
=== 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 BitFlippingWorker
=> Add worker BitFlippingWorker

=== Start adding graph ===
<codes.graph_utils.RandomSmallWorldGraph object at 0x7fb552be5400>

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([4, 8, 8, 6, 9], device='cuda:0')
Worker 11 has targets: tensor([5, 3, 6, 0, 9], device='cuda:0')



=== Log global consensus distance @ E1B0 ===
consensus_distance=0.002



=== Log average shortest path distance for small world @ E1B0 ===
2.7777777777777777


[E 1B10 |   4224/60000 (  7%) ] Loss: 0.2747 top1= 92.1875
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2054 top1= 96.2500
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.0764 top1= 98.4375
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.0598 top1= 99.0625
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.0584 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2249 top1= 32.6823

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1671 top1= 96.5625

=== Log global consensus distance @ E2B0 ===
consensus_distance=2.016


[E 2B10 |   4224/60000 (  7%) ] Loss: 0.0316 top1= 99.0625
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.0352 top1= 99.0625
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.0284 top1= 99.0625
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.0442 top1= 99.3750
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.0404 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.1643 top1= 32.8926

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.0811 top1= 97.5000

=== Log global consensus distance @ E3B0 ===
consensus_distance=1.941


[E 3B10 |   4224/60000 (  7%) ] Loss: 0.0213 top1= 99.6875
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0203 top1= 99.0625
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.0256 top1= 99.3750
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.0289 top1= 99.0625
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.0336 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.1659 top1= 31.1098

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0569 top1= 98.1250

=== Log global consensus distance @ E4B0 ===
consensus_distance=1.951


[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0137 top1= 99.6875
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0185 top1= 99.3750
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.0246 top1= 99.0625
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.0221 top1= 99.3750
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.0306 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.1170 top1= 32.3518

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0453 top1= 98.4375

=== Log global consensus distance @ E5B0 ===
consensus_distance=1.968


[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0131 top1= 99.6875
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0156 top1= 99.3750
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.0278 top1= 99.0625
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.0158 top1= 99.3750
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.0248 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0890 top1= 33.5036

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0406 top1= 97.8125

=== Log global consensus distance @ E6B0 ===
consensus_distance=1.990


[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0118 top1= 99.6875
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0120 top1= 99.6875
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.0170 top1= 99.3750
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.0156 top1= 99.3750
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.0240 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.1006 top1= 33.4535

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0362 top1= 98.1250

=== Log global consensus distance @ E7B0 ===
consensus_distance=2.003


[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0154 top1= 99.6875
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0166 top1= 99.3750
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.0202 top1= 99.3750
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.0113 top1= 99.6875
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.0205 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0852 top1= 32.5921

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0327 top1= 98.1250

=== Log global consensus distance @ E8B0 ===
consensus_distance=2.045


[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0107 top1= 99.6875
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0116 top1= 99.0625
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.0173 top1= 99.3750
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.0092 top1= 99.6875
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.0182 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0703 top1= 34.2248

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0271 top1= 98.7500

=== Log global consensus distance @ E9B0 ===
consensus_distance=2.074


[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0085 top1=100.0000
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0132 top1= 99.0625
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.0142 top1= 99.3750
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.0076 top1=100.0000
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.0172 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0426 top1= 34.6755

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0257 top1= 99.3750

=== Log global consensus distance @ E10B0 ===
consensus_distance=2.095


[E10B10 |   4224/60000 (  7%) ] Loss: 0.0113 top1= 99.3750
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0142 top1= 99.6875
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.0142 top1= 99.3750
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.0077 top1= 99.6875
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.0144 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0324 top1= 35.6571

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0240 top1= 98.7500

=== Log global consensus distance @ E11B0 ===
consensus_distance=2.114


[E11B10 |   4224/60000 (  7%) ] Loss: 0.0074 top1=100.0000
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0108 top1= 99.6875
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.0162 top1= 99.0625
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.0067 top1=100.0000
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.0118 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0454 top1= 34.5453

