
=== 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 0x7fc1895457c0>

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: 1.0068 top1= 64.3750
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.3243 top1= 89.3750
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.5455 top1= 85.6250
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.3137 top1= 88.4375
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.1994 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7016 top1= 85.7672


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8680 top1= 49.7696


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9276 top1= 45.2825

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1850 top1= 94.0625
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.1725 top1= 95.3125
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1043 top1= 97.1875
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.1484 top1= 93.7500
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.1168 top1= 94.6875
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.0658 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5964 top1= 87.9908


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8433 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7915 top1= 46.3842

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.0926 top1= 97.1875
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.0836 top1= 97.5000
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0547 top1= 98.7500
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.0836 top1= 96.5625
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.0658 top1= 97.8125
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.0382 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4798 top1= 89.4431


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0824 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1317 top1= 46.7248

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0534 top1= 98.7500
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0532 top1= 98.4375
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0275 top1=100.0000
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.0404 top1= 98.7500
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.0367 top1= 99.0625
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.0205 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3921 top1= 90.4447


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2894 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2849 top1= 47.0653

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0272 top1= 99.3750
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0300 top1= 99.3750
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0157 top1=100.0000
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.0246 top1= 99.6875
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.0238 top1= 99.3750
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.0102 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3474 top1= 90.6250


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4322 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3746 top1= 47.0252

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0116 top1= 99.6875
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0145 top1= 99.6875
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0088 top1=100.0000
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.0165 top1= 99.6875
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.0189 top1= 99.3750
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.0092 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3142 top1= 90.9155


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4088 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5244 top1= 47.0753

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0071 top1=100.0000
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0098 top1=100.0000
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0072 top1=100.0000
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.0089 top1=100.0000
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.0072 top1=100.0000
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.0073 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2950 top1= 90.9856


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3676 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5069 top1= 47.1554

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0049 top1=100.0000
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0120 top1= 99.6875
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0091 top1=100.0000
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.0076 top1=100.0000
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.0068 top1=100.0000
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.0050 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2893 top1= 90.6851


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1197 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4252 top1= 47.1254

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0040 top1=100.0000
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0054 top1=100.0000
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0033 top1=100.0000
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.0062 top1= 99.6875
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.0188 top1= 99.3750
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.0049 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2877 top1= 90.5349


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8486 top1= 51.0717


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1498 top1= 47.0052

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0042 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0047 top1=100.0000
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0029 top1=100.0000
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.0159 top1= 99.0625
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.0092 top1= 99.6875
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.0053 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2786 top1= 90.8253


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5629 top1= 51.9531


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7132 top1= 47.1554

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0047 top1=100.0000
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0050 top1=100.0000
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.0038 top1=100.0000
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.0031 top1=100.0000
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.0037 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2693 top1= 91.1458


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2678 top1= 52.9147


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6056 top1= 47.3658

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0052 top1=100.0000
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0037 top1=100.0000
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.0050 top1=100.0000
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.0028 top1=100.0000
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.0030 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2559 top1= 91.6667


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0187 top1= 54.2167


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3024 top1= 48.3474

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0037 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0045 top1=100.0000
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.0061 top1=100.0000
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.0042 top1=100.0000
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.0040 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2499 top1= 91.7368


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8127 top1= 55.4688


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0072 top1= 49.5793

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0026 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0023 top1=100.0000
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.0032 top1=100.0000
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.0023 top1=100.0000
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2408 top1= 92.1575


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6190 top1= 56.9812


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6448 top1= 51.6426

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0023 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0021 top1=100.0000
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.0036 top1=100.0000
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.0023 top1=100.0000
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2287 top1= 92.7784


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4388 top1= 58.4535


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3134 top1= 54.0565

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0028 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0022 top1=100.0000
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.0034 top1=100.0000
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.0025 top1=100.0000
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2242 top1= 92.9487


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2822 top1= 59.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1030 top1= 56.4804

