
=== 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 0x7f0a7bfe5400>

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: 0.2087 top1= 92.1875
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2130 top1= 97.5000
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.0389 top1= 98.7500
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.0612 top1= 98.4375
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.0705 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7505 top1= 40.9355

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1012 top1= 96.8750

=== Log global consensus distance @ E2B0 ===
consensus_distance=0.386


[E 2B10 |   4224/60000 (  7%) ] Loss: 0.0397 top1= 99.3750
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.0410 top1= 98.7500
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.0345 top1= 98.7500
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.0625 top1= 98.4375
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.0457 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2237 top1= 56.0296

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1046 top1= 97.1875

=== Log global consensus distance @ E3B0 ===
consensus_distance=0.166


[E 3B10 |   4224/60000 (  7%) ] Loss: 0.0354 top1= 99.6875
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0307 top1= 99.3750
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.0286 top1= 98.7500
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.0550 top1= 98.7500
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.0317 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9730 top1= 65.7853

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0831 top1= 98.4375

=== Log global consensus distance @ E4B0 ===
consensus_distance=0.122


[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0529 top1= 98.7500
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0244 top1= 99.3750
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.0429 top1= 98.7500
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.0626 top1= 98.4375
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.0445 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9684 top1= 64.1426

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0687 top1= 98.7500

=== Log global consensus distance @ E5B0 ===
consensus_distance=0.153


[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0214 top1= 99.6875
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0233 top1= 99.6875
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.0218 top1= 99.3750
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.0539 top1= 99.0625
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.0318 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9262 top1= 66.4163

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0842 top1= 98.4375

=== Log global consensus distance @ E6B0 ===
consensus_distance=0.126


[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0191 top1= 99.6875
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0143 top1= 99.6875
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.0253 top1= 99.0625
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.0393 top1= 99.0625
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.0429 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9309 top1= 66.4764

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0653 top1= 98.4375

=== Log global consensus distance @ E7B0 ===
consensus_distance=0.105


[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0120 top1= 99.3750
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0098 top1= 99.6875
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.0421 top1= 98.7500
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.0900 top1= 97.8125
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.0247 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8543 top1= 70.0921

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0471 top1= 97.8125

=== Log global consensus distance @ E8B0 ===
consensus_distance=0.132


[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0116 top1= 99.6875
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0125 top1= 99.6875
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.0057 top1=100.0000
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.0212 top1= 99.6875
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.0229 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8167 top1= 70.8033

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0255 top1= 99.0625

=== Log global consensus distance @ E9B0 ===
consensus_distance=0.055


[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0107 top1= 99.6875
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0261 top1= 99.3750
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.0091 top1= 99.6875
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.0145 top1= 99.6875
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.0145 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8438 top1= 69.0505

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.1130 top1= 97.8125

=== Log global consensus distance @ E10B0 ===
consensus_distance=0.119


[E10B10 |   4224/60000 (  7%) ] Loss: 0.0094 top1= 99.6875
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0137 top1= 99.6875
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.0341 top1= 99.0625
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.0289 top1= 99.3750
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.0220 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7693 top1= 72.2256

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0380 top1= 98.7500

=== Log global consensus distance @ E11B0 ===
consensus_distance=0.063


[E11B10 |   4224/60000 (  7%) ] Loss: 0.0156 top1= 99.6875
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0138 top1= 99.3750
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.0060 top1=100.0000
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.0147 top1= 99.3750
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.0141 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7745 top1= 73.6779

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0765 top1= 98.4375

=== Log global consensus distance @ E12B0 ===
consensus_distance=0.080


[E12B10 |   4224/60000 (  7%) ] Loss: 0.0240 top1= 99.0625
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0099 top1= 99.6875
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.0122 top1= 99.6875
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.0070 top1=100.0000
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.0225 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7547 top1= 73.7780

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0276 top1= 99.6875

=== Log global consensus distance @ E13B0 ===
consensus_distance=0.061


[E13B10 |   4224/60000 (  7%) ] Loss: 0.0037 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0106 top1= 99.6875
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.0090 top1= 99.6875
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.0171 top1= 99.6875
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.0170 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6495 top1= 77.2035

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0182 top1= 99.6875

=== Log global consensus distance @ E14B0 ===
consensus_distance=0.030


[E14B10 |   4224/60000 (  7%) ] Loss: 0.0035 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0084 top1= 99.6875
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.0038 top1=100.0000
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.0067 top1=100.0000
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.0110 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6854 top1= 77.3337

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0165 top1= 99.3750

=== Log global consensus distance @ E15B0 ===
consensus_distance=0.033


[E15B10 |   4224/60000 (  7%) ] Loss: 0.0262 top1= 99.3750
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0194 top1= 99.6875
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.0032 top1=100.0000
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.0102 top1= 99.6875
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.0095 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6744 top1= 76.7628

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0103 top1= 99.6875

=== Log global consensus distance @ E16B0 ===
consensus_distance=0.027


[E16B10 |   4224/60000 (  7%) ] Loss: 0.0025 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0068 top1= 99.6875
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.0528 top1= 99.0625
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.0421 top1= 99.0625
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.0128 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7442 top1= 73.3574

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0704 top1= 98.7500

=== Log global consensus distance @ E17B0 ===
consensus_distance=0.165


[E17B10 |   4224/60000 (  7%) ] Loss: 0.0135 top1= 99.6875
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0227 top1= 99.3750
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.0036 top1=100.0000
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.0069 top1=100.0000
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.0056 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6552 top1= 78.2252

