
=== 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 0x7fbf687192b0>

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: 1.0382 top1= 61.7188
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3978 top1= 88.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7383 top1= 78.0649


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.8975 top1= 49.2889


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6155 top1= 44.1206

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2846 top1= 90.7812
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1908 top1= 94.0625
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1964 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6863 top1= 84.0044


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5132 top1= 49.8498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2690 top1= 45.8033

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1604 top1= 95.3125
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1105 top1= 96.8750
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1273 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6266 top1= 84.8758


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3515 top1= 50.1202


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3729 top1= 46.0938

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1208 top1= 96.4062
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0801 top1= 98.2812
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0831 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5756 top1= 85.7272


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4502 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3517 top1= 46.3742

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0844 top1= 97.8125
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0645 top1= 98.1250
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0579 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5365 top1= 85.8474


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6050 top1= 50.4407


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4209 top1= 46.5445

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0627 top1= 98.7500
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0490 top1= 98.9062
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0461 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5023 top1= 86.4683


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6519 top1= 50.5108


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4440 top1= 46.8249

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0451 top1= 99.2188
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0314 top1= 99.5312
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0444 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4761 top1= 87.2696


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7694 top1= 50.5108


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2884 top1= 46.7248

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0399 top1= 99.0625
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0269 top1= 99.2188
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0300 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4582 top1= 86.9291


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8410 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3641 top1= 46.9752

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0301 top1= 99.2188
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0213 top1= 99.5312
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0230 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4349 top1= 87.4499


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8126 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6864 top1= 46.8550

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0277 top1= 99.0625
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0145 top1= 99.8438
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0237 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4531 top1= 86.1779


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6570 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9355 top1= 46.9251

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0136 top1= 99.6875
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0107 top1= 99.8438
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0132 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4330 top1= 86.6787


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7431 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1723 top1= 47.1054

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0099 top1= 99.8438
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0094 top1= 99.8438
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0133 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4187 top1= 87.3297


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8008 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1908 top1= 47.1154

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0056 top1=100.0000
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0044 top1=100.0000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0091 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4038 top1= 87.7604


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9593 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3057 top1= 47.0353

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0071 top1= 99.8438
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0038 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0055 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4051 top1= 87.1595


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2370 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5181 top1= 47.0553

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0027 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0033 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3923 top1= 87.4700


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4842 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6379 top1= 47.1855

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0024 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4100 top1= 86.7788


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.6168 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8281 top1= 47.1755

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0022 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4123 top1= 86.5385


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7581 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9895 top1= 47.1655

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4109 top1= 86.4483


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8760 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1596 top1= 47.1054

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4067 top1= 86.4784


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9883 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3195 top1= 47.0553

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4005 top1= 86.6887


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0931 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4393 top1= 47.0553

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3949 top1= 86.8990


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1863 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5119 top1= 47.1354

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3888 top1= 87.2796


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2737 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5553 top1= 47.2256

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0009 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3820 top1= 87.4900


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3544 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6081 top1= 47.1855

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0008 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3784 top1= 87.6202


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4333 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6846 top1= 47.1955

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0007 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3786 top1= 87.5901


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5032 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7746 top1= 47.2256

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0006 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3800 top1= 87.5801


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5697 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8606 top1= 47.2356

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0006 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3802 top1= 87.5801


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6386 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9318 top1= 47.2356

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0006 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3803 top1= 87.5801


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6994 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9990 top1= 47.2256

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0005 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3805 top1= 87.5601


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.7551 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0610 top1= 47.2356

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0005 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3807 top1= 87.5701


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8111 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1203 top1= 47.2356

