
=== 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 ByzantineWorker(index=10)
=> Add worker ByzantineWorker(index=11)

=== Start adding graph ===
<codes.graph_utils.RandomSmallWorldGraph object at 0x7f08fe26b400>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.3054 top1= 10.0000

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



=== Log global consensus distance @ E1B0 ===
consensus_distance=0.001



=== Log average shortest path distance for small world @ E1B0 ===
2.7777777777777777


[E 1B10 |   4224/60000 (  7%) ] Loss: 0.2120 top1= 92.1875
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2178 top1= 97.5000
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.0406 top1= 98.4375
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.0603 top1= 98.1250
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.0754 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.5912 top1= 56.5104

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.0991 top1= 97.1875

=== Log global consensus distance @ E2B0 ===
consensus_distance=0.383


[E 2B10 |   4224/60000 (  7%) ] Loss: 0.0400 top1= 99.6875
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.0407 top1= 98.7500
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.0361 top1= 98.7500
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.0646 top1= 98.7500
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.0564 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0066 top1= 64.8337

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1057 top1= 97.1875

=== Log global consensus distance @ E3B0 ===
consensus_distance=0.106


[E 3B10 |   4224/60000 (  7%) ] Loss: 0.0354 top1= 99.3750
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0308 top1= 99.3750
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.0328 top1= 98.7500
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.0615 top1= 98.4375
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.0412 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7104 top1= 75.4507

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0794 top1= 99.0625

=== Log global consensus distance @ E4B0 ===
consensus_distance=0.076


[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0377 top1= 99.6875
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0174 top1= 99.6875
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.0238 top1= 99.0625
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.0528 top1= 99.3750
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.0501 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6403 top1= 77.1434

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0919 top1= 98.7500

=== Log global consensus distance @ E5B0 ===
consensus_distance=0.073


[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0209 top1= 99.6875
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0107 top1= 99.6875
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.0318 top1= 98.7500
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.0676 top1= 98.4375
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.0424 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5570 top1= 81.1899

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0721 top1= 98.4375

=== Log global consensus distance @ E6B0 ===
consensus_distance=0.068


[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0220 top1= 99.6875
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0160 top1= 99.6875
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.0497 top1= 98.4375
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.0489 top1= 98.7500
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.0295 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4861 top1= 84.8257

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0315 top1= 99.0625

=== Log global consensus distance @ E7B0 ===
consensus_distance=0.071


[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0059 top1=100.0000
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0120 top1= 99.6875
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.0443 top1= 99.0625
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.0152 top1= 99.6875
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.0245 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4750 top1= 84.3049

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0272 top1= 99.0625

=== Log global consensus distance @ E8B0 ===
consensus_distance=0.038


[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0093 top1= 99.6875
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0099 top1= 99.6875
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.0074 top1= 99.6875
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.0204 top1= 99.3750
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.0398 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4589 top1= 84.4551

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0343 top1= 99.0625

=== Log global consensus distance @ E9B0 ===
consensus_distance=0.053


[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0064 top1=100.0000
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0079 top1=100.0000
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.0090 top1= 99.6875
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.0073 top1=100.0000
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.0199 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4146 top1= 86.4984

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0221 top1= 99.0625

=== Log global consensus distance @ E10B0 ===
consensus_distance=0.031


[E10B10 |   4224/60000 (  7%) ] Loss: 0.0125 top1= 99.6875
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0133 top1= 99.3750
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.0045 top1=100.0000
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.0100 top1= 99.6875
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.0214 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4154 top1= 86.9992

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0270 top1= 99.6875

=== Log global consensus distance @ E11B0 ===
consensus_distance=0.044


[E11B10 |   4224/60000 (  7%) ] Loss: 0.0085 top1= 99.6875
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0049 top1=100.0000
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.0136 top1= 99.6875
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.0109 top1= 99.6875
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.0137 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3695 top1= 88.0208

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0525 top1= 97.8125

=== Log global consensus distance @ E12B0 ===
consensus_distance=0.036


[E12B10 |   4224/60000 (  7%) ] Loss: 0.0043 top1=100.0000
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0084 top1= 99.6875
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.0097 top1= 99.6875
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.0219 top1= 99.6875
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.0146 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4016 top1= 87.0092

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0162 top1= 99.6875

=== Log global consensus distance @ E13B0 ===
consensus_distance=0.027


[E13B10 |   4224/60000 (  7%) ] Loss: 0.0028 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0223 top1= 99.6875
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.0132 top1= 99.6875
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.0118 top1= 99.6875
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.0076 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3962 top1= 87.2095

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0356 top1= 99.6875

=== Log global consensus distance @ E14B0 ===
consensus_distance=0.027


[E14B10 |   4224/60000 (  7%) ] Loss: 0.0050 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0070 top1=100.0000
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.0067 top1= 99.6875
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.0099 top1= 99.6875
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.0043 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3365 top1= 89.4231

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0078 top1= 99.3750

=== Log global consensus distance @ E15B0 ===
consensus_distance=0.019


[E15B10 |   4224/60000 (  7%) ] Loss: 0.0042 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0046 top1=100.0000
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.0044 top1=100.0000
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.0038 top1=100.0000
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.0052 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4028 top1= 87.4199

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0276 top1= 99.6875

=== Log global consensus distance @ E16B0 ===
consensus_distance=0.056


[E16B10 |   4224/60000 (  7%) ] Loss: 0.0430 top1= 99.3750
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0106 top1= 99.3750
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.0192 top1= 99.6875
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.0153 top1= 99.0625
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.0318 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4535 top1= 84.6254

