
=== 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 0x7fc51efff9d0>

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: 1.0021 top1= 63.1250
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2621 top1= 90.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6835 top1= 78.9062


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.7801 top1= 48.6478


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5461 top1= 43.5296

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3906 top1= 90.3125
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.2581 top1= 92.5000
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1568 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7271 top1= 84.3950


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1181 top1= 49.7696


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0702 top1= 45.5329

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1466 top1= 95.3125
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1276 top1= 95.3125
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0822 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6095 top1= 85.2865


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7096 top1= 50.0100


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1398 top1= 45.9836

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0839 top1= 97.1875
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0662 top1= 97.1875
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0554 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5320 top1= 86.8389


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6990 top1= 50.1803


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2441 top1= 46.0537

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0522 top1= 98.4375
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0478 top1= 99.0625
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0300 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4696 top1= 88.0909


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7472 top1= 50.2103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5636 top1= 46.3241

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0278 top1= 99.0625
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0332 top1= 99.3750
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0216 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4429 top1= 87.6903


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7046 top1= 50.2404


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8039 top1= 46.3041

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0162 top1=100.0000
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0209 top1=100.0000
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0156 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4408 top1= 86.9792


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7243 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7979 top1= 45.9135

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0140 top1=100.0000
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0153 top1=100.0000
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0131 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4123 top1= 87.5601


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6644 top1= 50.2704


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5900 top1= 46.2740

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0114 top1=100.0000
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0183 top1=100.0000
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0091 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4007 top1= 87.4800


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5511 top1= 50.3405


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5294 top1= 46.4543

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0083 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0125 top1=100.0000
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0087 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3780 top1= 88.2512


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4496 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4755 top1= 46.6346

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0119 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0170 top1= 99.6875
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0108 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3791 top1= 88.1110


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2798 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3326 top1= 46.2440

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0124 top1= 99.6875
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0198 top1= 99.6875
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0104 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3820 top1= 88.0609


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1155 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8506 top1= 46.2640

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0097 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0324 top1= 99.6875
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0090 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3842 top1= 87.4099


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9176 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8503 top1= 46.8049

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0071 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0091 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0062 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3897 top1= 86.9692


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7284 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7732 top1= 46.6747

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0070 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0068 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0056 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3725 top1= 87.7704


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5726 top1= 50.4307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6982 top1= 46.7949

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0070 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0087 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0054 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3606 top1= 88.1510


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4305 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5316 top1= 47.2356

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0056 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0066 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0057 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3494 top1= 88.5917


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3086 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3721 top1= 47.6663

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0057 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0066 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0052 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3432 top1= 88.9123


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2018 top1= 50.9515


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2390 top1= 48.1170

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0058 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0067 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0057 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3375 top1= 89.1326


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0946 top1= 51.3722


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0995 top1= 48.4976

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0059 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0070 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0058 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3338 top1= 89.1827


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9906 top1= 51.7628


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0025 top1= 49.0084

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0058 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0071 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0058 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3296 top1= 89.4531


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9162 top1= 52.1334


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8963 top1= 49.5793

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0060 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0071 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0058 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3274 top1= 89.3930


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8390 top1= 52.7644


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8223 top1= 50.0000

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0058 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0071 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0058 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3234 top1= 89.4631


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7516 top1= 53.2953


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7424 top1= 50.4607

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0061 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0072 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0057 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3221 top1= 89.5533


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6859 top1= 53.9563


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6696 top1= 50.9816

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0057 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0070 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0057 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3203 top1= 89.5533


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6270 top1= 54.5473


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6014 top1= 51.5425

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0056 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0068 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0058 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3173 top1= 89.7035


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5571 top1= 55.0881


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5296 top1= 52.1434

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0054 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0066 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0057 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3153 top1= 89.8037


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4901 top1= 55.8994


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4660 top1= 52.6643

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0055 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0067 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0055 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3129 top1= 89.8738


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4245 top1= 56.3702


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4015 top1= 53.0749

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0052 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0067 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0053 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3122 top1= 89.9139


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3700 top1= 56.7007


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3558 top1= 53.4756

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0051 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0067 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0051 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3116 top1= 89.9940


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3212 top1= 57.2716


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2979 top1= 53.8662

