
=== 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 0x7fab3a956400>

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: 0.3272 top1= 85.7639
[E 1B20 |   7392/60000 ( 12%) ] Loss: 0.1633 top1= 94.7917
[E 1B30 |  10912/60000 ( 18%) ] Loss: 0.1010 top1= 96.8750
[E 1B40 |  14432/60000 ( 24%) ] Loss: 0.0784 top1= 98.6111
[E 1B50 |  17952/60000 ( 30%) ] Loss: 0.0898 top1= 97.2222

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9632 top1= 70.7332

Train epoch 2
[E 2B0  |    352/60000 (  1%) ] Loss: 0.0514 top1= 98.2639

=== Log global consensus distance @ E2B0 ===
consensus_distance=0.098


[E 2B10 |   3872/60000 (  6%) ] Loss: 0.0782 top1= 98.2639
[E 2B20 |   7392/60000 ( 12%) ] Loss: 0.0921 top1= 96.8750
[E 2B30 |  10912/60000 ( 18%) ] Loss: 0.0680 top1= 98.6111
[E 2B40 |  14432/60000 ( 24%) ] Loss: 0.0434 top1= 98.6111
[E 2B50 |  17952/60000 ( 30%) ] Loss: 0.0492 top1= 97.5694

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6775 top1= 76.7829

Train epoch 3
[E 3B0  |    352/60000 (  1%) ] Loss: 0.0437 top1= 99.3056

=== Log global consensus distance @ E3B0 ===
consensus_distance=0.082


[E 3B10 |   3872/60000 (  6%) ] Loss: 0.0684 top1= 98.6111
[E 3B20 |   7392/60000 ( 12%) ] Loss: 0.0463 top1= 99.3056
[E 3B30 |  10912/60000 ( 18%) ] Loss: 0.0628 top1= 97.9167
[E 3B40 |  14432/60000 ( 24%) ] Loss: 0.0332 top1= 98.6111
[E 3B50 |  17952/60000 ( 30%) ] Loss: 0.0371 top1= 98.9583

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5624 top1= 79.3069

Train epoch 4
[E 4B0  |    352/60000 (  1%) ] Loss: 0.0370 top1= 99.3056

=== Log global consensus distance @ E4B0 ===
consensus_distance=0.066


[E 4B10 |   3872/60000 (  6%) ] Loss: 0.0502 top1= 98.9583
[E 4B20 |   7392/60000 ( 12%) ] Loss: 0.0411 top1= 99.3056
[E 4B30 |  10912/60000 ( 18%) ] Loss: 0.0359 top1= 98.9583
[E 4B40 |  14432/60000 ( 24%) ] Loss: 0.0158 top1=100.0000
[E 4B50 |  17952/60000 ( 30%) ] Loss: 0.0161 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4655 top1= 83.2532

Train epoch 5
[E 5B0  |    352/60000 (  1%) ] Loss: 0.0207 top1= 99.6528

=== Log global consensus distance @ E5B0 ===
consensus_distance=0.035


[E 5B10 |   3872/60000 (  6%) ] Loss: 0.0466 top1= 99.3056
[E 5B20 |   7392/60000 ( 12%) ] Loss: 0.0208 top1=100.0000
[E 5B30 |  10912/60000 ( 18%) ] Loss: 0.0707 top1= 98.2639
[E 5B40 |  14432/60000 ( 24%) ] Loss: 0.0241 top1= 99.6528
[E 5B50 |  17952/60000 ( 30%) ] Loss: 0.0198 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4458 top1= 84.2949

Train epoch 6
[E 6B0  |    352/60000 (  1%) ] Loss: 0.0254 top1= 99.3056

=== Log global consensus distance @ E6B0 ===
consensus_distance=0.036


[E 6B10 |   3872/60000 (  6%) ] Loss: 0.0325 top1= 98.9583
[E 6B20 |   7392/60000 ( 12%) ] Loss: 0.0295 top1= 98.9583
[E 6B30 |  10912/60000 ( 18%) ] Loss: 0.0427 top1= 98.6111
[E 6B40 |  14432/60000 ( 24%) ] Loss: 0.0130 top1= 99.6528
[E 6B50 |  17952/60000 ( 30%) ] Loss: 0.0151 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4313 top1= 84.6054

