
=== 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 LabelFlippingWorker
=> Add worker LabelFlippingWorker

=== Start adding graph ===
<codes.graph_utils.RandomSmallWorldGraph object at 0x7f5679c72730>

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([5, 1, 1, 3, 0], device='cuda:0')
Worker 11 has targets: tensor([4, 6, 3, 9, 0], 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: 0.1634 top1= 95.0000
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.0774 top1= 98.4375
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.1061 top1= 97.5000
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.0715 top1= 98.4375
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.0725 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9525 top1= 64.7536

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.0971 top1= 97.5000

=== Log global consensus distance @ E2B0 ===
consensus_distance=0.061


[E 2B10 |   4224/60000 (  7%) ] Loss: 0.0445 top1= 99.3750
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.0345 top1= 99.0625
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.0570 top1= 98.7500
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.0725 top1= 97.8125
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.0433 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7477 top1= 72.6863

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.0717 top1= 97.8125

=== Log global consensus distance @ E3B0 ===
consensus_distance=0.041


[E 3B10 |   4224/60000 (  7%) ] Loss: 0.0287 top1= 99.3750
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0209 top1= 99.6875
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.0313 top1= 99.3750
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.0712 top1= 97.5000
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.0381 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7196 top1= 73.0268

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0728 top1= 97.5000

=== Log global consensus distance @ E4B0 ===
consensus_distance=0.037


[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0233 top1= 99.6875
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0168 top1=100.0000
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.0224 top1= 99.3750
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.0519 top1= 98.1250
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.0282 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7139 top1= 74.0485

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0583 top1= 98.7500

=== Log global consensus distance @ E5B0 ===
consensus_distance=0.034


[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0199 top1= 99.3750
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0211 top1= 99.3750
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.0116 top1=100.0000
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.0377 top1= 99.0625
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.0287 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6224 top1= 76.9131

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0458 top1= 99.0625

=== Log global consensus distance @ E6B0 ===
consensus_distance=0.029


[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0312 top1= 99.3750
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0374 top1= 99.0625
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.0191 top1= 99.3750
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.0478 top1= 98.4375
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.0284 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5891 top1= 78.7360

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0347 top1= 99.3750

=== Log global consensus distance @ E7B0 ===
consensus_distance=0.033


[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0093 top1=100.0000
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0110 top1=100.0000
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.0559 top1= 98.4375
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.0415 top1= 98.7500
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.0261 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7070 top1= 75.1803

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.1316 top1= 97.8125

=== Log global consensus distance @ E8B0 ===
consensus_distance=0.036


[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0117 top1=100.0000
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0274 top1= 99.3750
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.0336 top1= 99.0625
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.0552 top1= 98.1250
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.0404 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5826 top1= 80.6290

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0281 top1= 99.0625

=== Log global consensus distance @ E9B0 ===
consensus_distance=0.039


[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0150 top1= 99.6875
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0169 top1= 99.6875
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.0245 top1= 99.0625
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.0416 top1= 99.0625
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.0145 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5312 top1= 81.9211

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0232 top1= 99.0625

=== Log global consensus distance @ E10B0 ===
consensus_distance=0.022


[E10B10 |   4224/60000 (  7%) ] Loss: 0.0084 top1=100.0000
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0194 top1= 99.6875
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.0065 top1=100.0000
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.0095 top1=100.0000
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.0161 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4989 top1= 83.6939

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0304 top1= 99.0625

=== Log global consensus distance @ E11B0 ===
consensus_distance=0.019


[E11B10 |   4224/60000 (  7%) ] Loss: 0.0126 top1= 99.6875
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0175 top1= 99.3750
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.0063 top1=100.0000
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.0103 top1=100.0000
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.0140 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5211 top1= 83.0629

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0276 top1= 99.0625

=== Log global consensus distance @ E12B0 ===
consensus_distance=0.019


[E12B10 |   4224/60000 (  7%) ] Loss: 0.0093 top1= 99.6875
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0155 top1= 99.6875
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.0120 top1= 99.3750
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.0087 top1= 99.6875
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.0106 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4817 top1= 84.3950

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0160 top1= 99.6875

=== Log global consensus distance @ E13B0 ===
consensus_distance=0.016


[E13B10 |   4224/60000 (  7%) ] Loss: 0.0059 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0062 top1= 99.6875
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.0043 top1=100.0000
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.0184 top1= 99.3750
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.0192 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5344 top1= 81.5505

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0154 top1= 99.3750

=== Log global consensus distance @ E14B0 ===
consensus_distance=0.025


[E14B10 |   4224/60000 (  7%) ] Loss: 0.0117 top1= 99.6875
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0068 top1= 99.6875
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.0279 top1= 98.7500
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.0098 top1=100.0000
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.0167 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5238 top1= 82.0312

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0424 top1= 98.4375

=== Log global consensus distance @ E15B0 ===
consensus_distance=0.039


[E15B10 |   4224/60000 (  7%) ] Loss: 0.0187 top1= 99.3750
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0335 top1= 99.0625
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.0112 top1= 99.6875
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.0055 top1=100.0000
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.0362 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5660 top1= 80.7392

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0282 top1= 99.6875

=== Log global consensus distance @ E16B0 ===
consensus_distance=0.044


[E16B10 |   4224/60000 (  7%) ] Loss: 0.0080 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0119 top1= 99.3750
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.0038 top1=100.0000
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.0214 top1= 99.3750
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.0046 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4470 top1= 85.6070

