
=== 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 LabelFlippingWorker
=> Add worker LabelFlippingWorker

=== Start adding graph ===
<codes.graph_utils.TorusByzantineGraph object at 0x7f1c6be1a400>

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



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


[E 1B10 |   3872/60000 (  6%) ] Loss: 1.0772 top1= 75.0000
[E 1B20 |   7392/60000 ( 12%) ] Loss: 0.2927 top1= 92.0139
[E 1B30 |  10912/60000 ( 18%) ] Loss: 0.2245 top1= 94.0972
[E 1B40 |  14432/60000 ( 24%) ] Loss: 0.1587 top1= 96.5278
[E 1B50 |  17952/60000 ( 30%) ] Loss: 0.1459 top1= 94.7917

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5688 top1= 81.6807

Train epoch 2
[E 2B0  |    352/60000 (  1%) ] Loss: 0.0889 top1= 97.5694

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


[E 2B10 |   3872/60000 (  6%) ] Loss: 0.1386 top1= 95.8333
[E 2B20 |   7392/60000 ( 12%) ] Loss: 0.1113 top1= 97.9167
[E 2B30 |  10912/60000 ( 18%) ] Loss: 0.1117 top1= 96.1806
[E 2B40 |  14432/60000 ( 24%) ] Loss: 0.0849 top1= 98.6111
[E 2B50 |  17952/60000 ( 30%) ] Loss: 0.0692 top1= 98.6111

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5186 top1= 82.6623

Train epoch 3
[E 3B0  |    352/60000 (  1%) ] Loss: 0.0467 top1= 99.3056

=== Log global consensus distance @ E3B0 ===
consensus_distance=0.012


[E 3B10 |   3872/60000 (  6%) ] Loss: 0.0913 top1= 96.8750
[E 3B20 |   7392/60000 ( 12%) ] Loss: 0.0602 top1= 98.6111
[E 3B30 |  10912/60000 ( 18%) ] Loss: 0.0600 top1= 97.5694
[E 3B40 |  14432/60000 ( 24%) ] Loss: 0.0566 top1= 97.9167
[E 3B50 |  17952/60000 ( 30%) ] Loss: 0.0478 top1= 98.6111

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5612 top1= 81.2700

Train epoch 4
[E 4B0  |    352/60000 (  1%) ] Loss: 0.0409 top1= 98.9583

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


[E 4B10 |   3872/60000 (  6%) ] Loss: 0.0716 top1= 97.9167
[E 4B20 |   7392/60000 ( 12%) ] Loss: 0.0498 top1= 98.9583
[E 4B30 |  10912/60000 ( 18%) ] Loss: 0.0515 top1= 98.2639
[E 4B40 |  14432/60000 ( 24%) ] Loss: 0.0538 top1= 98.9583
[E 4B50 |  17952/60000 ( 30%) ] Loss: 0.0734 top1= 97.5694

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4587 top1= 84.9459

Train epoch 5
[E 5B0  |    352/60000 (  1%) ] Loss: 0.0255 top1= 99.3056

=== Log global consensus distance @ E5B0 ===
consensus_distance=0.010


[E 5B10 |   3872/60000 (  6%) ] Loss: 0.0626 top1= 97.9167
[E 5B20 |   7392/60000 ( 12%) ] Loss: 0.0591 top1= 98.2639
[E 5B30 |  10912/60000 ( 18%) ] Loss: 0.0376 top1= 98.9583
[E 5B40 |  14432/60000 ( 24%) ] Loss: 0.0270 top1= 99.3056
[E 5B50 |  17952/60000 ( 30%) ] Loss: 0.0400 top1= 98.6111

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4062 top1= 86.9992

Train epoch 6
[E 6B0  |    352/60000 (  1%) ] Loss: 0.0232 top1= 99.6528

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


[E 6B10 |   3872/60000 (  6%) ] Loss: 0.0626 top1= 97.9167
[E 6B20 |   7392/60000 ( 12%) ] Loss: 0.0397 top1= 99.6528
[E 6B30 |  10912/60000 ( 18%) ] Loss: 0.0291 top1= 99.3056
[E 6B40 |  14432/60000 ( 24%) ] Loss: 0.0398 top1= 98.6111
[E 6B50 |  17952/60000 ( 30%) ] Loss: 0.0417 top1= 98.2639