Train epoch 7
[E 7B0  |    352/60000 (  1%) ] Loss: 0.0093 top1=100.0000

=== Log global consensus distance @ E7B0 ===
consensus_distance=0.038


[E 7B10 |   3872/60000 (  6%) ] Loss: 0.0242 top1= 98.9583
[E 7B20 |   7392/60000 ( 12%) ] Loss: 0.0260 top1= 99.3056
[E 7B30 |  10912/60000 ( 18%) ] Loss: 0.0140 top1= 99.6528
[E 7B40 |  14432/60000 ( 24%) ] Loss: 0.0134 top1= 99.6528
[E 7B50 |  17952/60000 ( 30%) ] Loss: 0.0216 top1= 98.9583

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3867 top1= 86.1679

Train epoch 8
[E 8B0  |    352/60000 (  1%) ] Loss: 0.0155 top1= 99.6528

=== Log global consensus distance @ E8B0 ===
consensus_distance=0.018


[E 8B10 |   3872/60000 (  6%) ] Loss: 0.0128 top1=100.0000
[E 8B20 |   7392/60000 ( 12%) ] Loss: 0.0239 top1= 99.3056
[E 8B30 |  10912/60000 ( 18%) ] Loss: 0.0190 top1= 99.6528
[E 8B40 |  14432/60000 ( 24%) ] Loss: 0.0086 top1=100.0000
[E 8B50 |  17952/60000 ( 30%) ] Loss: 0.0052 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3244 top1= 89.4531

Train epoch 9
[E 9B0  |    352/60000 (  1%) ] Loss: 0.0170 top1= 99.3056

=== Log global consensus distance @ E9B0 ===
consensus_distance=0.019


[E 9B10 |   3872/60000 (  6%) ] Loss: 0.0429 top1= 98.6111
[E 9B20 |   7392/60000 ( 12%) ] Loss: 0.0401 top1= 98.2639
[E 9B30 |  10912/60000 ( 18%) ] Loss: 0.0849 top1= 97.9167
[E 9B40 |  14432/60000 ( 24%) ] Loss: 0.0198 top1= 99.3056
[E 9B50 |  17952/60000 ( 30%) ] Loss: 0.0087 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3273 top1= 89.3830

Train epoch 10
[E10B0  |    352/60000 (  1%) ] Loss: 0.0110 top1=100.0000

=== Log global consensus distance @ E10B0 ===
consensus_distance=0.036


[E10B10 |   3872/60000 (  6%) ] Loss: 0.0213 top1= 99.3056
[E10B20 |   7392/60000 ( 12%) ] Loss: 0.0156 top1= 99.6528
[E10B30 |  10912/60000 ( 18%) ] Loss: 0.0114 top1= 99.6528
[E10B40 |  14432/60000 ( 24%) ] Loss: 0.0093 top1=100.0000
[E10B50 |  17952/60000 ( 30%) ] Loss: 0.0078 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3215 top1= 88.6218

Train epoch 11
[E11B0  |    352/60000 (  1%) ] Loss: 0.0077 top1=100.0000

=== Log global consensus distance @ E11B0 ===
consensus_distance=0.009


[E11B10 |   3872/60000 (  6%) ] Loss: 0.0123 top1=100.0000
[E11B20 |   7392/60000 ( 12%) ] Loss: 0.0113 top1=100.0000
[E11B30 |  10912/60000 ( 18%) ] Loss: 0.0065 top1=100.0000
[E11B40 |  14432/60000 ( 24%) ] Loss: 0.0269 top1= 99.6528
[E11B50 |  17952/60000 ( 30%) ] Loss: 0.0070 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2617 top1= 91.6567

Train epoch 12
[E12B0  |    352/60000 (  1%) ] Loss: 0.0057 top1=100.0000

=== Log global consensus distance @ E12B0 ===
consensus_distance=0.012


[E12B10 |   3872/60000 (  6%) ] Loss: 0.0102 top1=100.0000
[E12B20 |   7392/60000 ( 12%) ] Loss: 0.0194 top1= 99.6528
[E12B30 |  10912/60000 ( 18%) ] Loss: 0.0292 top1= 99.3056
[E12B40 |  14432/60000 ( 24%) ] Loss: 0.0061 top1= 99.6528
[E12B50 |  17952/60000 ( 30%) ] Loss: 0.0120 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3396 top1= 88.0308

