
=== 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 0x7f88487469d0>

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: 1.0334 top1= 65.9375
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2603 top1= 91.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5307 top1= 83.4235


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6516 top1= 48.9683


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4441 top1= 44.0104

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3668 top1= 90.6250
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3321 top1= 90.0000
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1682 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3999 top1= 88.1210


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8540 top1= 55.6891


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9295 top1= 49.9299

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1500 top1= 94.6875
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1380 top1= 95.0000
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1017 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3432 top1= 89.2127


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6752 top1= 58.6639


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6910 top1= 54.6675

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1040 top1= 96.8750
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0867 top1= 96.8750
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0725 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3143 top1= 89.8237


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6597 top1= 60.1663


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4287 top1= 59.5453

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0614 top1= 98.1250
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0704 top1= 97.8125
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0560 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2946 top1= 90.3546


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6878 top1= 61.2380


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3189 top1= 62.5901

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0428 top1= 98.4375
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0657 top1= 97.5000
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0339 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2881 top1= 90.6350


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8606 top1= 60.6571


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3026 top1= 63.6118

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0454 top1= 98.7500
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0391 top1= 98.7500
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0366 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2918 top1= 90.6450


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9853 top1= 61.4383


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2643 top1= 65.8053

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0466 top1= 98.7500
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0344 top1= 98.7500
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0191 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2856 top1= 91.1058


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8400 top1= 63.1911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9828 top1= 73.0469

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0144 top1= 99.6875
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0326 top1= 99.6875
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0118 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2754 top1= 91.5565


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5844 top1= 66.4263


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9709 top1= 73.3273

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0077 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0142 top1= 99.6875
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0266 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3055 top1= 91.0958


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4336 top1= 69.2808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0102 top1= 74.8898

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0144 top1= 99.6875
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0208 top1= 99.3750
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0070 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2848 top1= 91.6266


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3217 top1= 70.6831


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9991 top1= 75.1002

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0041 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0086 top1= 99.6875
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0046 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2840 top1= 91.8670


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0589 top1= 74.6995


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2505 top1= 72.6863

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0107 top1= 99.6875
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0049 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0030 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2780 top1= 91.9772


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8679 top1= 78.2252


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0007 top1= 76.7728

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0047 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0038 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2767 top1= 92.2476


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7815 top1= 80.3886


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8973 top1= 79.2468

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0051 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0031 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0033 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2767 top1= 92.3778


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7386 top1= 81.4603


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8961 top1= 79.5974

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0025 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2723 top1= 92.8686


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7231 top1= 81.8409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8148 top1= 81.0797

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0022 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2739 top1= 92.8285


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6868 top1= 82.9627


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7765 top1= 81.9812

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0017 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2744 top1= 92.9587


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6711 top1= 83.4535


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7154 top1= 83.1931

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0015 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2751 top1= 93.0489


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6590 top1= 83.9343


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6716 top1= 84.3149

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2761 top1= 93.0489


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6514 top1= 84.2949


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6371 top1= 84.9659

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0013 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=0.2773 top1= 93.1490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6416 top1= 84.7356


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6128 top1= 85.5869

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2785 top1= 93.2592


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6307 top1= 85.1062


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5949 top1= 86.1478

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2796 top1= 93.2993


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6180 top1= 85.6771


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5821 top1= 86.5284

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0010 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=0.2808 top1= 93.3293


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6048 top1= 86.1078


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5742 top1= 86.7588

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0010 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=0.2819 top1= 93.3594


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5907 top1= 86.4884


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5692 top1= 86.9591

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0009 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=0.2830 top1= 93.3794


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5771 top1= 86.8590


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5658 top1= 87.0893

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2841 top1= 93.3894


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5626 top1= 87.3898


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5651 top1= 87.1895

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0008 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=0.2853 top1= 93.3794


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5499 top1= 87.7704


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5646 top1= 87.2897

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0008 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=0.2865 top1= 93.3694


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5375 top1= 88.0709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5642 top1= 87.3698

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2877 top1= 93.3393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5262 top1= 88.3413


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5643 top1= 87.4299

