
=== 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 0x7f242b5909d0>

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: 1.0007 top1= 64.0625
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2621 top1= 90.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6991 top1= 78.5857


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.6771 top1= 48.7079


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1352 top1= 43.9704

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3747 top1= 90.9375
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.2740 top1= 92.1875
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1507 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7409 top1= 84.2748


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1828 top1= 49.7696


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0655 top1= 45.4928

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1467 top1= 95.0000
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1330 top1= 95.0000
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0803 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6284 top1= 85.2965


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9576 top1= 50.0100


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2473 top1= 45.9936

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0817 top1= 97.1875
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0679 top1= 97.1875
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0491 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5594 top1= 86.5585


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1206 top1= 50.2204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5594 top1= 46.1138

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0489 top1= 98.4375
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0508 top1= 98.1250
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0295 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5120 top1= 86.6987


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4156 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0205 top1= 46.3542

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0250 top1= 99.6875
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0280 top1= 99.3750
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0149 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5076 top1= 85.8774


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7282 top1= 50.2704


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2654 top1= 45.9635

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0165 top1=100.0000
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0172 top1=100.0000
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0109 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4767 top1= 86.2881


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1431 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2710 top1= 46.3942

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0094 top1=100.0000
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0149 top1=100.0000
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0053 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4549 top1= 86.8490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4938 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8017 top1= 46.3542

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0140 top1= 99.6875
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0158 top1= 99.6875
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0088 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4653 top1= 86.1579


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8238 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9336 top1= 46.4744

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0053 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0055 top1=100.0000
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0051 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4392 top1= 86.6787


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0272 top1= 50.2804


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1025 top1= 46.6647

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0046 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0088 top1=100.0000
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0042 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4125 top1= 87.4499


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1643 top1= 50.2704


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4958 top1= 46.7448

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0081 top1=100.0000
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4110 top1= 87.0292


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2997 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6504 top1= 46.7348

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0041 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4107 top1= 87.0693


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4174 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.0103 top1= 46.6246

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0024 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4218 top1= 86.6787


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5655 top1= 50.3405


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8012 top1= 46.5946

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0014 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4206 top1= 86.6286


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6947 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8901 top1= 46.6246

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0013 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4154 top1= 86.5385


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8042 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.0486 top1= 46.6346

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4192 top1= 86.3982


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9035 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1063 top1= 46.6346

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4207 top1= 86.2780


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9979 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1721 top1= 46.6146

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4178 top1= 86.4483


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.0798 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2326 top1= 46.7448

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0013 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4119 top1= 86.4984


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1595 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3318 top1= 46.8249

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0012 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4098 top1= 86.5184


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2301 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4411 top1= 46.7748

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4132 top1= 86.4683


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.3006 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4835 top1= 46.8349

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4115 top1= 86.4683


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.3655 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5785 top1= 46.8349

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0003 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4112 top1= 86.4784


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.4238 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6516 top1= 46.8349

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0003 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4111 top1= 86.5184


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.4792 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7158 top1= 46.8450

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0003 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4112 top1= 86.5284


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.5357 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7744 top1= 46.8450

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0003 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0003 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4111 top1= 86.5184


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.5888 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8290 top1= 46.8450

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0003 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0004 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0003 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4113 top1= 86.5184


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.6352 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8798 top1= 46.8450

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0003 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0004 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0002 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4113 top1= 86.5284


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.6838 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9288 top1= 46.8450

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0003 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0004 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0002 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4116 top1= 86.5184


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.7285 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9743 top1= 46.8450