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0074 top1=100.0000

=== Log global consensus distance @ E18B0 ===
consensus_distance=0.032


[E18B10 |   4224/60000 (  7%) ] Loss: 0.0032 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0056 top1=100.0000
[E18B30 |  11904/60000 ( 20%) ] Loss: 0.0035 top1=100.0000
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.0043 top1=100.0000
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.0070 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6131 top1= 78.8462

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0212 top1= 99.3750

=== Log global consensus distance @ E19B0 ===
consensus_distance=0.023


[E19B10 |   4224/60000 (  7%) ] Loss: 0.0027 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0053 top1=100.0000
[E19B30 |  11904/60000 ( 20%) ] Loss: 0.0170 top1= 99.6875
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.0053 top1=100.0000
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.0043 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6513 top1= 77.2236

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0060 top1= 99.6875

=== Log global consensus distance @ E20B0 ===
consensus_distance=0.020


[E20B10 |   4224/60000 (  7%) ] Loss: 0.0033 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0039 top1=100.0000
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.0034 top1=100.0000
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.0042 top1=100.0000
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.0053 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6078 top1= 79.1767

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0081 top1= 99.6875

=== Log global consensus distance @ E21B0 ===
consensus_distance=0.016


[E21B10 |   4224/60000 (  7%) ] Loss: 0.0028 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0041 top1=100.0000
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.0020 top1=100.0000
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.0028 top1=100.0000
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6152 top1= 79.3369

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0042 top1=100.0000

=== Log global consensus distance @ E22B0 ===
consensus_distance=0.013


[E22B10 |   4224/60000 (  7%) ] Loss: 0.0036 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0128 top1= 99.6875
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.0022 top1=100.0000
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.0145 top1= 99.6875
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5613 top1= 81.2099

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0030 top1=100.0000

=== Log global consensus distance @ E23B0 ===
consensus_distance=0.016


[E23B10 |   4224/60000 (  7%) ] Loss: 0.0034 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0027 top1=100.0000
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.0035 top1=100.0000
[E23B40 |  15744/60000 ( 26%) ] Loss: 0.0044 top1=100.0000
[E23B50 |  19584/60000 ( 33%) ] Loss: 0.0069 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6112 top1= 79.3069

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0117 top1= 99.6875

=== Log global consensus distance @ E24B0 ===
consensus_distance=0.021


[E24B10 |   4224/60000 (  7%) ] Loss: 0.0044 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0379 top1= 99.0625
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.0250 top1= 99.3750
[E24B40 |  15744/60000 ( 26%) ] Loss: 0.0962 top1= 99.0625
[E24B50 |  19584/60000 ( 33%) ] Loss: 0.0675 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0209 top1= 65.1242

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.1907 top1= 98.1250

=== Log global consensus distance @ E25B0 ===
consensus_distance=0.833


[E25B10 |   4224/60000 (  7%) ] Loss: 0.0448 top1= 99.0625
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0150 top1= 99.6875
[E25B30 |  11904/60000 ( 20%) ] Loss: 0.0040 top1=100.0000
[E25B40 |  15744/60000 ( 26%) ] Loss: 0.0168 top1= 99.6875
[E25B50 |  19584/60000 ( 33%) ] Loss: 0.0047 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7704 top1= 72.6663

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0076 top1= 99.6875

=== Log global consensus distance @ E26B0 ===
consensus_distance=0.136


[E26B10 |   4224/60000 (  7%) ] Loss: 0.0049 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0029 top1=100.0000
[E26B30 |  11904/60000 ( 20%) ] Loss: 0.0031 top1=100.0000
[E26B40 |  15744/60000 ( 26%) ] Loss: 0.0052 top1=100.0000
[E26B50 |  19584/60000 ( 33%) ] Loss: 0.0087 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5903 top1= 78.4756

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0051 top1=100.0000

=== Log global consensus distance @ E27B0 ===
consensus_distance=0.021


[E27B10 |   4224/60000 (  7%) ] Loss: 0.0036 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0027 top1=100.0000
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.0024 top1=100.0000
[E27B40 |  15744/60000 ( 26%) ] Loss: 0.0035 top1=100.0000
[E27B50 |  19584/60000 ( 33%) ] Loss: 0.0043 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5638 top1= 80.7792

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0031 top1=100.0000

=== Log global consensus distance @ E28B0 ===
consensus_distance=0.015


[E28B10 |   4224/60000 (  7%) ] Loss: 0.0058 top1= 99.6875
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0037 top1=100.0000
[E28B30 |  11904/60000 ( 20%) ] Loss: 0.0027 top1=100.0000
[E28B40 |  15744/60000 ( 26%) ] Loss: 0.0026 top1=100.0000
[E28B50 |  19584/60000 ( 33%) ] Loss: 0.0038 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5162 top1= 82.1314

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0040 top1=100.0000

=== Log global consensus distance @ E29B0 ===
consensus_distance=0.012


[E29B10 |   4224/60000 (  7%) ] Loss: 0.0039 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0035 top1=100.0000
[E29B30 |  11904/60000 ( 20%) ] Loss: 0.0021 top1=100.0000
[E29B40 |  15744/60000 ( 26%) ] Loss: 0.0032 top1=100.0000
[E29B50 |  19584/60000 ( 33%) ] Loss: 0.0033 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5638 top1= 80.9996

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0027 top1=100.0000

=== Log global consensus distance @ E30B0 ===
consensus_distance=0.011


[E30B10 |   4224/60000 (  7%) ] Loss: 0.0023 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0047 top1=100.0000
[E30B30 |  11904/60000 ( 20%) ] Loss: 0.0020 top1=100.0000
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.0036 top1=100.0000
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5251 top1= 82.0513