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0026 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0023 top1=100.0000
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.0035 top1=100.0000
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.0027 top1=100.0000
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2213 top1= 93.0990


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1202 top1= 61.5084


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9385 top1= 58.4135

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0024 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0022 top1=100.0000
[E18B30 |  11904/60000 ( 20%) ] Loss: 0.0035 top1=100.0000
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.0027 top1=100.0000
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2180 top1= 93.2091


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9786 top1= 62.6302


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7582 top1= 60.9876

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0023 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0023 top1=100.0000
[E19B30 |  11904/60000 ( 20%) ] Loss: 0.0035 top1=100.0000
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.0025 top1=100.0000
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2154 top1= 93.2893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8415 top1= 64.0825


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6026 top1= 63.3614

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0022 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0022 top1=100.0000
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.0034 top1=100.0000
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.0023 top1=100.0000
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2131 top1= 93.4495


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7227 top1= 65.6150


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4614 top1= 65.9255

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0027 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0021 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0021 top1=100.0000
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.0031 top1=100.0000
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.0021 top1=100.0000
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2111 top1= 93.5397


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6073 top1= 67.0072


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3309 top1= 68.7300

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0019 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.0029 top1=100.0000
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.0018 top1=100.0000
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2096 top1= 93.6599


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5107 top1= 68.5296


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2201 top1= 70.9635

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0017 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.0026 top1=100.0000
[E23B40 |  15744/60000 ( 26%) ] Loss: 0.0016 top1=100.0000
[E23B50 |  19584/60000 ( 33%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2086 top1= 93.8301


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4179 top1= 69.8417


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1129 top1= 73.2372

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0015 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.0024 top1=100.0000
[E24B40 |  15744/60000 ( 26%) ] Loss: 0.0015 top1=100.0000
[E24B50 |  19584/60000 ( 33%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2077 top1= 93.9904


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3255 top1= 71.3442


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0260 top1= 75.4307

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0014 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E25B30 |  11904/60000 ( 20%) ] Loss: 0.0022 top1=100.0000
[E25B40 |  15744/60000 ( 26%) ] Loss: 0.0013 top1=100.0000
[E25B50 |  19584/60000 ( 33%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2066 top1= 94.0705


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2424 top1= 72.6663


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9509 top1= 77.2436

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0012 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E26B30 |  11904/60000 ( 20%) ] Loss: 0.0020 top1=100.0000
[E26B40 |  15744/60000 ( 26%) ] Loss: 0.0012 top1=100.0000
[E26B50 |  19584/60000 ( 33%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2061 top1= 94.1807


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1644 top1= 73.7981


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8849 top1= 78.8962

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.0018 top1=100.0000
[E27B40 |  15744/60000 ( 26%) ] Loss: 0.0011 top1=100.0000
[E27B50 |  19584/60000 ( 33%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2055 top1= 94.2107


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0977 top1= 74.8197


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8279 top1= 80.2684

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0010 top1=100.0000
[E28B30 |  11904/60000 ( 20%) ] Loss: 0.0016 top1=100.0000
[E28B40 |  15744/60000 ( 26%) ] Loss: 0.0010 top1=100.0000
[E28B50 |  19584/60000 ( 33%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2049 top1= 94.2909


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0334 top1= 76.0116


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7766 top1= 81.4503

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000
[E29B30 |  11904/60000 ( 20%) ] Loss: 0.0015 top1=100.0000
[E29B40 |  15744/60000 ( 26%) ] Loss: 0.0009 top1=100.0000
[E29B50 |  19584/60000 ( 33%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2043 top1= 94.4010


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9774 top1= 77.0232


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7310 top1= 82.5521

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000
[E30B30 |  11904/60000 ( 20%) ] Loss: 0.0014 top1=100.0000
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.0008 top1=100.0000
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2039 top1= 94.4611


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9267 top1= 78.1150


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6904 top1= 83.5236