Train epoch 13
[E13B0  |    352/60000 (  1%) ] Loss: 0.0578 top1= 99.6528

=== Log global consensus distance @ E13B0 ===
consensus_distance=0.230


[E13B10 |   3872/60000 (  6%) ] Loss: 0.0201 top1= 99.6528
[E13B20 |   7392/60000 ( 12%) ] Loss: 0.0086 top1=100.0000
[E13B30 |  10912/60000 ( 18%) ] Loss: 0.0182 top1= 99.6528
[E13B40 |  14432/60000 ( 24%) ] Loss: 0.0085 top1=100.0000
[E13B50 |  17952/60000 ( 30%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2720 top1= 91.2861

Train epoch 14
[E14B0  |    352/60000 (  1%) ] Loss: 0.0055 top1=100.0000

=== Log global consensus distance @ E14B0 ===
consensus_distance=0.013


[E14B10 |   3872/60000 (  6%) ] Loss: 0.0084 top1=100.0000
[E14B20 |   7392/60000 ( 12%) ] Loss: 0.0089 top1=100.0000
[E14B30 |  10912/60000 ( 18%) ] Loss: 0.0074 top1=100.0000
[E14B40 |  14432/60000 ( 24%) ] Loss: 0.0029 top1=100.0000
[E14B50 |  17952/60000 ( 30%) ] Loss: 0.0040 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2532 top1= 91.8770

Train epoch 15
[E15B0  |    352/60000 (  1%) ] Loss: 0.0090 top1= 99.6528

=== Log global consensus distance @ E15B0 ===
consensus_distance=0.012


[E15B10 |   3872/60000 (  6%) ] Loss: 0.0095 top1=100.0000
[E15B20 |   7392/60000 ( 12%) ] Loss: 0.0092 top1= 99.6528
[E15B30 |  10912/60000 ( 18%) ] Loss: 0.1158 top1= 99.3056
[E15B40 |  14432/60000 ( 24%) ] Loss: 0.0258 top1= 98.9583
[E15B50 |  17952/60000 ( 30%) ] Loss: 0.0450 top1= 97.9167

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4539 top1= 83.3233

Train epoch 16
[E16B0  |    352/60000 (  1%) ] Loss: 0.0151 top1= 99.6528

=== Log global consensus distance @ E16B0 ===
consensus_distance=0.457


[E16B10 |   3872/60000 (  6%) ] Loss: 0.0195 top1= 98.9583
[E16B20 |   7392/60000 ( 12%) ] Loss: 0.0470 top1= 98.9583
[E16B30 |  10912/60000 ( 18%) ] Loss: 0.0271 top1= 99.3056
[E16B40 |  14432/60000 ( 24%) ] Loss: 0.0398 top1= 98.9583
[E16B50 |  17952/60000 ( 30%) ] Loss: 0.0055 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2889 top1= 90.4848

Train epoch 17
[E17B0  |    352/60000 (  1%) ] Loss: 0.0054 top1=100.0000

=== Log global consensus distance @ E17B0 ===
consensus_distance=0.048


[E17B10 |   3872/60000 (  6%) ] Loss: 0.0081 top1=100.0000
[E17B20 |   7392/60000 ( 12%) ] Loss: 0.0164 top1= 99.3056
[E17B30 |  10912/60000 ( 18%) ] Loss: 0.0059 top1=100.0000
[E17B40 |  14432/60000 ( 24%) ] Loss: 0.0154 top1= 99.3056
[E17B50 |  17952/60000 ( 30%) ] Loss: 0.0060 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2251 top1= 92.6683

Train epoch 18
[E18B0  |    352/60000 (  1%) ] Loss: 0.0101 top1=100.0000

=== Log global consensus distance @ E18B0 ===
consensus_distance=0.007


[E18B10 |   3872/60000 (  6%) ] Loss: 0.0096 top1=100.0000
[E18B20 |   7392/60000 ( 12%) ] Loss: 0.0079 top1=100.0000
[E18B30 |  10912/60000 ( 18%) ] Loss: 0.0108 top1= 99.6528
[E18B40 |  14432/60000 ( 24%) ] Loss: 0.0129 top1= 99.6528
[E18B50 |  17952/60000 ( 30%) ] Loss: 0.0068 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3187 top1= 89.4030

