
=== 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.RandomSmallWorldGraph object at 0x7fc27a1ba400>

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: 0.2102 top1= 92.1875
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2134 top1= 97.5000
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.0370 top1= 98.7500
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.0606 top1= 98.4375
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.0706 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6445 top1= 50.7512

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.0988 top1= 97.1875

=== Log global consensus distance @ E2B0 ===
consensus_distance=0.421


[E 2B10 |   4224/60000 (  7%) ] Loss: 0.0388 top1= 99.6875
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.0395 top1= 98.7500
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.0351 top1= 98.4375
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.0633 top1= 98.4375
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.0512 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0337 top1= 65.2444

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.0922 top1= 96.8750

=== Log global consensus distance @ E3B0 ===
consensus_distance=0.176


[E 3B10 |   4224/60000 (  7%) ] Loss: 0.0336 top1= 99.6875
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0282 top1= 99.6875
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.0311 top1= 98.7500
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.0544 top1= 98.7500
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.0391 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7228 top1= 76.7127

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0780 top1= 98.7500

=== Log global consensus distance @ E4B0 ===
consensus_distance=0.129


[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0341 top1= 99.3750
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0233 top1= 99.6875
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.0270 top1= 98.7500
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.0590 top1= 98.7500
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.0359 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6054 top1= 80.5288

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0754 top1= 98.7500

=== Log global consensus distance @ E5B0 ===
consensus_distance=0.111


[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0302 top1= 99.6875
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0160 top1= 99.3750
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.0227 top1= 99.0625
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.0489 top1= 99.0625
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.0403 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5402 top1= 82.5821

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0822 top1= 98.1250

=== Log global consensus distance @ E6B0 ===
consensus_distance=0.099


[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0183 top1= 99.6875
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0093 top1=100.0000
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.0369 top1= 98.7500
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.0718 top1= 98.4375
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.0335 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4915 top1= 85.1362

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0561 top1= 98.7500

=== Log global consensus distance @ E7B0 ===
consensus_distance=0.106


[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0196 top1= 99.3750
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0169 top1= 99.3750
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.0363 top1= 99.0625
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.0401 top1= 98.7500
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.0280 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4485 top1= 86.6386

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0537 top1= 98.7500

=== Log global consensus distance @ E8B0 ===
consensus_distance=0.074


[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0128 top1= 99.3750
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0094 top1=100.0000
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.0663 top1= 97.8125
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.0663 top1= 98.1250
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.0285 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4294 top1= 87.6402

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0405 top1= 99.0625

=== Log global consensus distance @ E9B0 ===
consensus_distance=0.080


[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0080 top1=100.0000
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0125 top1= 99.3750
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.0106 top1=100.0000
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.0209 top1= 99.3750
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.0212 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4041 top1= 88.0208

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0429 top1= 99.3750

=== Log global consensus distance @ E10B0 ===
consensus_distance=0.055


[E10B10 |   4224/60000 (  7%) ] Loss: 0.0089 top1= 99.6875
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0155 top1= 99.6875
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.0083 top1=100.0000
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.0186 top1= 99.0625
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.0209 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3897 top1= 88.4215

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0369 top1= 98.4375

=== Log global consensus distance @ E11B0 ===
consensus_distance=0.046


[E11B10 |   4224/60000 (  7%) ] Loss: 0.0197 top1= 99.3750
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0158 top1= 99.6875
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.0118 top1=100.0000
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.0124 top1= 99.3750
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.0135 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3776 top1= 88.7720

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0520 top1= 98.4375

=== Log global consensus distance @ E12B0 ===
consensus_distance=0.044


[E12B10 |   4224/60000 (  7%) ] Loss: 0.0500 top1= 98.1250
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0249 top1= 99.3750
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.0133 top1= 99.6875
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.0121 top1= 99.3750
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.0108 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3723 top1= 88.9323

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0462 top1= 99.0625

=== Log global consensus distance @ E13B0 ===
consensus_distance=0.041


[E13B10 |   4224/60000 (  7%) ] Loss: 0.0125 top1= 99.6875
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0165 top1= 99.6875
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.0124 top1= 99.6875
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.0130 top1= 99.3750
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.0151 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3709 top1= 88.8622

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0505 top1= 98.4375

=== Log global consensus distance @ E14B0 ===
consensus_distance=0.041


[E14B10 |   4224/60000 (  7%) ] Loss: 0.0084 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0048 top1=100.0000
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.0109 top1= 99.6875
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.0085 top1=100.0000
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.0182 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3659 top1= 88.9323

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0390 top1= 99.0625

=== Log global consensus distance @ E15B0 ===
consensus_distance=0.037


[E15B10 |   4224/60000 (  7%) ] Loss: 0.0273 top1= 99.3750
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0074 top1=100.0000
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.0108 top1=100.0000
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.0113 top1= 99.6875
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.0192 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3658 top1= 89.0124

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0157 top1= 99.6875

=== Log global consensus distance @ E16B0 ===
consensus_distance=0.030


[E16B10 |   4224/60000 (  7%) ] Loss: 0.0051 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0084 top1= 99.6875
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.0072 top1=100.0000
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.0102 top1= 99.6875
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.0155 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3721 top1= 88.6418

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0401 top1= 98.4375

=== Log global consensus distance @ E17B0 ===
consensus_distance=0.036


[E17B10 |   4224/60000 (  7%) ] Loss: 0.0101 top1= 99.3750
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0196 top1= 99.3750
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.0066 top1=100.0000
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.0095 top1= 99.6875
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.0091 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3537 top1= 89.3530

