
=== 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 0x7f74d25407c0>

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: 1.0133 top1= 65.0000
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2612 top1= 90.9375
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.4505 top1= 87.1875
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.2640 top1= 90.0000
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.1712 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4533 top1= 87.0593


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4594 top1= 51.9631


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1165 top1= 48.5477

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1820 top1= 95.0000
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.1684 top1= 94.3750
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1264 top1= 95.9375
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.1730 top1= 95.3125
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.1354 top1= 95.0000
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.1044 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3348 top1= 89.5333


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2322 top1= 55.7692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6008 top1= 54.7977

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1122 top1= 96.8750
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1197 top1= 95.9375
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0841 top1= 97.1875
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.1207 top1= 96.8750
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.0985 top1= 96.8750
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.0540 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2825 top1= 90.6851


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8955 top1= 58.6038


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5549 top1= 57.9127

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0663 top1= 99.0625
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0875 top1= 95.6250
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0545 top1= 99.3750
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.0751 top1= 97.8125
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.0736 top1= 97.8125
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.0347 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2489 top1= 91.4864


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6927 top1= 61.7588


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6390 top1= 58.9944

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0523 top1= 98.4375
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0674 top1= 97.8125
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0384 top1= 98.7500
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.0527 top1= 98.1250
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.0470 top1= 98.7500
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.0280 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2399 top1= 91.9972


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6881 top1= 63.3013


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5297 top1= 63.2512

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0373 top1= 99.3750
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0476 top1= 98.4375
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0411 top1= 99.0625
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.0490 top1= 98.7500
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.0306 top1= 99.6875
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.0237 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2250 top1= 92.3678


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4474 top1= 66.1558


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3752 top1= 66.9972

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0295 top1= 99.3750
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0288 top1= 98.7500
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0118 top1= 99.6875
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.0433 top1= 98.1250
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.0164 top1=100.0000
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.0112 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2023 top1= 93.5397


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1640 top1= 70.1422


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1920 top1= 69.6715

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0219 top1= 99.3750
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0116 top1=100.0000
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0195 top1= 99.0625
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.0134 top1= 99.6875
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.0160 top1= 99.6875
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.0100 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1958 top1= 93.7400


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1375 top1= 71.5645


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0239 top1= 72.6262

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0120 top1= 99.3750
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0199 top1= 99.0625
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0080 top1=100.0000
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.0079 top1=100.0000
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.0103 top1=100.0000
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.0117 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1898 top1= 94.2308


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0939 top1= 73.1470


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9095 top1= 75.8714

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0058 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0124 top1= 99.6875
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0050 top1=100.0000
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.0064 top1=100.0000
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.0040 top1=100.0000
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.0064 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1882 top1= 94.4511


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8790 top1= 77.1034


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8549 top1= 77.9147

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0047 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0029 top1=100.0000
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0028 top1=100.0000
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.0045 top1=100.0000
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.0036 top1=100.0000
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1938 top1= 94.4010


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7448 top1= 80.1883


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8283 top1= 79.1066

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0036 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0023 top1=100.0000
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0024 top1=100.0000
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.0036 top1=100.0000
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.0041 top1=100.0000
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1952 top1= 94.4411


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7133 top1= 81.5104


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7722 top1= 80.5288

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0024 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.0032 top1=100.0000
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.0026 top1=100.0000
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1882 top1= 94.6615


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6640 top1= 82.6823


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6873 top1= 82.4820

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0020 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.0028 top1=100.0000
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.0017 top1=100.0000
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1886 top1= 94.8718


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6217 top1= 83.7841


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6494 top1= 83.7139

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0014 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.0021 top1=100.0000
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.0014 top1=100.0000
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1874 top1= 94.9619


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6146 top1= 84.0845


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5608 top1= 85.6971

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0010 top1=100.0000
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.0017 top1=100.0000
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.0012 top1=100.0000
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1903 top1= 95.0421


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5809 top1= 85.3165


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5438 top1= 86.4583

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.0014 top1=100.0000
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.0011 top1=100.0000
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1909 top1= 95.0621


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5579 top1= 86.1879


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5189 top1= 87.1895

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0011 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: 0.0012 top1=100.0000
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.0011 top1=100.0000
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1913 top1= 95.0921


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5380 top1= 86.7188


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5085 top1= 87.5300

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0010 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: 0.0011 top1=100.0000
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.0010 top1=100.0000
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1918 top1= 95.1122


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5207 top1= 87.2596


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4973 top1= 87.9107

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.0010 top1=100.0000
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.0009 top1=100.0000
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1923 top1= 95.1623


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5054 top1= 87.6502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4871 top1= 88.2412

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.0009 top1=100.0000
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.0009 top1=100.0000
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1929 top1= 95.1823


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4914 top1= 88.0909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4779 top1= 88.4816

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.0008 top1=100.0000
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.0008 top1=100.0000
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1935 top1= 95.2324


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4793 top1= 88.4115


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4695 top1= 88.6719

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.0008 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=0.1940 top1= 95.2224


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4683 top1= 88.7720


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4627 top1= 88.8822

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.0007 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=0.1946 top1= 95.2524


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4582 top1= 89.0425


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4559 top1= 89.1526

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0006 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=0.1952 top1= 95.2724


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4489 top1= 89.3329


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4497 top1= 89.3329

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0006 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=0.1957 top1= 95.2925


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4403 top1= 89.5933


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4439 top1= 89.5333

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0004 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.0006 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=0.1962 top1= 95.3225


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4325 top1= 89.9139


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4386 top1= 89.6935

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0004 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=0.1968 top1= 95.3225


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4249 top1= 90.2043


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4336 top1= 89.9439

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0004 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0005 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=0.1973 top1= 95.3325


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4182 top1= 90.3846


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4286 top1= 90.0741

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: 0.0005 top1=100.0000
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.0006 top1=100.0000
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1977 top1= 95.3325


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4117 top1= 90.5349


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4243 top1= 90.2644

