
=== 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 ByzantineWorker(index=9)
=> Add worker ByzantineWorker(index=10)

=== Start adding graph ===
<codes.graph_utils.TorusByzantineGraph object at 0x7eff0ce02400>

Train epoch 1
[E 1B0  |    352/60000 (  1%) ] Loss: 2.3038 top1= 11.1111

=== 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([2, 2, 2, 2, 2], device='cuda:0')
Worker 3 has targets: tensor([4, 3, 3, 4, 3], device='cuda:0')
Worker 4 has targets: tensor([5, 4, 4, 5, 4], device='cuda:0')
Worker 5 has targets: tensor([6, 6, 6, 6, 5], device='cuda:0')
Worker 6 has targets: tensor([7, 7, 7, 7, 6], device='cuda:0')
Worker 7 has targets: tensor([8, 8, 8, 8, 7], device='cuda:0')
Worker 8 has targets: tensor([9, 9, 9, 9, 8], device='cuda:0')
Worker 9 has targets: tensor([1, 1, 2, 1, 5], device='cuda:0')
Worker 10 has targets: tensor([8, 9, 1, 0, 3], device='cuda:0')



=== Log global consensus distance @ E1B0 ===
consensus_distance=0.000


[E 1B10 |   3872/60000 (  6%) ] Loss: 1.0346 top1= 74.3056
[E 1B20 |   7392/60000 ( 12%) ] Loss: 0.2831 top1= 90.6250
[E 1B30 |  10912/60000 ( 18%) ] Loss: 0.2276 top1= 94.0972
[E 1B40 |  14432/60000 ( 24%) ] Loss: 0.1569 top1= 96.8750
[E 1B50 |  17952/60000 ( 30%) ] Loss: 0.1584 top1= 95.1389

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6141 top1= 79.5673

Train epoch 2
[E 2B0  |    352/60000 (  1%) ] Loss: 0.0958 top1= 95.8333

=== Log global consensus distance @ E2B0 ===
consensus_distance=0.015


[E 2B10 |   3872/60000 (  6%) ] Loss: 0.1389 top1= 95.4861
[E 2B20 |   7392/60000 ( 12%) ] Loss: 0.0953 top1= 96.8750
[E 2B30 |  10912/60000 ( 18%) ] Loss: 0.1314 top1= 95.8333
[E 2B40 |  14432/60000 ( 24%) ] Loss: 0.0720 top1= 97.9167
[E 2B50 |  17952/60000 ( 30%) ] Loss: 0.0869 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5303 top1= 83.0929

Train epoch 3
[E 3B0  |    352/60000 (  1%) ] Loss: 0.0384 top1= 99.3056

=== Log global consensus distance @ E3B0 ===
consensus_distance=0.010


[E 3B10 |   3872/60000 (  6%) ] Loss: 0.0791 top1= 97.5694
[E 3B20 |   7392/60000 ( 12%) ] Loss: 0.0600 top1= 98.2639
[E 3B30 |  10912/60000 ( 18%) ] Loss: 0.0832 top1= 97.9167
[E 3B40 |  14432/60000 ( 24%) ] Loss: 0.0535 top1= 98.2639
[E 3B50 |  17952/60000 ( 30%) ] Loss: 0.0529 top1= 97.9167

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6620 top1= 79.1166

Train epoch 4
[E 4B0  |    352/60000 (  1%) ] Loss: 0.0497 top1= 98.6111

=== Log global consensus distance @ E4B0 ===
consensus_distance=0.010


[E 4B10 |   3872/60000 (  6%) ] Loss: 0.0607 top1= 97.5694
[E 4B20 |   7392/60000 ( 12%) ] Loss: 0.0360 top1= 98.6111
[E 4B30 |  10912/60000 ( 18%) ] Loss: 0.0652 top1= 97.9167
[E 4B40 |  14432/60000 ( 24%) ] Loss: 0.0590 top1= 97.5694
[E 4B50 |  17952/60000 ( 30%) ] Loss: 0.0200 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4422 top1= 86.1679

Train epoch 5
[E 5B0  |    352/60000 (  1%) ] Loss: 0.0248 top1= 99.6528

=== Log global consensus distance @ E5B0 ===
consensus_distance=0.009


[E 5B10 |   3872/60000 (  6%) ] Loss: 0.0437 top1= 98.2639
[E 5B20 |   7392/60000 ( 12%) ] Loss: 0.0515 top1= 98.2639
[E 5B30 |  10912/60000 ( 18%) ] Loss: 0.0362 top1= 99.3056
[E 5B40 |  14432/60000 ( 24%) ] Loss: 0.0514 top1= 98.6111
[E 5B50 |  17952/60000 ( 30%) ] Loss: 0.0286 top1= 98.6111

