
=== 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 LabelFlippingWorker
=> Add worker LabelFlippingWorker

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f0e770447c0>

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([6, 9, 7, 7, 8], device='cuda:0')
Worker 11 has targets: tensor([3, 2, 3, 1, 3], device='cuda:0')


[E 1B10 |   4224/60000 (  7%) ] Loss: 1.0398 top1= 65.0000
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2641 top1= 91.2500
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.4563 top1= 86.8750
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.2715 top1= 90.6250
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.1640 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6044 top1= 85.5869


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1496 top1= 49.8698


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7955 top1= 45.3926

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1917 top1= 94.3750
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.1765 top1= 94.3750
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1330 top1= 95.0000
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.1768 top1= 94.3750
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.1532 top1= 94.3750
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.0958 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4524 top1= 87.9107


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8799 top1= 50.2204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5022 top1= 46.2039

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1252 top1= 95.9375
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1126 top1= 95.9375
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1021 top1= 96.5625
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.1356 top1= 96.2500
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.1030 top1= 96.8750
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.0778 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3674 top1= 89.3329


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6121 top1= 52.0333


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3028 top1= 47.3257

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0759 top1= 97.8125
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0791 top1= 97.1875
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0672 top1= 98.7500
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.0861 top1= 97.8125
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.0784 top1= 97.8125
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.0658 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3161 top1= 90.1442


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3845 top1= 54.2768


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2551 top1= 48.7580

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0403 top1= 99.6875
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0600 top1= 98.1250
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0585 top1= 99.0625
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.0645 top1= 97.8125
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.0528 top1= 98.1250
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.0492 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2846 top1= 91.1058


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2741 top1= 55.7192


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1856 top1= 50.6611

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0340 top1= 99.6875
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0449 top1= 98.4375
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0297 top1=100.0000
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.0524 top1= 98.7500
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.0629 top1= 97.8125
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.0395 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2818 top1= 91.1158


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1305 top1= 57.8726


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3690 top1= 49.7095

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0270 top1= 99.3750
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0399 top1= 99.3750
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0169 top1=100.0000
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.0386 top1= 98.4375
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.0420 top1= 98.4375
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.0169 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2589 top1= 91.7067


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8646 top1= 59.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1794 top1= 54.4471

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0233 top1= 99.0625
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0321 top1= 98.7500
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0201 top1= 99.6875
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.0341 top1= 99.3750
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.0300 top1= 99.0625
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.0155 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2491 top1= 92.1174


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8991 top1= 60.3065


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3059 top1= 54.2067

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0197 top1= 99.0625
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0336 top1= 99.3750
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0257 top1= 99.6875
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.0307 top1= 99.3750
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.0163 top1=100.0000
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.0152 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2340 top1= 92.6382


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7884 top1= 61.3582


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0459 top1= 54.2668

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0306 top1= 98.4375
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0247 top1= 99.3750
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0493 top1= 98.4375
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.0100 top1=100.0000
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.0144 top1= 99.6875
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.0247 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2334 top1= 92.8085


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9143 top1= 60.9575


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3055 top1= 54.2268

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0149 top1= 99.3750
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0121 top1= 99.6875
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0139 top1= 99.6875
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.0155 top1= 99.6875
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.0110 top1=100.0000
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.0091 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2189 top1= 93.4095


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6731 top1= 55.3285


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8359 top1= 58.6939

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0077 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0136 top1= 99.6875
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0056 top1=100.0000
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.0069 top1=100.0000
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.0095 top1= 99.6875
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.0062 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2096 top1= 93.7099


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5659 top1= 64.5633


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6121 top1= 62.6603

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0051 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0039 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0037 top1=100.0000
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.0041 top1=100.0000
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.0054 top1=100.0000
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.0068 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2347 top1= 92.9487


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1842 top1= 70.0020


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9378 top1= 58.3233

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0035 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0052 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0026 top1=100.0000
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.0026 top1=100.0000
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.0021 top1=100.0000
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.0043 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2142 top1= 93.7099


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0533 top1= 72.2256


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5293 top1= 64.2528

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0038 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0022 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0029 top1=100.0000
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.0034 top1=100.0000
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.0017 top1=100.0000
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2156 top1= 93.8802