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0270 top1= 99.6875

=== Log global consensus distance @ E12B0 ===
consensus_distance=2.134


[E12B10 |   4224/60000 (  7%) ] Loss: 0.0070 top1= 99.6875
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0123 top1= 99.0625
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.0166 top1= 99.3750
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.0090 top1= 99.6875
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.0127 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0338 top1= 34.8958

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0182 top1= 99.6875

=== Log global consensus distance @ E13B0 ===
consensus_distance=2.151


[E13B10 |   4224/60000 (  7%) ] Loss: 0.0072 top1= 99.6875
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0091 top1= 99.6875
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.0184 top1= 99.3750
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.0110 top1= 99.3750
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.0154 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0288 top1= 34.1847

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0238 top1= 99.3750

=== Log global consensus distance @ E14B0 ===
consensus_distance=2.166


[E14B10 |   4224/60000 (  7%) ] Loss: 0.0061 top1= 99.6875
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0142 top1= 99.6875
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.0168 top1= 99.0625
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.0066 top1= 99.6875
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.0150 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0073 top1= 34.7155

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0221 top1= 99.3750

=== Log global consensus distance @ E15B0 ===
consensus_distance=2.183


[E15B10 |   4224/60000 (  7%) ] Loss: 0.0103 top1= 99.6875
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0059 top1= 99.6875
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.0115 top1= 99.3750
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.0115 top1= 99.3750
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.0191 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0048 top1= 33.7540

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0337 top1= 99.3750

=== Log global consensus distance @ E16B0 ===
consensus_distance=2.194


[E16B10 |   4224/60000 (  7%) ] Loss: 0.0088 top1= 99.6875
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0258 top1= 99.0625
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.0176 top1= 99.0625
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.0083 top1= 99.6875
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.0138 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9713 top1= 34.4651

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0240 top1= 98.7500

=== Log global consensus distance @ E17B0 ===
consensus_distance=2.216


[E17B10 |   4224/60000 (  7%) ] Loss: 0.0085 top1= 99.6875
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0068 top1= 99.6875
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.0087 top1= 99.6875
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.0083 top1= 99.6875
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.0152 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9375 top1= 35.3065

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0257 top1= 98.7500

=== Log global consensus distance @ E18B0 ===
consensus_distance=2.227


[E18B10 |   4224/60000 (  7%) ] Loss: 0.0050 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0116 top1= 99.3750
[E18B30 |  11904/60000 ( 20%) ] Loss: 0.0177 top1= 99.3750
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.0084 top1= 99.6875
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.0141 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9421 top1= 34.5954

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0223 top1= 99.3750

=== Log global consensus distance @ E19B0 ===
consensus_distance=2.234


[E19B10 |   4224/60000 (  7%) ] Loss: 0.0048 top1= 99.6875
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0130 top1= 99.6875
[E19B30 |  11904/60000 ( 20%) ] Loss: 0.0202 top1= 99.0625
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.0072 top1= 99.6875
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.0136 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9420 top1= 35.0661

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0168 top1= 99.0625

=== Log global consensus distance @ E20B0 ===
consensus_distance=2.247


[E20B10 |   4224/60000 (  7%) ] Loss: 0.0047 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0117 top1= 99.3750
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.0098 top1= 99.6875
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.0048 top1=100.0000
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.0124 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9313 top1= 35.3766

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0210 top1= 99.3750

=== Log global consensus distance @ E21B0 ===
consensus_distance=2.258


[E21B10 |   4224/60000 (  7%) ] Loss: 0.0059 top1= 99.6875
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0105 top1= 99.6875
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.0151 top1= 99.3750
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.0123 top1= 99.3750
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.0154 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9404 top1= 34.4551

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0227 top1= 99.0625

=== Log global consensus distance @ E22B0 ===
consensus_distance=2.274


[E22B10 |   4224/60000 (  7%) ] Loss: 0.0046 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0067 top1=100.0000
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.0125 top1= 99.3750
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.0049 top1=100.0000
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.0196 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9420 top1= 34.7456