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5342 top1= 83.2933

Train epoch 6
[E 6B0  |    352/60000 (  1%) ] Loss: 0.0310 top1= 99.3056

=== Log global consensus distance @ E6B0 ===
consensus_distance=0.009


[E 6B10 |   3872/60000 (  6%) ] Loss: 0.0542 top1= 98.2639
[E 6B20 |   7392/60000 ( 12%) ] Loss: 0.0343 top1= 98.9583
[E 6B30 |  10912/60000 ( 18%) ] Loss: 0.0215 top1= 99.3056
[E 6B40 |  14432/60000 ( 24%) ] Loss: 0.0312 top1= 99.3056
[E 6B50 |  17952/60000 ( 30%) ] Loss: 0.0307 top1= 98.9583

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6023 top1= 83.7340

Train epoch 7
[E 7B0  |    352/60000 (  1%) ] Loss: 0.0203 top1= 98.9583

=== Log global consensus distance @ E7B0 ===
consensus_distance=0.011


[E 7B10 |   3872/60000 (  6%) ] Loss: 0.0545 top1= 97.9167
[E 7B20 |   7392/60000 ( 12%) ] Loss: 0.0546 top1= 97.5694
[E 7B30 |  10912/60000 ( 18%) ] Loss: 0.0204 top1= 99.6528
[E 7B40 |  14432/60000 ( 24%) ] Loss: 0.0448 top1= 97.9167
[E 7B50 |  17952/60000 ( 30%) ] Loss: 0.0276 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3792 top1= 88.6819

Train epoch 8
[E 8B0  |    352/60000 (  1%) ] Loss: 0.0205 top1= 99.3056

=== Log global consensus distance @ E8B0 ===
consensus_distance=0.008


[E 8B10 |   3872/60000 (  6%) ] Loss: 0.0350 top1= 98.9583
[E 8B20 |   7392/60000 ( 12%) ] Loss: 0.0435 top1= 98.2639
[E 8B30 |  10912/60000 ( 18%) ] Loss: 0.0291 top1= 98.6111
[E 8B40 |  14432/60000 ( 24%) ] Loss: 0.0273 top1= 98.9583
[E 8B50 |  17952/60000 ( 30%) ] Loss: 0.0287 top1= 98.9583

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3905 top1= 87.9908

Train epoch 9
[E 9B0  |    352/60000 (  1%) ] Loss: 0.0261 top1= 98.9583

=== Log global consensus distance @ E9B0 ===
consensus_distance=0.009


[E 9B10 |   3872/60000 (  6%) ] Loss: 0.0269 top1= 98.9583
[E 9B20 |   7392/60000 ( 12%) ] Loss: 0.0294 top1= 98.9583
[E 9B30 |  10912/60000 ( 18%) ] Loss: 0.0211 top1= 99.6528
[E 9B40 |  14432/60000 ( 24%) ] Loss: 0.0477 top1= 97.5694
[E 9B50 |  17952/60000 ( 30%) ] Loss: 0.0236 top1= 98.6111

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2310 top1= 93.2492

Train epoch 10
[E10B0  |    352/60000 (  1%) ] Loss: 0.0340 top1= 98.9583

=== Log global consensus distance @ E10B0 ===
consensus_distance=0.007


[E10B10 |   3872/60000 (  6%) ] Loss: 0.0593 top1= 97.2222
[E10B20 |   7392/60000 ( 12%) ] Loss: 0.0785 top1= 97.2222
[E10B30 |  10912/60000 ( 18%) ] Loss: 0.0141 top1= 99.6528
[E10B40 |  14432/60000 ( 24%) ] Loss: 0.0121 top1= 99.6528
[E10B50 |  17952/60000 ( 30%) ] Loss: 0.0227 top1= 99.3056

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2556 top1= 92.5581

Train epoch 11
[E11B0  |    352/60000 (  1%) ] Loss: 0.0132 top1=100.0000

=== Log global consensus distance @ E11B0 ===
consensus_distance=0.006


[E11B10 |   3872/60000 (  6%) ] Loss: 0.0211 top1= 99.6528
[E11B20 |   7392/60000 ( 12%) ] Loss: 0.0199 top1= 98.9583
[E11B30 |  10912/60000 ( 18%) ] Loss: 0.0274 top1= 99.3056
[E11B40 |  14432/60000 ( 24%) ] Loss: 0.0038 top1=100.0000
[E11B50 |  17952/60000 ( 30%) ] Loss: 0.0109 top1= 99.3056

