
=== 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 0x7f182f5da9d0>

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: 0.2614 top1= 91.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5236 top1= 83.8141


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5480 top1= 48.9583


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4436 top1= 44.1206

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3643 top1= 90.6250
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3326 top1= 90.0000
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1656 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4000 top1= 88.1110


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8574 top1= 55.7792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9317 top1= 50.0501

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1529 top1= 94.6875
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1328 top1= 95.0000
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1039 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3415 top1= 89.3129


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6697 top1= 58.5236


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6623 top1= 55.1583

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1039 top1= 96.2500
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0849 top1= 96.8750
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0800 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3141 top1= 89.8738


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6880 top1= 60.0060


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4149 top1= 59.3249

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0648 top1= 97.8125
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0719 top1= 97.5000
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0545 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2962 top1= 90.3946


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7616 top1= 60.9275


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3268 top1= 62.5300

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0439 top1= 99.3750
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0643 top1= 97.5000
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0400 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2869 top1= 90.7552


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8953 top1= 60.4367


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3574 top1= 62.3197

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0463 top1= 98.7500
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0356 top1= 99.0625
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0321 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2867 top1= 90.7853


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8740 top1= 62.1695


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2135 top1= 66.7368

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0341 top1= 99.3750
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0410 top1= 98.4375
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0169 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2772 top1= 91.4163


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7452 top1= 63.8922


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0587 top1= 71.2740

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0146 top1= 99.6875
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0331 top1= 99.0625
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0231 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2788 top1= 91.5865


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5151 top1= 67.2075


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0284 top1= 72.1755

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0112 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0108 top1=100.0000
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0237 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2952 top1= 91.4463


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3655 top1= 70.0721


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0032 top1= 74.4692

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0099 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0288 top1= 99.0625
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0058 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2986 top1= 91.2861


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1228 top1= 72.7163


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0877 top1= 73.1971

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0087 top1= 99.6875
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0102 top1= 99.6875
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0145 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2852 top1= 91.8570


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0762 top1= 74.2788


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1283 top1= 74.1687

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0113 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0049 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0038 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2743 top1= 92.0473


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8632 top1= 78.2652


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8692 top1= 78.9163

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0039 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0044 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0036 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2686 top1= 92.6282


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8420 top1= 78.9964


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8175 top1= 80.7692

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0041 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2712 top1= 92.7784


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7357 top1= 81.5905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7772 top1= 81.7007

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0027 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0031 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2768 top1= 92.7083


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6929 top1= 82.6823


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8428 top1= 80.6390

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0024 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2803 top1= 92.7183


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6542 top1= 83.6238


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8443 top1= 80.8694

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0018 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=0.2783 top1= 92.8986


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6317 top1= 84.4451


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7441 top1= 82.8125

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0016 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=0.2775 top1= 93.0188


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6247 top1= 84.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6875 top1= 84.1346

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0014 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2779 top1= 93.0489


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6208 top1= 85.0361


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6480 top1= 84.8658

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0013 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2785 top1= 93.1591


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6168 top1= 85.3666


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6184 top1= 85.5970

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2794 top1= 93.2192


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6103 top1= 85.7973


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5962 top1= 86.1278

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=0.2805 top1= 93.2592


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6017 top1= 86.0577


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5810 top1= 86.5685

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=0.2816 top1= 93.2692


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5916 top1= 86.4283


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5713 top1= 86.8289

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2829 top1= 93.2492


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5790 top1= 86.8189


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5658 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=0.2841 top1= 93.3093


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5658 top1= 87.2095


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5634 top1= 87.0593

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0009 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=0.2854 top1= 93.3393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5523 top1= 87.4900


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5634 top1= 87.1895

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2867 top1= 93.3293


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5395 top1= 87.8506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5642 top1= 87.2396

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=0.2880 top1= 93.3393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5266 top1= 88.2913


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5654 top1= 87.3397

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=0.2894 top1= 93.3393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5149 top1= 88.6218


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5664 top1= 87.3898

