
=== 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 0x7f7d06221400>

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: 0.9950 top1= 74.6528
[E 1B20 |   7392/60000 ( 12%) ] Loss: 0.4425 top1= 85.0694
[E 1B30 |  10912/60000 ( 18%) ] Loss: 0.2398 top1= 93.7500
[E 1B40 |  14432/60000 ( 24%) ] Loss: 0.1814 top1= 94.0972
[E 1B50 |  17952/60000 ( 30%) ] Loss: 0.1556 top1= 94.7917

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5066 top1= 84.8157

Train epoch 2
[E 2B0  |    352/60000 (  1%) ] Loss: 0.0801 top1= 97.9167

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


[E 2B10 |   3872/60000 (  6%) ] Loss: 0.1382 top1= 95.1389
[E 2B20 |   7392/60000 ( 12%) ] Loss: 0.1180 top1= 96.8750
[E 2B30 |  10912/60000 ( 18%) ] Loss: 0.1175 top1= 95.8333
[E 2B40 |  14432/60000 ( 24%) ] Loss: 0.0871 top1= 97.2222
[E 2B50 |  17952/60000 ( 30%) ] Loss: 0.0860 top1= 97.5694

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4462 top1= 85.6470

Train epoch 3
[E 3B0  |    352/60000 (  1%) ] Loss: 0.0415 top1= 99.3056

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


[E 3B10 |   3872/60000 (  6%) ] Loss: 0.0738 top1= 97.9167
[E 3B20 |   7392/60000 ( 12%) ] Loss: 0.0855 top1= 97.2222
[E 3B30 |  10912/60000 ( 18%) ] Loss: 0.0746 top1= 96.5278
[E 3B40 |  14432/60000 ( 24%) ] Loss: 0.0540 top1= 98.9583
[E 3B50 |  17952/60000 ( 30%) ] Loss: 0.0480 top1= 98.6111

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4175 top1= 86.2780

Train epoch 4
[E 4B0  |    352/60000 (  1%) ] Loss: 0.0257 top1=100.0000

=== Log global consensus distance @ E4B0 ===
consensus_distance=0.007


[E 4B10 |   3872/60000 (  6%) ] Loss: 0.0485 top1= 98.9583
[E 4B20 |   7392/60000 ( 12%) ] Loss: 0.0499 top1= 98.6111
[E 4B30 |  10912/60000 ( 18%) ] Loss: 0.0441 top1= 97.9167
[E 4B40 |  14432/60000 ( 24%) ] Loss: 0.0277 top1= 99.6528
[E 4B50 |  17952/60000 ( 30%) ] Loss: 0.0344 top1= 98.6111

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3560 top1= 88.6418

Train epoch 5
[E 5B0  |    352/60000 (  1%) ] Loss: 0.0256 top1=100.0000

=== Log global consensus distance @ E5B0 ===
consensus_distance=0.006


[E 5B10 |   3872/60000 (  6%) ] Loss: 0.0682 top1= 97.9167
[E 5B20 |   7392/60000 ( 12%) ] Loss: 0.0552 top1= 98.2639
[E 5B30 |  10912/60000 ( 18%) ] Loss: 0.0300 top1= 98.9583
[E 5B40 |  14432/60000 ( 24%) ] Loss: 0.0229 top1= 99.3056
[E 5B50 |  17952/60000 ( 30%) ] Loss: 0.0268 top1= 98.9583

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3598 top1= 88.7620

Train epoch 6
[E 6B0  |    352/60000 (  1%) ] Loss: 0.0280 top1= 99.3056

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


[E 6B10 |   3872/60000 (  6%) ] Loss: 0.0348 top1= 99.3056
[E 6B20 |   7392/60000 ( 12%) ] Loss: 0.0329 top1= 99.6528
[E 6B30 |  10912/60000 ( 18%) ] Loss: 0.0345 top1= 98.9583
[E 6B40 |  14432/60000 ( 24%) ] Loss: 0.0173 top1= 99.3056
[E 6B50 |  17952/60000 ( 30%) ] Loss: 0.0136 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4242 top1= 86.0978

