
=== 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.Dumbbell object at 0x7f658967c730>

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([0, 0, 0, 0, 0], device='cuda:0')
Worker 11 has targets: tensor([1, 1, 1, 1, 1], device='cuda:0')


[E 1B10 |   4224/60000 (  7%) ] Loss: 0.2883 top1= 92.8125
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.0840 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.7704 top1= 37.9307


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.0600 top1= 47.0954


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3341 top1= 47.5962

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1570 top1= 96.2500
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.0580 top1= 98.4375
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.0602 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3261 top1= 51.9531


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1251 top1= 48.0569


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5123 top1= 49.6795

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.0873 top1= 96.5625
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.0322 top1= 98.7500
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0240 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8707 top1= 68.7500


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1191 top1= 48.1671


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2218 top1= 51.8229

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0484 top1= 98.7500
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0361 top1= 99.0625
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0310 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7909 top1= 72.0152


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8588 top1= 48.1370


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9965 top1= 53.7861

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0681 top1= 98.1250
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0120 top1= 99.6875
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0146 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6940 top1= 77.0833


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7917 top1= 50.1603


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0329 top1= 58.4936

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0181 top1= 99.0625
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0514 top1= 99.3750
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0213 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6419 top1= 78.5757


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2118 top1= 51.8730


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8957 top1= 56.7808

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0413 top1= 99.3750
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0289 top1= 99.3750
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0215 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6059 top1= 80.4788


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3242 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8054 top1= 59.6655

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0437 top1= 98.7500
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0266 top1= 99.3750
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0493 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9959 top1= 70.9635


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5155 top1= 48.5677


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0427 top1= 62.0793

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0593 top1= 97.8125
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0215 top1= 99.0625
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0029 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5410 top1= 82.2316


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3086 top1= 53.3153


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6920 top1= 61.8289

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0374 top1= 98.4375
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0165 top1= 99.6875
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0261 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7641 top1= 75.5509


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2962 top1= 50.1002


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3590 top1= 67.5681

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0098 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0253 top1= 99.3750
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0142 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5470 top1= 82.6322


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7863 top1= 51.3622


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8987 top1= 60.8874

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0209 top1= 99.3750
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0068 top1=100.0000
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0083 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5018 top1= 84.1647


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5379 top1= 55.9495


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4934 top1= 65.3446

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0222 top1= 99.6875
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0222 top1= 99.3750
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0096 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5809 top1= 82.7524


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8341 top1= 55.1983


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5457 top1= 66.2360

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0175 top1= 99.0625
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0072 top1= 99.6875
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0109 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5431 top1= 83.2933


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1093 top1= 56.9010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3140 top1= 72.0553

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0066 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0166 top1= 99.6875
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0153 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4915 top1= 85.1663


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7635 top1= 54.9579


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2780 top1= 72.4760

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0063 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0037 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0035 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5363 top1= 84.3950


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8415 top1= 57.4820


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5055 top1= 68.6699

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0266 top1= 98.7500
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0036 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0060 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5386 top1= 84.6755


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4429 top1= 58.1831


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4200 top1= 70.2424

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0062 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0039 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0367 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4872 top1= 85.0461


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4080 top1= 57.0513


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5527 top1= 70.5629

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0164 top1= 99.3750
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0200 top1= 99.3750
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0084 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5137 top1= 85.4968


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4256 top1= 56.3802


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0738 top1= 64.4431

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0225 top1= 99.3750
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0045 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0161 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4596 top1= 86.3982


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4787 top1= 58.9543


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6481 top1= 68.1490

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0084 top1= 99.6875
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0039 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0065 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5045 top1= 85.9075


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5403 top1= 59.5553


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3190 top1= 72.6262

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0067 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0070 top1= 99.6875
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0058 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5163 top1= 86.3682


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5931 top1= 58.6839


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9535 top1= 66.0657

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0106 top1= 99.6875
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0190 top1= 99.6875
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0144 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5000 top1= 86.0577


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2012 top1= 59.3550


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4595 top1= 74.2288

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0066 top1= 99.6875
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0097 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0049 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4766 top1= 86.8990


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0820 top1= 62.3798


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7214 top1= 71.1238

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0165 top1= 99.3750
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0099 top1= 99.6875
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0253 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4568 top1= 87.6002


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4362 top1= 58.4034


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9811 top1= 65.5849

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0137 top1= 99.6875
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0118 top1= 99.3750
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0248 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4731 top1= 87.4900


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0906 top1= 61.1979


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6867 top1= 68.2091

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0078 top1= 99.6875
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0038 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0058 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5660 top1= 85.4567


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3769 top1= 58.9443


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5303 top1= 70.9535

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0222 top1= 99.3750
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0066 top1= 99.3750
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6084 top1= 84.5853


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6945 top1= 66.8470


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1098 top1= 64.7837

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0057 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0140 top1= 99.6875
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0089 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5414 top1= 85.6370


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5802 top1= 58.1530


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5305 top1= 71.3442

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0038 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0133 top1= 99.6875
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4595 top1= 87.8005


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2506 top1= 61.6787


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5617 top1= 72.0152

Train epoch 31
[E31B0  |    384/60000 (  1%) ] Loss: 0.0048 top1= 99.6875
[E31B10 |   4224/60000 (  7%) ] Loss: 0.0034 top1=100.0000
[E31B20 |   8064/60000 ( 13%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4368 top1= 88.4215


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6567 top1= 67.7784


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0728 top1= 78.1350

Train epoch 32
[E32B0  |    384/60000 (  1%) ] Loss: 0.0068 top1=100.0000
[E32B10 |   4224/60000 (  7%) ] Loss: 0.0051 top1=100.0000
[E32B20 |   8064/60000 ( 13%) ] Loss: 0.0078 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4805 top1= 87.2396