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2200 top1= 93.7200

Train epoch 12
[E12B0  |    352/60000 (  1%) ] Loss: 0.0165 top1= 98.9583

=== Log global consensus distance @ E12B0 ===
consensus_distance=0.006


[E12B10 |   3872/60000 (  6%) ] Loss: 0.0167 top1= 99.6528
[E12B20 |   7392/60000 ( 12%) ] Loss: 0.0151 top1= 99.6528
[E12B30 |  10912/60000 ( 18%) ] Loss: 0.0271 top1= 98.9583
[E12B40 |  14432/60000 ( 24%) ] Loss: 0.0116 top1= 99.6528
[E12B50 |  17952/60000 ( 30%) ] Loss: 0.0233 top1= 98.9583

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2212 top1= 93.8702

Train epoch 13
[E13B0  |    352/60000 (  1%) ] Loss: 0.0178 top1= 99.6528

=== Log global consensus distance @ E13B0 ===
consensus_distance=0.004


[E13B10 |   3872/60000 (  6%) ] Loss: 0.0238 top1= 98.9583
[E13B20 |   7392/60000 ( 12%) ] Loss: 0.0167 top1= 99.6528
[E13B30 |  10912/60000 ( 18%) ] Loss: 0.0143 top1= 99.3056
[E13B40 |  14432/60000 ( 24%) ] Loss: 0.0075 top1=100.0000
[E13B50 |  17952/60000 ( 30%) ] Loss: 0.0127 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2350 top1= 93.4195

Train epoch 14
[E14B0  |    352/60000 (  1%) ] Loss: 0.0051 top1=100.0000

=== Log global consensus distance @ E14B0 ===
consensus_distance=0.004


[E14B10 |   3872/60000 (  6%) ] Loss: 0.0225 top1= 98.9583
[E14B20 |   7392/60000 ( 12%) ] Loss: 0.0241 top1= 99.3056
[E14B30 |  10912/60000 ( 18%) ] Loss: 0.0179 top1= 99.3056
[E14B40 |  14432/60000 ( 24%) ] Loss: 0.0050 top1=100.0000
[E14B50 |  17952/60000 ( 30%) ] Loss: 0.0054 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2324 top1= 93.7901

Train epoch 15
[E15B0  |    352/60000 (  1%) ] Loss: 0.0140 top1= 99.3056

=== Log global consensus distance @ E15B0 ===
consensus_distance=0.004


[E15B10 |   3872/60000 (  6%) ] Loss: 0.0225 top1= 99.6528
[E15B20 |   7392/60000 ( 12%) ] Loss: 0.0148 top1= 99.3056
[E15B30 |  10912/60000 ( 18%) ] Loss: 0.0260 top1= 99.3056
[E15B40 |  14432/60000 ( 24%) ] Loss: 0.0116 top1= 99.6528
[E15B50 |  17952/60000 ( 30%) ] Loss: 0.0162 top1= 98.9583

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2300 top1= 94.1206

Train epoch 16
[E16B0  |    352/60000 (  1%) ] Loss: 0.0184 top1= 99.3056

=== Log global consensus distance @ E16B0 ===
consensus_distance=0.006


[E16B10 |   3872/60000 (  6%) ] Loss: 0.0076 top1=100.0000
[E16B20 |   7392/60000 ( 12%) ] Loss: 0.0214 top1= 99.3056
[E16B30 |  10912/60000 ( 18%) ] Loss: 0.0156 top1= 99.6528
[E16B40 |  14432/60000 ( 24%) ] Loss: 0.0178 top1= 98.9583
[E16B50 |  17952/60000 ( 30%) ] Loss: 0.0277 top1= 98.9583

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2219 top1= 94.5413

Train epoch 17
[E17B0  |    352/60000 (  1%) ] Loss: 0.0507 top1= 98.2639

=== Log global consensus distance @ E17B0 ===
consensus_distance=0.004


[E17B10 |   3872/60000 (  6%) ] Loss: 0.0289 top1= 98.6111
[E17B20 |   7392/60000 ( 12%) ] Loss: 0.0035 top1=100.0000
[E17B30 |  10912/60000 ( 18%) ] Loss: 0.0141 top1= 99.3056
[E17B40 |  14432/60000 ( 24%) ] Loss: 0.0281 top1= 98.9583
[E17B50 |  17952/60000 ( 30%) ] Loss: 0.0059 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2043 top1= 94.7316