Train epoch 7
[E 7B0  |    352/60000 (  1%) ] Loss: 0.0451 top1= 98.2639

=== Log global consensus distance @ E7B0 ===
consensus_distance=0.007


[E 7B10 |   3872/60000 (  6%) ] Loss: 0.0344 top1= 98.6111
[E 7B20 |   7392/60000 ( 12%) ] Loss: 0.0270 top1= 99.6528
[E 7B30 |  10912/60000 ( 18%) ] Loss: 0.0755 top1= 97.9167
[E 7B40 |  14432/60000 ( 24%) ] Loss: 0.0299 top1= 99.6528
[E 7B50 |  17952/60000 ( 30%) ] Loss: 0.0201 top1= 99.3056

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5271 top1= 82.2316

Train epoch 8
[E 8B0  |    352/60000 (  1%) ] Loss: 0.0310 top1= 98.9583

=== Log global consensus distance @ E8B0 ===
consensus_distance=0.006


[E 8B10 |   3872/60000 (  6%) ] Loss: 0.0297 top1= 99.6528
[E 8B20 |   7392/60000 ( 12%) ] Loss: 0.0507 top1= 97.9167
[E 8B30 |  10912/60000 ( 18%) ] Loss: 0.0305 top1= 98.6111
[E 8B40 |  14432/60000 ( 24%) ] Loss: 0.0455 top1= 97.5694
[E 8B50 |  17952/60000 ( 30%) ] Loss: 0.0392 top1= 97.9167

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5591 top1= 81.5705

Train epoch 9
[E 9B0  |    352/60000 (  1%) ] Loss: 0.0306 top1= 98.2639

=== Log global consensus distance @ E9B0 ===
consensus_distance=0.008


[E 9B10 |   3872/60000 (  6%) ] Loss: 0.0344 top1= 98.9583
[E 9B20 |   7392/60000 ( 12%) ] Loss: 0.0270 top1= 99.3056
[E 9B30 |  10912/60000 ( 18%) ] Loss: 0.0163 top1= 99.6528
[E 9B40 |  14432/60000 ( 24%) ] Loss: 0.0225 top1= 99.6528
[E 9B50 |  17952/60000 ( 30%) ] Loss: 0.0305 top1= 99.3056

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2810 top1= 91.2260

Train epoch 10
[E10B0  |    352/60000 (  1%) ] Loss: 0.0204 top1= 99.6528

=== Log global consensus distance @ E10B0 ===
consensus_distance=0.006


[E10B10 |   3872/60000 (  6%) ] Loss: 0.0198 top1= 99.6528
[E10B20 |   7392/60000 ( 12%) ] Loss: 0.0207 top1= 99.6528
[E10B30 |  10912/60000 ( 18%) ] Loss: 0.0163 top1= 99.3056
[E10B40 |  14432/60000 ( 24%) ] Loss: 0.0151 top1=100.0000
[E10B50 |  17952/60000 ( 30%) ] Loss: 0.0181 top1= 99.3056

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3332 top1= 89.4631

Train epoch 11
[E11B0  |    352/60000 (  1%) ] Loss: 0.0140 top1=100.0000

=== Log global consensus distance @ E11B0 ===
consensus_distance=0.004


[E11B10 |   3872/60000 (  6%) ] Loss: 0.0235 top1= 99.6528
[E11B20 |   7392/60000 ( 12%) ] Loss: 0.0137 top1=100.0000
[E11B30 |  10912/60000 ( 18%) ] Loss: 0.0097 top1= 99.6528
[E11B40 |  14432/60000 ( 24%) ] Loss: 0.0234 top1= 99.3056
[E11B50 |  17952/60000 ( 30%) ] Loss: 0.0057 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2574 top1= 92.0172

Train epoch 12
[E12B0  |    352/60000 (  1%) ] Loss: 0.0135 top1= 99.6528

=== Log global consensus distance @ E12B0 ===
consensus_distance=0.003


[E12B10 |   3872/60000 (  6%) ] Loss: 0.0121 top1= 99.6528
[E12B20 |   7392/60000 ( 12%) ] Loss: 0.0151 top1= 99.3056
[E12B30 |  10912/60000 ( 18%) ] Loss: 0.0163 top1= 99.3056
[E12B40 |  14432/60000 ( 24%) ] Loss: 0.0126 top1= 99.6528
[E12B50 |  17952/60000 ( 30%) ] Loss: 0.0052 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3087 top1= 89.7636

