
=== 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 0x7fdb98e7f6d0>

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: 1.0429 top1= 61.4062
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.4023 top1= 88.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7318 top1= 78.4155


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9299 top1= 49.2588


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6446 top1= 44.3710

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2856 top1= 90.6250
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1951 top1= 93.4375
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1948 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6752 top1= 84.2748


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4834 top1= 49.7796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5382 top1= 45.8233

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1637 top1= 95.0000
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1096 top1= 96.5625
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1195 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6022 top1= 85.7672


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5308 top1= 50.1102


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7479 top1= 46.2139

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1154 top1= 96.7188
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0784 top1= 97.6562
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0789 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5542 top1= 86.2079


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8974 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7939 top1= 46.4944

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0784 top1= 98.4375
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0598 top1= 98.1250
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0545 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5075 top1= 86.8890


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1641 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0611 top1= 46.7047

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0549 top1= 98.9062
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0382 top1= 99.2188
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0407 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4675 top1= 87.6102


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4685 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2639 top1= 46.8550

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0409 top1= 99.3750
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0256 top1= 99.5312
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0294 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4370 top1= 87.7304


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.6653 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7773 top1= 46.8750

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0320 top1= 99.3750
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0181 top1= 99.6875
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0199 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4284 top1= 86.9491


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8313 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3411 top1= 46.7849

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0259 top1= 99.3750
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0134 top1= 99.8438
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0219 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4361 top1= 86.1579


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7491 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7297 top1= 46.8450

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0157 top1= 99.6875
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0099 top1= 99.8438
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0109 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4349 top1= 86.0377


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9716 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9682 top1= 46.7548

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0148 top1= 99.5312
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0073 top1=100.0000
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0095 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4193 top1= 86.6787


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2524 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2317 top1= 46.7248

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0123 top1= 99.5312
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0098 top1= 99.8438
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0105 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3938 top1= 87.5801


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4911 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3831 top1= 47.0954

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0057 top1=100.0000
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0083 top1=100.0000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0055 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3691 top1= 88.3914


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8832 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0749 top1= 47.0753

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0035 top1=100.0000
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0031 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0057 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3641 top1= 88.6819


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1266 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1371 top1= 46.9251

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0132 top1= 99.6875
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0027 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0095 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3690 top1= 88.1410


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.3257 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.4619 top1= 47.1755

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3675 top1= 88.0909


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.5046 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5866 top1= 47.2456

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0021 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3742 top1= 87.4700


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.6701 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.7409 top1= 47.2356

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3745 top1= 87.4099


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.8206 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.9106 top1= 47.2556

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0009 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3692 top1= 87.5601


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9552 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.1568 top1= 47.2656

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0007 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3622 top1= 87.9708


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.0811 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.3435 top1= 47.3057

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0007 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3600 top1= 88.0809


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.1952 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.4179 top1= 47.3057

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0006 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0007 top1=100.0000
