
=== 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 BitFlippingWorker
=> Add worker BitFlippingWorker

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f1cc41882e0>

Train epoch 1
[E 1B0  |    704/60000 (  1%) ] Loss: 2.3080 top1=  8.4375

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([4, 0, 4, 4, 4], device='cuda:0')
Worker 1 has targets: tensor([2, 6, 1, 4, 8], device='cuda:0')
Worker 2 has targets: tensor([3, 0, 3, 2, 7], device='cuda:0')
Worker 3 has targets: tensor([1, 4, 8, 2, 8], device='cuda:0')
Worker 4 has targets: tensor([9, 5, 0, 1, 3], device='cuda:0')
Worker 5 has targets: tensor([5, 6, 2, 4, 3], device='cuda:0')
Worker 6 has targets: tensor([2, 5, 0, 9, 9], device='cuda:0')
Worker 7 has targets: tensor([2, 2, 1, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([3, 8, 7, 0, 3], device='cuda:0')
Worker 9 has targets: tensor([1, 7, 1, 7, 2], device='cuda:0')
Worker 10 has targets: tensor([8, 4, 4, 3, 9], device='cuda:0')
Worker 11 has targets: tensor([3, 4, 7, 7, 9], device='cuda:0')
Worker 12 has targets: tensor([7, 4, 3, 9, 4], device='cuda:0')
Worker 13 has targets: tensor([4, 5, 0, 7, 1], device='cuda:0')
Worker 14 has targets: tensor([4, 2, 3, 5, 5], device='cuda:0')
Worker 15 has targets: tensor([4, 7, 5, 4, 7], device='cuda:0')
Worker 16 has targets: tensor([1, 1, 5, 7, 9], device='cuda:0')
Worker 17 has targets: tensor([8, 7, 2, 2, 0], device='cuda:0')
Worker 18 has targets: tensor([7, 8, 0, 0, 6], device='cuda:0')
Worker 19 has targets: tensor([9, 9, 5, 2, 8], device='cuda:0')
Worker 20 has targets: tensor([4, 0, 4, 4, 4], device='cuda:0')
Worker 21 has targets: tensor([2, 6, 1, 4, 8], device='cuda:0')


[E 1B10 |   7744/60000 ( 13%) ] Loss: 2.0046 top1= 47.6562
[E 1B20 |  14784/60000 ( 25%) ] Loss: 1.0686 top1= 69.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4752 top1= 86.1378


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4873 top1= 86.4083


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5128 top1= 84.4551

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.5547 top1= 82.0312
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.4999 top1= 83.1250
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.4430 top1= 87.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3558 top1= 90.3345


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3667 top1= 90.0541


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3754 top1= 89.4331

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.3472 top1= 90.4688
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.3426 top1= 90.0000
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.3493 top1= 90.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3235 top1= 91.4163


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3412 top1= 90.5749


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3311 top1= 91.1659

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.2957 top1= 91.4062
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.2955 top1= 92.5000
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.3000 top1= 90.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3015 top1= 91.9872


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3163 top1= 91.5164


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3061 top1= 91.6567

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.2542 top1= 93.1250
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.2662 top1= 93.1250
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.2712 top1= 91.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2888 top1= 92.2877


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3024 top1= 91.8069


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2920 top1= 91.9972

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.2299 top1= 93.9062
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.2484 top1= 92.8125
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.2525 top1= 92.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2798 top1= 92.4780


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2960 top1= 91.9271


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2818 top1= 92.2776

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.2167 top1= 94.2188
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.2358 top1= 93.2812
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.2442 top1= 92.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2718 top1= 92.5481


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2881 top1= 92.2075


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2778 top1= 92.3377

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.2108 top1= 94.6875
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.2240 top1= 93.1250
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.2362 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2674 top1= 92.7484


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2842 top1= 92.2776


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2794 top1= 92.1074

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.2096 top1= 94.8438
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.2195 top1= 93.1250
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.2261 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2631 top1= 92.8385