Train epoch 13
[E13B0  |    352/60000 (  1%) ] Loss: 0.0119 top1= 99.6528

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


[E13B10 |   3872/60000 (  6%) ] Loss: 0.0122 top1=100.0000
[E13B20 |   7392/60000 ( 12%) ] Loss: 0.0256 top1= 99.3056
[E13B30 |  10912/60000 ( 18%) ] Loss: 0.0140 top1=100.0000
[E13B40 |  14432/60000 ( 24%) ] Loss: 0.0092 top1=100.0000
[E13B50 |  17952/60000 ( 30%) ] Loss: 0.0128 top1= 99.3056

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4232 top1= 86.4784

Train epoch 14
[E14B0  |    352/60000 (  1%) ] Loss: 0.0243 top1= 98.6111

=== Log global consensus distance @ E14B0 ===
consensus_distance=0.003


[E14B10 |   3872/60000 (  6%) ] Loss: 0.0123 top1=100.0000
[E14B20 |   7392/60000 ( 12%) ] Loss: 0.0072 top1=100.0000
[E14B30 |  10912/60000 ( 18%) ] Loss: 0.0161 top1= 98.9583
[E14B40 |  14432/60000 ( 24%) ] Loss: 0.0226 top1= 99.3056
[E14B50 |  17952/60000 ( 30%) ] Loss: 0.0089 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2185 top1= 93.2893

Train epoch 15
[E15B0  |    352/60000 (  1%) ] Loss: 0.0087 top1= 99.6528

=== Log global consensus distance @ E15B0 ===
consensus_distance=0.003


[E15B10 |   3872/60000 (  6%) ] Loss: 0.0103 top1= 99.6528
[E15B20 |   7392/60000 ( 12%) ] Loss: 0.0048 top1=100.0000
[E15B30 |  10912/60000 ( 18%) ] Loss: 0.0423 top1= 98.6111
[E15B40 |  14432/60000 ( 24%) ] Loss: 0.0103 top1=100.0000
[E15B50 |  17952/60000 ( 30%) ] Loss: 0.0265 top1= 99.3056

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3489 top1= 89.9139

Train epoch 16
[E16B0  |    352/60000 (  1%) ] Loss: 0.0121 top1= 99.6528

=== Log global consensus distance @ E16B0 ===
consensus_distance=0.005


[E16B10 |   3872/60000 (  6%) ] Loss: 0.0158 top1= 99.6528
[E16B20 |   7392/60000 ( 12%) ] Loss: 0.0173 top1= 99.6528
[E16B30 |  10912/60000 ( 18%) ] Loss: 0.0515 top1= 98.6111
[E16B40 |  14432/60000 ( 24%) ] Loss: 0.0070 top1=100.0000
[E16B50 |  17952/60000 ( 30%) ] Loss: 0.0212 top1= 98.9583

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3330 top1= 90.2444

Train epoch 17
[E17B0  |    352/60000 (  1%) ] Loss: 0.0388 top1= 98.9583

=== Log global consensus distance @ E17B0 ===
consensus_distance=0.005


[E17B10 |   3872/60000 (  6%) ] Loss: 0.0492 top1= 98.6111
[E17B20 |   7392/60000 ( 12%) ] Loss: 0.0181 top1= 99.3056
[E17B30 |  10912/60000 ( 18%) ] Loss: 0.0199 top1= 98.9583
[E17B40 |  14432/60000 ( 24%) ] Loss: 0.0118 top1= 99.6528
[E17B50 |  17952/60000 ( 30%) ] Loss: 0.0314 top1= 98.6111

