
=== 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 0x7facc48f09d0>

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: 1.0133 top1= 65.0000
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2612 top1= 90.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6222 top1= 79.1366


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7354 top1= 48.9083


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8477 top1= 43.6298

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3669 top1= 90.3125
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3255 top1= 89.6875
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1659 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4386 top1= 87.6402


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3452 top1= 51.9531


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2734 top1= 48.0669

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1426 top1= 96.5625
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1287 top1= 95.6250
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1044 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3644 top1= 88.7720


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1672 top1= 55.0581


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8319 top1= 52.1034

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0948 top1= 96.8750
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0837 top1= 97.1875
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0615 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3311 top1= 89.2228


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2847 top1= 55.4988


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8391 top1= 53.9563

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0710 top1= 97.1875
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0607 top1= 98.1250
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0450 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3103 top1= 89.9539


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3083 top1= 56.5004


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8040 top1= 55.5489

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0530 top1= 98.1250
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0609 top1= 99.0625
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0295 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2911 top1= 90.4848


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1961 top1= 57.6923


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8686 top1= 56.2300

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0346 top1= 99.3750
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0352 top1= 98.7500
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0279 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2877 top1= 90.8153


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1197 top1= 59.9960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9643 top1= 57.4119

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0284 top1= 99.6875
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0575 top1= 97.8125
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0448 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2832 top1= 90.9555


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7529 top1= 63.1410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7522 top1= 60.0160

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0164 top1=100.0000
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0167 top1=100.0000
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0196 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2966 top1= 90.7752


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5870 top1= 64.7536


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9162 top1= 58.5837

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0149 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0303 top1= 99.0625
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0329 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2804 top1= 91.2460


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5900 top1= 65.9255


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5189 top1= 63.8421

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0118 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0137 top1=100.0000
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0322 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3214 top1= 89.7035


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3030 top1= 69.1607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6375 top1= 59.7055

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0289 top1= 99.0625
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0369 top1= 98.4375
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0077 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2679 top1= 91.7468


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3734 top1= 68.5196


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0814 top1= 72.0052

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0048 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0051 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0045 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2645 top1= 92.1374


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3183 top1= 69.6114


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0107 top1= 74.1286

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0035 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0042 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2584 top1= 92.4079


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1419 top1= 72.5661


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9432 top1= 75.9716

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0037 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2595 top1= 92.3678


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1207 top1= 73.5276


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8994 top1= 77.3838

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0031 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2629 top1= 92.4880


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0687 top1= 74.7796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9062 top1= 77.3538

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0020 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2664 top1= 92.4079


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0201 top1= 75.9315


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8591 top1= 78.7560

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0016 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2695 top1= 92.4279


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9836 top1= 76.6727


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7384 top1= 81.6306

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0014 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2699 top1= 92.5381


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9469 top1= 77.5541


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7062 top1= 82.5721

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0013 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2698 top1= 92.5982


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9012 top1= 78.6458


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7069 top1= 82.7324

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0012 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2705 top1= 92.6983


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8647 top1= 79.5773


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6993 top1= 83.0529

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2714 top1= 92.7784


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8385 top1= 80.3285


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6880 top1= 83.3634

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2723 top1= 92.7784


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8164 top1= 80.7993


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6795 top1= 83.6639

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2733 top1= 92.8486


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7956 top1= 81.3301


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6722 top1= 83.9243

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2742 top1= 92.9187


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7764 top1= 81.7208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6654 top1= 84.1346

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2751 top1= 92.9387


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7592 top1= 82.2015


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6582 top1= 84.3850

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2760 top1= 92.9187


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7427 top1= 82.6923


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6507 top1= 84.6855

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2769 top1= 92.8986


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7273 top1= 83.1130


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6448 top1= 84.8357

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2777 top1= 92.9587


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7126 top1= 83.4535


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6384 top1= 84.9960

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2786 top1= 92.9688


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6998 top1= 83.7540


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6324 top1= 85.0962

