
=== 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.Dumbbell object at 0x7f6061dc1490>

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: 1.4579 top1= 50.6250
[E 1B20 |  14784/60000 ( 25%) ] Loss: 1.1109 top1= 62.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4208 top1= 65.2344


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3756 top1= 48.2071


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7474 top1= 43.1490

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.7548 top1= 72.9688
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.5050 top1= 85.4688
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.5746 top1= 80.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2407 top1= 53.1550


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0929 top1= 49.2588


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2612 top1= 44.2208

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.4224 top1= 88.4375
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.3346 top1= 90.0000
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.3419 top1= 89.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2883 top1= 51.0817


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8315 top1= 51.3021


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8021 top1= 44.8117

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.3765 top1= 88.7500
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.3325 top1= 89.2188
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.3649 top1= 89.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3229 top1= 50.2604


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7506 top1= 53.5256


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2490 top1= 45.1823

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.3787 top1= 87.6562
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.2568 top1= 92.6562
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.3742 top1= 88.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3099 top1= 50.5709


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5262 top1= 56.2099


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1194 top1= 45.2524

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.3074 top1= 90.7812
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.3375 top1= 88.9062
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.3197 top1= 91.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2936 top1= 50.9515


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5256 top1= 57.2817


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1052 top1= 45.8133

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.2721 top1= 92.5000
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.2764 top1= 90.9375
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.2848 top1= 92.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2702 top1= 51.5224


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4957 top1= 57.8526


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1676 top1= 46.1138

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.2367 top1= 93.1250
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.2639 top1= 92.1875
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.2509 top1= 92.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2487 top1= 52.5040


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4889 top1= 58.8041


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1431 top1= 46.1739

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.2490 top1= 92.0312
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.2080 top1= 93.7500
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.2992 top1= 91.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2302 top1= 53.1250


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4762 top1= 59.4050


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2235 top1= 46.3141

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.2248 top1= 92.9688
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.2260 top1= 92.8125
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.2224 top1= 93.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2978 top1= 51.4423


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4281 top1= 60.2564


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3562 top1= 46.3642

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.2545 top1= 92.1875
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.1719 top1= 95.4688
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.2834 top1= 91.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2129 top1= 53.6458


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4007 top1= 60.5869


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2806 top1= 46.3642

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.2815 top1= 91.5625
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.2576 top1= 92.9688
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.2271 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1823 top1= 55.0180


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4492 top1= 60.4067


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2154 top1= 46.4744

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.2545 top1= 92.3438
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.2167 top1= 93.1250
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.2661 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1772 top1= 55.2985


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3645 top1= 61.7989


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2833 top1= 46.5946

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.2559 top1= 93.1250
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.1977 top1= 93.7500
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.3069 top1= 92.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1082 top1= 57.0212


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4491 top1= 60.7672


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1872 top1= 46.5445

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.1591 top1= 95.7812
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.1904 top1= 94.3750
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.1795 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1648 top1= 55.3285


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2838 top1= 62.8405


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2073 top1= 46.7348

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.2505 top1= 92.3438
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.2015 top1= 95.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.2014 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1456 top1= 57.0413


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3974 top1= 62.4900


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3765 top1= 46.7348

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.2435 top1= 92.8125
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.1749 top1= 94.6875
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.2001 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0962 top1= 58.7740


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4336 top1= 62.1394


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2718 top1= 46.6446

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.3039 top1= 92.6562
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.2489 top1= 92.5000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.1875 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0687 top1= 59.7957


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4194 top1= 62.1795


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2837 top1= 46.8950

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.2017 top1= 93.5938
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.2014 top1= 93.4375
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.2460 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0458 top1= 60.4868


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4014 top1= 62.0393


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2798 top1= 46.7849

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.2953 top1= 92.1875
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.1883 top1= 94.6875
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.2707 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0613 top1= 59.6655


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3549 top1= 62.8906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1578 top1= 46.8650

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.2712 top1= 91.7188
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.1927 top1= 94.8438
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.2407 top1= 92.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0658 top1= 59.9159


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3810 top1= 62.6803


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1325 top1= 46.9151

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.2098 top1= 93.4375
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.2486 top1= 93.4375
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.1756 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0335 top1= 61.4984


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4250 top1= 62.5000


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3119 top1= 46.9952

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.3002 top1= 92.0312
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.1629 top1= 95.3125
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.1946 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0350 top1= 61.9091


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3820 top1= 62.6703


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3470 top1= 46.9651

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.2377 top1= 93.1250
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.1944 top1= 95.3125
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.2320 top1= 92.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9530 top1= 64.4631


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4492 top1= 61.8189


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2296 top1= 47.0052

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.2040 top1= 93.5938
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.1884 top1= 95.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.1441 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0065 top1= 62.3197


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4251 top1= 62.6502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4087 top1= 46.9551

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.2244 top1= 93.9062
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.1938 top1= 94.5312
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.2164 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9613 top1= 64.2328


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3952 top1= 63.0609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2523 top1= 47.1855

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.1537 top1= 95.6250
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.1269 top1= 95.9375
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.1597 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9287 top1= 65.4547


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3951 top1= 63.0208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2528 top1= 47.1955

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.2153 top1= 93.1250
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.1233 top1= 96.4062
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.1343 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9720 top1= 64.0124


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3977 top1= 63.8922


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3069 top1= 47.1855

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.1664 top1= 95.6250
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.1697 top1= 94.3750
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.1704 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9230 top1= 65.6550


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3727 top1= 63.7821


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1459 top1= 47.1955

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.2008 top1= 94.0625
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.2752 top1= 94.3750
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.1578 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9166 top1= 66.0857


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3847 top1= 64.2328


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1867 top1= 47.2656