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3174 top1= 90.7452

Train epoch 18
[E18B0  |    352/60000 (  1%) ] Loss: 0.0111 top1=100.0000

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


[E18B10 |   3872/60000 (  6%) ] Loss: 0.0117 top1=100.0000
[E18B20 |   7392/60000 ( 12%) ] Loss: 0.0261 top1= 99.3056
[E18B30 |  10912/60000 ( 18%) ] Loss: 0.0146 top1= 99.6528
[E18B40 |  14432/60000 ( 24%) ] Loss: 0.0050 top1=100.0000
[E18B50 |  17952/60000 ( 30%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3023 top1= 91.0757

Train epoch 19
[E19B0  |    352/60000 (  1%) ] Loss: 0.0120 top1=100.0000

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


[E19B10 |   3872/60000 (  6%) ] Loss: 0.0087 top1=100.0000
[E19B20 |   7392/60000 ( 12%) ] Loss: 0.0138 top1= 99.3056
[E19B30 |  10912/60000 ( 18%) ] Loss: 0.0058 top1=100.0000
[E19B40 |  14432/60000 ( 24%) ] Loss: 0.0060 top1=100.0000
[E19B50 |  17952/60000 ( 30%) ] Loss: 0.0084 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2356 top1= 93.1791

Train epoch 20
[E20B0  |    352/60000 (  1%) ] Loss: 0.0067 top1= 99.6528

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


[E20B10 |   3872/60000 (  6%) ] Loss: 0.0197 top1= 99.3056
[E20B20 |   7392/60000 ( 12%) ] Loss: 0.0131 top1= 99.6528
[E20B30 |  10912/60000 ( 18%) ] Loss: 0.0290 top1= 99.3056
[E20B40 |  14432/60000 ( 24%) ] Loss: 0.0286 top1= 99.3056
[E20B50 |  17952/60000 ( 30%) ] Loss: 0.0069 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2148 top1= 93.8001

Train epoch 21
[E21B0  |    352/60000 (  1%) ] Loss: 0.0097 top1= 99.6528

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


[E21B10 |   3872/60000 (  6%) ] Loss: 0.0107 top1=100.0000
[E21B20 |   7392/60000 ( 12%) ] Loss: 0.0098 top1=100.0000
[E21B30 |  10912/60000 ( 18%) ] Loss: 0.0077 top1=100.0000
[E21B40 |  14432/60000 ( 24%) ] Loss: 0.0033 top1=100.0000
[E21B50 |  17952/60000 ( 30%) ] Loss: 0.0035 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2121 top1= 93.8902

Train epoch 22
[E22B0  |    352/60000 (  1%) ] Loss: 0.0130 top1= 99.6528

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


[E22B10 |   3872/60000 (  6%) ] Loss: 0.0065 top1=100.0000
[E22B20 |   7392/60000 ( 12%) ] Loss: 0.0104 top1= 99.6528
[E22B30 |  10912/60000 ( 18%) ] Loss: 0.0114 top1=100.0000
[E22B40 |  14432/60000 ( 24%) ] Loss: 0.0074 top1=100.0000
[E22B50 |  17952/60000 ( 30%) ] Loss: 0.0096 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1687 top1= 94.9319

Train epoch 23
[E23B0  |    352/60000 (  1%) ] Loss: 0.0051 top1=100.0000

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


[E23B10 |   3872/60000 (  6%) ] Loss: 0.0040 top1=100.0000
[E23B20 |   7392/60000 ( 12%) ] Loss: 0.0160 top1= 99.6528
[E23B30 |  10912/60000 ( 18%) ] Loss: 0.0044 top1=100.0000
[E23B40 |  14432/60000 ( 24%) ] Loss: 0.0036 top1=100.0000
[E23B50 |  17952/60000 ( 30%) ] Loss: 0.0107 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2210 top1= 93.8401

Train epoch 24
[E24B0  |    352/60000 (  1%) ] Loss: 0.0089 top1=100.0000

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


[E24B10 |   3872/60000 (  6%) ] Loss: 0.0083 top1=100.0000
[E24B20 |   7392/60000 ( 12%) ] Loss: 0.0198 top1= 98.9583
[E24B30 |  10912/60000 ( 18%) ] Loss: 0.0084 top1= 99.6528
[E24B40 |  14432/60000 ( 24%) ] Loss: 0.0074 top1=100.0000
[E24B50 |  17952/60000 ( 30%) ] Loss: 0.0053 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1667 top1= 95.1522

