
=== 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 ByzantineWorker(index=10)
=> Add worker ByzantineWorker(index=11)

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7fae7545b9d0>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.3109 top1=  9.6875

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 1 has targets: tensor([2, 1, 4, 4, 0], device='cuda:0')
Worker 2 has targets: tensor([3, 1, 4, 1, 3], device='cuda:0')
Worker 3 has targets: tensor([2, 3, 0, 0, 1], device='cuda:0')
Worker 4 has targets: tensor([2, 1, 1, 4, 2], device='cuda:0')
Worker 5 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')
Worker 6 has targets: tensor([9, 9, 6, 7, 9], device='cuda:0')
Worker 7 has targets: tensor([7, 5, 7, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([8, 9, 9, 5, 7], device='cuda:0')
Worker 9 has targets: tensor([8, 8, 7, 5, 9], device='cuda:0')
Worker 10 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 11 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')


[E 1B10 |   4224/60000 (  7%) ] Loss: 1.0084 top1= 64.0625
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2698 top1= 90.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2122 top1= 50.3706


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.6506 top1= 48.6478


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3388 top1= 43.9804

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3707 top1= 91.2500
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.2800 top1= 91.2500
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1723 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.5408 top1= 52.1034


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1728 top1= 49.7696


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1436 top1= 48.8381

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1678 top1= 95.0000
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1531 top1= 95.0000
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1275 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8000 top1= 51.6026


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0294 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7418 top1= 53.5256

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1025 top1= 97.1875
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0979 top1= 96.5625
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0919 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8843 top1= 51.6827


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2001 top1= 50.1803


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6082 top1= 56.6807

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0791 top1= 98.1250
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0723 top1= 98.1250
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0618 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9715 top1= 52.0933


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4708 top1= 50.2003


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5441 top1= 58.5537

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0610 top1= 98.7500
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0517 top1= 99.3750
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0551 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0129 top1= 52.5441


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8351 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6009 top1= 58.8742

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0517 top1= 98.7500
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0491 top1= 98.7500
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0546 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9779 top1= 52.7744


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2403 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6220 top1= 59.4151

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0465 top1= 98.7500
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0632 top1= 97.8125
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0791 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9904 top1= 53.0749


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5461 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7828 top1= 57.0413

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0796 top1= 97.1875
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0431 top1= 99.0625
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0391 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0280 top1= 53.7861


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8251 top1= 50.3005


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4186 top1= 62.4900

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0412 top1= 99.0625
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0385 top1= 99.6875
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0549 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0362 top1= 53.2652


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0311 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3873 top1= 63.2412

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0460 top1= 98.4375
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0542 top1= 99.0625
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0600 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.1514 top1= 53.2953


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1851 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2368 top1= 67.8986

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0435 top1= 98.4375
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0556 top1= 98.1250
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0541 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2027 top1= 53.5757


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3133 top1= 50.3005


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3789 top1= 65.7151

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0293 top1= 99.3750
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0338 top1= 99.6875
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0488 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2323 top1= 53.7360


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4043 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5566 top1= 64.3229

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0371 top1= 99.0625
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0279 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0429 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3752 top1= 53.4455


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5217 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4003 top1= 64.7336

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0568 top1= 98.1250
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0517 top1= 98.7500
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0405 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.1613 top1= 53.6358


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6537 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4083 top1= 63.2312

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0476 top1= 98.4375
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0764 top1= 97.5000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0634 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0355 top1= 54.8478


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.7656 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4964 top1= 61.3582

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0427 top1= 99.0625
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0517 top1= 98.1250
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0422 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9847 top1= 54.5272


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8571 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5417 top1= 63.1110

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0412 top1= 98.4375
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0434 top1= 99.0625
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0510 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.1347 top1= 54.1266


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9432 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4045 top1= 64.7035

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0296 top1= 99.3750
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0311 top1= 99.3750
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0338 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3234 top1= 53.4455


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.0220 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3614 top1= 65.0441

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0284 top1= 99.3750
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0327 top1= 99.6875
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0429 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3827 top1= 53.8562


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.0935 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5210 top1= 63.3413

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0344 top1= 99.0625
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0381 top1= 98.7500
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0372 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3266 top1= 53.8662


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1613 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5946 top1= 62.9006

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0592 top1= 97.1875
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0585 top1= 98.1250
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0681 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2744 top1= 54.2768


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2239 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6736 top1= 60.1162

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0554 top1= 98.4375
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0503 top1= 98.4375
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0314 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2859 top1= 53.5256


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2826 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5040 top1= 63.6218

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0457 top1= 98.7500
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0887 top1= 95.9375
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0372 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.1538 top1= 53.8061


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.3382 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7161 top1= 60.7572

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0422 top1= 99.0625
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0638 top1= 97.5000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0644 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9425 top1= 55.0381


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.3898 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7807 top1= 59.6855

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0554 top1= 97.8125
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0531 top1= 98.7500
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0671 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8230 top1= 56.2600


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.4401 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7069 top1= 59.6655

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0360 top1= 99.0625
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0417 top1= 99.3750
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0464 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0558 top1= 54.4571


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.4894 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7099 top1= 60.6971

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0325 top1= 99.3750
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0220 top1= 99.6875
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0324 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2884 top1= 53.7460


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.5351 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6450 top1= 60.7272

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0535 top1= 97.5000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0381 top1= 99.6875
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0365 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4033 top1= 53.4555


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.5780 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6737 top1= 61.4583

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0725 top1= 97.5000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0306 top1= 99.3750
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0379 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2304 top1= 54.2768


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.6203 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5969 top1= 62.7704

