
=== 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 0x7ff4254b6400>

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=0.017



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


[E 1B10 |   4224/60000 (  7%) ] Loss: 0.5992 top1= 83.4375
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.3268 top1= 94.6875
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.4709 top1= 82.8125
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.1685 top1= 97.5000
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.1330 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8832 top1= 34.5653

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.2517 top1= 93.4375

=== Log global consensus distance @ E2B0 ===
consensus_distance=0.357


[E 2B10 |   4224/60000 (  7%) ] Loss: 0.1454 top1= 96.8750
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1116 top1= 97.5000
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.0645 top1= 99.0625
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.1002 top1= 96.8750
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.0917 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7516 top1= 38.4515

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1640 top1= 95.6250

=== Log global consensus distance @ E3B0 ===
consensus_distance=0.477


[E 3B10 |   4224/60000 (  7%) ] Loss: 0.0841 top1= 97.8125
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0350 top1= 99.3750
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.0521 top1= 99.6875
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.0963 top1= 97.1875
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.0682 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7248 top1= 38.1911

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1163 top1= 96.2500

=== Log global consensus distance @ E4B0 ===
consensus_distance=0.585


[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0640 top1= 99.0625
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0356 top1= 98.7500
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.0441 top1= 99.0625
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.0662 top1= 97.8125
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.0477 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7189 top1= 38.6819

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.1057 top1= 96.8750

=== Log global consensus distance @ E5B0 ===
consensus_distance=0.685


[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0495 top1= 99.3750
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0676 top1= 97.1875
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.0436 top1= 98.1250
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.0680 top1= 97.5000
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.0408 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6767 top1= 40.3746

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0781 top1= 97.8125

=== Log global consensus distance @ E6B0 ===
consensus_distance=0.765


[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0210 top1=100.0000
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0120 top1= 99.3750
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.0234 top1= 99.3750
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.0520 top1= 97.8125
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.0274 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6718 top1= 39.5433

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0802 top1= 96.5625

=== Log global consensus distance @ E7B0 ===
consensus_distance=0.854


[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0296 top1= 99.3750
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0370 top1= 98.7500
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.0373 top1= 98.7500
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.0758 top1= 97.1875
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.0779 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6792 top1= 40.0140

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0599 top1= 97.5000

=== Log global consensus distance @ E8B0 ===
consensus_distance=0.940


[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0440 top1= 99.0625
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0576 top1= 98.1250
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.0157 top1=100.0000
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.0330 top1= 98.7500
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.0432 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6808 top1= 40.2444

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0470 top1= 97.8125

=== Log global consensus distance @ E9B0 ===
consensus_distance=1.014


[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0197 top1=100.0000
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0192 top1= 99.6875
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.0158 top1= 99.6875
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.0227 top1= 99.0625
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.0367 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6716 top1= 40.3245

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0517 top1= 98.1250

=== Log global consensus distance @ E10B0 ===
consensus_distance=1.097


[E10B10 |   4224/60000 (  7%) ] Loss: 0.0376 top1= 98.4375
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0424 top1= 98.7500
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.0119 top1= 99.6875
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.0340 top1= 98.7500
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.0316 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7236 top1= 39.3530

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0612 top1= 98.1250

=== Log global consensus distance @ E11B0 ===
consensus_distance=1.174


[E11B10 |   4224/60000 (  7%) ] Loss: 0.0165 top1=100.0000
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0182 top1= 99.3750
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.0144 top1= 99.3750
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.0299 top1= 98.7500
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.0255 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6902 top1= 40.0942

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0785 top1= 97.8125

=== Log global consensus distance @ E12B0 ===
consensus_distance=1.243


[E12B10 |   4224/60000 (  7%) ] Loss: 0.0078 top1=100.0000
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0048 top1=100.0000
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.0137 top1= 99.3750
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.0469 top1= 97.8125
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.0245 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7230 top1= 40.2744

