
=== 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 0x7ff9cb1852e0>

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: 1.4215 top1= 51.5625
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.8337 top1= 72.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3716 top1= 77.5541


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1627 top1= 48.4475


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9942 top1= 42.5581

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.5592 top1= 83.4375
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.3849 top1= 87.9688
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.3979 top1= 87.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0330 top1= 82.0012


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8164 top1= 49.5292


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6273 top1= 44.4211

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2865 top1= 91.0938
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.2398 top1= 92.9688
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.2629 top1= 91.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9198 top1= 83.1330


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1283 top1= 49.6494


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0123 top1= 44.8317

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.2546 top1= 92.3438
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1803 top1= 94.5312
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.2243 top1= 93.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8201 top1= 83.4836


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5192 top1= 49.8097


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5601 top1= 45.2123

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.2027 top1= 93.9062
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1697 top1= 94.8438
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.2331 top1= 92.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8082 top1= 83.5737


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4657 top1= 49.9199


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2857 top1= 45.4026

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1982 top1= 94.0625
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1470 top1= 95.7812
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1848 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7815 top1= 84.1046


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4923 top1= 50.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3144 top1= 45.7532

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1704 top1= 95.0000
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1355 top1= 95.1562
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1730 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7383 top1= 84.8257


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6768 top1= 50.1202


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5370 top1= 46.0337

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1443 top1= 96.2500
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1157 top1= 96.2500
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1469 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7309 top1= 84.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6233 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4270 top1= 46.1238

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1591 top1= 95.1562
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1097 top1= 96.7188
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1354 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7158 top1= 85.7071


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6258 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4746 top1= 46.2640

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1247 top1= 96.5625
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0999 top1= 97.3438
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1196 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6862 top1= 86.1078


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8056 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6304 top1= 46.3341

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1184 top1= 96.8750
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0916 top1= 97.6562
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1199 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6841 top1= 86.3582


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7169 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5012 top1= 46.3942

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1087 top1= 96.8750
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0834 top1= 97.1875
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1005 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6703 top1= 86.5284


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7285 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4950 top1= 46.5545

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1221 top1= 96.0938
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0772 top1= 97.5000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1003 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6495 top1= 86.9491


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8772 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6383 top1= 46.5745

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0904 top1= 98.2812
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0717 top1= 97.9688
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0767 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6515 top1= 86.8089


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8322 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5805 top1= 46.5745

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0924 top1= 97.8125
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0623 top1= 97.8125
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0854 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6391 top1= 86.9391


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8711 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6234 top1= 46.7648

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0843 top1= 97.6562
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0611 top1= 98.1250
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0723 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6178 top1= 87.1394


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9600 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7509 top1= 46.7949

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0786 top1= 97.9688
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0515 top1= 98.1250
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0728 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6184 top1= 87.5901


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8660 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6728 top1= 46.8249

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0794 top1= 97.9688
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0503 top1= 98.2812
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0628 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6159 top1= 87.0393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9269 top1= 50.5308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7467 top1= 46.8850

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0728 top1= 98.2812
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0448 top1= 98.7500
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0574 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5934 top1= 87.4700


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0506 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8467 top1= 46.9351

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0686 top1= 98.4375
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0511 top1= 98.2812
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0557 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5912 top1= 88.1010


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0054 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8027 top1= 46.9952

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0717 top1= 98.4375
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0449 top1= 98.4375
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0582 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5956 top1= 86.9491


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9781 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8536 top1= 46.9752

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0643 top1= 98.1250
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0356 top1= 98.9062
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0453 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5712 top1= 87.6302


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1303 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9705 top1= 47.0252

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0622 top1= 98.2812
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0403 top1= 99.2188
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0511 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5714 top1= 87.8405


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1076 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9743 top1= 47.0353

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0537 top1= 98.7500
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0295 top1= 99.2188
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0525 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5745 top1= 87.3197


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0854 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9454 top1= 47.0954

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0611 top1= 98.9062
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0277 top1= 99.5312
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0381 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5564 top1= 87.8806


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2312 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1436 top1= 47.0453

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0411 top1= 99.2188
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0354 top1= 99.0625
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0335 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5561 top1= 87.7304


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1988 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1247 top1= 47.1354

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0465 top1= 98.9062
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0281 top1= 99.2188
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0379 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5585 top1= 87.7204


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1900 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0955 top1= 47.1755

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0401 top1= 99.2188
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0229 top1= 99.6875
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0304 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5411 top1= 88.0409


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2908 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2737 top1= 47.1254

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0389 top1= 98.9062
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0336 top1= 98.7500
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0558 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5430 top1= 87.9708


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2564 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2543 top1= 47.1855

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0464 top1= 98.7500
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0199 top1= 99.6875
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0351 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5442 top1= 87.8606


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2715 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2602 top1= 47.1955

