
=== 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 0x7f43883477f0>

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: 1.0015 top1= 63.7500
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2633 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7024 top1= 79.1967


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.1980 top1= 48.7079


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.0474 top1= 43.8602

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3699 top1= 90.6250
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.2797 top1= 91.8750
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1523 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7461 top1= 83.7039


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1486 top1= 49.7897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9050 top1= 45.5329

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1462 top1= 95.6250
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1386 top1= 95.0000
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0845 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6459 top1= 84.1647


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7700 top1= 49.9399


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1997 top1= 45.9535

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0895 top1= 97.5000
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0759 top1= 96.2500
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0529 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5822 top1= 85.0361


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9227 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3513 top1= 45.9335

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0575 top1= 98.1250
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0464 top1= 98.4375
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0320 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5268 top1= 86.2580


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0563 top1= 50.2204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5832 top1= 46.2540

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0353 top1= 98.7500
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0339 top1= 99.3750
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0229 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4970 top1= 86.1979


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2579 top1= 50.3005


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9592 top1= 46.3742

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0167 top1=100.0000
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0251 top1= 99.3750
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0135 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5143 top1= 84.7756


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5592 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1056 top1= 45.9034

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0140 top1=100.0000
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0122 top1=100.0000
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0105 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4759 top1= 85.8173


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8111 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9323 top1= 46.2440

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0106 top1=100.0000
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0164 top1= 99.3750
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0051 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4567 top1= 86.2079


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1203 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2317 top1= 46.6146

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0122 top1= 99.6875
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0222 top1= 99.3750
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0065 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4522 top1= 86.1779


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3813 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3361 top1= 46.5445

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0059 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0062 top1=100.0000
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0047 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4788 top1= 85.2464


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5969 top1= 50.2804


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4644 top1= 46.4343

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0076 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0052 top1=100.0000
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0068 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4444 top1= 86.2881


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.6871 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6463 top1= 46.6546

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0063 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0151 top1= 99.0625
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0040 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4298 top1= 86.2179


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7928 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4677 top1= 46.6747

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0047 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4193 top1= 86.2881


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8617 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7153 top1= 46.7648

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0057 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4222 top1= 85.9375


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9484 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9816 top1= 46.7548

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0020 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4241 top1= 85.7973


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0645 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7997 top1= 46.8049

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0013 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4349 top1= 85.2564


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1769 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8637 top1= 46.7949

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4341 top1= 85.1763


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2704 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0004 top1= 46.7949

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4365 top1= 85.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3526 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0945 top1= 46.7548

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4361 top1= 85.0962


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4258 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1668 top1= 46.8049

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4308 top1= 85.3165


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4977 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2593 top1= 46.8650

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4285 top1= 85.4067


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5629 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3429 top1= 46.8850

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4308 top1= 85.2965


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6217 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4052 top1= 46.8650

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4307 top1= 85.2865


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6788 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4778 top1= 46.8650

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4305 top1= 85.2865


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.7314 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5394 top1= 46.8550

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4310 top1= 85.2664


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.7843 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5966 top1= 46.8650

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0003 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4312 top1= 85.2364


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8313 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6483 top1= 46.8650

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: 0.0003 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4314 top1= 85.2163


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8762 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6988 top1= 46.8650

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0003 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0004 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0003 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4318 top1= 85.1963


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9206 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7444 top1= 46.8650

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4321 top1= 85.1863


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9619 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7887 top1= 46.8650

