
=== 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 0x7f939c1f82b0>

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: 1.4210 top1= 51.0938
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.8525 top1= 71.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3719 top1= 77.1835


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1770 top1= 48.4375


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9690 top1= 42.3878

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.5584 top1= 82.0312
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.3903 top1= 87.5000
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.3632 top1= 89.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0330 top1= 81.5405


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8342 top1= 49.4792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6469 top1= 44.4111

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.3008 top1= 90.6250
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.2287 top1= 93.5938
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.2730 top1= 91.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9164 top1= 82.7925


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1786 top1= 49.7095


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0497 top1= 44.8417

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.2520 top1= 92.0312
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1775 top1= 94.6875
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.2263 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8191 top1= 83.4034


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5741 top1= 49.8197


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5840 top1= 45.2424

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.2072 top1= 93.7500
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1699 top1= 95.0000
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.2269 top1= 93.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8067 top1= 83.3333


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5188 top1= 49.9499


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2986 top1= 45.3225

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1970 top1= 93.7500
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1453 top1= 95.4688
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1863 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7785 top1= 83.7340


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5723 top1= 50.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3428 top1= 45.8133

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1667 top1= 95.0000
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1391 top1= 95.3125
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1748 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7360 top1= 84.3450


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7354 top1= 50.1603


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5937 top1= 46.0236

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1456 top1= 95.9375
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1172 top1= 96.4062
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1486 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7297 top1= 84.6955


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6788 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4715 top1= 46.1338

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1624 top1= 95.1562
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1128 top1= 96.0938
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1389 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7084 top1= 85.6170


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6988 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5080 top1= 46.2540

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1285 top1= 96.5625
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.1022 top1= 97.1875
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1227 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6825 top1= 85.6671


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8606 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6852 top1= 46.3542

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1256 top1= 96.8750
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0953 top1= 97.1875
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1255 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6825 top1= 85.8073


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7718 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5425 top1= 46.3442

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1090 top1= 97.0312
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0901 top1= 97.1875
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1024 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6649 top1= 86.3281


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8072 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5403 top1= 46.5244

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1267 top1= 95.9375
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0802 top1= 97.6562
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1016 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6433 top1= 86.4884


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9316 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6904 top1= 46.5244

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0963 top1= 97.8125
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0785 top1= 97.6562
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0852 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6488 top1= 86.4183


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8640 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6233 top1= 46.5545

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0940 top1= 97.5000
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0678 top1= 97.6562
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0932 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6354 top1= 86.8089


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9096 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6624 top1= 46.7248

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0862 top1= 97.3438
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0643 top1= 98.1250
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0767 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6139 top1= 86.9191


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0166 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8351 top1= 46.7348

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0829 top1= 97.6562
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0561 top1= 98.1250
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0775 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6132 top1= 87.3698


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9204 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7159 top1= 46.8049

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0775 top1= 97.6562
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0531 top1= 98.1250
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0674 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6156 top1= 86.7288


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9533 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8004 top1= 46.8149

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0740 top1= 97.9688
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0471 top1= 98.2812
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0605 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5905 top1= 87.0893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0621 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9258 top1= 46.9451

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0699 top1= 97.9688
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0548 top1= 97.5000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0604 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5880 top1= 87.7003


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0461 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8635 top1= 46.9351

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0766 top1= 97.9688
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0510 top1= 98.2812
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0626 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5913 top1= 86.6486


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9856 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9465 top1= 46.8650

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0705 top1= 97.8125
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0404 top1= 98.2812
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0476 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5664 top1= 87.5200


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1346 top1= 50.5308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0196 top1= 46.9852

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0614 top1= 98.4375
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0450 top1= 98.4375
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0564 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5646 top1= 87.7905


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1326 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0451 top1= 47.0052

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0583 top1= 98.7500
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0330 top1= 98.9062
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0559 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5688 top1= 86.9391


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1067 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0373 top1= 47.0453

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0625 top1= 98.7500
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0297 top1= 99.3750
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0406 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5493 top1= 87.7504


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2560 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1881 top1= 47.0453

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0431 top1= 99.2188
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0380 top1= 98.9062
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0370 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5498 top1= 87.6302


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2692 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1587 top1= 47.0954

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0454 top1= 99.2188
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0302 top1= 98.9062
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0387 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5502 top1= 87.1795


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2242 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1441 top1= 47.0954

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0430 top1= 99.2188
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0252 top1= 99.5312
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0314 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5320 top1= 87.9607


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3263 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3084 top1= 47.1354

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0414 top1= 99.3750
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0383 top1= 98.5938
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0526 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5377 top1= 87.4700


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3348 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3164 top1= 47.1454

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0518 top1= 98.5938
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0218 top1= 99.5312
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0379 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5393 top1= 87.4499


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3319 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3079 top1= 47.2155