Train epoch 19
[E19B0  |    352/60000 (  1%) ] Loss: 0.0086 top1= 99.6528

=== Log global consensus distance @ E19B0 ===
consensus_distance=0.009


[E19B10 |   3872/60000 (  6%) ] Loss: 0.0109 top1=100.0000
[E19B20 |   7392/60000 ( 12%) ] Loss: 0.0057 top1=100.0000
[E19B30 |  10912/60000 ( 18%) ] Loss: 0.0049 top1=100.0000
[E19B40 |  14432/60000 ( 24%) ] Loss: 0.0036 top1=100.0000
[E19B50 |  17952/60000 ( 30%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2504 top1= 92.0172

Train epoch 20
[E20B0  |    352/60000 (  1%) ] Loss: 0.0032 top1=100.0000

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


[E20B10 |   3872/60000 (  6%) ] Loss: 0.0051 top1=100.0000
[E20B20 |   7392/60000 ( 12%) ] Loss: 0.0045 top1=100.0000
[E20B30 |  10912/60000 ( 18%) ] Loss: 0.0058 top1=100.0000
[E20B40 |  14432/60000 ( 24%) ] Loss: 0.0085 top1=100.0000
[E20B50 |  17952/60000 ( 30%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2121 top1= 93.8001

Train epoch 21
[E21B0  |    352/60000 (  1%) ] Loss: 0.3315 top1= 97.9167

=== Log global consensus distance @ E21B0 ===
consensus_distance=0.029


[E21B10 |   3872/60000 (  6%) ] Loss: 0.0133 top1=100.0000
[E21B20 |   7392/60000 ( 12%) ] Loss: 0.0095 top1=100.0000
[E21B30 |  10912/60000 ( 18%) ] Loss: 0.0061 top1=100.0000
[E21B40 |  14432/60000 ( 24%) ] Loss: 0.0176 top1= 99.6528
[E21B50 |  17952/60000 ( 30%) ] Loss: 0.0051 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2882 top1= 90.2344

Train epoch 22
[E22B0  |    352/60000 (  1%) ] Loss: 0.0046 top1=100.0000

=== Log global consensus distance @ E22B0 ===
consensus_distance=0.071


[E22B10 |   3872/60000 (  6%) ] Loss: 0.0246 top1= 99.3056
[E22B20 |   7392/60000 ( 12%) ] Loss: 0.0077 top1=100.0000
[E22B30 |  10912/60000 ( 18%) ] Loss: 0.0064 top1=100.0000
[E22B40 |  14432/60000 ( 24%) ] Loss: 0.0050 top1=100.0000
[E22B50 |  17952/60000 ( 30%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2129 top1= 93.5497

Train epoch 23
[E23B0  |    352/60000 (  1%) ] Loss: 0.0042 top1=100.0000

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


[E23B10 |   3872/60000 (  6%) ] Loss: 0.0142 top1= 99.6528
[E23B20 |   7392/60000 ( 12%) ] Loss: 0.0051 top1=100.0000
[E23B30 |  10912/60000 ( 18%) ] Loss: 0.0054 top1=100.0000
[E23B40 |  14432/60000 ( 24%) ] Loss: 0.0029 top1=100.0000
[E23B50 |  17952/60000 ( 30%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1981 top1= 94.0204

Train epoch 24
[E24B0  |    352/60000 (  1%) ] Loss: 0.0033 top1=100.0000

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


[E24B10 |   3872/60000 (  6%) ] Loss: 0.0108 top1= 99.6528
[E24B20 |   7392/60000 ( 12%) ] Loss: 0.0027 top1=100.0000
[E24B30 |  10912/60000 ( 18%) ] Loss: 0.0023 top1=100.0000
[E24B40 |  14432/60000 ( 24%) ] Loss: 0.0058 top1=100.0000
[E24B50 |  17952/60000 ( 30%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2830 top1= 91.4764