Train epoch 18
[E18B0  |    352/60000 (  1%) ] Loss: 0.0123 top1= 99.3056

=== Log global consensus distance @ E18B0 ===
consensus_distance=0.003


[E18B10 |   3872/60000 (  6%) ] Loss: 0.0186 top1= 99.3056
[E18B20 |   7392/60000 ( 12%) ] Loss: 0.0079 top1= 99.6528
[E18B30 |  10912/60000 ( 18%) ] Loss: 0.0132 top1= 99.6528
[E18B40 |  14432/60000 ( 24%) ] Loss: 0.0052 top1= 99.6528
[E18B50 |  17952/60000 ( 30%) ] Loss: 0.0045 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2025 top1= 94.7015

Train epoch 19
[E19B0  |    352/60000 (  1%) ] Loss: 0.0115 top1= 99.6528

=== Log global consensus distance @ E19B0 ===
consensus_distance=0.003


[E19B10 |   3872/60000 (  6%) ] Loss: 0.0162 top1= 99.6528
[E19B20 |   7392/60000 ( 12%) ] Loss: 0.0626 top1= 98.2639
[E19B30 |  10912/60000 ( 18%) ] Loss: 0.0077 top1=100.0000
[E19B40 |  14432/60000 ( 24%) ] Loss: 0.0047 top1=100.0000
[E19B50 |  17952/60000 ( 30%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1735 top1= 95.4327

Train epoch 20
[E20B0  |    352/60000 (  1%) ] Loss: 0.0026 top1=100.0000

=== Log global consensus distance @ E20B0 ===
consensus_distance=0.003


[E20B10 |   3872/60000 (  6%) ] Loss: 0.0307 top1= 98.6111
[E20B20 |   7392/60000 ( 12%) ] Loss: 0.0145 top1= 99.6528
[E20B30 |  10912/60000 ( 18%) ] Loss: 0.0051 top1= 99.6528
[E20B40 |  14432/60000 ( 24%) ] Loss: 0.0097 top1= 99.6528
[E20B50 |  17952/60000 ( 30%) ] Loss: 0.0034 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1896 top1= 95.2925

Train epoch 21
[E21B0  |    352/60000 (  1%) ] Loss: 0.0035 top1=100.0000

=== Log global consensus distance @ E21B0 ===
consensus_distance=0.002


[E21B10 |   3872/60000 (  6%) ] Loss: 0.0025 top1=100.0000
[E21B20 |   7392/60000 ( 12%) ] Loss: 0.0151 top1= 99.6528
[E21B30 |  10912/60000 ( 18%) ] Loss: 0.0095 top1= 99.6528
[E21B40 |  14432/60000 ( 24%) ] Loss: 0.0017 top1=100.0000
[E21B50 |  17952/60000 ( 30%) ] Loss: 0.0037 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2403 top1= 94.2808

Train epoch 22
[E22B0  |    352/60000 (  1%) ] Loss: 0.0053 top1=100.0000

=== Log global consensus distance @ E22B0 ===
consensus_distance=0.002


[E22B10 |   3872/60000 (  6%) ] Loss: 0.0192 top1= 99.6528
[E22B20 |   7392/60000 ( 12%) ] Loss: 0.0040 top1=100.0000
[E22B30 |  10912/60000 ( 18%) ] Loss: 0.0445 top1= 99.3056
[E22B40 |  14432/60000 ( 24%) ] Loss: 0.0153 top1= 99.6528
[E22B50 |  17952/60000 ( 30%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1861 top1= 95.1122

Train epoch 23
[E23B0  |    352/60000 (  1%) ] Loss: 0.0015 top1=100.0000

=== Log global consensus distance @ E23B0 ===
consensus_distance=0.002


[E23B10 |   3872/60000 (  6%) ] Loss: 0.0038 top1=100.0000
[E23B20 |   7392/60000 ( 12%) ] Loss: 0.0030 top1=100.0000
[E23B30 |  10912/60000 ( 18%) ] Loss: 0.0210 top1= 99.6528
[E23B40 |  14432/60000 ( 24%) ] Loss: 0.0135 top1= 99.3056
[E23B50 |  17952/60000 ( 30%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1912 top1= 95.2724