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0543 top1= 72.3458


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5460 top1= 63.7019

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0034 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0029 top1=100.0000
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.0022 top1=100.0000
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.0017 top1=100.0000
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2193 top1= 93.8301


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0138 top1= 73.1871


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5901 top1= 62.6202

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0024 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0024 top1=100.0000
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.0022 top1=100.0000
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.0013 top1=100.0000
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2182 top1= 94.0805


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0733 top1= 72.5260


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5603 top1= 62.9607

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0026 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E18B30 |  11904/60000 ( 20%) ] Loss: 0.0017 top1=100.0000
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.0013 top1=100.0000
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2187 top1= 94.1506


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0642 top1= 72.9367


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5515 top1= 63.1711

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0018 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E19B30 |  11904/60000 ( 20%) ] Loss: 0.0014 top1=100.0000
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.0017 top1=100.0000
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2174 top1= 94.2007


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9838 top1= 74.4191


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4625 top1= 63.6919

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0016 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.0014 top1=100.0000
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.0013 top1=100.0000
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2232 top1= 94.1306


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9310 top1= 75.4407


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5602 top1= 62.3698

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0014 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.0013 top1=100.0000
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.0013 top1=100.0000
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2191 top1= 94.2107


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0007 top1= 74.0284


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5495 top1= 61.9391

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.0013 top1=100.0000
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.0010 top1=100.0000
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2196 top1= 94.1907


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9044 top1= 75.9716


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5276 top1= 62.5401

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.0011 top1=100.0000
[E23B40 |  15744/60000 ( 26%) ] Loss: 0.0009 top1=100.0000
[E23B50 |  19584/60000 ( 33%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2205 top1= 94.2508


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8933 top1= 76.2720


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5185 top1= 62.5901

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.0010 top1=100.0000
[E24B40 |  15744/60000 ( 26%) ] Loss: 0.0008 top1=100.0000
[E24B50 |  19584/60000 ( 33%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2250 top1= 94.1306


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8409 top1= 77.6943


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5245 top1= 62.6302

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0010 top1=100.0000
[E25B30 |  11904/60000 ( 20%) ] Loss: 0.0009 top1=100.0000
[E25B40 |  15744/60000 ( 26%) ] Loss: 0.0008 top1=100.0000
[E25B50 |  19584/60000 ( 33%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2359 top1= 93.9303


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8306 top1= 77.9547


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6873 top1= 60.2865

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E26B30 |  11904/60000 ( 20%) ] Loss: 0.0259 top1= 99.3750
[E26B40 |  15744/60000 ( 26%) ] Loss: 0.0380 top1= 98.7500
[E26B50 |  19584/60000 ( 33%) ] Loss: 0.0355 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9475 top1= 74.6294


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6223 top1= 64.3830


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1997 top1= 48.0068

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0126 top1= 99.3750
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0612 top1= 98.7500
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0333 top1= 98.1250
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.0346 top1= 98.7500
[E27B40 |  15744/60000 ( 26%) ] Loss: 0.0282 top1= 98.4375
[E27B50 |  19584/60000 ( 33%) ] Loss: 0.0136 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3186 top1= 91.0757


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4529 top1= 68.3093


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9844 top1= 50.9916

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0049 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0059 top1= 99.6875
[E28B30 |  11904/60000 ( 20%) ] Loss: 0.0211 top1= 99.0625
[E28B40 |  15744/60000 ( 26%) ] Loss: 0.0295 top1= 99.3750
[E28B50 |  19584/60000 ( 33%) ] Loss: 0.0040 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2026 top1= 94.4311


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9883 top1= 62.4399


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6849 top1= 62.1094

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0129 top1= 99.3750
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0048 top1= 99.6875
[E29B30 |  11904/60000 ( 20%) ] Loss: 0.0045 top1=100.0000
[E29B40 |  15744/60000 ( 26%) ] Loss: 0.0011 top1=100.0000
[E29B50 |  19584/60000 ( 33%) ] Loss: 0.0038 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2170 top1= 94.1106


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0132 top1= 56.2800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7702 top1= 59.4451

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0058 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0058 top1= 99.6875
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0031 top1=100.0000
[E30B30 |  11904/60000 ( 20%) ] Loss: 0.0012 top1=100.0000
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.0011 top1=100.0000
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1927 top1= 94.7516


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5933 top1= 65.2544


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3060 top1= 66.5765