Train epoch 25
[E25B0  |    352/60000 (  1%) ] Loss: 0.0039 top1=100.0000

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


[E25B10 |   3872/60000 (  6%) ] Loss: 0.0249 top1= 98.9583
[E25B20 |   7392/60000 ( 12%) ] Loss: 0.0072 top1=100.0000
[E25B30 |  10912/60000 ( 18%) ] Loss: 0.0169 top1= 99.6528
[E25B40 |  14432/60000 ( 24%) ] Loss: 0.0056 top1=100.0000
[E25B50 |  17952/60000 ( 30%) ] Loss: 0.0030 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1961 top1= 94.4812

Train epoch 26
[E26B0  |    352/60000 (  1%) ] Loss: 0.0019 top1=100.0000

=== Log global consensus distance @ E26B0 ===
consensus_distance=0.003


[E26B10 |   3872/60000 (  6%) ] Loss: 0.0163 top1= 99.6528
[E26B20 |   7392/60000 ( 12%) ] Loss: 0.0128 top1= 99.6528
[E26B30 |  10912/60000 ( 18%) ] Loss: 0.0105 top1= 99.6528
[E26B40 |  14432/60000 ( 24%) ] Loss: 0.0027 top1=100.0000
[E26B50 |  17952/60000 ( 30%) ] Loss: 0.0056 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1514 top1= 95.7332

Train epoch 27
[E27B0  |    352/60000 (  1%) ] Loss: 0.0037 top1=100.0000

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


[E27B10 |   3872/60000 (  6%) ] Loss: 0.0024 top1=100.0000
[E27B20 |   7392/60000 ( 12%) ] Loss: 0.0072 top1= 99.6528
[E27B30 |  10912/60000 ( 18%) ] Loss: 0.0034 top1=100.0000
[E27B40 |  14432/60000 ( 24%) ] Loss: 0.0016 top1=100.0000
[E27B50 |  17952/60000 ( 30%) ] Loss: 0.0087 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2146 top1= 94.0705

Train epoch 28
[E28B0  |    352/60000 (  1%) ] Loss: 0.0106 top1= 99.3056

=== Log global consensus distance @ E28B0 ===
consensus_distance=0.002


[E28B10 |   3872/60000 (  6%) ] Loss: 0.0068 top1=100.0000
[E28B20 |   7392/60000 ( 12%) ] Loss: 0.0071 top1= 99.6528
[E28B30 |  10912/60000 ( 18%) ] Loss: 0.0041 top1=100.0000
[E28B40 |  14432/60000 ( 24%) ] Loss: 0.0033 top1=100.0000
[E28B50 |  17952/60000 ( 30%) ] Loss: 0.0320 top1= 98.9583

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2834 top1= 92.0272

Train epoch 29
[E29B0  |    352/60000 (  1%) ] Loss: 0.0147 top1= 99.6528

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


[E29B10 |   3872/60000 (  6%) ] Loss: 0.0056 top1=100.0000
[E29B20 |   7392/60000 ( 12%) ] Loss: 0.0050 top1=100.0000
[E29B30 |  10912/60000 ( 18%) ] Loss: 0.0052 top1=100.0000
[E29B40 |  14432/60000 ( 24%) ] Loss: 0.0037 top1=100.0000
[E29B50 |  17952/60000 ( 30%) ] Loss: 0.0069 top1= 99.6528

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1539 top1= 95.6230

Train epoch 30
[E30B0  |    352/60000 (  1%) ] Loss: 0.0026 top1=100.0000

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


[E30B10 |   3872/60000 (  6%) ] Loss: 0.0033 top1=100.0000
[E30B20 |   7392/60000 ( 12%) ] Loss: 0.0045 top1=100.0000
[E30B30 |  10912/60000 ( 18%) ] Loss: 0.0138 top1= 99.3056
[E30B40 |  14432/60000 ( 24%) ] Loss: 0.0189 top1= 99.6528
[E30B50 |  17952/60000 ( 30%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1662 top1= 95.2624