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0153 top1= 99.6875

=== Log global consensus distance @ E17B0 ===
consensus_distance=0.026


[E17B10 |   4224/60000 (  7%) ] Loss: 0.0054 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0039 top1=100.0000
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.0078 top1= 99.6875
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.0094 top1= 99.6875
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.0181 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4744 top1= 85.1562

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0197 top1= 99.6875

=== Log global consensus distance @ E18B0 ===
consensus_distance=0.025


[E18B10 |   4224/60000 (  7%) ] Loss: 0.0026 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0036 top1=100.0000
[E18B30 |  11904/60000 ( 20%) ] Loss: 0.0124 top1= 99.6875
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.0075 top1= 99.6875
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.0082 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5207 top1= 82.3117

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0056 top1=100.0000

=== Log global consensus distance @ E19B0 ===
consensus_distance=0.025


[E19B10 |   4224/60000 (  7%) ] Loss: 0.0027 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0072 top1= 99.6875
[E19B30 |  11904/60000 ( 20%) ] Loss: 0.0080 top1= 99.6875
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.0035 top1=100.0000
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4204 top1= 87.1595

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0066 top1=100.0000

=== Log global consensus distance @ E20B0 ===
consensus_distance=0.016


[E20B10 |   4224/60000 (  7%) ] Loss: 0.0036 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0025 top1=100.0000
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.0020 top1=100.0000
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.0022 top1=100.0000
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3910 top1= 88.1510

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0123 top1= 99.6875

=== Log global consensus distance @ E21B0 ===
consensus_distance=0.021


[E21B10 |   4224/60000 (  7%) ] Loss: 0.0075 top1= 99.6875
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0057 top1=100.0000
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.0097 top1= 99.6875
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.0035 top1=100.0000
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4243 top1= 86.3081

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0036 top1=100.0000

=== Log global consensus distance @ E22B0 ===
consensus_distance=0.016


[E22B10 |   4224/60000 (  7%) ] Loss: 0.0025 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0046 top1=100.0000
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.0053 top1= 99.6875
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.0040 top1=100.0000
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.0033 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3993 top1= 87.4199

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0054 top1=100.0000

=== Log global consensus distance @ E23B0 ===
consensus_distance=0.013


[E23B10 |   4224/60000 (  7%) ] Loss: 0.0021 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0020 top1=100.0000
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.0032 top1=100.0000
[E23B40 |  15744/60000 ( 26%) ] Loss: 0.0020 top1=100.0000
[E23B50 |  19584/60000 ( 33%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3873 top1= 87.9908

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0038 top1=100.0000

=== Log global consensus distance @ E24B0 ===
consensus_distance=0.008


[E24B10 |   4224/60000 (  7%) ] Loss: 0.0021 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.0015 top1=100.0000
[E24B40 |  15744/60000 ( 26%) ] Loss: 0.0020 top1=100.0000
[E24B50 |  19584/60000 ( 33%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3612 top1= 88.4014

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0020 top1=100.0000

=== Log global consensus distance @ E25B0 ===
consensus_distance=0.008


[E25B10 |   4224/60000 (  7%) ] Loss: 0.0022 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0021 top1=100.0000
[E25B30 |  11904/60000 ( 20%) ] Loss: 0.0015 top1=100.0000
[E25B40 |  15744/60000 ( 26%) ] Loss: 0.0016 top1=100.0000
[E25B50 |  19584/60000 ( 33%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3616 top1= 89.1226

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0017 top1=100.0000

=== Log global consensus distance @ E26B0 ===
consensus_distance=0.007


[E26B10 |   4224/60000 (  7%) ] Loss: 0.0017 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0020 top1=100.0000
[E26B30 |  11904/60000 ( 20%) ] Loss: 0.0013 top1=100.0000
[E26B40 |  15744/60000 ( 26%) ] Loss: 0.0017 top1=100.0000
[E26B50 |  19584/60000 ( 33%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3418 top1= 89.5933

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0015 top1=100.0000

=== Log global consensus distance @ E27B0 ===
consensus_distance=0.006


[E27B10 |   4224/60000 (  7%) ] Loss: 0.0017 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.0009 top1=100.0000
[E27B40 |  15744/60000 ( 26%) ] Loss: 0.0013 top1=100.0000
[E27B50 |  19584/60000 ( 33%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3389 top1= 89.7035

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0014 top1=100.0000

=== Log global consensus distance @ E28B0 ===
consensus_distance=0.006


[E28B10 |   4224/60000 (  7%) ] Loss: 0.0015 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E28B30 |  11904/60000 ( 20%) ] Loss: 0.0011 top1=100.0000
[E28B40 |  15744/60000 ( 26%) ] Loss: 0.0015 top1=100.0000
[E28B50 |  19584/60000 ( 33%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3304 top1= 90.1042

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0016 top1=100.0000

=== Log global consensus distance @ E29B0 ===
consensus_distance=0.005


[E29B10 |   4224/60000 (  7%) ] Loss: 0.0014 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E29B30 |  11904/60000 ( 20%) ] Loss: 0.0006 top1=100.0000
[E29B40 |  15744/60000 ( 26%) ] Loss: 0.0014 top1=100.0000
[E29B50 |  19584/60000 ( 33%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3336 top1= 89.9639

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0013 top1=100.0000

=== Log global consensus distance @ E30B0 ===
consensus_distance=0.005


[E30B10 |   4224/60000 (  7%) ] Loss: 0.0016 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E30B30 |  11904/60000 ( 20%) ] Loss: 0.0009 top1=100.0000
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.0013 top1=100.0000
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3420 top1= 89.6835

