
=== 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 0x7f7b19d95730>

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: 0.1530 top1= 95.3125
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.0791 top1= 98.4375
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.1149 top1= 96.5625
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.0694 top1= 98.4375
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.0729 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9391 top1= 66.4163

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1079 top1= 97.8125

=== Log global consensus distance @ E2B0 ===
consensus_distance=0.135


[E 2B10 |   4224/60000 (  7%) ] Loss: 0.0423 top1= 99.0625
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.0412 top1= 99.0625
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.0560 top1= 98.1250
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.0697 top1= 97.5000
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.0555 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7655 top1= 72.6562

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.0751 top1= 97.8125

=== Log global consensus distance @ E3B0 ===
consensus_distance=0.092


[E 3B10 |   4224/60000 (  7%) ] Loss: 0.0385 top1= 99.3750
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0189 top1= 99.6875
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.0379 top1= 98.7500
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.0641 top1= 98.4375
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.0433 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7137 top1= 74.8998

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0572 top1= 99.0625

=== Log global consensus distance @ E4B0 ===
consensus_distance=0.078


[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0429 top1= 99.3750
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0198 top1= 99.6875
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.0260 top1= 99.3750
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.0522 top1= 98.1250
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.0364 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6694 top1= 77.3337

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0735 top1= 97.8125

=== Log global consensus distance @ E5B0 ===
consensus_distance=0.077


[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0582 top1= 99.0625
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0248 top1= 99.0625
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.0278 top1= 99.3750
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.0554 top1= 98.4375
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.0386 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6662 top1= 77.4840

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0633 top1= 98.7500

=== Log global consensus distance @ E6B0 ===
consensus_distance=0.075


[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0393 top1= 99.0625
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0251 top1= 99.3750
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.0194 top1= 99.6875
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.0521 top1= 98.4375
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.0345 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6459 top1= 78.7861

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0539 top1= 98.7500

=== Log global consensus distance @ E7B0 ===
consensus_distance=0.068


[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0225 top1= 99.6875
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0257 top1= 99.0625
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.0158 top1=100.0000
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.0443 top1= 98.7500
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.0345 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6476 top1= 78.9964

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0481 top1= 98.7500

=== Log global consensus distance @ E8B0 ===
consensus_distance=0.064


[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0238 top1= 99.6875
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0159 top1= 99.3750
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.0172 top1=100.0000
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.0350 top1= 98.7500
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.0323 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6564 top1= 78.3654

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0519 top1= 98.7500

=== Log global consensus distance @ E9B0 ===
consensus_distance=0.063


[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0264 top1= 99.6875
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0170 top1= 99.3750
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.0228 top1= 99.3750
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.0373 top1= 98.7500
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.0276 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6776 top1= 77.6042

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0521 top1= 99.0625

=== Log global consensus distance @ E10B0 ===
consensus_distance=0.063


[E10B10 |   4224/60000 (  7%) ] Loss: 0.0407 top1= 99.3750
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0167 top1= 99.6875
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.0298 top1= 99.0625
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.0351 top1= 98.7500
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.0276 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6889 top1= 77.9147

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0542 top1= 98.7500

=== Log global consensus distance @ E11B0 ===
consensus_distance=0.062


[E11B10 |   4224/60000 (  7%) ] Loss: 0.0210 top1= 99.6875
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0141 top1=100.0000
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.0333 top1= 99.0625
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.0327 top1= 99.0625
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.0285 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7116 top1= 77.5541

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0585 top1= 98.4375

=== Log global consensus distance @ E12B0 ===
consensus_distance=0.062


[E12B10 |   4224/60000 (  7%) ] Loss: 0.0272 top1= 99.6875
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0203 top1= 99.3750
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.0307 top1= 99.0625
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.0407 top1= 99.0625
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.0259 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7429 top1= 77.0132