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0141 top1= 99.6875

=== Log global consensus distance @ E18B0 ===
consensus_distance=0.027


[E18B10 |   4224/60000 (  7%) ] Loss: 0.0054 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0089 top1= 99.6875
[E18B30 |  11904/60000 ( 20%) ] Loss: 0.0100 top1= 99.6875
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.0079 top1=100.0000
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.0097 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3519 top1= 89.4030

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0110 top1=100.0000

=== Log global consensus distance @ E19B0 ===
consensus_distance=0.026


[E19B10 |   4224/60000 (  7%) ] Loss: 0.0051 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0080 top1= 99.6875
[E19B30 |  11904/60000 ( 20%) ] Loss: 0.0073 top1=100.0000
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.0159 top1= 99.6875
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.0200 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3720 top1= 88.6719

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0449 top1= 99.0625

=== Log global consensus distance @ E20B0 ===
consensus_distance=0.052


[E20B10 |   4224/60000 (  7%) ] Loss: 0.0302 top1= 99.3750
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0151 top1= 99.3750
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.0324 top1= 99.3750
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.0110 top1=100.0000
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.0220 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3639 top1= 89.1827

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0322 top1= 99.0625

=== Log global consensus distance @ E21B0 ===
consensus_distance=0.056


[E21B10 |   4224/60000 (  7%) ] Loss: 0.0044 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0067 top1=100.0000
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.0091 top1=100.0000
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.0068 top1=100.0000
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.0128 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3734 top1= 88.5517

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0118 top1= 99.6875

=== Log global consensus distance @ E22B0 ===
consensus_distance=0.044


[E22B10 |   4224/60000 (  7%) ] Loss: 0.0055 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0110 top1= 99.6875
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.0052 top1=100.0000
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.0087 top1=100.0000
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.0231 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3522 top1= 89.5633

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0206 top1= 99.3750

=== Log global consensus distance @ E23B0 ===
consensus_distance=0.030


[E23B10 |   4224/60000 (  7%) ] Loss: 0.0054 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0048 top1=100.0000
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.0054 top1=100.0000
[E23B40 |  15744/60000 ( 26%) ] Loss: 0.0113 top1= 99.6875
[E23B50 |  19584/60000 ( 33%) ] Loss: 0.0100 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3464 top1= 89.7636

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0223 top1= 99.6875

=== Log global consensus distance @ E24B0 ===
consensus_distance=0.027


[E24B10 |   4224/60000 (  7%) ] Loss: 0.0259 top1= 99.3750
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0285 top1= 99.3750
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.0261 top1= 99.0625
[E24B40 |  15744/60000 ( 26%) ] Loss: 0.0217 top1= 99.0625
[E24B50 |  19584/60000 ( 33%) ] Loss: 0.0118 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3535 top1= 89.5933

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0156 top1= 99.6875

=== Log global consensus distance @ E25B0 ===
consensus_distance=0.029


[E25B10 |   4224/60000 (  7%) ] Loss: 0.0064 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0107 top1= 99.6875
[E25B30 |  11904/60000 ( 20%) ] Loss: 0.0062 top1=100.0000
[E25B40 |  15744/60000 ( 26%) ] Loss: 0.0084 top1=100.0000
[E25B50 |  19584/60000 ( 33%) ] Loss: 0.0069 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3476 top1= 89.7436

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0146 top1= 99.6875

=== Log global consensus distance @ E26B0 ===
consensus_distance=0.025


[E26B10 |   4224/60000 (  7%) ] Loss: 0.0053 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0056 top1=100.0000
[E26B30 |  11904/60000 ( 20%) ] Loss: 0.0079 top1=100.0000
[E26B40 |  15744/60000 ( 26%) ] Loss: 0.0105 top1=100.0000
[E26B50 |  19584/60000 ( 33%) ] Loss: 0.0112 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3506 top1= 89.4631

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0312 top1= 99.0625

=== Log global consensus distance @ E27B0 ===
consensus_distance=0.030


[E27B10 |   4224/60000 (  7%) ] Loss: 0.0056 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0086 top1= 99.6875
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.0084 top1=100.0000
[E27B40 |  15744/60000 ( 26%) ] Loss: 0.0101 top1=100.0000
[E27B50 |  19584/60000 ( 33%) ] Loss: 0.0080 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3441 top1= 89.9139

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0185 top1= 99.6875

=== Log global consensus distance @ E28B0 ===
consensus_distance=0.024


[E28B10 |   4224/60000 (  7%) ] Loss: 0.0125 top1= 99.6875
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0257 top1= 99.6875
[E28B30 |  11904/60000 ( 20%) ] Loss: 0.0191 top1= 99.6875
[E28B40 |  15744/60000 ( 26%) ] Loss: 0.0121 top1= 99.6875
[E28B50 |  19584/60000 ( 33%) ] Loss: 0.0166 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3543 top1= 89.4932

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0325 top1= 99.0625

=== Log global consensus distance @ E29B0 ===
consensus_distance=0.040


[E29B10 |   4224/60000 (  7%) ] Loss: 0.0167 top1= 99.0625
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0380 top1= 99.0625
[E29B30 |  11904/60000 ( 20%) ] Loss: 0.0305 top1= 99.3750
[E29B40 |  15744/60000 ( 26%) ] Loss: 0.0584 top1= 99.3750
[E29B50 |  19584/60000 ( 33%) ] Loss: 0.0224 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3868 top1= 89.1827

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0593 top1= 98.4375

=== Log global consensus distance @ E30B0 ===
consensus_distance=0.071


[E30B10 |   4224/60000 (  7%) ] Loss: 0.0304 top1= 99.3750
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0051 top1=100.0000
[E30B30 |  11904/60000 ( 20%) ] Loss: 0.0518 top1= 98.4375
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.0299 top1= 99.0625
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.0174 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3925 top1= 88.8121

