
=== 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 ByzantineWorker(index=5)
=> Add worker ByzantineWorker(index=6)
=> Add worker ByzantineWorker(index=7)
=> Add worker ByzantineWorker(index=8)
=> Add worker ByzantineWorker(index=9)
=> Add worker ByzantineWorker(index=10)
=> Add worker ByzantineWorker(index=11)
=> Add worker ByzantineWorker(index=12)
=> Add worker ByzantineWorker(index=13)
=> Add worker ByzantineWorker(index=14)
=> Add worker ByzantineWorker(index=15)

=== Start adding graph ===
<__main__.MaliciousRing object at 0x7f6e4db16b20>

Train epoch 1
[E 1B0  |    512/60000 (  1%) ] Loss: 2.3090 top1=  5.6250

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([7, 0, 0, 8, 1], device='cuda:0')
Worker 1 has targets: tensor([6, 2, 0, 2, 4], device='cuda:0')
Worker 2 has targets: tensor([4, 4, 1, 2, 8], device='cuda:0')
Worker 3 has targets: tensor([3, 2, 1, 5, 1], device='cuda:0')
Worker 4 has targets: tensor([9, 6, 2, 8, 8], device='cuda:0')
Worker 5 has targets: tensor([1, 2, 3, 9, 2], device='cuda:0')
Worker 6 has targets: tensor([4, 8, 3, 6, 2], device='cuda:0')
Worker 7 has targets: tensor([0, 8, 4, 3, 8], device='cuda:0')
Worker 8 has targets: tensor([3, 3, 5, 0, 6], device='cuda:0')
Worker 9 has targets: tensor([9, 1, 5, 0, 6], device='cuda:0')
Worker 10 has targets: tensor([7, 7, 6, 6, 5], device='cuda:0')
Worker 11 has targets: tensor([5, 6, 7, 6, 0], device='cuda:0')
Worker 12 has targets: tensor([7, 6, 7, 7, 6], device='cuda:0')
Worker 13 has targets: tensor([8, 2, 8, 7, 2], device='cuda:0')
Worker 14 has targets: tensor([7, 4, 8, 8, 5], device='cuda:0')
Worker 15 has targets: tensor([2, 9, 9, 0, 6], device='cuda:0')



=== Log mixing matrix @ E1B0 ===
[[0.545 0.091 0.    0.    0.091 0.091 0.    0.    0.    0.    0.091 0.
  0.    0.    0.    0.091]
 [0.091 0.582 0.109 0.    0.    0.    0.109 0.    0.    0.    0.    0.109
  0.    0.    0.    0.   ]
 [0.    0.109 0.564 0.109 0.    0.    0.    0.109 0.    0.    0.    0.
  0.109 0.    0.    0.   ]
 [0.    0.    0.109 0.564 0.109 0.    0.    0.    0.109 0.    0.    0.
  0.    0.109 0.    0.   ]
 [0.091 0.    0.    0.109 0.582 0.    0.    0.    0.    0.109 0.    0.
  0.    0.    0.109 0.   ]
 [0.091 0.    0.    0.    0.    0.909 0.    0.    0.    0.    0.    0.
  0.    0.    0.    0.   ]
 [0.    0.109 0.    0.    0.    0.    0.891 0.    0.    0.    0.    0.
  0.    0.    0.    0.   ]
 [0.    0.    0.109 0.    0.    0.    0.    0.891 0.    0.    0.    0.
  0.    0.    0.    0.   ]
 [0.    0.    0.    0.109 0.    0.    0.    0.    0.891 0.    0.    0.
  0.    0.    0.    0.   ]
 [0.    0.    0.    0.    0.109 0.    0.    0.    0.    0.891 0.    0.
  0.    0.    0.    0.   ]
 [0.091 0.    0.    0.    0.    0.    0.    0.    0.    0.    0.909 0.
  0.    0.    0.    0.   ]
 [0.    0.109 0.    0.    0.    0.    0.    0.    0.    0.    0.    0.891
  0.    0.    0.    0.   ]
 [0.    0.    0.109 0.    0.    0.    0.    0.    0.    0.    0.    0.
  0.891 0.    0.    0.   ]
 [0.    0.    0.    0.109 0.    0.    0.    0.    0.    0.    0.    0.
  0.    0.891 0.    0.   ]
 [0.    0.    0.    0.    0.109 0.    0.    0.    0.    0.    0.    0.
  0.    0.    0.891 0.   ]
 [0.091 0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.
  0.    0.    0.    0.909]]


[E 1B10 |   5632/60000 (  9%) ] Loss: 1.7932 top1= 38.1250
[E 1B20 |  10752/60000 ( 18%) ] Loss: 1.2504 top1= 60.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7229 top1= 80.6190

Train epoch 2
[E 2B0  |    512/60000 (  1%) ] Loss: 0.5040 top1= 82.5000
[E 2B10 |   5632/60000 (  9%) ] Loss: 0.6487 top1= 81.2500
[E 2B20 |  10752/60000 ( 18%) ] Loss: 0.5134 top1= 80.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4888 top1= 85.4868