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0460 top1= 99.0625

=== Log global consensus distance @ E13B0 ===
consensus_distance=0.062


[E13B10 |   4224/60000 (  7%) ] Loss: 0.0170 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0222 top1= 99.6875
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.0404 top1= 99.0625
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.0357 top1= 99.0625
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.0267 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7753 top1= 77.3738

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0627 top1= 98.4375

=== Log global consensus distance @ E14B0 ===
consensus_distance=0.062


[E14B10 |   4224/60000 (  7%) ] Loss: 0.0216 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0193 top1= 99.6875
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.0436 top1= 99.0625
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.0368 top1= 99.0625
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.0305 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8169 top1= 75.9916

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0651 top1= 98.1250

=== Log global consensus distance @ E15B0 ===
consensus_distance=0.060


[E15B10 |   4224/60000 (  7%) ] Loss: 0.0370 top1= 99.3750
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0280 top1= 99.3750
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.0338 top1= 99.3750
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.0438 top1= 98.4375
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.0338 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8529 top1= 75.6911

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0619 top1= 98.4375

=== Log global consensus distance @ E16B0 ===
consensus_distance=0.060


[E16B10 |   4224/60000 (  7%) ] Loss: 0.0270 top1= 99.6875
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0242 top1= 99.6875
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.0395 top1= 99.3750
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.0452 top1= 98.4375
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.0332 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8931 top1= 75.0501

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0718 top1= 97.5000

=== Log global consensus distance @ E17B0 ===
consensus_distance=0.061


[E17B10 |   4224/60000 (  7%) ] Loss: 0.0694 top1= 99.0625
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0257 top1= 99.3750
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.0359 top1= 99.0625
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.0510 top1= 98.1250
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.0368 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9422 top1= 72.7364

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0752 top1= 98.1250

=== Log global consensus distance @ E18B0 ===
consensus_distance=0.061


[E18B10 |   4224/60000 (  7%) ] Loss: 0.0236 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0220 top1=100.0000
[E18B30 |  11904/60000 ( 20%) ] Loss: 0.0366 top1= 99.0625
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.0526 top1= 98.4375
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.0396 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9608 top1= 75.7512

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0838 top1= 97.5000

=== Log global consensus distance @ E19B0 ===
consensus_distance=0.062


[E19B10 |   4224/60000 (  7%) ] Loss: 0.0834 top1= 99.0625
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0397 top1= 99.0625
[E19B30 |  11904/60000 ( 20%) ] Loss: 0.0965 top1= 98.1250
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.0534 top1= 99.0625
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.0459 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0276 top1= 70.5829

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0764 top1= 97.8125

=== Log global consensus distance @ E20B0 ===
consensus_distance=0.064


[E20B10 |   4224/60000 (  7%) ] Loss: 0.0284 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0256 top1=100.0000
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.0625 top1= 98.4375
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.0507 top1= 98.7500
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.0468 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0408 top1= 72.3658

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0984 top1= 97.5000

=== Log global consensus distance @ E21B0 ===
consensus_distance=0.069


[E21B10 |   4224/60000 (  7%) ] Loss: 0.0479 top1= 99.3750
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0305 top1= 99.6875
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.0643 top1= 98.1250
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.0628 top1= 98.4375
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.0416 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0560 top1= 69.4010

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0920 top1= 97.5000

=== Log global consensus distance @ E22B0 ===
consensus_distance=0.064


[E22B10 |   4224/60000 (  7%) ] Loss: 0.0349 top1= 99.3750
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0291 top1= 99.6875
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.0511 top1= 98.7500
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.0566 top1= 98.1250
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.0401 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0608 top1= 72.1154

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0908 top1= 97.1875

=== Log global consensus distance @ E23B0 ===
consensus_distance=0.065


[E23B10 |   4224/60000 (  7%) ] Loss: 0.0809 top1= 99.0625
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0425 top1= 99.0625
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.0517 top1= 98.7500
[E23B40 |  15744/60000 ( 26%) ] Loss: 0.0613 top1= 98.4375
[E23B50 |  19584/60000 ( 33%) ] Loss: 0.0587 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0839 top1= 69.6514

