
=== 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 0x7f4da72da310>

Train epoch 1
[E 1B0  |    512/60000 (  1%) ] Loss: 2.3055 top1= 12.5000

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([9, 6, 7, 7, 2], device='cuda:0')
Worker 1 has targets: tensor([3, 8, 4, 0, 8], device='cuda:0')
Worker 2 has targets: tensor([5, 9, 1, 6, 8], device='cuda:0')
Worker 3 has targets: tensor([4, 9, 8, 7, 5], device='cuda:0')
Worker 4 has targets: tensor([7, 3, 7, 8, 7], device='cuda:0')
Worker 5 has targets: tensor([4, 1, 3, 9, 1], device='cuda:0')
Worker 6 has targets: tensor([9, 3, 3, 2, 9], device='cuda:0')
Worker 7 has targets: tensor([6, 2, 5, 1, 3], device='cuda:0')
Worker 8 has targets: tensor([8, 5, 1, 0, 1], device='cuda:0')
Worker 9 has targets: tensor([8, 0, 6, 7, 2], device='cuda:0')
Worker 10 has targets: tensor([7, 2, 0, 9, 4], device='cuda:0')
Worker 11 has targets: tensor([4, 1, 1, 2, 8], device='cuda:0')
Worker 12 has targets: tensor([8, 6, 4, 6, 6], device='cuda:0')
Worker 13 has targets: tensor([9, 5, 4, 8, 5], device='cuda:0')
Worker 14 has targets: tensor([4, 5, 0, 7, 1], device='cuda:0')
Worker 15 has targets: tensor([0, 4, 0, 7, 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: 2.0305 top1= 31.8750
[E 1B20 |  10752/60000 ( 18%) ] Loss: 1.1696 top1= 67.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7873 top1= 83.4936

Train epoch 2
[E 2B0  |    512/60000 (  1%) ] Loss: 0.7518 top1= 73.7500
[E 2B10 |   5632/60000 (  9%) ] Loss: 0.7497 top1= 76.8750
[E 2B20 |  10752/60000 ( 18%) ] Loss: 0.3823 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5620 top1= 87.7304

Train epoch 3
[E 3B0  |    512/60000 (  1%) ] Loss: 0.2343 top1= 91.8750
[E 3B10 |   5632/60000 (  9%) ] Loss: 0.2413 top1= 92.5000
[E 3B20 |  10752/60000 ( 18%) ] Loss: 0.1175 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4876 top1= 89.4531

Train epoch 4
[E 4B0  |    512/60000 (  1%) ] Loss: 0.1142 top1= 95.6250
[E 4B10 |   5632/60000 (  9%) ] Loss: 0.0756 top1= 96.8750
[E 4B20 |  10752/60000 ( 18%) ] Loss: 0.0959 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4533 top1= 89.6134

Train epoch 5
[E 5B0  |    512/60000 (  1%) ] Loss: 0.0562 top1= 98.1250
[E 5B10 |   5632/60000 (  9%) ] Loss: 0.0653 top1= 97.5000
[E 5B20 |  10752/60000 ( 18%) ] Loss: 0.0158 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4284 top1= 89.9740

Train epoch 6
[E 6B0  |    512/60000 (  1%) ] Loss: 0.0341 top1= 98.7500
[E 6B10 |   5632/60000 (  9%) ] Loss: 0.0450 top1= 98.1250
[E 6B20 |  10752/60000 ( 18%) ] Loss: 0.0203 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3968 top1= 89.2929

Train epoch 7
[E 7B0  |    512/60000 (  1%) ] Loss: 0.0372 top1= 99.3750
[E 7B10 |   5632/60000 (  9%) ] Loss: 0.0472 top1= 98.7500
[E 7B20 |  10752/60000 ( 18%) ] Loss: 0.0190 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3853 top1= 89.7436

Train epoch 8
[E 8B0  |    512/60000 (  1%) ] Loss: 0.0310 top1= 98.7500
[E 8B10 |   5632/60000 (  9%) ] Loss: 0.0691 top1= 99.3750
[E 8B20 |  10752/60000 ( 18%) ] Loss: 0.0319 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3742 top1= 89.8538

Train epoch 9
[E 9B0  |    512/60000 (  1%) ] Loss: 0.0700 top1= 98.7500
[E 9B10 |   5632/60000 (  9%) ] Loss: 0.0937 top1= 96.2500
[E 9B20 |  10752/60000 ( 18%) ] Loss: 0.0995 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4089 top1= 88.7119

Train epoch 10
[E10B0  |    512/60000 (  1%) ] Loss: 0.0577 top1= 98.1250
[E10B10 |   5632/60000 (  9%) ] Loss: 0.1632 top1= 96.8750
[E10B20 |  10752/60000 ( 18%) ] Loss: 0.3286 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4094 top1= 88.2612

Train epoch 11
[E11B0  |    512/60000 (  1%) ] Loss: 0.7895 top1= 93.7500
[E11B10 |   5632/60000 (  9%) ] Loss: 0.4432 top1= 96.2500
[E11B20 |  10752/60000 ( 18%) ] Loss: 0.4551 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4937 top1= 88.8922

Train epoch 12
[E12B0  |    512/60000 (  1%) ] Loss: 0.8766 top1= 96.8750
[E12B10 |   5632/60000 (  9%) ] Loss: 0.4762 top1= 96.8750
[E12B20 |  10752/60000 ( 18%) ] Loss: 0.2504 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6337 top1= 88.9123