Train epoch 3
[E 3B0  |    512/60000 (  1%) ] Loss: 0.1963 top1= 94.3750
[E 3B10 |   5632/60000 (  9%) ] Loss: 0.2048 top1= 92.5000
[E 3B20 |  10752/60000 ( 18%) ] Loss: 0.1325 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4195 top1= 87.1494

Train epoch 4
[E 4B0  |    512/60000 (  1%) ] Loss: 0.1037 top1= 97.5000
[E 4B10 |   5632/60000 (  9%) ] Loss: 0.0628 top1= 98.1250
[E 4B20 |  10752/60000 ( 18%) ] Loss: 0.0462 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3918 top1= 88.2913

Train epoch 5
[E 5B0  |    512/60000 (  1%) ] Loss: 0.0116 top1=100.0000
[E 5B10 |   5632/60000 (  9%) ] Loss: 0.0509 top1= 99.3750
[E 5B20 |  10752/60000 ( 18%) ] Loss: 0.0156 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3958 top1= 88.2612

Train epoch 6
[E 6B0  |    512/60000 (  1%) ] Loss: 0.0046 top1=100.0000
[E 6B10 |   5632/60000 (  9%) ] Loss: 0.0369 top1= 98.7500
[E 6B20 |  10752/60000 ( 18%) ] Loss: 0.0058 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3924 top1= 88.5417

Train epoch 7
[E 7B0  |    512/60000 (  1%) ] Loss: 0.0089 top1=100.0000
[E 7B10 |   5632/60000 (  9%) ] Loss: 0.0213 top1= 99.3750
[E 7B20 |  10752/60000 ( 18%) ] Loss: 0.0172 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3982 top1= 88.4115

Train epoch 8
[E 8B0  |    512/60000 (  1%) ] Loss: 0.0415 top1= 99.3750
[E 8B10 |   5632/60000 (  9%) ] Loss: 0.0107 top1= 99.3750
[E 8B20 |  10752/60000 ( 18%) ] Loss: 0.0113 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4138 top1= 87.9407

Train epoch 9
[E 9B0  |    512/60000 (  1%) ] Loss: 0.0119 top1= 99.3750
[E 9B10 |   5632/60000 (  9%) ] Loss: 0.0009 top1=100.0000
[E 9B20 |  10752/60000 ( 18%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4065 top1= 88.1911

Train epoch 10
[E10B0  |    512/60000 (  1%) ] Loss: 0.0137 top1= 99.3750
[E10B10 |   5632/60000 (  9%) ] Loss: 0.0015 top1=100.0000
[E10B20 |  10752/60000 ( 18%) ] Loss: 0.0255 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4171 top1= 87.9908

Train epoch 11
[E11B0  |    512/60000 (  1%) ] Loss: 0.0002 top1=100.0000
[E11B10 |   5632/60000 (  9%) ] Loss: 0.0004 top1=100.0000
[E11B20 |  10752/60000 ( 18%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4151 top1= 87.9507

Train epoch 12
[E12B0  |    512/60000 (  1%) ] Loss: 0.0002 top1=100.0000
[E12B10 |   5632/60000 (  9%) ] Loss: 0.0003 top1=100.0000
[E12B20 |  10752/60000 ( 18%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4164 top1= 87.9006

Train epoch 13
[E13B0  |    512/60000 (  1%) ] Loss: 0.0001 top1=100.0000
[E13B10 |   5632/60000 (  9%) ] Loss: 0.0003 top1=100.0000
[E13B20 |  10752/60000 ( 18%) ] Loss: 0.0003 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4178 top1= 87.8706

Train epoch 14
[E14B0  |    512/60000 (  1%) ] Loss: 0.0001 top1=100.0000
[E14B10 |   5632/60000 (  9%) ] Loss: 0.0002 top1=100.0000
[E14B20 |  10752/60000 ( 18%) ] Loss: 0.0002 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4201 top1= 87.8506

Train epoch 15
[E15B0  |    512/60000 (  1%) ] Loss: 0.0001 top1=100.0000
[E15B10 |   5632/60000 (  9%) ] Loss: 0.0002 top1=100.0000
[E15B20 |  10752/60000 ( 18%) ] Loss: 0.0002 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4223 top1= 87.8305

Train epoch 16
[E16B0  |    512/60000 (  1%) ] Loss: 0.0001 top1=100.0000
[E16B10 |   5632/60000 (  9%) ] Loss: 0.0002 top1=100.0000
[E16B20 |  10752/60000 ( 18%) ] Loss: 0.0001 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4243 top1= 87.8105

Train epoch 17
[E17B0  |    512/60000 (  1%) ] Loss: 0.0001 top1=100.0000
[E17B10 |   5632/60000 (  9%) ] Loss: 0.0001 top1=100.0000
[E17B20 |  10752/60000 ( 18%) ] Loss: 0.0001 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4262 top1= 87.7905

Train epoch 18
[E18B0  |    512/60000 (  1%) ] Loss: 0.0001 top1=100.0000
[E18B10 |   5632/60000 (  9%) ] Loss: 0.0001 top1=100.0000
[E18B20 |  10752/60000 ( 18%) ] Loss: 0.0001 top1=100.0000