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0823 top1= 97.5000

=== Log global consensus distance @ E24B0 ===
consensus_distance=0.064


[E24B10 |   4224/60000 (  7%) ] Loss: 0.0287 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0308 top1= 99.3750
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.0374 top1= 99.0625
[E24B40 |  15744/60000 ( 26%) ] Loss: 0.0663 top1= 98.4375
[E24B50 |  19584/60000 ( 33%) ] Loss: 0.0453 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1002 top1= 69.4511

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0945 top1= 96.8750

=== Log global consensus distance @ E25B0 ===
consensus_distance=0.068


[E25B10 |   4224/60000 (  7%) ] Loss: 0.0454 top1= 99.3750
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0437 top1= 98.7500
[E25B30 |  11904/60000 ( 20%) ] Loss: 0.0688 top1= 98.4375
[E25B40 |  15744/60000 ( 26%) ] Loss: 0.0641 top1= 98.4375
[E25B50 |  19584/60000 ( 33%) ] Loss: 0.0549 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1142 top1= 68.2792

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0798 top1= 97.8125

=== Log global consensus distance @ E26B0 ===
consensus_distance=0.065


[E26B10 |   4224/60000 (  7%) ] Loss: 0.0306 top1= 99.6875
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0329 top1= 98.7500
[E26B30 |  11904/60000 ( 20%) ] Loss: 0.0556 top1= 98.4375
[E26B40 |  15744/60000 ( 26%) ] Loss: 0.0568 top1= 97.8125
[E26B50 |  19584/60000 ( 33%) ] Loss: 0.0431 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1327 top1= 69.0104

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0953 top1= 98.1250

=== Log global consensus distance @ E27B0 ===
consensus_distance=0.067


[E27B10 |   4224/60000 (  7%) ] Loss: 0.0548 top1= 99.0625
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0390 top1= 99.0625
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.0466 top1= 98.7500
[E27B40 |  15744/60000 ( 26%) ] Loss: 0.0593 top1= 98.1250
[E27B50 |  19584/60000 ( 33%) ] Loss: 0.0533 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1395 top1= 69.4912

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.1012 top1= 97.5000

=== Log global consensus distance @ E28B0 ===
consensus_distance=0.074


[E28B10 |   4224/60000 (  7%) ] Loss: 0.0398 top1= 99.6875
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0357 top1= 99.0625
[E28B30 |  11904/60000 ( 20%) ] Loss: 0.0674 top1= 98.1250
[E28B40 |  15744/60000 ( 26%) ] Loss: 0.0633 top1= 98.4375
[E28B50 |  19584/60000 ( 33%) ] Loss: 0.0471 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1369 top1= 69.2408

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.1046 top1= 97.5000

=== Log global consensus distance @ E29B0 ===
consensus_distance=0.068


[E29B10 |   4224/60000 (  7%) ] Loss: 0.0335 top1= 99.3750
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0337 top1= 99.0625
[E29B30 |  11904/60000 ( 20%) ] Loss: 0.0593 top1= 98.7500
[E29B40 |  15744/60000 ( 26%) ] Loss: 0.0592 top1= 98.4375
[E29B50 |  19584/60000 ( 33%) ] Loss: 0.0491 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1372 top1= 69.6915

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.1075 top1= 97.1875

=== Log global consensus distance @ E30B0 ===
consensus_distance=0.068


[E30B10 |   4224/60000 (  7%) ] Loss: 0.0358 top1= 99.3750
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0368 top1= 99.3750
[E30B30 |  11904/60000 ( 20%) ] Loss: 0.0685 top1= 98.4375
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.0579 top1= 98.4375
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.0576 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1611 top1= 67.8986

