
=== 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 0x7fd8b1c42400>

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: 0.2121 top1= 92.1875
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2148 top1= 97.5000
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.0360 top1= 98.7500
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.0589 top1= 98.4375
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.0706 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6209 top1= 56.4603

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.0971 top1= 96.8750

=== Log global consensus distance @ E2B0 ===
consensus_distance=0.543


[E 2B10 |   4224/60000 (  7%) ] Loss: 0.0380 top1= 99.3750
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.0396 top1= 98.7500
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.0339 top1= 98.7500
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.0619 top1= 98.4375
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.0524 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1085 top1= 65.7051

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.0928 top1= 97.5000

=== Log global consensus distance @ E3B0 ===
consensus_distance=0.262


[E 3B10 |   4224/60000 (  7%) ] Loss: 0.0352 top1= 99.3750
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0267 top1= 99.6875
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.0311 top1= 99.0625
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.0546 top1= 98.7500
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.0400 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8354 top1= 73.8181

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0777 top1= 98.7500

=== Log global consensus distance @ E4B0 ===
consensus_distance=0.197


[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0352 top1= 99.6875
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0177 top1= 99.3750
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.0233 top1= 99.3750
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.0520 top1= 99.0625
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.0378 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7265 top1= 76.3722

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0872 top1= 98.7500

=== Log global consensus distance @ E5B0 ===
consensus_distance=0.161


[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0250 top1= 99.6875
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0120 top1= 99.6875
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.0309 top1= 98.4375
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.0462 top1= 99.0625
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.0376 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6631 top1= 78.1250

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0764 top1= 98.1250

=== Log global consensus distance @ E6B0 ===
consensus_distance=0.139


[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0229 top1= 99.6875
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0119 top1= 99.6875
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.0509 top1= 98.1250
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.0667 top1= 98.4375
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.0332 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6249 top1= 80.3786

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0629 top1= 99.0625

=== Log global consensus distance @ E7B0 ===
consensus_distance=0.134


[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0203 top1= 99.6875
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0178 top1= 99.3750
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.0381 top1= 98.4375
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.0393 top1= 98.7500
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.0333 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5640 top1= 83.1530

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0659 top1= 98.4375

=== Log global consensus distance @ E8B0 ===
consensus_distance=0.099


[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0136 top1= 99.3750
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0090 top1= 99.6875
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.0639 top1= 98.1250
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.0718 top1= 98.1250
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.0276 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5465 top1= 83.7139

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0469 top1= 98.4375

=== Log global consensus distance @ E9B0 ===
consensus_distance=0.098


[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0106 top1= 99.6875
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0121 top1= 99.3750
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.0059 top1=100.0000
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.0132 top1= 99.6875
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.0169 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5126 top1= 84.3249

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0394 top1= 98.7500

=== Log global consensus distance @ E10B0 ===
consensus_distance=0.066


[E10B10 |   4224/60000 (  7%) ] Loss: 0.0079 top1=100.0000
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0137 top1= 99.6875
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.0078 top1=100.0000
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.0202 top1= 99.3750
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.0200 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5085 top1= 84.3249

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0325 top1= 99.0625

=== Log global consensus distance @ E11B0 ===
consensus_distance=0.067


[E11B10 |   4224/60000 (  7%) ] Loss: 0.0135 top1= 99.6875
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0061 top1=100.0000
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.0152 top1= 99.3750
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.0125 top1=100.0000
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.0144 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4870 top1= 84.9760

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0316 top1= 99.0625

=== Log global consensus distance @ E12B0 ===
consensus_distance=0.054


[E12B10 |   4224/60000 (  7%) ] Loss: 0.0142 top1= 99.3750
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0073 top1=100.0000
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.0071 top1=100.0000
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.0111 top1=100.0000
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.0218 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4949 top1= 84.2548

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0273 top1= 99.3750

=== Log global consensus distance @ E13B0 ===
consensus_distance=0.051


[E13B10 |   4224/60000 (  7%) ] Loss: 0.0090 top1= 99.6875
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0083 top1= 99.6875
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.0072 top1=100.0000
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.0102 top1= 99.6875
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.0208 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5591 top1= 80.6390

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0327 top1= 98.7500

=== Log global consensus distance @ E14B0 ===
consensus_distance=0.083


[E14B10 |   4224/60000 (  7%) ] Loss: 0.0067 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0201 top1= 99.6875
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.0095 top1= 99.6875
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.0081 top1=100.0000
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.0181 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4911 top1= 85.3165

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0353 top1= 99.0625

=== Log global consensus distance @ E15B0 ===
consensus_distance=0.062


[E15B10 |   4224/60000 (  7%) ] Loss: 0.0067 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0066 top1=100.0000
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.0065 top1=100.0000
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.0094 top1= 99.6875
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.0098 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4896 top1= 85.1062

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0243 top1= 99.0625

=== Log global consensus distance @ E16B0 ===
consensus_distance=0.046


[E16B10 |   4224/60000 (  7%) ] Loss: 0.0080 top1= 99.6875
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0041 top1=100.0000
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.0143 top1= 99.6875
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.0313 top1= 99.3750
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.0068 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4773 top1= 85.5168

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0234 top1= 99.0625

=== Log global consensus distance @ E17B0 ===
consensus_distance=0.051


[E17B10 |   4224/60000 (  7%) ] Loss: 0.0063 top1= 99.6875
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0106 top1= 99.6875
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.0068 top1=100.0000
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.0088 top1= 99.6875
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.0201 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4766 top1= 85.7672

