
=== 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 SGDMWorker(index=10, momentum=0.9)
=> Add worker ByzantineWorker(index=11)

=== Start adding graph ===
TwoCliquesWithByzantine(m=5,b=1)

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.3142 top1=  7.6705

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



=== Log global consensus distance @ E1B0 ===
consensus_distance=0.001



=== Log clique consensus distance @ E1B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=0.002



=== Log mixing matrix @ E1B0 ===
[[0.167 0.167 0.167 0.167 0.167 0.    0.    0.    0.    0.    0.167 0.   ]
 [0.167 0.233 0.2   0.2   0.2   0.    0.    0.    0.    0.    0.    0.   ]
 [0.167 0.2   0.233 0.2   0.2   0.    0.    0.    0.    0.    0.    0.   ]
 [0.167 0.2   0.2   0.233 0.2   0.    0.    0.    0.    0.    0.    0.   ]
 [0.167 0.2   0.2   0.2   0.233 0.    0.    0.    0.    0.    0.    0.   ]
 [0.    0.    0.    0.    0.    0.233 0.2   0.2   0.2   0.167 0.    0.   ]
 [0.    0.    0.    0.    0.    0.2   0.233 0.2   0.2   0.167 0.    0.   ]
 [0.    0.    0.    0.    0.    0.2   0.2   0.233 0.2   0.167 0.    0.   ]
 [0.    0.    0.    0.    0.    0.2   0.2   0.2   0.233 0.167 0.    0.   ]
 [0.    0.    0.    0.    0.    0.167 0.167 0.167 0.167 0.167 0.167 0.   ]
 [0.167 0.    0.    0.    0.    0.    0.    0.    0.    0.167 0.167 0.5  ]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.5   0.5  ]]


[E 1B10 |   4224/60000 (  7%) ] Loss: 0.9041 top1= 72.1591

=== Log global consensus distance @ E1B10 ===
consensus_distance=1.116



=== Log clique consensus distance @ E1B10 ===
clique1_consensus_distance=0.020
clique2_consensus_distance=1.647


[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.3775 top1= 90.9091

=== Log global consensus distance @ E1B20 ===
consensus_distance=5.184



=== Log clique consensus distance @ E1B20 ===
clique1_consensus_distance=0.023
clique2_consensus_distance=4.686



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=8.9308 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8805 top1= 41.1659


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5145 top1= 38.2612

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1671 top1= 95.4545

=== Log global consensus distance @ E2B0 ===
consensus_distance=10.944



=== Log clique consensus distance @ E2B0 ===
clique1_consensus_distance=0.024
clique2_consensus_distance=6.706


[E 2B10 |   4224/60000 (  7%) ] Loss: 0.2321 top1= 95.1705

=== Log global consensus distance @ E2B10 ===
consensus_distance=17.851



=== Log clique consensus distance @ E2B10 ===
clique1_consensus_distance=0.025
clique2_consensus_distance=8.059


[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1711 top1= 95.4545

=== Log global consensus distance @ E2B20 ===
consensus_distance=25.847



=== Log clique consensus distance @ E2B20 ===
clique1_consensus_distance=0.025
clique2_consensus_distance=9.244



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=7.1566 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5937 top1= 43.1090


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3257 top1= 43.9804

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.0876 top1= 97.7273

=== Log global consensus distance @ E3B0 ===
consensus_distance=35.303



=== Log clique consensus distance @ E3B0 ===
clique1_consensus_distance=0.025
clique2_consensus_distance=10.670


[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1008 top1= 97.1591

=== Log global consensus distance @ E3B10 ===
consensus_distance=45.882



=== Log clique consensus distance @ E3B10 ===
clique1_consensus_distance=0.025
clique2_consensus_distance=12.084


[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1133 top1= 96.5909

=== Log global consensus distance @ E3B20 ===
consensus_distance=57.575



=== Log clique consensus distance @ E3B20 ===
clique1_consensus_distance=0.025
clique2_consensus_distance=13.472