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2858 top1= 92.3377


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2759 top1= 92.1675

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.2054 top1= 95.0000
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.2132 top1= 93.2812
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.2173 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2545 top1= 93.0789


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2817 top1= 92.4179


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2719 top1= 92.2576

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.2042 top1= 94.8438
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.2100 top1= 94.2188
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.2158 top1= 93.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2497 top1= 93.1290


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2715 top1= 92.6182


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2646 top1= 92.3177

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1927 top1= 95.1562
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.1983 top1= 94.3750
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.2105 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2450 top1= 93.3293


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2720 top1= 92.6783


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2675 top1= 92.2476

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1888 top1= 95.4688
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.2029 top1= 94.0625
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.2087 top1= 93.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2421 top1= 93.3694


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2689 top1= 92.7083


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2589 top1= 92.5481

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.1860 top1= 95.3125
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.1901 top1= 94.6875
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.2146 top1= 93.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2415 top1= 93.4896


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2750 top1= 92.4479


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2576 top1= 92.7183

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.1930 top1= 95.6250
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.1902 top1= 94.6875
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.2107 top1= 93.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2481 top1= 93.2692


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3070 top1= 91.3161


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2526 top1= 92.7183

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.2167 top1= 94.3750
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.1901 top1= 94.6875
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.2060 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2481 top1= 93.2893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3105 top1= 91.3061


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2440 top1= 93.0389

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.2189 top1= 93.2812
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.1987 top1= 93.4375
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.2048 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2432 top1= 93.3694


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2774 top1= 92.1374


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2513 top1= 92.9387

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.2018 top1= 94.8438
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.1932 top1= 94.6875
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.1914 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2423 top1= 93.4295


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2620 top1= 92.7885


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2619 top1= 92.5881

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.1988 top1= 95.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.1865 top1= 94.6875
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.2145 top1= 92.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2412 top1= 93.5497


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2607 top1= 92.6282


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2624 top1= 92.5681

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.1935 top1= 94.8438
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.1772 top1= 95.1562
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.2224 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2410 top1= 93.5897


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2587 top1= 92.7484


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2590 top1= 92.8285

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.1986 top1= 94.2188
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.1793 top1= 94.5312
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.2053 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2347 top1= 93.6799


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2601 top1= 92.8285


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2469 top1= 93.1490

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.1990 top1= 94.8438
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.1706 top1= 94.8438
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.2039 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2401 top1= 93.3393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2732 top1= 92.2977


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2564 top1= 92.6883

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.1951 top1= 95.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.2006 top1= 93.5938
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.2019 top1= 93.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2376 top1= 93.4295


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2643 top1= 92.7584


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2537 top1= 92.6282

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.1934 top1= 94.8438
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.1872 top1= 94.6875
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.2035 top1= 92.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2374 top1= 93.4395


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2546 top1= 92.9988


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2695 top1= 92.0673

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.1927 top1= 94.5312
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.1744 top1= 94.8438
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.1882 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2307 top1= 93.7200


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2445 top1= 93.2792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2462 top1= 93.1090

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.1742 top1= 95.7812
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.1608 top1= 95.4688
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.1889 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2289 top1= 93.6498


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2368 top1= 93.5296


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2586 top1= 92.5982

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.1764 top1= 95.6250
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.1753 top1= 94.2188
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.1734 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2339 top1= 93.3494


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2404 top1= 93.4696


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2695 top1= 92.3277

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.1785 top1= 96.0938
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.1769 top1= 93.9062
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.1856 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2413 top1= 93.4696


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2682 top1= 92.6783


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2584 top1= 92.7384

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.2075 top1= 94.6875
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.1754 top1= 95.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.1972 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2363 top1= 93.6298


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2746 top1= 92.3077


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2398 top1= 93.3794

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.1954 top1= 94.5312
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.1774 top1= 94.5312
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.1822 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2329 top1= 93.7700


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2679 top1= 92.7684


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2363 top1= 93.7099