Train epoch 13
[E13B0  |    512/60000 (  1%) ] Loss: 0.0094 top1= 99.3750
[E13B10 |   5632/60000 (  9%) ] Loss: 0.4635 top1= 96.8750
[E13B20 |  10752/60000 ( 18%) ] Loss: 0.1477 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5920 top1= 90.3145

Train epoch 14
[E14B0  |    512/60000 (  1%) ] Loss: 0.1259 top1= 98.7500
[E14B10 |   5632/60000 (  9%) ] Loss: 0.1721 top1= 96.2500
[E14B20 |  10752/60000 ( 18%) ] Loss: 0.9026 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5758 top1= 89.3630

Train epoch 15
[E15B0  |    512/60000 (  1%) ] Loss: 0.1790 top1= 97.5000
[E15B10 |   5632/60000 (  9%) ] Loss: 0.3458 top1= 96.2500
[E15B20 |  10752/60000 ( 18%) ] Loss: 1.1635 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5133 top1= 89.3329

Train epoch 16
[E16B0  |    512/60000 (  1%) ] Loss: 1.6054 top1= 95.6250
[E16B10 |   5632/60000 (  9%) ] Loss: 0.4727 top1= 93.1250
[E16B20 |  10752/60000 ( 18%) ] Loss: 0.1935 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6340 top1= 86.7889

Train epoch 17
[E17B0  |    512/60000 (  1%) ] Loss: 0.9180 top1= 98.7500
[E17B10 |   5632/60000 (  9%) ] Loss: 1.5364 top1= 97.5000
[E17B20 |  10752/60000 ( 18%) ] Loss: 1.8272 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6574 top1= 87.5401

Train epoch 18
[E18B0  |    512/60000 (  1%) ] Loss: 0.9728 top1= 97.5000
[E18B10 |   5632/60000 (  9%) ] Loss: 0.4365 top1= 98.7500
[E18B20 |  10752/60000 ( 18%) ] Loss: 2.0854 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8406 top1= 85.4768

Train epoch 19
[E19B0  |    512/60000 (  1%) ] Loss: 7.8500 top1= 95.6250
[E19B10 |   5632/60000 (  9%) ] Loss: 13.0777 top1= 96.2500
[E19B20 |  10752/60000 ( 18%) ] Loss: nan top1= 78.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057

Train epoch 20
[E20B0  |    512/60000 (  1%) ] Loss: nan top1= 80.0000
[E20B10 |   5632/60000 (  9%) ] Loss: nan top1= 78.1250
[E20B20 |  10752/60000 ( 18%) ] Loss: nan top1= 80.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057

Train epoch 21
[E21B0  |    512/60000 (  1%) ] Loss: nan top1= 81.2500
[E21B10 |   5632/60000 (  9%) ] Loss: nan top1= 81.8750
[E21B20 |  10752/60000 ( 18%) ] Loss: nan top1= 79.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057

Train epoch 22
[E22B0  |    512/60000 (  1%) ] Loss: nan top1= 81.2500
[E22B10 |   5632/60000 (  9%) ] Loss: nan top1= 80.6250
[E22B20 |  10752/60000 ( 18%) ] Loss: nan top1= 78.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057

Train epoch 23
[E23B0  |    512/60000 (  1%) ] Loss: nan top1= 81.8750
[E23B10 |   5632/60000 (  9%) ] Loss: nan top1= 80.6250
[E23B20 |  10752/60000 ( 18%) ] Loss: nan top1= 80.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057

Train epoch 24
[E24B0  |    512/60000 (  1%) ] Loss: nan top1= 79.3750
[E24B10 |   5632/60000 (  9%) ] Loss: nan top1= 79.3750
[E24B20 |  10752/60000 ( 18%) ] Loss: nan top1= 80.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057

Train epoch 25
[E25B0  |    512/60000 (  1%) ] Loss: nan top1= 81.2500
[E25B10 |   5632/60000 (  9%) ] Loss: nan top1= 79.3750
[E25B20 |  10752/60000 ( 18%) ] Loss: nan top1= 78.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057

Train epoch 26
[E26B0  |    512/60000 (  1%) ] Loss: nan top1= 79.3750
[E26B10 |   5632/60000 (  9%) ] Loss: nan top1= 79.3750
[E26B20 |  10752/60000 ( 18%) ] Loss: nan top1= 80.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057

Train epoch 27
[E27B0  |    512/60000 (  1%) ] Loss: nan top1= 81.2500
[E27B10 |   5632/60000 (  9%) ] Loss: nan top1= 79.3750
[E27B20 |  10752/60000 ( 18%) ] Loss: nan top1= 79.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057

Train epoch 28
[E28B0  |    512/60000 (  1%) ] Loss: nan top1= 80.0000
[E28B10 |   5632/60000 (  9%) ] Loss: nan top1= 79.3750
[E28B20 |  10752/60000 ( 18%) ] Loss: nan top1= 78.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057

Train epoch 29
[E29B0  |    512/60000 (  1%) ] Loss: nan top1= 76.8750
[E29B10 |   5632/60000 (  9%) ] Loss: nan top1= 80.0000
[E29B20 |  10752/60000 ( 18%) ] Loss: nan top1= 79.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057

Train epoch 30
[E30B0  |    512/60000 (  1%) ] Loss: nan top1= 81.2500
[E30B10 |   5632/60000 (  9%) ] Loss: nan top1= 80.6250
[E30B20 |  10752/60000 ( 18%) ] Loss: nan top1= 80.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057

