
=== 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 SGDMWorker(index=10, momentum=0.9)
=> Add worker SGDMWorker(index=11, momentum=0.9)
=> Add worker SGDMWorker(index=12, momentum=0.9)
=> Add worker SGDMWorker(index=13, momentum=0.9)
=> Add worker SGDMWorker(index=14, momentum=0.9)
=> Add worker SGDMWorker(index=15, momentum=0.9)
=> Add worker SGDMWorker(index=16, momentum=0.9)
=> Add worker SGDMWorker(index=17, momentum=0.9)
=> Add worker SGDMWorker(index=18, momentum=0.9)
=> Add worker SGDMWorker(index=19, momentum=0.9)
=> Add worker ByzantineWorker(index=20)
=> Add worker ByzantineWorker(index=21)

=== Start adding graph ===
<codes.graph_utils.Dumbbell object at 0x7f5aebe806d0>

Train epoch 1
[E 1B0  |    704/60000 (  1%) ] Loss: 2.3066 top1=  9.2188

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([3, 2, 2, 4, 3], device='cuda:0')
Worker 1 has targets: tensor([1, 0, 0, 4, 0], device='cuda:0')
Worker 2 has targets: tensor([4, 1, 0, 1, 0], device='cuda:0')
Worker 3 has targets: tensor([0, 1, 4, 1, 3], device='cuda:0')
Worker 4 has targets: tensor([0, 4, 1, 2, 4], device='cuda:0')
Worker 5 has targets: tensor([2, 2, 4, 4, 4], device='cuda:0')
Worker 6 has targets: tensor([1, 1, 4, 4, 3], device='cuda:0')
Worker 7 has targets: tensor([4, 4, 1, 3, 0], device='cuda:0')
Worker 8 has targets: tensor([1, 3, 1, 0, 4], device='cuda:0')
Worker 9 has targets: tensor([1, 3, 3, 3, 1], device='cuda:0')
Worker 10 has targets: tensor([8, 9, 7, 7, 9], device='cuda:0')
Worker 11 has targets: tensor([8, 9, 6, 6, 7], device='cuda:0')
Worker 12 has targets: tensor([8, 6, 5, 7, 8], device='cuda:0')
Worker 13 has targets: tensor([7, 6, 9, 6, 5], device='cuda:0')
Worker 14 has targets: tensor([8, 5, 8, 6, 7], device='cuda:0')
Worker 15 has targets: tensor([9, 5, 6, 8, 6], device='cuda:0')
Worker 16 has targets: tensor([7, 7, 8, 5, 8], device='cuda:0')
Worker 17 has targets: tensor([9, 7, 5, 6, 6], device='cuda:0')
Worker 18 has targets: tensor([7, 7, 7, 6, 6], device='cuda:0')
Worker 19 has targets: tensor([5, 7, 9, 9, 7], device='cuda:0')
Worker 20 has targets: tensor([3, 2, 2, 4, 3], device='cuda:0')
Worker 21 has targets: tensor([8, 9, 7, 7, 9], device='cuda:0')


[E 1B10 |   7744/60000 ( 13%) ] Loss: 1.0279 top1= 62.3438
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.4002 top1= 87.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7368 top1= 78.4255


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.1674 top1= 49.2889


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8722 top1= 44.2508

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2818 top1= 90.7812
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1886 top1= 93.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1976 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6943 top1= 84.1947


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6744 top1= 49.8197


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7177 top1= 45.8634

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1619 top1= 94.5312
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1092 top1= 96.5625
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1194 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6359 top1= 85.5469


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7197 top1= 50.1302


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8956 top1= 46.1739

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1125 top1= 96.7188
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0785 top1= 97.8125
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0767 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5814 top1= 85.9275


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0332 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0638 top1= 46.5144

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0763 top1= 98.2812
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0570 top1= 98.4375
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0527 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5443 top1= 85.8674


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3076 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2878 top1= 46.7348

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0545 top1= 98.5938
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0373 top1= 99.2188
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0400 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5093 top1= 86.3682


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5826 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4213 top1= 46.8850

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0415 top1= 99.0625
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0266 top1= 99.2188
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0275 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4820 top1= 86.1378


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9586 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8309 top1= 46.9251

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0308 top1= 99.3750
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0191 top1= 99.6875
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0212 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4636 top1= 85.9776


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0832 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4615 top1= 46.7949

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0232 top1= 99.3750
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0137 top1= 99.8438
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0220 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4729 top1= 85.0260


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1119 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8735 top1= 46.9351

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0140 top1= 99.6875
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0107 top1= 99.8438
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0104 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4778 top1= 84.5853


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3604 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1798 top1= 46.8049

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0147 top1= 99.6875
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0097 top1= 99.8438
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0101 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4520 top1= 85.6370


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3641 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.4429 top1= 46.8950

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0089 top1= 99.5312
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0109 top1= 99.6875
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0091 top1= 99.8438