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2638 top1= 61.9992


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1521 top1= 76.2520

Train epoch 33
[E33B0  |    384/60000 (  1%) ] Loss: 0.0182 top1= 99.6875
[E33B10 |   4224/60000 (  7%) ] Loss: 0.0031 top1=100.0000
[E33B20 |   8064/60000 ( 13%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4538 top1= 87.8005


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8030 top1= 66.8069


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1320 top1= 78.5657

Train epoch 34
[E34B0  |    384/60000 (  1%) ] Loss: 0.0090 top1= 99.3750
[E34B10 |   4224/60000 (  7%) ] Loss: 0.0014 top1=100.0000
[E34B20 |   8064/60000 ( 13%) ] Loss: 0.0042 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4173 top1= 89.2628


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9557 top1= 66.0657


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2162 top1= 75.3005

Train epoch 35
[E35B0  |    384/60000 (  1%) ] Loss: 0.0162 top1= 99.0625
[E35B10 |   4224/60000 (  7%) ] Loss: 0.0051 top1=100.0000
[E35B20 |   8064/60000 ( 13%) ] Loss: 0.0090 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4837 top1= 87.3097


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4279 top1= 59.4050


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1357 top1= 77.7945

Train epoch 36
[E36B0  |    384/60000 (  1%) ] Loss: 0.0041 top1= 99.6875
[E36B10 |   4224/60000 (  7%) ] Loss: 0.0378 top1= 98.4375
[E36B20 |   8064/60000 ( 13%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5433 top1= 86.6687


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7028 top1= 67.2576


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9288 top1= 70.7031

Train epoch 37
[E37B0  |    384/60000 (  1%) ] Loss: 0.0350 top1= 99.0625
[E37B10 |   4224/60000 (  7%) ] Loss: 0.0032 top1=100.0000
[E37B20 |   8064/60000 ( 13%) ] Loss: 0.0029 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4208 top1= 89.1226


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6110 top1= 67.4079


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1895 top1= 78.3153

Train epoch 38
[E38B0  |    384/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E38B10 |   4224/60000 (  7%) ] Loss: 0.0015 top1=100.0000
[E38B20 |   8064/60000 ( 13%) ] Loss: 0.0063 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4471 top1= 88.5717


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5122 top1= 70.4627


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1019 top1= 77.5841

Train epoch 39
[E39B0  |    384/60000 (  1%) ] Loss: 0.0027 top1=100.0000
[E39B10 |   4224/60000 (  7%) ] Loss: 0.0013 top1=100.0000
[E39B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3799 top1= 90.2043


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4671 top1= 71.1438


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8921 top1= 81.1899

Train epoch 40
[E40B0  |    384/60000 (  1%) ] Loss: 0.0035 top1=100.0000
[E40B10 |   4224/60000 (  7%) ] Loss: 0.0101 top1= 99.6875
[E40B20 |   8064/60000 ( 13%) ] Loss: 0.0060 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4247 top1= 89.8438


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3556 top1= 73.3173


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4025 top1= 74.1086

Train epoch 41
[E41B0  |    384/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E41B10 |   4224/60000 (  7%) ] Loss: 0.0018 top1=100.0000
[E41B20 |   8064/60000 ( 13%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4191 top1= 89.5833


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3440 top1= 74.0885


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8401 top1= 82.6322

Train epoch 42
[E42B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E42B10 |   4224/60000 (  7%) ] Loss: 0.0039 top1=100.0000
[E42B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4093 top1= 89.4131


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6264 top1= 70.1422


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7134 top1= 84.1947

Train epoch 43
[E43B0  |    384/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E43B10 |   4224/60000 (  7%) ] Loss: 0.0023 top1=100.0000
[E43B20 |   8064/60000 ( 13%) ] Loss: 0.0045 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4178 top1= 89.3830


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4047 top1= 73.1270


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7667 top1= 83.9944

Train epoch 44
[E44B0  |    384/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E44B10 |   4224/60000 (  7%) ] Loss: 0.0038 top1= 99.6875
[E44B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4561 top1= 89.0024


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1128 top1= 77.0232


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3683 top1= 78.4655

Train epoch 45
[E45B0  |    384/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E45B10 |   4224/60000 (  7%) ] Loss: 0.0051 top1=100.0000
[E45B20 |   8064/60000 ( 13%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3914 top1= 90.6851


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2718 top1= 73.9683


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1846 top1= 79.2768

Train epoch 46
[E46B0  |    384/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E46B10 |   4224/60000 (  7%) ] Loss: 0.0023 top1=100.0000
[E46B20 |   8064/60000 ( 13%) ] Loss: 0.0030 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4110 top1= 90.3345


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5781 top1= 72.7163


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0887 top1= 81.1098

Train epoch 47
[E47B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E47B10 |   4224/60000 (  7%) ] Loss: 0.0050 top1= 99.6875
[E47B20 |   8064/60000 ( 13%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4306 top1= 89.7035


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0296 top1= 78.8662


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9622 top1= 81.6006

Train epoch 48
[E48B0  |    384/60000 (  1%) ] Loss: 0.0068 top1=100.0000
[E48B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E48B20 |   8064/60000 ( 13%) ] Loss: 0.0029 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4149 top1= 89.9339


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5176 top1= 72.1454


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1772 top1= 79.3169

Train epoch 49
[E49B0  |    384/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E49B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E49B20 |   8064/60000 ( 13%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4092 top1= 90.2444


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4108 top1= 74.8498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8337 top1= 83.1731

Train epoch 50
[E50B0  |    384/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E50B10 |   4224/60000 (  7%) ] Loss: 0.0024 top1=100.0000
[E50B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4036 top1= 90.8454


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0688 top1= 78.7460


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9451 top1= 82.0913