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=4.8499 top1= 16.6567


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0390 top1= 47.2055


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2930 top1= 45.6631

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1477 top1= 97.1591

=== Log global consensus distance @ E4B0 ===
consensus_distance=71.110



=== Log clique consensus distance @ E4B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=14.930


[E 4B10 |   4224/60000 (  7%) ] Loss: 0.2627 top1= 96.3068

=== Log global consensus distance @ E4B10 ===
consensus_distance=86.863



=== Log clique consensus distance @ E4B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=16.439


[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.1238 top1= 97.4432

=== Log global consensus distance @ E4B20 ===
consensus_distance=104.977



=== Log clique consensus distance @ E4B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=17.874



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=4.4642 top1= 17.7083


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5922 top1= 48.3674


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9202 top1= 43.9904

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0896 top1= 97.4432

=== Log global consensus distance @ E5B0 ===
consensus_distance=123.573



=== Log clique consensus distance @ E5B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=19.278


[E 5B10 |   4224/60000 (  7%) ] Loss: 0.1135 top1= 95.7386

=== Log global consensus distance @ E5B10 ===
consensus_distance=142.860



=== Log clique consensus distance @ E5B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=20.820


[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.3164 top1= 96.5909

=== Log global consensus distance @ E5B20 ===
consensus_distance=162.861



=== Log clique consensus distance @ E5B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=22.111



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.8667 top1=  9.8357


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0368 top1= 48.2372


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7841 top1= 41.9972

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.1440 top1= 96.0227

=== Log global consensus distance @ E6B0 ===
consensus_distance=184.008



=== Log clique consensus distance @ E6B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=23.498


[E 6B10 |   4224/60000 (  7%) ] Loss: 0.1377 top1= 95.4545

=== Log global consensus distance @ E6B10 ===
consensus_distance=214.811



=== Log clique consensus distance @ E6B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=25.267


[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.1209 top1= 96.0227

=== Log global consensus distance @ E6B20 ===
consensus_distance=246.839



=== Log clique consensus distance @ E6B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=26.591



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1= 13.9423


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9302 top1= 48.1470


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0814 top1= 42.5881

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: nan top1= 89.4886

=== Log global consensus distance @ E7B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E7B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=28.090


[E 7B10 |   4224/60000 (  7%) ] Loss: nan top1= 87.7841

=== Log global consensus distance @ E7B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E7B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=29.778


[E 7B20 |   8064/60000 ( 13%) ] Loss: nan top1= 89.7727

=== Log global consensus distance @ E7B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E7B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=31.018



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4799 top1= 48.3373


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.1321 top1= 45.1823

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: nan top1= 89.4886

=== Log global consensus distance @ E8B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E8B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=31.938


[E 8B10 |   4224/60000 (  7%) ] Loss: nan top1= 89.2045

=== Log global consensus distance @ E8B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E8B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=33.046


[E 8B20 |   8064/60000 ( 13%) ] Loss: nan top1= 88.6364

=== Log global consensus distance @ E8B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E8B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=33.829



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1507 top1= 49.0084


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7180 top1= 44.4211

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: nan top1= 89.4886

=== Log global consensus distance @ E9B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E9B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=34.448


[E 9B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.0568

=== Log global consensus distance @ E9B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E9B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=35.114


[E 9B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.0568

=== Log global consensus distance @ E9B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E9B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=35.537



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6154 top1= 49.2588


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2610 top1= 45.7933

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E10B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E10B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=36.007


[E10B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.3409

=== Log global consensus distance @ E10B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E10B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=36.328


[E10B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E10B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E10B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=36.700



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0349 top1= 49.1386


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.8776 top1= 44.4411

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E11B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E11B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=37.100


[E11B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E11B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E11B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=37.375


[E11B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.6250

=== Log global consensus distance @ E11B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E11B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=37.543



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3140 top1= 49.7095


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.7758 top1= 45.0421

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E12B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E12B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=37.920


[E12B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E12B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E12B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=38.165


[E12B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E12B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E12B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=38.376



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9810 top1= 49.7496


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.1401 top1= 45.9836

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E13B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E13B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=38.664