Train epoch 25
[E25B0  |    352/60000 (  1%) ] Loss: 0.0008 top1=100.0000

=== Log global consensus distance @ E25B0 ===
consensus_distance=0.104


[E25B10 |   3872/60000 (  6%) ] Loss: 0.0053 top1=100.0000
[E25B20 |   7392/60000 ( 12%) ] Loss: 0.0046 top1=100.0000
[E25B30 |  10912/60000 ( 18%) ] Loss: 0.0081 top1= 99.6528
[E25B40 |  14432/60000 ( 24%) ] Loss: 0.0115 top1= 99.6528
[E25B50 |  17952/60000 ( 30%) ] Loss: 0.0054 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1911 top1= 94.3710

Train epoch 26
[E26B0  |    352/60000 (  1%) ] Loss: 0.0061 top1=100.0000

=== Log global consensus distance @ E26B0 ===
consensus_distance=0.007


[E26B10 |   3872/60000 (  6%) ] Loss: 0.0037 top1=100.0000
[E26B20 |   7392/60000 ( 12%) ] Loss: 0.0038 top1=100.0000
[E26B30 |  10912/60000 ( 18%) ] Loss: 0.0044 top1=100.0000
[E26B40 |  14432/60000 ( 24%) ] Loss: 0.0068 top1=100.0000
[E26B50 |  17952/60000 ( 30%) ] Loss: 0.0055 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1785 top1= 94.6214

Train epoch 27
[E27B0  |    352/60000 (  1%) ] Loss: 0.0032 top1=100.0000

=== Log global consensus distance @ E27B0 ===
consensus_distance=0.005


[E27B10 |   3872/60000 (  6%) ] Loss: 0.0074 top1= 99.6528
[E27B20 |   7392/60000 ( 12%) ] Loss: 0.0107 top1=100.0000
[E27B30 |  10912/60000 ( 18%) ] Loss: 0.0057 top1=100.0000
[E27B40 |  14432/60000 ( 24%) ] Loss: 0.0111 top1=100.0000
[E27B50 |  17952/60000 ( 30%) ] Loss: 0.0030 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1758 top1= 94.8417

Train epoch 28
[E28B0  |    352/60000 (  1%) ] Loss: 0.0030 top1=100.0000

=== Log global consensus distance @ E28B0 ===
consensus_distance=0.003


[E28B10 |   3872/60000 (  6%) ] Loss: 0.0107 top1= 99.6528
[E28B20 |   7392/60000 ( 12%) ] Loss: 0.0136 top1= 99.3056
[E28B30 |  10912/60000 ( 18%) ] Loss: 0.0048 top1=100.0000
[E28B40 |  14432/60000 ( 24%) ] Loss: 0.0029 top1=100.0000
[E28B50 |  17952/60000 ( 30%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1720 top1= 95.0120

Train epoch 29
[E29B0  |    352/60000 (  1%) ] Loss: 0.0038 top1=100.0000

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


[E29B10 |   3872/60000 (  6%) ] Loss: 0.0042 top1=100.0000
[E29B20 |   7392/60000 ( 12%) ] Loss: 0.0065 top1=100.0000
[E29B30 |  10912/60000 ( 18%) ] Loss: 0.0041 top1=100.0000
[E29B40 |  14432/60000 ( 24%) ] Loss: 0.0029 top1=100.0000
[E29B50 |  17952/60000 ( 30%) ] Loss: 0.0030 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2246 top1= 93.3994

Train epoch 30
[E30B0  |    352/60000 (  1%) ] Loss: 0.0097 top1= 99.6528

=== Log global consensus distance @ E30B0 ===
consensus_distance=0.015


[E30B10 |   3872/60000 (  6%) ] Loss: 0.0034 top1=100.0000
[E30B20 |   7392/60000 ( 12%) ] Loss: 0.0030 top1=100.0000
[E30B30 |  10912/60000 ( 18%) ] Loss: 0.0121 top1= 99.6528
[E30B40 |  14432/60000 ( 24%) ] Loss: 0.0069 top1= 99.6528
[E30B50 |  17952/60000 ( 30%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1734 top1= 95.1022