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0604 top1= 97.5000

=== Log global consensus distance @ E13B0 ===
consensus_distance=1.313


[E13B10 |   4224/60000 (  7%) ] Loss: 0.0076 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0100 top1= 99.6875
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.0085 top1=100.0000
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.0231 top1= 99.3750
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.0393 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7132 top1= 40.1743

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0405 top1= 98.4375

=== Log global consensus distance @ E14B0 ===
consensus_distance=1.383


[E14B10 |   4224/60000 (  7%) ] Loss: 0.0293 top1= 98.7500
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0206 top1= 99.3750
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.0129 top1= 99.6875
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.0187 top1= 99.3750
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.0231 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7682 top1= 39.5132

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0444 top1= 98.4375

=== Log global consensus distance @ E15B0 ===
consensus_distance=1.446


[E15B10 |   4224/60000 (  7%) ] Loss: 0.0140 top1= 99.6875
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0287 top1= 99.0625
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.0075 top1=100.0000
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.0234 top1= 98.7500
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.0364 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6971 top1= 41.2260

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0470 top1= 98.7500

=== Log global consensus distance @ E16B0 ===
consensus_distance=1.509


[E16B10 |   4224/60000 (  7%) ] Loss: 0.0059 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0326 top1= 99.0625
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.0179 top1= 99.3750
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.0178 top1= 99.6875
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.0301 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6921 top1= 40.7552

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0228 top1= 99.0625

=== Log global consensus distance @ E17B0 ===
consensus_distance=1.576


[E17B10 |   4224/60000 (  7%) ] Loss: 0.0141 top1= 99.6875
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0298 top1= 99.0625
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.0057 top1=100.0000
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.0175 top1= 99.3750
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.0190 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7171 top1= 41.2159

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0262 top1= 99.3750

=== Log global consensus distance @ E18B0 ===
consensus_distance=1.628


[E18B10 |   4224/60000 (  7%) ] Loss: 0.0439 top1= 98.7500
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0283 top1= 98.7500
[E18B30 |  11904/60000 ( 20%) ] Loss: 0.0058 top1=100.0000
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.0230 top1= 99.0625
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.0480 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7649 top1= 40.5749

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0316 top1= 98.7500

=== Log global consensus distance @ E19B0 ===
consensus_distance=1.694


[E19B10 |   4224/60000 (  7%) ] Loss: 0.0238 top1= 99.0625
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0048 top1=100.0000
[E19B30 |  11904/60000 ( 20%) ] Loss: 0.0080 top1=100.0000
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.0080 top1=100.0000
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.0213 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7452 top1= 40.3446

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0308 top1= 99.0625

=== Log global consensus distance @ E20B0 ===
consensus_distance=1.761


[E20B10 |   4224/60000 (  7%) ] Loss: 0.0053 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0189 top1= 99.6875
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.0063 top1=100.0000
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.0225 top1= 99.0625
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.0210 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7035 top1= 40.7652

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0273 top1= 99.0625

=== Log global consensus distance @ E21B0 ===
consensus_distance=1.807


[E21B10 |   4224/60000 (  7%) ] Loss: 0.0062 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0429 top1= 98.4375
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.0076 top1=100.0000
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.0164 top1= 99.3750
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.0353 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6737 top1= 41.8970

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0145 top1= 99.6875

=== Log global consensus distance @ E22B0 ===
consensus_distance=1.874


[E22B10 |   4224/60000 (  7%) ] Loss: 0.0113 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0180 top1= 99.6875
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.0114 top1= 99.6875
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.0093 top1=100.0000
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.0391 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7109 top1= 41.2260

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0126 top1= 99.6875

=== Log global consensus distance @ E23B0 ===
consensus_distance=1.937


[E23B10 |   4224/60000 (  7%) ] Loss: 0.0035 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0453 top1= 97.8125
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.0081 top1=100.0000
[E23B40 |  15744/60000 ( 26%) ] Loss: 0.0941 top1= 95.3125
[E23B50 |  19584/60000 ( 33%) ] Loss: 0.0536 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2399 top1= 54.5272