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4600 top1= 85.0361

Train epoch 7
[E 7B0  |    352/60000 (  1%) ] Loss: 0.0285 top1= 99.6528

=== Log global consensus distance @ E7B0 ===
consensus_distance=0.012


[E 7B10 |   3872/60000 (  6%) ] Loss: 0.0753 top1= 97.9167
[E 7B20 |   7392/60000 ( 12%) ] Loss: 0.0476 top1= 98.9583
[E 7B30 |  10912/60000 ( 18%) ] Loss: 0.0310 top1= 98.9583
[E 7B40 |  14432/60000 ( 24%) ] Loss: 0.0436 top1= 98.2639
[E 7B50 |  17952/60000 ( 30%) ] Loss: 0.0218 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3155 top1= 90.0140

Train epoch 8
[E 8B0  |    352/60000 (  1%) ] Loss: 0.0112 top1=100.0000

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


[E 8B10 |   3872/60000 (  6%) ] Loss: 0.0364 top1= 98.6111
[E 8B20 |   7392/60000 ( 12%) ] Loss: 0.0219 top1= 99.6528
[E 8B30 |  10912/60000 ( 18%) ] Loss: 0.0259 top1= 98.9583
[E 8B40 |  14432/60000 ( 24%) ] Loss: 0.0235 top1= 99.3056
[E 8B50 |  17952/60000 ( 30%) ] Loss: 0.0645 top1= 97.5694

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4069 top1= 87.2596

Train epoch 9
[E 9B0  |    352/60000 (  1%) ] Loss: 0.0204 top1= 99.3056

=== Log global consensus distance @ E9B0 ===
consensus_distance=0.011


[E 9B10 |   3872/60000 (  6%) ] Loss: 0.0478 top1= 99.3056
[E 9B20 |   7392/60000 ( 12%) ] Loss: 0.0227 top1= 99.6528
[E 9B30 |  10912/60000 ( 18%) ] Loss: 0.0498 top1= 98.2639
[E 9B40 |  14432/60000 ( 24%) ] Loss: 0.0381 top1= 98.9583
[E 9B50 |  17952/60000 ( 30%) ] Loss: 0.0257 top1= 98.2639

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3507 top1= 89.2528

Train epoch 10
[E10B0  |    352/60000 (  1%) ] Loss: 0.0294 top1= 98.9583

=== Log global consensus distance @ E10B0 ===
consensus_distance=0.010


[E10B10 |   3872/60000 (  6%) ] Loss: 0.0499 top1= 97.5694
[E10B20 |   7392/60000 ( 12%) ] Loss: 0.0246 top1= 99.6528
[E10B30 |  10912/60000 ( 18%) ] Loss: 0.0328 top1= 98.9583
[E10B40 |  14432/60000 ( 24%) ] Loss: 0.0281 top1= 98.6111
[E10B50 |  17952/60000 ( 30%) ] Loss: 0.0101 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2658 top1= 91.8970

Train epoch 11
[E11B0  |    352/60000 (  1%) ] Loss: 0.0175 top1= 99.3056

=== Log global consensus distance @ E11B0 ===
consensus_distance=0.008


[E11B10 |   3872/60000 (  6%) ] Loss: 0.0293 top1= 98.9583
[E11B20 |   7392/60000 ( 12%) ] Loss: 0.0443 top1= 98.9583
[E11B30 |  10912/60000 ( 18%) ] Loss: 0.0320 top1= 98.9583
[E11B40 |  14432/60000 ( 24%) ] Loss: 0.0313 top1= 98.9583
[E11B50 |  17952/60000 ( 30%) ] Loss: 0.0221 top1= 98.9583

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4612 top1= 85.3365

Train epoch 12
[E12B0  |    352/60000 (  1%) ] Loss: 0.0441 top1= 98.2639

=== Log global consensus distance @ E12B0 ===
consensus_distance=0.010


[E12B10 |   3872/60000 (  6%) ] Loss: 0.0315 top1= 98.6111
[E12B20 |   7392/60000 ( 12%) ] Loss: 0.0169 top1=100.0000
[E12B30 |  10912/60000 ( 18%) ] Loss: 0.0424 top1= 98.2639
[E12B40 |  14432/60000 ( 24%) ] Loss: 0.0092 top1= 99.6528
[E12B50 |  17952/60000 ( 30%) ] Loss: 0.0055 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2465 top1= 92.3578

