
=== 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 0x7fa27b87db20>

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: 1.8794 top1= 38.7500
[E 1B20 |  10752/60000 ( 18%) ] Loss: 1.2935 top1= 58.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1811 top1= 63.7019

Train epoch 2
[E 2B0  |    512/60000 (  1%) ] Loss: 0.4511 top1= 84.3750
[E 2B10 |   5632/60000 (  9%) ] Loss: 0.7664 top1= 81.2500
[E 2B20 |  10752/60000 ( 18%) ] Loss: 0.4872 top1= 84.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0127 top1= 70.3626

Train epoch 3
[E 3B0  |    512/60000 (  1%) ] Loss: 0.2277 top1= 93.7500
[E 3B10 |   5632/60000 (  9%) ] Loss: 0.1853 top1= 93.1250
[E 3B20 |  10752/60000 ( 18%) ] Loss: 0.3552 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9806 top1= 71.2039

Train epoch 4
[E 4B0  |    512/60000 (  1%) ] Loss: 0.1550 top1= 95.6250
[E 4B10 |   5632/60000 (  9%) ] Loss: 0.0809 top1= 96.8750
[E 4B20 |  10752/60000 ( 18%) ] Loss: 0.2961 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0494 top1= 66.4864

Train epoch 5
[E 5B0  |    512/60000 (  1%) ] Loss: 0.0515 top1= 97.5000
[E 5B10 |   5632/60000 (  9%) ] Loss: 0.4597 top1= 95.6250
[E 5B20 |  10752/60000 ( 18%) ] Loss: 0.9798 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9527 top1= 72.4659

Train epoch 6
[E 6B0  |    512/60000 (  1%) ] Loss: 36.8892 top1= 91.2500
[E 6B10 |   5632/60000 (  9%) ] Loss: 31026.6263 top1= 83.7500
[E 6B20 |  10752/60000 ( 18%) ] Loss: 350834508.8260 top1= 79.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=4190.8180 top1=  6.9311

Train epoch 7
[E 7B0  |    512/60000 (  1%) ] Loss: 1848.0924 top1= 79.3750
[E 7B10 |   5632/60000 (  9%) ] Loss: 10301.5478 top1= 78.1250
[E 7B20 |  10752/60000 ( 18%) ] Loss: 0.5055 top1= 78.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2538.4598 top1=  6.8510

Train epoch 8
[E 8B0  |    512/60000 (  1%) ] Loss: 0.5046 top1= 80.6250
[E 8B10 |   5632/60000 (  9%) ] Loss: 0.5315 top1= 78.1250
[E 8B20 |  10752/60000 ( 18%) ] Loss: 0.4907 top1= 78.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=5077.0783 top1=  9.2147

Train epoch 9
[E 9B0  |    512/60000 (  1%) ] Loss: 0.4949 top1= 79.3750
[E 9B10 |   5632/60000 (  9%) ] Loss: 0.5456 top1= 78.7500
[E 9B20 |  10752/60000 ( 18%) ] Loss: 0.6459 top1= 76.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=4284.1478 top1=  6.1098

Train epoch 10
[E10B0  |    512/60000 (  1%) ] Loss: 0.5515 top1= 78.1250
[E10B10 |   5632/60000 (  9%) ] Loss: 0.6427 top1= 76.2500
[E10B20 |  10752/60000 ( 18%) ] Loss: 203.1548 top1= 78.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1583.2060 top1=  9.5753

Train epoch 11
[E11B0  |    512/60000 (  1%) ] Loss: 0.5730 top1= 80.6250
[E11B10 |   5632/60000 (  9%) ] Loss: 0.9882 top1= 75.0000
[E11B20 |  10752/60000 ( 18%) ] Loss: 0.8373 top1= 78.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=761.6510 top1=  9.5753

Train epoch 12
[E12B0  |    512/60000 (  1%) ] Loss: 1.0601 top1= 76.2500
[E12B10 |   5632/60000 (  9%) ] Loss: 3.6146 top1= 75.6250
[E12B20 |  10752/60000 ( 18%) ] Loss: 1.0593 top1= 75.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=208.0597 top1=  9.5753

Train epoch 13
[E13B0  |    512/60000 (  1%) ] Loss: 0.4842 top1= 80.6250
[E13B10 |   5632/60000 (  9%) ] Loss: 0.9254 top1= 80.6250
[E13B20 |  10752/60000 ( 18%) ] Loss: 0.9975 top1= 81.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=197.3444 top1=  9.5753

Train epoch 14
[E14B0  |    512/60000 (  1%) ] Loss: 0.9753 top1= 88.1250
[E14B10 |   5632/60000 (  9%) ] Loss: 1.1739 top1= 83.7500
[E14B20 |  10752/60000 ( 18%) ] Loss: 0.9037 top1= 83.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=96.7947 top1= 11.6687

Train epoch 15
[E15B0  |    512/60000 (  1%) ] Loss: 0.5194 top1= 91.2500
[E15B10 |   5632/60000 (  9%) ] Loss: 4.8625 top1= 85.0000
[E15B20 |  10752/60000 ( 18%) ] Loss: 20.9783 top1= 77.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=54.2122 top1=  9.5753

Train epoch 16
[E16B0  |    512/60000 (  1%) ] Loss: 3.7189 top1= 85.0000
[E16B10 |   5632/60000 (  9%) ] Loss: 12.3975 top1= 67.5000
[E16B20 |  10752/60000 ( 18%) ] Loss: 1.4809 top1= 58.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.6225 top1=  6.9411

Train epoch 17
[E17B0  |    512/60000 (  1%) ] Loss: 1.1967 top1= 67.5000
[E17B10 |   5632/60000 (  9%) ] Loss: 1.2917 top1= 60.0000
[E17B20 |  10752/60000 ( 18%) ] Loss: 1.3739 top1= 55.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=4.6147 top1= 10.0962

Train epoch 18
[E18B0  |    512/60000 (  1%) ] Loss: 1.1729 top1= 67.5000
[E18B10 |   5632/60000 (  9%) ] Loss: 1.3268 top1= 59.3750
[E18B20 |  10752/60000 ( 18%) ] Loss: 1.3239 top1= 55.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=7.3147 top1= 10.0962

Train epoch 19
[E19B0  |    512/60000 (  1%) ] Loss: 1.1609 top1= 67.5000
[E19B10 |   5632/60000 (  9%) ] Loss: 2.4002 top1= 58.7500
[E19B20 |  10752/60000 ( 18%) ] Loss: 1.6048 top1= 54.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=15.3755 top1= 10.3766

Train epoch 20
[E20B0  |    512/60000 (  1%) ] Loss: 2.2089 top1= 65.0000
[E20B10 |   5632/60000 (  9%) ] Loss: 3.3959 top1= 55.6250
[E20B20 |  10752/60000 ( 18%) ] Loss: 9.7577 top1= 45.0000

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