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0330 top1= 99.3750

=== Log global consensus distance @ E18B0 ===
consensus_distance=0.038


[E18B10 |   4224/60000 (  7%) ] Loss: 0.0224 top1= 99.3750
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0194 top1= 99.3750
[E18B30 |  11904/60000 ( 20%) ] Loss: 0.0096 top1= 99.6875
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.0115 top1= 99.6875
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.0169 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4799 top1= 85.6971

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0343 top1= 99.3750

=== Log global consensus distance @ E19B0 ===
consensus_distance=0.037


[E19B10 |   4224/60000 (  7%) ] Loss: 0.0345 top1= 99.3750
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0053 top1=100.0000
[E19B30 |  11904/60000 ( 20%) ] Loss: 0.0136 top1= 99.6875
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.0124 top1= 99.6875
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.0158 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4826 top1= 85.7572

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0192 top1= 99.6875

=== Log global consensus distance @ E20B0 ===
consensus_distance=0.037


[E20B10 |   4224/60000 (  7%) ] Loss: 0.0053 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0067 top1= 99.6875
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.0065 top1=100.0000
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.0081 top1=100.0000
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.0111 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5202 top1= 82.5020

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0390 top1= 99.0625

=== Log global consensus distance @ E21B0 ===
consensus_distance=0.054


[E21B10 |   4224/60000 (  7%) ] Loss: 0.0709 top1= 98.4375
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0093 top1= 99.6875
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.0404 top1= 99.6875
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.0205 top1= 99.3750
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.0302 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5664 top1= 81.3702

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0427 top1= 98.7500

=== Log global consensus distance @ E22B0 ===
consensus_distance=0.107


[E22B10 |   4224/60000 (  7%) ] Loss: 0.0057 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0154 top1= 99.3750
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.0063 top1=100.0000
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.0163 top1= 99.6875
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.0269 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5194 top1= 84.4451

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0320 top1= 99.3750

=== Log global consensus distance @ E23B0 ===
consensus_distance=0.059


[E23B10 |   4224/60000 (  7%) ] Loss: 0.0276 top1= 99.3750
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0124 top1= 99.6875
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.0148 top1= 99.3750
[E23B40 |  15744/60000 ( 26%) ] Loss: 0.0137 top1= 99.6875
[E23B50 |  19584/60000 ( 33%) ] Loss: 0.0151 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5109 top1= 85.1062

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0430 top1= 99.0625

=== Log global consensus distance @ E24B0 ===
consensus_distance=0.047


[E24B10 |   4224/60000 (  7%) ] Loss: 0.0059 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0069 top1=100.0000
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.0059 top1=100.0000
[E24B40 |  15744/60000 ( 26%) ] Loss: 0.0109 top1=100.0000
[E24B50 |  19584/60000 ( 33%) ] Loss: 0.0125 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5004 top1= 85.4367

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0165 top1= 99.6875

=== Log global consensus distance @ E25B0 ===
consensus_distance=0.038


[E25B10 |   4224/60000 (  7%) ] Loss: 0.0057 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0087 top1= 99.6875
[E25B30 |  11904/60000 ( 20%) ] Loss: 0.0079 top1=100.0000
[E25B40 |  15744/60000 ( 26%) ] Loss: 0.0105 top1=100.0000
[E25B50 |  19584/60000 ( 33%) ] Loss: 0.0116 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5259 top1= 84.2748

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0231 top1= 99.3750

=== Log global consensus distance @ E26B0 ===
consensus_distance=0.041


[E26B10 |   4224/60000 (  7%) ] Loss: 0.0263 top1= 98.7500
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0170 top1= 99.3750
[E26B30 |  11904/60000 ( 20%) ] Loss: 0.0141 top1= 99.6875
[E26B40 |  15744/60000 ( 26%) ] Loss: 0.0094 top1=100.0000
[E26B50 |  19584/60000 ( 33%) ] Loss: 0.0183 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5442 top1= 82.9627

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0483 top1= 98.1250

=== Log global consensus distance @ E27B0 ===
consensus_distance=0.053


[E27B10 |   4224/60000 (  7%) ] Loss: 0.0067 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0191 top1= 99.6875
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.0209 top1= 99.0625
[E27B40 |  15744/60000 ( 26%) ] Loss: 0.0203 top1= 99.6875
[E27B50 |  19584/60000 ( 33%) ] Loss: 0.0158 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5719 top1= 82.0713

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0288 top1= 99.3750

=== Log global consensus distance @ E28B0 ===
consensus_distance=0.072


[E28B10 |   4224/60000 (  7%) ] Loss: 0.0090 top1= 99.6875
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0054 top1=100.0000
[E28B30 |  11904/60000 ( 20%) ] Loss: 0.0088 top1=100.0000
[E28B40 |  15744/60000 ( 26%) ] Loss: 0.0082 top1=100.0000
[E28B50 |  19584/60000 ( 33%) ] Loss: 0.0102 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5494 top1= 83.3534

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0205 top1= 99.0625

=== Log global consensus distance @ E29B0 ===
consensus_distance=0.047


[E29B10 |   4224/60000 (  7%) ] Loss: 0.0121 top1= 99.3750
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0064 top1= 99.6875
[E29B30 |  11904/60000 ( 20%) ] Loss: 0.0250 top1= 99.3750
[E29B40 |  15744/60000 ( 26%) ] Loss: 0.0243 top1= 99.3750
[E29B50 |  19584/60000 ( 33%) ] Loss: 0.0127 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5754 top1= 81.6707

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0391 top1= 99.3750

=== Log global consensus distance @ E30B0 ===
consensus_distance=0.055


[E30B10 |   4224/60000 (  7%) ] Loss: 0.0980 top1= 98.7500
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0298 top1= 99.3750
[E30B30 |  11904/60000 ( 20%) ] Loss: 0.0476 top1= 98.7500
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.0249 top1= 99.0625
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.0198 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6124 top1= 80.7492