Train epoch 13
[E13B0  |    352/60000 (  1%) ] Loss: 0.0245 top1= 99.3056

=== Log global consensus distance @ E13B0 ===
consensus_distance=0.007


[E13B10 |   3872/60000 (  6%) ] Loss: 0.0207 top1= 99.6528
[E13B20 |   7392/60000 ( 12%) ] Loss: 0.0246 top1= 99.3056
[E13B30 |  10912/60000 ( 18%) ] Loss: 0.0148 top1= 99.6528
[E13B40 |  14432/60000 ( 24%) ] Loss: 0.0246 top1= 99.3056
[E13B50 |  17952/60000 ( 30%) ] Loss: 0.0122 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3968 top1= 88.1510

Train epoch 14
[E14B0  |    352/60000 (  1%) ] Loss: 0.0172 top1= 99.6528

=== Log global consensus distance @ E14B0 ===
consensus_distance=0.009


[E14B10 |   3872/60000 (  6%) ] Loss: 0.0292 top1= 98.9583
[E14B20 |   7392/60000 ( 12%) ] Loss: 0.0195 top1= 99.6528
[E14B30 |  10912/60000 ( 18%) ] Loss: 0.0163 top1= 99.3056
[E14B40 |  14432/60000 ( 24%) ] Loss: 0.0152 top1= 99.6528
[E14B50 |  17952/60000 ( 30%) ] Loss: 0.0167 top1= 99.3056

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2583 top1= 92.5280

Train epoch 15
[E15B0  |    352/60000 (  1%) ] Loss: 0.0189 top1= 99.3056

=== Log global consensus distance @ E15B0 ===
consensus_distance=0.008


[E15B10 |   3872/60000 (  6%) ] Loss: 0.0117 top1=100.0000
[E15B20 |   7392/60000 ( 12%) ] Loss: 0.0127 top1= 99.6528
[E15B30 |  10912/60000 ( 18%) ] Loss: 0.0193 top1= 99.6528
[E15B40 |  14432/60000 ( 24%) ] Loss: 0.0240 top1= 99.6528
[E15B50 |  17952/60000 ( 30%) ] Loss: 0.0303 top1= 99.3056

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2266 top1= 93.4095

Train epoch 16
[E16B0  |    352/60000 (  1%) ] Loss: 0.0286 top1= 98.6111

=== Log global consensus distance @ E16B0 ===
consensus_distance=0.007


[E16B10 |   3872/60000 (  6%) ] Loss: 0.0170 top1= 99.6528
[E16B20 |   7392/60000 ( 12%) ] Loss: 0.0163 top1= 99.6528
[E16B30 |  10912/60000 ( 18%) ] Loss: 0.0120 top1= 99.6528
[E16B40 |  14432/60000 ( 24%) ] Loss: 0.0105 top1=100.0000
[E16B50 |  17952/60000 ( 30%) ] Loss: 0.0055 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3220 top1= 90.4147

Train epoch 17
[E17B0  |    352/60000 (  1%) ] Loss: 0.0406 top1= 99.3056

=== Log global consensus distance @ E17B0 ===
consensus_distance=0.007


[E17B10 |   3872/60000 (  6%) ] Loss: 0.0171 top1= 98.9583
[E17B20 |   7392/60000 ( 12%) ] Loss: 0.0168 top1=100.0000
[E17B30 |  10912/60000 ( 18%) ] Loss: 0.0157 top1= 99.3056
[E17B40 |  14432/60000 ( 24%) ] Loss: 0.0196 top1= 99.3056
[E17B50 |  17952/60000 ( 30%) ] Loss: 0.0124 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2246 top1= 93.6298

Train epoch 18
[E18B0  |    352/60000 (  1%) ] Loss: 0.0105 top1=100.0000

=== Log global consensus distance @ E18B0 ===
consensus_distance=0.006


[E18B10 |   3872/60000 (  6%) ] Loss: 0.0221 top1= 99.3056
[E18B20 |   7392/60000 ( 12%) ] Loss: 0.0277 top1= 98.9583
[E18B30 |  10912/60000 ( 18%) ] Loss: 0.0187 top1= 99.6528
[E18B40 |  14432/60000 ( 24%) ] Loss: 0.0066 top1=100.0000
[E18B50 |  17952/60000 ( 30%) ] Loss: 0.0117 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2463 top1= 92.7083

