
=== 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 0x7f1d39e529d0>

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: 1.0312 top1= 67.1875
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2593 top1= 91.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5049 top1= 84.6354


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8042 top1= 51.6326


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2693 top1= 44.8217

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3377 top1= 91.8750
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3327 top1= 90.6250
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1670 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3912 top1= 88.1210


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7785 top1= 56.8009


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8664 top1= 50.9515

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1404 top1= 95.6250
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1459 top1= 95.0000
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0996 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3406 top1= 89.4832


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5876 top1= 59.7556


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6512 top1= 55.2284

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1105 top1= 95.9375
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0924 top1= 97.5000
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0812 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3097 top1= 90.0741


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5862 top1= 61.1979


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4253 top1= 59.5152

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0566 top1= 98.4375
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0743 top1= 97.5000
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0588 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2878 top1= 90.6951


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5447 top1= 62.8506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3088 top1= 62.5901

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0441 top1= 98.7500
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0542 top1= 98.1250
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0306 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2812 top1= 91.0056


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6345 top1= 63.0709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2318 top1= 66.0256

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0503 top1= 98.1250
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0472 top1= 98.4375
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0255 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2906 top1= 90.5649


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8217 top1= 62.8305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9758 top1= 72.0052

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0291 top1= 98.7500
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0583 top1= 98.1250
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0159 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2835 top1= 91.3562


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7032 top1= 63.7821


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9873 top1= 74.1286

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0117 top1=100.0000
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0158 top1= 99.6875
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0201 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2896 top1= 91.3762


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6144 top1= 66.8269


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0176 top1= 74.5192

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0084 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0090 top1=100.0000
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0124 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2965 top1= 91.4263


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4245 top1= 70.0220


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8985 top1= 77.0833

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0089 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0112 top1= 99.6875
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0111 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2867 top1= 91.6066


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0949 top1= 74.0084


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9368 top1= 76.8129

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0068 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0103 top1= 99.6875
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0036 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2851 top1= 91.7768


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0284 top1= 75.1402


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1206 top1= 74.7095

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0040 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0103 top1= 99.6875
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2890 top1= 92.1575


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7938 top1= 80.1382


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9946 top1= 77.2236

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0038 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0074 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2789 top1= 92.6082


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7665 top1= 81.1098


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7618 top1= 81.7608

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0039 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0038 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2847 top1= 92.6282


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7353 top1= 81.8710


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8450 top1= 80.9696

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0031 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2863 top1= 92.6482


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6578 top1= 83.8241


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8298 top1= 81.1498

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0032 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2855 top1= 92.5681


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6342 top1= 84.5252


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8289 top1= 81.0196

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0021 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3020 top1= 92.2175


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6188 top1= 85.0461


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9967 top1= 78.8562

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0019 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2937 top1= 92.4880


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5829 top1= 86.1178


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8060 top1= 82.0613

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0016 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=0.2896 top1= 92.7484


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5602 top1= 86.8389


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7111 top1= 83.7941

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0014 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=0.2886 top1= 92.8285


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5527 top1= 87.0793


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6611 top1= 84.9259

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0012 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2887 top1= 92.9287


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5472 top1= 87.3097


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6330 top1= 85.4868

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2891 top1= 92.9788


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5426 top1= 87.4900


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6126 top1= 85.9675

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0011 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=0.2898 top1= 93.0288


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5372 top1= 87.8005


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5959 top1= 86.3982

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: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2907 top1= 93.0889


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5317 top1= 88.0208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5837 top1= 86.7889

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=0.2916 top1= 93.1290


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5256 top1= 88.2412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5736 top1= 87.0893

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: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2926 top1= 93.1190


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5199 top1= 88.5116


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5659 top1= 87.3397

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=0.2936 top1= 93.1490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5131 top1= 88.7320


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5599 top1= 87.5401

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=0.2946 top1= 93.1791


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5065 top1= 88.9223


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5555 top1= 87.6703

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0007 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=0.2957 top1= 93.1991


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4993 top1= 89.1226


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5529 top1= 87.8205

