
=== 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 ByzantineWorker(index=10)
=> Add worker ByzantineWorker(index=11)

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f5fbef957c0>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.3109 top1=  9.6875

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 1 has targets: tensor([2, 1, 4, 4, 0], device='cuda:0')
Worker 2 has targets: tensor([3, 1, 4, 1, 3], device='cuda:0')
Worker 3 has targets: tensor([2, 3, 0, 0, 1], device='cuda:0')
Worker 4 has targets: tensor([2, 1, 1, 4, 2], device='cuda:0')
Worker 5 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')
Worker 6 has targets: tensor([9, 9, 6, 7, 9], device='cuda:0')
Worker 7 has targets: tensor([7, 5, 7, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([8, 9, 9, 5, 7], device='cuda:0')
Worker 9 has targets: tensor([8, 8, 7, 5, 9], device='cuda:0')
Worker 10 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 11 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')


[E 1B10 |   4224/60000 (  7%) ] Loss: 1.0076 top1= 65.0000
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2602 top1= 91.5625
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.4861 top1= 85.6250
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.2666 top1= 90.6250
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.1816 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6030 top1= 84.8458


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5726 top1= 49.8898


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9506 top1= 45.6130

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1751 top1= 94.6875
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.1546 top1= 94.6875
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1252 top1= 95.9375
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.1476 top1= 95.3125
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.1423 top1= 95.3125
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.0835 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3958 top1= 88.7921


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4900 top1= 52.8546


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1959 top1= 47.7865

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1043 top1= 96.5625
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1045 top1= 95.9375
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0801 top1= 97.5000
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.1086 top1= 97.1875
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.0944 top1= 97.1875
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.0528 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3002 top1= 90.4547


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0745 top1= 57.0012


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7550 top1= 53.2352

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0692 top1= 97.8125
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0887 top1= 96.8750
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0538 top1= 98.7500
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.0779 top1= 97.8125
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.0734 top1= 97.8125
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.0310 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2514 top1= 91.6967


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7326 top1= 61.0877


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6038 top1= 58.5737

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0438 top1= 99.6875
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0647 top1= 97.5000
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0456 top1= 98.7500
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.0524 top1= 98.4375
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.0554 top1= 98.4375
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.0273 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2290 top1= 92.3678


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6284 top1= 63.8622


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6321 top1= 59.2147

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0342 top1= 99.3750
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0549 top1= 98.1250
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0224 top1= 99.6875
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.0416 top1= 99.0625
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.0280 top1= 99.3750
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.0302 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2276 top1= 92.4479


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4628 top1= 66.6166


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5660 top1= 63.6118

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0344 top1= 99.0625
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0297 top1= 99.6875
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0191 top1= 99.6875
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.0333 top1= 99.3750
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.0146 top1=100.0000
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.0146 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2122 top1= 93.2292


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2164 top1= 70.1022


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2454 top1= 69.3109

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0366 top1= 98.7500
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0141 top1= 99.6875
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0231 top1= 99.0625
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.0198 top1= 99.6875
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.0124 top1=100.0000
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.0196 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1976 top1= 93.6699


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0725 top1= 72.1554


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1830 top1= 70.1823

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0085 top1=100.0000
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0250 top1= 99.0625
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0115 top1= 99.6875
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.0280 top1= 99.3750
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.0166 top1= 99.6875
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.0086 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1871 top1= 94.2007


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9761 top1= 73.5677


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0428 top1= 73.0268

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0084 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0164 top1= 99.3750
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0108 top1= 99.6875
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.0113 top1= 99.6875
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.0158 top1= 99.3750
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.0093 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1862 top1= 94.2808


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8995 top1= 75.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9823 top1= 73.7380

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0037 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0042 top1=100.0000
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0038 top1=100.0000
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.0048 top1=100.0000
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.0076 top1=100.0000
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.0038 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1847 top1= 94.3810


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6921 top1= 80.5689


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8283 top1= 78.4455

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0075 top1= 99.6875
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0024 top1=100.0000
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.0044 top1=100.0000
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.0021 top1=100.0000
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1816 top1= 94.7015


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6507 top1= 81.7408


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6834 top1= 81.7508

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0031 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0023 top1=100.0000
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.0030 top1=100.0000
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.0019 top1=100.0000
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1923 top1= 94.5513


