
=== 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 0x7f6406066490>

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: 1.1210 top1= 60.6250
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3976 top1= 87.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7824 top1= 79.3470


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7008 top1= 49.1687


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4608 top1= 43.7600

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2900 top1= 90.0000
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.2128 top1= 94.5312
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2155 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7886 top1= 85.2163


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8152 top1= 49.8397


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8190 top1= 45.6731

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1908 top1= 94.2188
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1577 top1= 95.7812
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1802 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7274 top1= 86.3682


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5265 top1= 49.9199


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7352 top1= 45.8834

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1714 top1= 95.0000
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1366 top1= 96.5625
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1577 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6924 top1= 86.4784


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3587 top1= 50.0401


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5745 top1= 46.0236

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1526 top1= 95.4688
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1241 top1= 96.4062
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1413 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6711 top1= 86.8490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2535 top1= 50.0000


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5348 top1= 46.0737

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1446 top1= 95.9375
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1167 top1= 97.0312
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1366 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6681 top1= 86.3682


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1892 top1= 49.8998


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5185 top1= 46.0236

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1416 top1= 95.6250
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1127 top1= 97.5000
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1315 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6694 top1= 85.8173


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1619 top1= 49.8197


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5649 top1= 46.0437

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1378 top1= 95.3125
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1156 top1= 97.0312
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1272 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6794 top1= 84.4952


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1515 top1= 49.6394


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5420 top1= 45.9836

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1415 top1= 95.6250
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1109 top1= 97.3438
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1243 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6792 top1= 84.2348


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1429 top1= 49.7897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5847 top1= 45.9335

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1374 top1= 96.0938
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.1000 top1= 97.5000
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1213 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6764 top1= 84.6154


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1359 top1= 50.1903


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6240 top1= 45.6831

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1271 top1= 95.9375
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0937 top1= 97.5000
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1179 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6712 top1= 84.6955


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1241 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6416 top1= 45.8133

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1120 top1= 97.3438
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0905 top1= 97.9688
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1148 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6752 top1= 84.4050


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0958 top1= 50.3405


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6288 top1= 46.0737

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1009 top1= 98.1250
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0842 top1= 98.1250
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1131 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6857 top1= 83.2833


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0412 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5638 top1= 46.1939

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.1004 top1= 97.9688
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0821 top1= 98.4375
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.1042 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6876 top1= 82.5120


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0081 top1= 50.2704


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5388 top1= 46.4243

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0988 top1= 98.2812
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0902 top1= 97.9688
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.1033 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6675 top1= 84.6154


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9943 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5632 top1= 45.9836

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.1100 top1= 96.4062
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0873 top1= 97.8125
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.1168 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7079 top1= 81.7708


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9960 top1= 50.2704


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5602 top1= 46.2240

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.1056 top1= 97.3438
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0896 top1= 97.8125
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.1262 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7048 top1= 82.0012


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9688 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4985 top1= 46.2139

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0961 top1= 97.1875
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0968 top1= 96.8750
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.1242 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7127 top1= 81.0998


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9992 top1= 50.2003


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6108 top1= 45.7432

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.1141 top1= 97.0312
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0931 top1= 97.3438
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.1158 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7195 top1= 81.0697


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9595 top1= 50.2103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6215 top1= 45.5228

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.1186 top1= 96.5625
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.1131 top1= 96.0938
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.1294 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6939 top1= 83.8041


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9201 top1= 50.2103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5558 top1= 46.1338

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.1094 top1= 97.0312
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.1231 top1= 96.4062
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.1271 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6937 top1= 83.9944


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9493 top1= 50.0801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5870 top1= 45.9736

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.1173 top1= 95.9375
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.1056 top1= 97.1875
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.1096 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6881 top1= 84.4251


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9253 top1= 49.6995


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4476 top1= 46.0938

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.1218 top1= 95.7812
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0770 top1= 98.2812
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.1033 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6869 top1= 84.1546


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8913 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4661 top1= 46.1038

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0922 top1= 97.5000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0767 top1= 98.2812
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0880 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6886 top1= 85.0060


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9185 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4494 top1= 46.2139

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0904 top1= 97.6562
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0820 top1= 97.9688
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0923 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6847 top1= 84.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8767 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3974 top1= 46.3642

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0964 top1= 97.3438
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0841 top1= 97.9688
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.1028 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6777 top1= 84.2849


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8510 top1= 50.4407


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5140 top1= 46.4744

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0907 top1= 98.4375
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0833 top1= 97.6562
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.1135 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6839 top1= 84.0044


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8652 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3377 top1= 46.5144

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0880 top1= 98.1250
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0867 top1= 97.8125
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.1145 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6800 top1= 85.3165


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9413 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2276 top1= 46.4844

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0873 top1= 97.9688
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0875 top1= 97.6562
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.1083 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7054 top1= 82.9527


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9128 top1= 50.4407


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3896 top1= 46.0737

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.1044 top1= 96.8750
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.1062 top1= 96.2500
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.1042 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7018 top1= 83.0929


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8437 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5761 top1= 45.8934

