
=== 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 0x7f35414ab9d0>

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: 0.2596 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6345 top1= 78.9363


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5569 top1= 48.8982


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4840 top1= 43.6098

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3784 top1= 90.6250
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3159 top1= 89.3750
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1658 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4544 top1= 87.5701


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3144 top1= 51.7228


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2658 top1= 47.5561

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1429 top1= 96.5625
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1274 top1= 95.6250
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1034 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3667 top1= 88.7220


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1797 top1= 54.6875


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8536 top1= 51.7628

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0993 top1= 96.5625
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0858 top1= 97.1875
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0626 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3309 top1= 89.4231


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2490 top1= 55.3886


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8647 top1= 53.6659

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0744 top1= 97.5000
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0632 top1= 98.4375
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0456 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3152 top1= 89.5533


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3705 top1= 55.8994


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6879 top1= 56.7308

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0534 top1= 97.8125
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0553 top1= 99.0625
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0408 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2932 top1= 90.5549


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2954 top1= 57.5421


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7866 top1= 57.5521

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0285 top1= 99.3750
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0326 top1= 99.0625
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0248 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2966 top1= 90.5950


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2506 top1= 59.1747


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9469 top1= 58.2532

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0358 top1= 99.0625
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0182 top1=100.0000
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0105 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2912 top1= 90.9155


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7526 top1= 62.9006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8699 top1= 58.9543

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0211 top1= 99.3750
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0574 top1= 99.0625
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0482 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2875 top1= 91.0256


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6370 top1= 64.0325


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6428 top1= 61.5785

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0111 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0306 top1= 98.4375
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0107 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2870 top1= 91.2159


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7256 top1= 64.4131


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4958 top1= 62.5801

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0151 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0131 top1= 99.6875
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0098 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2858 top1= 90.9355


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5446 top1= 65.8253


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3535 top1= 68.7700

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0076 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0086 top1=100.0000
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0064 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2774 top1= 91.6667


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4577 top1= 67.5280


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1160 top1= 72.4359

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0087 top1= 99.6875
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0051 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0047 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2735 top1= 91.9071


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2431 top1= 70.9535


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0363 top1= 74.1386

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0036 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0053 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2720 top1= 92.0573


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2014 top1= 72.2857


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9944 top1= 76.4423

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0044 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2711 top1= 92.3077


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1834 top1= 72.9167


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9418 top1= 77.1434

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0034 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2720 top1= 92.3778


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1125 top1= 74.5292


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0050 top1= 76.3822

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0021 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2719 top1= 92.4579


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0510 top1= 75.8614


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0114 top1= 76.6026

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0018 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2762 top1= 92.4679


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0235 top1= 76.5725


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8439 top1= 80.0681

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0014 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2796 top1= 92.5681


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0047 top1= 77.0232


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7639 top1= 81.7308

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0012 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2801 top1= 92.6282


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9662 top1= 77.8245


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7326 top1= 82.4619

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2802 top1= 92.6382


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9257 top1= 78.6759


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7255 top1= 82.7123

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=0.2806 top1= 92.6983


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8931 top1= 79.4371


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7172 top1= 82.9728

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2812 top1= 92.7284


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8677 top1= 80.1382


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7082 top1= 83.3734

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0013 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=0.2819 top1= 92.7083


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8453 top1= 80.7792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7007 top1= 83.6538

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2827 top1= 92.7985


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8236 top1= 81.2500


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6964 top1= 83.9543

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2834 top1= 92.8285


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8038 top1= 81.7208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6925 top1= 84.0745

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=0.2843 top1= 92.8285


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7855 top1= 82.1915


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6893 top1= 84.1747

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=0.2850 top1= 92.8686


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7692 top1= 82.7023


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6834 top1= 84.4351

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2859 top1= 92.8686


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7542 top1= 83.0629


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6785 top1= 84.6154

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0009 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=0.2867 top1= 92.8586


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7401 top1= 83.3133


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6727 top1= 84.7656

