
=== 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 0x7f733d927490>

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: 1.4170 top1= 52.3438
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.8591 top1= 71.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3660 top1= 77.3938


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1246 top1= 48.4675


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9011 top1= 42.9688

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.5216 top1= 84.3750
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.3896 top1= 87.9688
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.3683 top1= 88.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0210 top1= 82.3217


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7754 top1= 49.5092


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5845 top1= 44.3910

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2924 top1= 91.4062
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.2321 top1= 93.2812
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.2704 top1= 91.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9001 top1= 83.2131


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0798 top1= 49.6695


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9525 top1= 44.8217

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.2556 top1= 92.0312
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1776 top1= 94.8438
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.2295 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8011 top1= 83.7540


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4566 top1= 49.8297


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4784 top1= 45.2023

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.2141 top1= 93.5938
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1697 top1= 94.8438
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.2359 top1= 92.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7815 top1= 83.5537


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3831 top1= 49.9199


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1966 top1= 45.2925

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.2027 top1= 93.9062
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1538 top1= 95.9375
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1879 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7515 top1= 84.2548


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3537 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1658 top1= 45.6931

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1827 top1= 94.2188
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1400 top1= 95.4688
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1815 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7015 top1= 84.8357


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4830 top1= 50.1703


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4169 top1= 45.9836

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1503 top1= 95.4688
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1253 top1= 95.4688
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1507 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6872 top1= 85.3566


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3846 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2259 top1= 46.1138

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1717 top1= 95.1562
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1246 top1= 95.7812
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1439 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6642 top1= 86.1478


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3941 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2776 top1= 46.2039

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1291 top1= 96.4062
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.1085 top1= 97.1875
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1310 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6356 top1= 86.1979


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4948 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4218 top1= 46.3341

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1224 top1= 96.8750
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.1008 top1= 97.5000
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1434 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6297 top1= 86.0677


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3441 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2402 top1= 46.3842

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1109 top1= 96.8750
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0928 top1= 97.0312
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1124 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6125 top1= 86.3482


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2980 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2073 top1= 46.4944

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1324 top1= 95.7812
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0874 top1= 97.3438
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1095 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5869 top1= 86.8590


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3897 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3122 top1= 46.5445

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0964 top1= 97.8125
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0779 top1= 97.8125
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0895 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5858 top1= 86.9191


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2607 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2336 top1= 46.5345

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0963 top1= 97.5000
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0894 top1= 97.1875
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0971 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5687 top1= 87.0893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3038 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2401 top1= 46.7047

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0858 top1= 97.5000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0696 top1= 98.1250
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0822 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5456 top1= 87.0393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3610 top1= 50.4407


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3425 top1= 46.6947

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0930 top1= 97.0312
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0583 top1= 98.4375
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0976 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5437 top1= 87.3297


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1894 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2366 top1= 46.7949

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0842 top1= 97.8125
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0632 top1= 97.9688
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0682 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5386 top1= 86.8590


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2593 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3401 top1= 46.7949

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0777 top1= 97.5000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0634 top1= 97.9688
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0683 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5177 top1= 87.2296


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3000 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4064 top1= 46.9251

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0726 top1= 98.2812
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0748 top1= 97.1875
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0635 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5151 top1= 87.6002


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2259 top1= 50.5308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3083 top1= 46.9752

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0800 top1= 98.2812
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0626 top1= 97.9688
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0653 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5159 top1= 86.5885


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1634 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3602 top1= 46.8450

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0703 top1= 97.9688
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0492 top1= 98.7500
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0539 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4920 top1= 87.1094


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2637 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4274 top1= 46.9251

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0663 top1= 98.2812
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0732 top1= 97.8125
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0625 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4922 top1= 87.1194


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1579 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3739 top1= 47.0353

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0596 top1= 98.5938
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0409 top1= 98.9062
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0628 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4954 top1= 86.4683


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0978 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3589 top1= 47.0453

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0713 top1= 98.4375
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0409 top1= 98.9062
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0448 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4764 top1= 87.2696


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2205 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4675 top1= 47.0152

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0465 top1= 99.0625
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0717 top1= 98.2812
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0470 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4730 top1= 87.3998


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1606 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3622 top1= 47.1254

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0520 top1= 98.7500
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0429 top1= 98.5938
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0509 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4707 top1= 87.0893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0923 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2907 top1= 47.0853

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0467 top1= 99.0625
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0327 top1= 99.3750
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0349 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4599 top1= 87.0393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1002 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4537 top1= 47.0553

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0474 top1= 98.7500
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0405 top1= 98.4375
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0661 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4612 top1= 87.2997


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1114 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3533 top1= 47.1554

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0687 top1= 97.8125
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0265 top1= 99.3750
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0413 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4553 top1= 87.1494


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0475 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3737 top1= 47.1554

