ByzantineWorker(index=11)

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7fc68668f9d0>

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: 1.0273 top1= 63.7500
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2658 top1= 90.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0676 top1= 64.0425


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3877 top1= 48.7280


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5355 top1= 44.4611

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3893 top1= 90.3125
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3324 top1= 89.3750
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1800 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4537 top1= 85.1763


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3427 top1= 52.0232


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9026 top1= 51.7428

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1636 top1= 94.6875
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1392 top1= 95.9375
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1118 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3704 top1= 88.0308


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0505 top1= 54.7776


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6629 top1= 55.6490

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1122 top1= 95.3125
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0979 top1= 97.5000
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0848 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3405 top1= 88.7620


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0981 top1= 56.0797


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4269 top1= 60.0260

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0699 top1= 97.5000
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0871 top1= 97.8125
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0660 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3151 top1= 89.6034


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1582 top1= 56.5004


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3285 top1= 63.4615

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0430 top1= 98.7500
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0638 top1= 97.8125
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0517 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3101 top1= 89.8337


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1881 top1= 57.4820


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1506 top1= 67.3478

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0324 top1= 99.3750
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0373 top1= 99.3750
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0312 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2990 top1= 90.2444


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0827 top1= 59.6354


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1476 top1= 69.3710

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0298 top1= 99.3750
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0191 top1= 99.6875
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0384 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2731 top1= 91.2961


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6593 top1= 64.1526


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4106 top1= 65.9155

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0340 top1= 98.7500
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0443 top1= 98.7500
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0247 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2715 top1= 91.2460


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6127 top1= 64.6134


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2398 top1= 70.0921

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0243 top1= 99.0625
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0650 top1= 97.8125
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0305 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2684 top1= 91.5966


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7171 top1= 64.9038


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1686 top1= 72.5461

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0213 top1= 99.0625
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0153 top1= 99.3750
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0162 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2655 top1= 92.0473


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5095 top1= 68.8101


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1755 top1= 72.0653

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0117 top1= 99.6875
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0164 top1= 99.3750
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0164 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2677 top1= 92.0072


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1379 top1= 72.2256


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9065 top1= 77.4139

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0084 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0239 top1= 99.0625
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0082 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2746 top1= 91.6767


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1096 top1= 72.9567


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9710 top1= 77.2236

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0077 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0115 top1= 99.3750
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0062 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2647 top1= 92.3778


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1188 top1= 73.1971


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8698 top1= 79.6975

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0047 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0058 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0036 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2682 top1= 92.3878


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0526 top1= 74.6895


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7641 top1= 81.9411

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0038 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0034 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2707 top1= 92.2776


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9922 top1= 76.1619


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7531 top1= 82.3818

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0028 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2685 top1= 92.6082


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9368 top1= 77.6542


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7198 top1= 83.2532

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0026 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2667 top1= 92.7985


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9103 top1= 78.2853


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6854 top1= 83.9643

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0023 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2675 top1= 92.8986


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8779 top1= 78.9263


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6760 top1= 84.2849

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0019 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2691 top1= 92.9688


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8498 top1= 79.6074


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6525 top1= 84.8357

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0017 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2710 top1= 92.9988


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8309 top1= 80.0982


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6316 top1= 85.3265

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0015 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2730 top1= 93.0188


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8174 top1= 80.5889


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6026 top1= 85.8574

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0014 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2749 top1= 93.0489


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8027 top1= 80.9796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5827 top1= 86.4483

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0013 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2765 top1= 93.0789


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7878 top1= 81.4904


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5645 top1= 86.7989

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0012 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2780 top1= 93.1190


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7715 top1= 81.8209


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5506 top1= 87.2696

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2793 top1= 93.1390


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7568 top1= 82.3217


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5400 top1= 87.6302

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2805 top1= 93.1691


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7422 top1= 82.7424


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5302 top1= 87.8706

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2817 top1= 93.1991


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7295 top1= 83.1430


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5228 top1= 88.0609

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2827 top1= 93.2091


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7166 top1= 83.4335


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5155 top1= 88.3313

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2838 top1= 93.1891


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7052 top1= 83.7139


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5107 top1= 88.5317

