
=== 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 0x7f2eb5d787f0>

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=0.6346 top1= 78.9363


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5571 top1= 48.8982


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4838 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: 0.1657 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4544 top1= 87.5401


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3154 top1= 51.7228


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2622 top1= 47.5361

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1428 top1= 96.5625
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1270 top1= 95.6250
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1032 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3668 top1= 88.6619


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1723 top1= 54.7075


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8470 top1= 51.7628

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0989 top1= 96.8750
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0862 top1= 97.1875
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0610 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3292 top1= 89.4832


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2387 top1= 55.4187


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8861 top1= 53.6558

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0744 top1= 97.1875
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0625 top1= 98.1250
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0463 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3154 top1= 89.6334


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3811 top1= 55.7592


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7199 top1= 56.5905

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0535 top1= 97.5000
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0598 top1= 98.7500
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0371 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2923 top1= 90.5148


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3225 top1= 57.4519


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7572 top1= 57.6623

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0300 top1= 99.3750
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0298 top1=100.0000
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0331 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2961 top1= 90.5749


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2271 top1= 59.0946


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9226 top1= 57.9427

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0298 top1= 99.3750
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0349 top1= 98.7500
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0092 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3086 top1= 90.2544


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7472 top1= 63.2011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0596 top1= 57.9928

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0306 top1= 98.7500
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0243 top1= 99.6875
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0458 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2840 top1= 91.0256


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6663 top1= 64.2929


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6525 top1= 62.4599

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0074 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0293 top1= 99.0625
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0104 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2848 top1= 91.1458


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7137 top1= 64.5933


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3728 top1= 64.1526

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0155 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0234 top1= 99.0625
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0315 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2861 top1= 91.1558


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5395 top1= 66.0357


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3205 top1= 67.4179

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0135 top1= 99.6875
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0165 top1= 99.6875
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0110 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2744 top1= 91.4463


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4192 top1= 68.1090


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3230 top1= 69.2007

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0103 top1= 99.6875
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0205 top1= 99.0625
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0035 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2686 top1= 91.9071


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2389 top1= 70.6430


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0000 top1= 73.9884

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0045 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0039 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2706 top1= 92.1174


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2178 top1= 71.7448


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0230 top1= 75.2003

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0036 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2664 top1= 92.3578


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1342 top1= 73.5777


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9989 top1= 75.7913

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0029 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2679 top1= 92.5180


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0778 top1= 74.9900


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9749 top1= 76.5425

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: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2706 top1= 92.5581


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0357 top1= 76.0717


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9165 top1= 77.9046

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=0.2746 top1= 92.4980


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0076 top1= 76.7728


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7944 top1= 80.6190

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=0.2757 top1= 92.4980


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9754 top1= 77.4639


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7458 top1= 81.8209

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: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2760 top1= 92.5881


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9344 top1= 78.3153


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7353 top1= 82.2616

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=0.2764 top1= 92.6583


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8993 top1= 79.0865


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7264 top1= 82.6022

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=0.2771 top1= 92.7484


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8731 top1= 79.9079


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7154 top1= 82.8425

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: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2779 top1= 92.8185


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8501 top1= 80.4387


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7062 top1= 83.0629

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2787 top1= 92.8185


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8282 top1= 81.0096


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6997 top1= 83.3734

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: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2796 top1= 92.7985


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8079 top1= 81.4303


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6951 top1= 83.5337

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=0.2803 top1= 92.7985


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7883 top1= 81.8109


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6907 top1= 83.7841

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=0.2812 top1= 92.8185


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7713 top1= 82.3518


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6857 top1= 84.0144

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0010 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=0.2820 top1= 92.8586


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7548 top1= 82.7324


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6793 top1= 84.1947

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=0.2829 top1= 92.9087


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7402 top1= 83.1030


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6739 top1= 84.4651

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=0.2837 top1= 92.9387


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7267 top1= 83.4836


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6671 top1= 84.6254

