
=== 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 0x7fd6afe1d7f0>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.2959 top1= 10.0000

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


[E 1B10 |   4224/60000 (  7%) ] Loss: 1.9299 top1= 45.0000
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.8843 top1= 71.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5054 top1= 83.9643


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4969 top1= 83.7640


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5575 top1= 82.8726

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.7046 top1= 80.3125
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.4755 top1= 82.5000
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.3912 top1= 88.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3020 top1= 91.0757


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3043 top1= 90.8954


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3273 top1= 90.2845

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.3298 top1= 89.3750
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.2465 top1= 92.1875
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.2733 top1= 91.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2483 top1= 92.6683


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2606 top1= 92.2676


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2545 top1= 92.4079

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1787 top1= 94.6875
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.1387 top1= 96.2500
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.1587 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2303 top1= 93.2993


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2404 top1= 92.8786


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2433 top1= 92.7784

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.1266 top1= 96.2500
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0677 top1= 97.5000
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0909 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2399 top1= 93.2192


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2551 top1= 92.7784


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2466 top1= 92.9988

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.1048 top1= 96.8750
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0572 top1= 98.4375
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0390 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2350 top1= 93.4896


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2324 top1= 93.5797


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2685 top1= 92.7284

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0576 top1= 99.0625
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0316 top1= 99.6875
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0370 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2265 top1= 94.1106


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2495 top1= 93.6498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2268 top1= 93.9403

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0263 top1= 99.0625
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0479 top1= 98.7500
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0377 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2416 top1= 93.9804


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2757 top1= 93.2792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2570 top1= 93.2292

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0493 top1= 98.4375
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0318 top1= 99.0625
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0173 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2219 top1= 94.5813


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2433 top1= 94.0805


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2249 top1= 94.2909

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0236 top1= 99.3750
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0129 top1=100.0000
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0109 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2330 top1= 94.2508


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2569 top1= 93.9503


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2418 top1= 93.9203

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0084 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0097 top1=100.0000
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0103 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2461 top1= 94.2909


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2631 top1= 94.0605


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2563 top1= 93.7200

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0076 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0091 top1=100.0000
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0084 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2483 top1= 94.2408


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2736 top1= 93.8602


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2450 top1= 94.0805

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0095 top1= 99.6875
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0025 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0075 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2459 top1= 94.5813


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2607 top1= 94.2107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2433 top1= 94.3610

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0027 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0020 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2466 top1= 94.7416


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2645 top1= 94.4111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2422 top1= 94.4511

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0013 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2522 top1= 94.6715


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2670 top1= 94.4712


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2456 top1= 94.5212

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2541 top1= 94.6214


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2650 top1= 94.5012


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2495 top1= 94.4912

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2572 top1= 94.6815


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2677 top1= 94.5112


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2525 top1= 94.5012

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2598 top1= 94.6915


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2701 top1= 94.4912


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2552 top1= 94.5112

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2623 top1= 94.6915


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2724 top1= 94.4912


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2578 top1= 94.5212

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2646 top1= 94.6615


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2745 top1= 94.5012


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2600 top1= 94.5212

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2667 top1= 94.6414


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2765 top1= 94.4912


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2623 top1= 94.5112

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2687 top1= 94.6414


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2784 top1= 94.4912


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2643 top1= 94.4912

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0004 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2706 top1= 94.6414


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2802 top1= 94.4812


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2661 top1= 94.4912

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0004 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2724 top1= 94.6414


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2818 top1= 94.4812


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2680 top1= 94.5012

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0004 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2740 top1= 94.6414


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2834 top1= 94.4812


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2697 top1= 94.4912

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0004 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2756 top1= 94.6414


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2849 top1= 94.4812


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2713 top1= 94.4812

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0003 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0003 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2771 top1= 94.6314


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2863 top1= 94.4912


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2728 top1= 94.4812

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0003 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0003 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2786 top1= 94.6314


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2877 top1= 94.5012


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2743 top1= 94.4912

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0003 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0003 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2800 top1= 94.6314


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2890 top1= 94.4912


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2757 top1= 94.4912

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0003 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0003 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2813 top1= 94.6214


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2903 top1= 94.5012


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2771 top1= 94.5012