Train epoch 19
[E19B0  |    352/60000 (  1%) ] Loss: 0.0114 top1= 99.6528

=== Log global consensus distance @ E19B0 ===
consensus_distance=0.005


[E19B10 |   3872/60000 (  6%) ] Loss: 0.0369 top1= 98.6111
[E19B20 |   7392/60000 ( 12%) ] Loss: 0.0332 top1= 99.6528
[E19B30 |  10912/60000 ( 18%) ] Loss: 0.0094 top1=100.0000
[E19B40 |  14432/60000 ( 24%) ] Loss: 0.0074 top1=100.0000
[E19B50 |  17952/60000 ( 30%) ] Loss: 0.0041 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2369 top1= 93.2792

Train epoch 20
[E20B0  |    352/60000 (  1%) ] Loss: 0.0058 top1=100.0000

=== Log global consensus distance @ E20B0 ===
consensus_distance=0.006


[E20B10 |   3872/60000 (  6%) ] Loss: 0.0094 top1=100.0000
[E20B20 |   7392/60000 ( 12%) ] Loss: 0.0080 top1=100.0000
[E20B30 |  10912/60000 ( 18%) ] Loss: 0.0092 top1=100.0000
[E20B40 |  14432/60000 ( 24%) ] Loss: 0.0058 top1=100.0000
[E20B50 |  17952/60000 ( 30%) ] Loss: 0.0067 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1854 top1= 94.8618

Train epoch 21
[E21B0  |    352/60000 (  1%) ] Loss: 0.0047 top1=100.0000

=== Log global consensus distance @ E21B0 ===
consensus_distance=0.004


[E21B10 |   3872/60000 (  6%) ] Loss: 0.0080 top1=100.0000
[E21B20 |   7392/60000 ( 12%) ] Loss: 0.0085 top1= 99.6528
[E21B30 |  10912/60000 ( 18%) ] Loss: 0.0084 top1= 99.6528
[E21B40 |  14432/60000 ( 24%) ] Loss: 0.0103 top1= 99.6528
[E21B50 |  17952/60000 ( 30%) ] Loss: 0.0288 top1= 98.6111

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2547 top1= 93.0188

Train epoch 22
[E22B0  |    352/60000 (  1%) ] Loss: 0.0167 top1= 99.6528

=== Log global consensus distance @ E22B0 ===
consensus_distance=0.008


[E22B10 |   3872/60000 (  6%) ] Loss: 0.0115 top1= 99.6528
[E22B20 |   7392/60000 ( 12%) ] Loss: 0.0259 top1= 98.9583
[E22B30 |  10912/60000 ( 18%) ] Loss: 0.0234 top1= 99.3056
[E22B40 |  14432/60000 ( 24%) ] Loss: 0.0082 top1=100.0000
[E22B50 |  17952/60000 ( 30%) ] Loss: 0.0041 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1827 top1= 94.9119

Train epoch 23
[E23B0  |    352/60000 (  1%) ] Loss: 0.0148 top1= 99.3056

=== Log global consensus distance @ E23B0 ===
consensus_distance=0.005


[E23B10 |   3872/60000 (  6%) ] Loss: 0.0158 top1= 99.3056
[E23B20 |   7392/60000 ( 12%) ] Loss: 0.0111 top1= 99.6528
[E23B30 |  10912/60000 ( 18%) ] Loss: 0.0048 top1=100.0000
[E23B40 |  14432/60000 ( 24%) ] Loss: 0.0108 top1= 99.6528
[E23B50 |  17952/60000 ( 30%) ] Loss: 0.0224 top1= 98.9583

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2245 top1= 93.8101

Train epoch 24
[E24B0  |    352/60000 (  1%) ] Loss: 0.0175 top1= 99.6528

=== Log global consensus distance @ E24B0 ===
consensus_distance=0.005


[E24B10 |   3872/60000 (  6%) ] Loss: 0.0054 top1=100.0000
[E24B20 |   7392/60000 ( 12%) ] Loss: 0.0145 top1= 99.3056
[E24B30 |  10912/60000 ( 18%) ] Loss: 0.0083 top1=100.0000
[E24B40 |  14432/60000 ( 24%) ] Loss: 0.0067 top1= 99.6528
[E24B50 |  17952/60000 ( 30%) ] Loss: 0.0042 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2239 top1= 93.9603