Train epoch 24
[E24B0  |    352/60000 (  1%) ] Loss: 0.0040 top1=100.0000

=== Log global consensus distance @ E24B0 ===
consensus_distance=0.002


[E24B10 |   3872/60000 (  6%) ] Loss: 0.0070 top1=100.0000
[E24B20 |   7392/60000 ( 12%) ] Loss: 0.0102 top1= 99.6528
[E24B30 |  10912/60000 ( 18%) ] Loss: 0.0616 top1= 98.9583
[E24B40 |  14432/60000 ( 24%) ] Loss: 0.0133 top1= 99.6528
[E24B50 |  17952/60000 ( 30%) ] Loss: 0.0043 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1627 top1= 95.9435

Train epoch 25
[E25B0  |    352/60000 (  1%) ] Loss: 0.0034 top1=100.0000

=== Log global consensus distance @ E25B0 ===
consensus_distance=0.002


[E25B10 |   3872/60000 (  6%) ] Loss: 0.0091 top1= 99.6528
[E25B20 |   7392/60000 ( 12%) ] Loss: 0.0046 top1=100.0000
[E25B30 |  10912/60000 ( 18%) ] Loss: 0.0219 top1= 99.3056
[E25B40 |  14432/60000 ( 24%) ] Loss: 0.0030 top1=100.0000
[E25B50 |  17952/60000 ( 30%) ] Loss: 0.0079 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1921 top1= 95.4026

Train epoch 26
[E26B0  |    352/60000 (  1%) ] Loss: 0.0141 top1= 99.3056

=== Log global consensus distance @ E26B0 ===
consensus_distance=0.002


[E26B10 |   3872/60000 (  6%) ] Loss: 0.0030 top1=100.0000
[E26B20 |   7392/60000 ( 12%) ] Loss: 0.0035 top1=100.0000
[E26B30 |  10912/60000 ( 18%) ] Loss: 0.0028 top1=100.0000
[E26B40 |  14432/60000 ( 24%) ] Loss: 0.0039 top1=100.0000
[E26B50 |  17952/60000 ( 30%) ] Loss: 0.0049 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1788 top1= 95.7332

Train epoch 27
[E27B0  |    352/60000 (  1%) ] Loss: 0.0014 top1=100.0000

=== Log global consensus distance @ E27B0 ===
consensus_distance=0.001


[E27B10 |   3872/60000 (  6%) ] Loss: 0.0361 top1= 99.6528
[E27B20 |   7392/60000 ( 12%) ] Loss: 0.0034 top1=100.0000
[E27B30 |  10912/60000 ( 18%) ] Loss: 0.0025 top1=100.0000
[E27B40 |  14432/60000 ( 24%) ] Loss: 0.0039 top1=100.0000
[E27B50 |  17952/60000 ( 30%) ] Loss: 0.0105 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2043 top1= 95.3125

Train epoch 28
[E28B0  |    352/60000 (  1%) ] Loss: 0.0041 top1=100.0000

=== Log global consensus distance @ E28B0 ===
consensus_distance=0.001


[E28B10 |   3872/60000 (  6%) ] Loss: 0.0042 top1=100.0000
[E28B20 |   7392/60000 ( 12%) ] Loss: 0.0025 top1=100.0000
[E28B30 |  10912/60000 ( 18%) ] Loss: 0.0048 top1=100.0000
[E28B40 |  14432/60000 ( 24%) ] Loss: 0.0017 top1=100.0000
[E28B50 |  17952/60000 ( 30%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1860 top1= 95.6731

Train epoch 29
[E29B0  |    352/60000 (  1%) ] Loss: 0.0173 top1= 99.6528

=== Log global consensus distance @ E29B0 ===
consensus_distance=0.002


[E29B10 |   3872/60000 (  6%) ] Loss: 0.0030 top1=100.0000
[E29B20 |   7392/60000 ( 12%) ] Loss: 0.0031 top1=100.0000
[E29B30 |  10912/60000 ( 18%) ] Loss: 0.0036 top1=100.0000
[E29B40 |  14432/60000 ( 24%) ] Loss: 0.0040 top1=100.0000
[E29B50 |  17952/60000 ( 30%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1820 top1= 95.7833

Train epoch 30
[E30B0  |    352/60000 (  1%) ] Loss: 0.0021 top1=100.0000

=== Log global consensus distance @ E30B0 ===
consensus_distance=0.001


[E30B10 |   3872/60000 (  6%) ] Loss: 0.0090 top1= 99.6528
[E30B20 |   7392/60000 ( 12%) ] Loss: 0.0034 top1=100.0000
[E30B30 |  10912/60000 ( 18%) ] Loss: 0.0060 top1=100.0000
[E30B40 |  14432/60000 ( 24%) ] Loss: 0.0010 top1=100.0000
[E30B50 |  17952/60000 ( 30%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2402 top1= 94.9319

