
=== 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 0x7f775ebd6490>

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: 1.0404 top1= 61.7188
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3941 top1= 87.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7412 top1= 78.0349


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.4242 top1= 49.2488


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3486 top1= 44.0204

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2873 top1= 90.6250
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1918 top1= 94.2188
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1977 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6870 top1= 83.9944


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1400 top1= 49.8998


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9966 top1= 45.7632

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1628 top1= 95.4688
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1138 top1= 96.8750
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1367 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6221 top1= 85.1663


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9152 top1= 49.8998


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8458 top1= 46.2740

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1319 top1= 95.9375
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0835 top1= 97.9688
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1005 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5659 top1= 86.1979


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8814 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7544 top1= 46.4042

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0920 top1= 97.3438
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0662 top1= 97.9688
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0725 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5164 top1= 86.8089


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9110 top1= 50.3405


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7763 top1= 46.5345

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0687 top1= 98.7500
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0513 top1= 98.5938
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0513 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4774 top1= 87.2796


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9724 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8798 top1= 46.6346

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0564 top1= 98.9062
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0412 top1= 98.7500
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0388 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4517 top1= 87.4800


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9936 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9526 top1= 46.6346

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0435 top1= 99.2188
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0316 top1= 99.2188
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0300 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4336 top1= 88.0409


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0205 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9558 top1= 46.6947

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0327 top1= 99.3750
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0270 top1= 99.2188
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0259 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4134 top1= 88.6018


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0455 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9890 top1= 46.6246

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0304 top1= 99.2188
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0311 top1= 99.2188
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0255 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4002 top1= 88.5216


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1475 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7616 top1= 46.7548

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0251 top1= 99.3750
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0230 top1= 99.3750
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0247 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3843 top1= 89.1526


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0488 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6383 top1= 46.8049

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0188 top1= 99.5312
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0184 top1= 99.6875
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0282 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3922 top1= 87.7604


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0180 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4826 top1= 46.7348

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0257 top1= 99.0625
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0291 top1= 99.3750
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0286 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4025 top1= 88.0509


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7883 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0849 top1= 46.8249

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0132 top1= 99.6875
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0156 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0303 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3936 top1= 88.9924


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6664 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7628 top1= 47.0152

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0221 top1= 99.2188
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0128 top1= 99.6875
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0129 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3828 top1= 88.5817


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6603 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0760 top1= 47.1655

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0164 top1= 99.6875
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0158 top1= 99.5312
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0160 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3631 top1= 89.2228


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6471 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2400 top1= 47.1955

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0172 top1= 99.3750
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0078 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0072 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3614 top1= 89.4431


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3168 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4233 top1= 47.3057

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0056 top1= 99.8438
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0109 top1= 99.8438
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0176 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3612 top1= 89.3630


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0880 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6258 top1= 47.3458

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0038 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0056 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0107 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3715 top1= 88.7119


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9179 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7667 top1= 47.2957

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0069 top1= 99.8438
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0060 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0039 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3609 top1= 88.8421


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0523 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8760 top1= 47.3057

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0034 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0033 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3551 top1= 88.8522


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2509 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9720 top1= 47.3658

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0025 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3480 top1= 89.0425


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4210 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0608 top1= 47.3658

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3403 top1= 89.3429


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6338 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1366 top1= 47.3458

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3412 top1= 89.2027


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7379 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2200 top1= 47.3357

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3405 top1= 89.1526


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8329 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2907 top1= 47.3458

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3388 top1= 89.1927


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9212 top1= 50.7612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3655 top1= 47.3458

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3371 top1= 89.2328


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9957 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4370 top1= 47.3257

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0010 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3354 top1= 89.2228


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0623 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5009 top1= 47.3157

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0009 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3342 top1= 89.1927


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1218 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5515 top1= 47.3057

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0008 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3334 top1= 89.1927


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1772 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5957 top1= 47.3057