[E13B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.6250

=== Log global consensus distance @ E13B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E13B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=38.807


[E13B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E13B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E13B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=39.032



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8330 top1= 49.7396


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.0655 top1= 45.6731

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E14B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E14B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=39.353


[E14B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.6250

=== Log global consensus distance @ E14B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E14B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=39.477


[E14B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E14B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E14B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=39.759



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5009 top1= 49.5092


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.6282 top1= 46.8750

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: nan top1= 90.6250

=== Log global consensus distance @ E15B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E15B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=39.985


[E15B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E15B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E15B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=40.144


[E15B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E15B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E15B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=40.374



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8924 top1= 49.5292


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.0551 top1= 46.9551

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: nan top1= 90.6250

=== Log global consensus distance @ E16B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E16B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=40.436


[E16B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E16B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E16B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=40.565


[E16B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E16B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E16B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=40.654



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9975 top1= 49.6795


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.8157 top1= 46.9852

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E17B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E17B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=40.720


[E17B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E17B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E17B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=40.782


[E17B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E17B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E17B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=40.827



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2554 top1= 49.6194


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.6162 top1= 47.0954

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E18B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E18B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=40.872


[E18B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E18B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E18B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=40.912


[E18B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E18B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E18B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=40.941



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.4128 top1= 49.6194


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.8205 top1= 47.1254

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E19B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E19B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=40.971


[E19B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E19B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E19B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.002


[E19B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E19B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E19B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.026



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.5554 top1= 49.5893


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.0232 top1= 47.1154

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E20B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E20B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.053


[E20B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E20B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E20B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.080


[E20B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E20B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E20B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.102



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.6815 top1= 49.6094


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.2022 top1= 47.1254

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E21B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E21B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.126


[E21B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E21B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E21B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.151


[E21B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E21B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E21B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.170



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.7978 top1= 49.5994


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.3555 top1= 47.1154

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E22B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E22B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.192


[E22B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E22B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E22B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.215


[E22B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E22B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E22B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.233



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9016 top1= 49.5893


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.5010 top1= 47.1254

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E23B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E23B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.253


[E23B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E23B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E23B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.274


[E23B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E23B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E23B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.291



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9978 top1= 49.5893


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.6289 top1= 47.1254

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E24B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E24B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.310


[E24B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E24B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E24B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.329


[E24B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E24B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E24B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.345



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.0882 top1= 49.5893


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7480 top1= 47.1154

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E25B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E25B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.362


[E25B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E25B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E25B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.380


[E25B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E25B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E25B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.395



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.1714 top1= 49.5793


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8545 top1= 47.1154

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E26B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E26B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.411


[E26B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E26B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E26B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.428


[E26B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E26B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E26B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.442



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.2491 top1= 49.5693


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.9552 top1= 47.1154

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E27B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E27B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.458


[E27B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E27B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E27B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.473


[E27B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E27B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E27B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.487



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.3239 top1= 49.5593


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.0492 top1= 47.1054

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E28B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E28B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.501


[E28B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E28B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E28B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.516


[E28B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E28B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E28B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.529



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.3952 top1= 49.5593


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.1367 top1= 47.0853

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E29B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E29B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.543


[E29B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E29B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E29B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.557


[E29B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E29B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E29B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.569



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.4616 top1= 49.5593


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.2233 top1= 47.1054

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E30B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E30B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.582


[E30B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E30B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E30B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.596


[E30B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E30B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E30B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.607



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.5249 top1= 49.5593


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.3053 top1= 47.0853

Train epoch 31
[E31B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E31B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E31B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.620


[E31B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E31B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E31B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.633


[E31B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E31B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E31B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.644



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.5869 top1= 49.5593


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.3820 top1= 47.0853

Train epoch 32
[E32B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E32B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E32B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.656


[E32B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E32B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E32B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.669


[E32B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E32B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E32B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.679



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.6439 top1= 49.5593


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.4550 top1= 47.0853

Train epoch 33
[E33B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E33B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E33B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.691


[E33B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E33B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E33B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.703


[E33B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E33B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E33B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.713