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.1031 top1= 96.2500

=== Log global consensus distance @ E24B0 ===
consensus_distance=1.865


[E24B10 |   4224/60000 (  7%) ] Loss: 0.0873 top1= 97.1875
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0659 top1= 98.7500
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.0287 top1= 99.0625
[E24B40 |  15744/60000 ( 26%) ] Loss: 0.0542 top1= 98.4375
[E24B50 |  19584/60000 ( 33%) ] Loss: 0.0368 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1938 top1= 55.9996

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0736 top1= 97.8125

=== Log global consensus distance @ E25B0 ===
consensus_distance=1.924


[E25B10 |   4224/60000 (  7%) ] Loss: 0.0329 top1= 99.3750
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0452 top1= 99.0625
[E25B30 |  11904/60000 ( 20%) ] Loss: 0.0365 top1= 99.0625
[E25B40 |  15744/60000 ( 26%) ] Loss: 0.0679 top1= 98.1250
[E25B50 |  19584/60000 ( 33%) ] Loss: 0.0456 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1763 top1= 55.5489

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0620 top1= 98.4375

=== Log global consensus distance @ E26B0 ===
consensus_distance=1.990


[E26B10 |   4224/60000 (  7%) ] Loss: 0.0204 top1= 99.3750
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0560 top1= 99.3750
[E26B30 |  11904/60000 ( 20%) ] Loss: 0.0131 top1= 99.6875
[E26B40 |  15744/60000 ( 26%) ] Loss: 0.0497 top1= 98.1250
[E26B50 |  19584/60000 ( 33%) ] Loss: 0.0351 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1437 top1= 57.3618

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0703 top1= 98.7500

=== Log global consensus distance @ E27B0 ===
consensus_distance=2.018


[E27B10 |   4224/60000 (  7%) ] Loss: 0.0267 top1= 98.7500
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0498 top1= 98.1250
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.0132 top1= 99.3750
[E27B40 |  15744/60000 ( 26%) ] Loss: 0.0526 top1= 98.4375
[E27B50 |  19584/60000 ( 33%) ] Loss: 0.0286 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1478 top1= 57.8826

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0764 top1= 98.4375

=== Log global consensus distance @ E28B0 ===
consensus_distance=2.082


[E28B10 |   4224/60000 (  7%) ] Loss: 0.0229 top1= 98.7500
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0462 top1= 98.4375
[E28B30 |  11904/60000 ( 20%) ] Loss: 0.0110 top1= 99.6875
[E28B40 |  15744/60000 ( 26%) ] Loss: 0.0489 top1= 98.7500
[E28B50 |  19584/60000 ( 33%) ] Loss: 0.0247 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1476 top1= 57.0513

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0720 top1= 98.4375

=== Log global consensus distance @ E29B0 ===
consensus_distance=2.151


[E29B10 |   4224/60000 (  7%) ] Loss: 0.0185 top1= 99.6875
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0649 top1= 98.7500
[E29B30 |  11904/60000 ( 20%) ] Loss: 0.0169 top1= 99.6875
[E29B40 |  15744/60000 ( 26%) ] Loss: 0.0720 top1= 98.1250
[E29B50 |  19584/60000 ( 33%) ] Loss: 0.0365 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1342 top1= 57.5421

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0534 top1= 99.0625

=== Log global consensus distance @ E30B0 ===
consensus_distance=2.168


[E30B10 |   4224/60000 (  7%) ] Loss: 0.0112 top1= 99.6875
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0504 top1= 99.3750
[E30B30 |  11904/60000 ( 20%) ] Loss: 0.0146 top1=100.0000
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.0658 top1= 98.4375
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.0266 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1848 top1= 56.8109

