
=== 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 BitFlippingWorker
=> Add worker BitFlippingWorker

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f64dd4aa9d0>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.3109 top1=  9.6875

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 1 has targets: tensor([2, 1, 4, 4, 0], device='cuda:0')
Worker 2 has targets: tensor([3, 1, 4, 1, 3], device='cuda:0')
Worker 3 has targets: tensor([2, 3, 0, 0, 1], device='cuda:0')
Worker 4 has targets: tensor([2, 1, 1, 4, 2], device='cuda:0')
Worker 5 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')
Worker 6 has targets: tensor([9, 9, 6, 7, 9], device='cuda:0')
Worker 7 has targets: tensor([7, 5, 7, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([8, 9, 9, 5, 7], device='cuda:0')
Worker 9 has targets: tensor([8, 8, 7, 5, 9], device='cuda:0')
Worker 10 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 11 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')


[E 1B10 |   4224/60000 (  7%) ] Loss: 1.0088 top1= 64.3750
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2624 top1= 91.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7099 top1= 78.7260


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.7225 top1= 48.7179


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7569 top1= 43.8301

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3719 top1= 91.5625
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.2830 top1= 90.9375
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1547 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7199 top1= 83.4335


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1949 top1= 49.8898


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7193 top1= 45.5028

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1434 top1= 95.6250
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1404 top1= 94.3750
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0906 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6324 top1= 83.6739


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6194 top1= 49.9700


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9415 top1= 45.8333

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0952 top1= 97.1875
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0931 top1= 96.8750
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0539 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5695 top1= 84.6354


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7106 top1= 50.1402


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0603 top1= 46.1839

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0605 top1= 98.4375
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0505 top1= 98.1250
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0353 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5236 top1= 85.4067


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8668 top1= 50.2704


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0668 top1= 46.2139

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0392 top1= 98.4375
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0326 top1= 99.6875
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0308 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5002 top1= 85.6871


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8722 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0998 top1= 46.0737

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0286 top1= 99.0625
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0365 top1= 98.4375
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0215 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4633 top1= 86.7688


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8552 top1= 50.1002


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1766 top1= 46.4143

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0203 top1= 99.3750
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0187 top1= 99.6875
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0214 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4351 top1= 87.5701


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8435 top1= 50.1302


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4147 top1= 46.4143

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0152 top1=100.0000
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0226 top1= 99.3750
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0143 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4594 top1= 86.4383


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8286 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3683 top1= 46.2340

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0099 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0235 top1= 99.6875
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0066 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4544 top1= 86.6286


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6711 top1= 50.0801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3712 top1= 46.0938

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0183 top1= 99.6875
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0191 top1= 99.3750
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0092 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4155 top1= 87.7504


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7230 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5467 top1= 46.4143

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0114 top1= 99.6875
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0128 top1= 99.6875
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0083 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4040 top1= 87.9607


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0007 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4173 top1= 46.7949

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0078 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0163 top1= 99.3750
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0041 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4114 top1= 87.3898


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3485 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3486 top1= 46.7748

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0062 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0052 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0033 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4113 top1= 87.1895


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5085 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5421 top1= 46.8049

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0055 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0046 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0041 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3889 top1= 88.1410


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5564 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8067 top1= 46.8450

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0046 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3723 top1= 88.2512


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6157 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8987 top1= 46.8349

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0026 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3848 top1= 87.8305


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7316 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0482 top1= 46.8650

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0020 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3974 top1= 87.2897


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8380 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0414 top1= 46.8149

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3972 top1= 87.1494


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9184 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1468 top1= 46.8149

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3946 top1= 87.2396


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9946 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2379 top1= 46.8550

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3955 top1= 87.1394


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0630 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3185 top1= 46.8450

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3950 top1= 87.1194


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1269 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3833 top1= 46.8550

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3921 top1= 87.2296


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1841 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4564 top1= 46.8650

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3897 top1= 87.3998


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2388 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5255 top1= 46.8650

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3882 top1= 87.4199


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2892 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5932 top1= 46.8550

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3885 top1= 87.4099


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3380 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6516 top1= 46.8550

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3888 top1= 87.3698


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3829 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7013 top1= 46.8750

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3888 top1= 87.3798


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4238 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7502 top1= 46.8750

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3888 top1= 87.3898


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4626 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7953 top1= 46.8750

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0003 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3889 top1= 87.3598


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5019 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8385 top1= 46.8750