Train epoch 25
[E25B0  |    352/60000 (  1%) ] Loss: 0.0068 top1=100.0000

=== Log global consensus distance @ E25B0 ===
consensus_distance=0.004


[E25B10 |   3872/60000 (  6%) ] Loss: 0.0068 top1= 99.6528
[E25B20 |   7392/60000 ( 12%) ] Loss: 0.0142 top1= 99.6528
[E25B30 |  10912/60000 ( 18%) ] Loss: 0.0318 top1= 99.3056
[E25B40 |  14432/60000 ( 24%) ] Loss: 0.0064 top1=100.0000
[E25B50 |  17952/60000 ( 30%) ] Loss: 0.0061 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2134 top1= 94.1506

Train epoch 26
[E26B0  |    352/60000 (  1%) ] Loss: 0.0130 top1= 99.6528

=== Log global consensus distance @ E26B0 ===
consensus_distance=0.005


[E26B10 |   3872/60000 (  6%) ] Loss: 0.0397 top1= 98.6111
[E26B20 |   7392/60000 ( 12%) ] Loss: 0.0312 top1= 98.9583
[E26B30 |  10912/60000 ( 18%) ] Loss: 0.0037 top1=100.0000
[E26B40 |  14432/60000 ( 24%) ] Loss: 0.0088 top1=100.0000
[E26B50 |  17952/60000 ( 30%) ] Loss: 0.0075 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1720 top1= 95.2324

Train epoch 27
[E27B0  |    352/60000 (  1%) ] Loss: 0.0243 top1= 98.9583

=== Log global consensus distance @ E27B0 ===
consensus_distance=0.004


[E27B10 |   3872/60000 (  6%) ] Loss: 0.0081 top1= 99.6528
[E27B20 |   7392/60000 ( 12%) ] Loss: 0.0284 top1= 99.3056
[E27B30 |  10912/60000 ( 18%) ] Loss: 0.0108 top1= 99.6528
[E27B40 |  14432/60000 ( 24%) ] Loss: 0.0048 top1=100.0000
[E27B50 |  17952/60000 ( 30%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1739 top1= 95.4227

Train epoch 28
[E28B0  |    352/60000 (  1%) ] Loss: 0.0064 top1=100.0000

=== Log global consensus distance @ E28B0 ===
consensus_distance=0.004


[E28B10 |   3872/60000 (  6%) ] Loss: 0.0055 top1=100.0000
[E28B20 |   7392/60000 ( 12%) ] Loss: 0.0116 top1=100.0000
[E28B30 |  10912/60000 ( 18%) ] Loss: 0.0066 top1= 99.6528
[E28B40 |  14432/60000 ( 24%) ] Loss: 0.0042 top1=100.0000
[E28B50 |  17952/60000 ( 30%) ] Loss: 0.0036 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2076 top1= 94.5112

Train epoch 29
[E29B0  |    352/60000 (  1%) ] Loss: 0.0101 top1= 99.6528

=== Log global consensus distance @ E29B0 ===
consensus_distance=0.003


[E29B10 |   3872/60000 (  6%) ] Loss: 0.0081 top1=100.0000
[E29B20 |   7392/60000 ( 12%) ] Loss: 0.0037 top1=100.0000
[E29B30 |  10912/60000 ( 18%) ] Loss: 0.0211 top1= 99.3056
[E29B40 |  14432/60000 ( 24%) ] Loss: 0.0391 top1= 98.6111
[E29B50 |  17952/60000 ( 30%) ] Loss: 0.0151 top1= 99.3056

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2356 top1= 93.3193

Train epoch 30
[E30B0  |    352/60000 (  1%) ] Loss: 0.0160 top1= 99.3056

=== Log global consensus distance @ E30B0 ===
consensus_distance=0.006


[E30B10 |   3872/60000 (  6%) ] Loss: 0.0221 top1= 98.6111
[E30B20 |   7392/60000 ( 12%) ] Loss: 0.0135 top1= 99.6528
[E30B30 |  10912/60000 ( 18%) ] Loss: 0.0144 top1= 99.3056
[E30B40 |  14432/60000 ( 24%) ] Loss: 0.0043 top1=100.0000
[E30B50 |  17952/60000 ( 30%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1807 top1= 95.0921