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0221 top1= 99.6875

=== Log global consensus distance @ E23B0 ===
consensus_distance=2.288


[E23B10 |   4224/60000 (  7%) ] Loss: 0.0064 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0100 top1= 99.6875
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.0102 top1= 99.6875
[E23B40 |  15744/60000 ( 26%) ] Loss: 0.0190 top1= 99.3750
[E23B50 |  19584/60000 ( 33%) ] Loss: 0.0189 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9130 top1= 34.9960

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0186 top1= 99.0625

=== Log global consensus distance @ E24B0 ===
consensus_distance=2.302


[E24B10 |   4224/60000 (  7%) ] Loss: 0.0043 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0072 top1=100.0000
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.0156 top1= 99.0625
[E24B40 |  15744/60000 ( 26%) ] Loss: 0.0070 top1= 99.3750
[E24B50 |  19584/60000 ( 33%) ] Loss: 0.0153 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9620 top1= 33.6238

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0322 top1= 99.0625

=== Log global consensus distance @ E25B0 ===
consensus_distance=2.314


[E25B10 |   4224/60000 (  7%) ] Loss: 0.0053 top1= 99.6875
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0143 top1= 99.6875
[E25B30 |  11904/60000 ( 20%) ] Loss: 0.0081 top1= 99.6875
[E25B40 |  15744/60000 ( 26%) ] Loss: 0.0063 top1= 99.6875
[E25B50 |  19584/60000 ( 33%) ] Loss: 0.0114 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9122 top1= 35.5769

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0214 top1= 98.7500

=== Log global consensus distance @ E26B0 ===
consensus_distance=2.322


[E26B10 |   4224/60000 (  7%) ] Loss: 0.0033 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0098 top1= 99.3750
[E26B30 |  11904/60000 ( 20%) ] Loss: 0.0061 top1= 99.6875
[E26B40 |  15744/60000 ( 26%) ] Loss: 0.0035 top1=100.0000
[E26B50 |  19584/60000 ( 33%) ] Loss: 0.0128 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9173 top1= 34.6254

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0213 top1= 99.3750

=== Log global consensus distance @ E27B0 ===
consensus_distance=2.337


[E27B10 |   4224/60000 (  7%) ] Loss: 0.0047 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0081 top1= 99.6875
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.0073 top1= 99.6875
[E27B40 |  15744/60000 ( 26%) ] Loss: 0.0077 top1= 99.6875
[E27B50 |  19584/60000 ( 33%) ] Loss: 0.0111 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9038 top1= 35.5970

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0148 top1= 99.6875

=== Log global consensus distance @ E28B0 ===
consensus_distance=2.346


[E28B10 |   4224/60000 (  7%) ] Loss: 0.0039 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0043 top1=100.0000
[E28B30 |  11904/60000 ( 20%) ] Loss: 0.0069 top1= 99.6875
[E28B40 |  15744/60000 ( 26%) ] Loss: 0.0040 top1=100.0000
[E28B50 |  19584/60000 ( 33%) ] Loss: 0.0099 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9187 top1= 34.9259

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0152 top1= 99.3750

=== Log global consensus distance @ E29B0 ===
consensus_distance=2.355


[E29B10 |   4224/60000 (  7%) ] Loss: 0.0068 top1= 99.6875
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0080 top1= 99.6875
[E29B30 |  11904/60000 ( 20%) ] Loss: 0.0090 top1= 99.3750
[E29B40 |  15744/60000 ( 26%) ] Loss: 0.0085 top1= 99.3750
[E29B50 |  19584/60000 ( 33%) ] Loss: 0.0193 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9029 top1= 35.2264

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0227 top1= 98.7500

=== Log global consensus distance @ E30B0 ===
consensus_distance=2.368


[E30B10 |   4224/60000 (  7%) ] Loss: 0.0040 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0126 top1= 99.6875
[E30B30 |  11904/60000 ( 20%) ] Loss: 0.0130 top1= 99.3750
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.0118 top1= 99.3750
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.0107 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9283 top1= 34.2748

