
=== 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.DumbbellVariant object at 0x7fea003f32b0>

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: 1.0376 top1= 61.8750
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3999 top1= 88.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7365 top1= 78.0950


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.0041 top1= 49.2989


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6565 top1= 44.1506

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2842 top1= 91.0938
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1923 top1= 93.9062
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1976 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6858 top1= 83.9243


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5577 top1= 49.8197


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3498 top1= 45.7632

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1610 top1= 94.8438
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1093 top1= 97.0312
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1260 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6251 top1= 84.7055


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4504 top1= 50.1402


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4494 top1= 46.1438

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1195 top1= 96.8750
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0792 top1= 98.1250
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0821 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5736 top1= 85.5068


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5578 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4601 top1= 46.3642

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0833 top1= 97.9688
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0649 top1= 98.1250
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0580 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5347 top1= 85.8674


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6906 top1= 50.4407


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4958 top1= 46.5946

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0603 top1= 98.9062
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0465 top1= 98.7500
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0484 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4982 top1= 86.5284


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7756 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5469 top1= 46.7448

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0452 top1= 99.0625
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0314 top1= 99.2188
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0420 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4709 top1= 87.1995


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8780 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5087 top1= 46.8149

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0362 top1= 99.2188
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0242 top1= 99.5312
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0264 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4501 top1= 87.0393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8935 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8392 top1= 46.8149

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0316 top1= 99.0625
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0181 top1= 99.6875
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0205 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4415 top1= 86.5785


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9077 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1988 top1= 46.8750

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0177 top1= 99.5312
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0121 top1=100.0000
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0191 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4608 top1= 85.4467


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7909 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5133 top1= 46.8450

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0195 top1= 99.5312
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0134 top1= 99.6875
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0108 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4362 top1= 86.3181


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9234 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6853 top1= 46.9651

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0069 top1= 99.8438
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0083 top1=100.0000
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0107 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4210 top1= 86.9191


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1048 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7504 top1= 47.1154

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0054 top1=100.0000
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0050 top1=100.0000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0186 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4174 top1= 86.7288


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3769 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4869 top1= 47.0954

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0039 top1=100.0000
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0046 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0071 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3794 top1= 88.6218


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.6715 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6028 top1= 46.8850

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0147 top1= 99.5312
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0031 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0137 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3863 top1= 88.0609


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8484 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1183 top1= 46.7849

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0048 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0118 top1= 99.5312
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0102 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4101 top1= 86.6486


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0044 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4574 top1= 47.0252

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0049 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0033 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3992 top1= 87.0994


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1356 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5479 top1= 47.2256

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4031 top1= 86.6887


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2502 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7683 top1= 47.2356

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3939 top1= 87.0292


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3604 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9706 top1= 47.2356

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3792 top1= 87.7204


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4728 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1240 top1= 47.2356

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3750 top1= 87.8305


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5690 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2176 top1= 47.2857

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0010 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3752 top1= 87.8005


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6648 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3319 top1= 47.2857

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0008 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3746 top1= 87.7804


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.7498 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4572 top1= 47.2957

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0007 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3741 top1= 87.7304


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8303 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5649 top1= 47.2756

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0007 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3739 top1= 87.7103


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9085 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6555 top1= 47.2857

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0006 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3738 top1= 87.7304


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9800 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7387 top1= 47.2857

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0006 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3737 top1= 87.7204


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.0517 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8150 top1= 47.2756

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0005 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3737 top1= 87.7103


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1123 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8874 top1= 47.2857

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0005 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3735 top1= 87.6903


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1743 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9533 top1= 47.2857

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0005 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3735 top1= 87.6903


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2338 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0176 top1= 47.2857