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.6999 top1= 49.5593


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.5235 top1= 47.0853

Train epoch 34
[E34B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E34B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E34B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.724


[E34B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E34B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E34B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.735


[E34B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E34B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E34B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.745



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.7552 top1= 49.5493


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.5933 top1= 47.0853

Train epoch 35
[E35B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E35B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E35B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.756


[E35B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E35B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E35B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.767


[E35B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E35B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E35B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.776



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.8054 top1= 49.5493


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.6584 top1= 47.0853

Train epoch 36
[E36B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E36B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E36B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.787


[E36B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E36B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E36B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.797


[E36B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E36B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E36B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.806



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.8545 top1= 49.5292


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.7196 top1= 47.0853

Train epoch 37
[E37B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E37B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E37B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.816


[E37B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E37B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E37B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.827


[E37B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E37B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E37B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.835



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.9032 top1= 49.5292


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.7777 top1= 47.0753

Train epoch 38
[E38B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E38B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E38B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.845


[E38B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E38B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E38B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.855


[E38B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E38B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E38B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.863



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.9489 top1= 49.5292


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.8337 top1= 47.0753

Train epoch 39
[E39B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E39B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E39B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.873


[E39B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E39B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E39B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.882


[E39B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E39B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E39B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.890



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.9929 top1= 49.5292


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.8879 top1= 47.0753

Train epoch 40
[E40B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E40B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E40B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.899


[E40B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E40B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E40B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.908


[E40B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E40B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E40B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.916



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.0367 top1= 49.5292


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.9405 top1= 47.0753

Train epoch 41
[E41B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E41B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E41B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.925


[E41B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E41B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E41B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.934


[E41B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E41B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E41B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.942



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.0773 top1= 49.5393


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.9903 top1= 47.0753

Train epoch 42
[E42B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E42B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E42B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.950


[E42B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E42B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E42B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.959


[E42B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E42B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E42B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.966



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.1176 top1= 49.5292


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=13.0395 top1= 47.0753

Train epoch 43
[E43B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E43B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E43B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.975


[E43B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E43B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E43B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.983


[E43B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E43B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E43B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.990



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.1576 top1= 49.5393


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=13.0868 top1= 47.0753

Train epoch 44
[E44B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E44B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E44B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=41.999


[E44B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E44B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E44B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=42.007


[E44B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E44B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E44B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=42.014



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.1952 top1= 49.5393


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=13.1322 top1= 47.0653

Train epoch 45
[E45B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E45B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E45B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=42.022


[E45B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E45B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E45B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=42.030


[E45B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E45B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E45B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=42.037



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.2315 top1= 49.5493


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=13.1763 top1= 47.0653

Train epoch 46
[E46B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E46B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E46B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=42.044


[E46B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E46B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E46B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=42.052


[E46B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E46B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E46B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=42.059



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.2676 top1= 49.5493


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=13.2202 top1= 47.0653

Train epoch 47
[E47B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E47B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E47B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=42.066


[E47B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E47B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E47B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=42.074


[E47B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E47B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E47B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=42.080



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.3021 top1= 49.5493


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=13.2627 top1= 47.0653

Train epoch 48
[E48B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E48B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E48B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=42.088


[E48B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E48B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E48B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=42.095


[E48B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E48B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E48B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=42.101



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.3368 top1= 49.5493


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=13.3032 top1= 47.0653

Train epoch 49
[E49B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E49B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E49B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=42.109


[E49B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E49B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E49B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=42.116


[E49B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E49B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E49B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=42.122



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.3695 top1= 49.5493


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=13.3423 top1= 47.0653

Train epoch 50
[E50B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E50B0 ===
consensus_distance=nan



=== Log clique consensus distance @ E50B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=42.129


[E50B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E50B10 ===
consensus_distance=nan



=== Log clique consensus distance @ E50B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=42.136


[E50B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

=== Log global consensus distance @ E50B20 ===
consensus_distance=nan



=== Log clique consensus distance @ E50B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=42.142



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.4012 top1= 49.5493


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=13.3805 top1= 47.0653