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5981 top1= 83.4736


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7675 top1= 80.3486

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0022 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.0022 top1=100.0000
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.0042 top1=100.0000
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.0087 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2052 top1= 94.1506


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5783 top1= 84.3550


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8376 top1= 79.2568

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0014 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.0032 top1=100.0000
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.0023 top1=100.0000
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1775 top1= 95.0220


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5247 top1= 85.7071


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6011 top1= 84.3349

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0044 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.0019 top1=100.0000
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.0023 top1=100.0000
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1758 top1= 95.1022


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5086 top1= 86.2179


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6056 top1= 84.2147

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.0029 top1=100.0000
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.0048 top1= 99.6875
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1758 top1= 95.2324


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5044 top1= 86.5184


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4829 top1= 87.3498

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000
[E18B30 |  11904/60000 ( 20%) ] Loss: 0.0015 top1=100.0000
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.0010 top1=100.0000
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1777 top1= 95.2123


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4925 top1= 87.0092


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4717 top1= 87.6002

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000
[E19B30 |  11904/60000 ( 20%) ] Loss: 0.0015 top1=100.0000
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.0013 top1=100.0000
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1748 top1= 95.2724


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4699 top1= 87.6002


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4432 top1= 88.4115

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.0012 top1=100.0000
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.0012 top1=100.0000
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1760 top1= 95.3225


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4505 top1= 88.1611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4438 top1= 88.4816

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.0011 top1=100.0000
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.0009 top1=100.0000
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1748 top1= 95.4928


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4368 top1= 88.6719


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4175 top1= 89.2929

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.0010 top1=100.0000
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.0009 top1=100.0000
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1758 top1= 95.5228


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4193 top1= 89.3229


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4066 top1= 89.6635

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.0009 top1=100.0000
[E23B40 |  15744/60000 ( 26%) ] Loss: 0.0008 top1=100.0000
[E23B50 |  19584/60000 ( 33%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1759 top1= 95.6030


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4075 top1= 89.6735


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3940 top1= 90.0441

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.0008 top1=100.0000
[E24B40 |  15744/60000 ( 26%) ] Loss: 0.0007 top1=100.0000
[E24B50 |  19584/60000 ( 33%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1760 top1= 95.6230


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3960 top1= 90.0741


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3873 top1= 90.2544

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000
[E25B30 |  11904/60000 ( 20%) ] Loss: 0.0007 top1=100.0000
[E25B40 |  15744/60000 ( 26%) ] Loss: 0.0007 top1=100.0000
[E25B50 |  19584/60000 ( 33%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1762 top1= 95.6430


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3870 top1= 90.3245


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3810 top1= 90.5048

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000
[E26B30 |  11904/60000 ( 20%) ] Loss: 0.0007 top1=100.0000
[E26B40 |  15744/60000 ( 26%) ] Loss: 0.0007 top1=100.0000
[E26B50 |  19584/60000 ( 33%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1765 top1= 95.6631


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3782 top1= 90.5849


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3753 top1= 90.7051

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.0007 top1=100.0000
[E27B40 |  15744/60000 ( 26%) ] Loss: 0.0006 top1=100.0000
[E27B50 |  19584/60000 ( 33%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1767 top1= 95.7131


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3706 top1= 90.8353


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3696 top1= 90.8454

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000
[E28B30 |  11904/60000 ( 20%) ] Loss: 0.0006 top1=100.0000
[E28B40 |  15744/60000 ( 26%) ] Loss: 0.0006 top1=100.0000
[E28B50 |  19584/60000 ( 33%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1771 top1= 95.7031


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3632 top1= 91.0958


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3648 top1= 91.0457

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000
[E29B30 |  11904/60000 ( 20%) ] Loss: 0.0006 top1=100.0000
[E29B40 |  15744/60000 ( 26%) ] Loss: 0.0006 top1=100.0000
[E29B50 |  19584/60000 ( 33%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1774 top1= 95.7131


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3567 top1= 91.2760


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3598 top1= 91.2059

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0004 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000
[E30B30 |  11904/60000 ( 20%) ] Loss: 0.0006 top1=100.0000
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.0005 top1=100.0000
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1778 top1= 95.7232


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3507 top1= 91.4163


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3554 top1= 91.3361