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0066 top1=100.0000

=== Log global consensus distance @ E17B0 ===
consensus_distance=0.090


[E17B10 |   4224/60000 (  7%) ] Loss: 0.0051 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0049 top1=100.0000
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.0037 top1=100.0000
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.0049 top1=100.0000
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.0071 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3427 top1= 89.1627

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0085 top1= 99.6875

=== Log global consensus distance @ E18B0 ===
consensus_distance=0.021


[E18B10 |   4224/60000 (  7%) ] Loss: 0.0047 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0043 top1=100.0000
[E18B30 |  11904/60000 ( 20%) ] Loss: 0.0022 top1=100.0000
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.0034 top1=100.0000
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.0039 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3199 top1= 89.8037

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0048 top1=100.0000

=== Log global consensus distance @ E19B0 ===
consensus_distance=0.013


[E19B10 |   4224/60000 (  7%) ] Loss: 0.0025 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0029 top1=100.0000
[E19B30 |  11904/60000 ( 20%) ] Loss: 0.0048 top1=100.0000
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.0064 top1=100.0000
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3232 top1= 89.8838

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0031 top1=100.0000

=== Log global consensus distance @ E20B0 ===
consensus_distance=0.011


[E20B10 |   4224/60000 (  7%) ] Loss: 0.0025 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0041 top1=100.0000
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.0016 top1=100.0000
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.0068 top1=100.0000
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3348 top1= 89.5232

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0022 top1=100.0000

=== Log global consensus distance @ E21B0 ===
consensus_distance=0.012


[E21B10 |   4224/60000 (  7%) ] Loss: 0.0051 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0028 top1=100.0000
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.0016 top1=100.0000
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.0077 top1= 99.6875
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3519 top1= 88.9523

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0041 top1=100.0000

=== Log global consensus distance @ E22B0 ===
consensus_distance=0.012


[E22B10 |   4224/60000 (  7%) ] Loss: 0.0058 top1= 99.6875
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0024 top1=100.0000
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.0057 top1= 99.6875
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.0016 top1=100.0000
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3251 top1= 90.2344

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0036 top1=100.0000

=== Log global consensus distance @ E23B0 ===
consensus_distance=0.009


[E23B10 |   4224/60000 (  7%) ] Loss: 0.0033 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0023 top1=100.0000
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.0012 top1=100.0000
[E23B40 |  15744/60000 ( 26%) ] Loss: 0.0034 top1=100.0000
[E23B50 |  19584/60000 ( 33%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3382 top1= 89.7035

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0018 top1=100.0000

=== Log global consensus distance @ E24B0 ===
consensus_distance=0.012


[E24B10 |   4224/60000 (  7%) ] Loss: 0.0020 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.0016 top1=100.0000
[E24B40 |  15744/60000 ( 26%) ] Loss: 0.0039 top1=100.0000
[E24B50 |  19584/60000 ( 33%) ] Loss: 0.0046 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3576 top1= 89.5533

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0041 top1=100.0000

=== Log global consensus distance @ E25B0 ===
consensus_distance=0.051


[E25B10 |   4224/60000 (  7%) ] Loss: 0.0015 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E25B30 |  11904/60000 ( 20%) ] Loss: 0.0229 top1= 99.3750
[E25B40 |  15744/60000 ( 26%) ] Loss: 0.0113 top1= 99.3750
[E25B50 |  19584/60000 ( 33%) ] Loss: 0.0247 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4817 top1= 84.9860

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0368 top1= 98.7500

=== Log global consensus distance @ E26B0 ===
consensus_distance=0.086


[E26B10 |   4224/60000 (  7%) ] Loss: 0.0505 top1= 99.0625
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0233 top1= 99.6875
[E26B30 |  11904/60000 ( 20%) ] Loss: 0.0291 top1= 99.0625
[E26B40 |  15744/60000 ( 26%) ] Loss: 0.0182 top1= 99.3750
[E26B50 |  19584/60000 ( 33%) ] Loss: 0.0168 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3194 top1= 89.9139

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0355 top1= 98.4375

=== Log global consensus distance @ E27B0 ===
consensus_distance=0.056


[E27B10 |   4224/60000 (  7%) ] Loss: 0.0064 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0020 top1=100.0000
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.0030 top1=100.0000
[E27B40 |  15744/60000 ( 26%) ] Loss: 0.0037 top1=100.0000
[E27B50 |  19584/60000 ( 33%) ] Loss: 0.0039 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3412 top1= 89.0825

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0030 top1=100.0000

=== Log global consensus distance @ E28B0 ===
consensus_distance=0.012


[E28B10 |   4224/60000 (  7%) ] Loss: 0.0044 top1= 99.6875
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0021 top1=100.0000
[E28B30 |  11904/60000 ( 20%) ] Loss: 0.0058 top1= 99.6875
[E28B40 |  15744/60000 ( 26%) ] Loss: 0.0053 top1=100.0000
[E28B50 |  19584/60000 ( 33%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3345 top1= 89.7236

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0026 top1=100.0000

=== Log global consensus distance @ E29B0 ===
consensus_distance=0.009


[E29B10 |   4224/60000 (  7%) ] Loss: 0.0026 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0024 top1=100.0000
[E29B30 |  11904/60000 ( 20%) ] Loss: 0.0010 top1=100.0000
[E29B40 |  15744/60000 ( 26%) ] Loss: 0.0024 top1=100.0000
[E29B50 |  19584/60000 ( 33%) ] Loss: 0.0044 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3031 top1= 90.8153

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0016 top1=100.0000

=== Log global consensus distance @ E30B0 ===
consensus_distance=0.011


[E30B10 |   4224/60000 (  7%) ] Loss: 0.0026 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0045 top1= 99.6875
[E30B30 |  11904/60000 ( 20%) ] Loss: 0.0011 top1=100.0000
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.0023 top1=100.0000
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3187 top1= 90.3145

