
=== 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 0.667 0.   ]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    1.   ]]


[E 1B10 |   4224/60000 (  7%) ] Loss: 0.6843 top1= 78.6932

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



=== Log clique consensus distance @ E1B10 ===
clique1_consensus_distance=0.005
clique2_consensus_distance=1.433


[E 1B20 |   8064/60000 ( 13%) ] Loss: nan top1= 84.3750

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



=== Log clique consensus distance @ E1B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=4.476



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.8562 top1= 40.1843


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.6530 top1= 43.4395

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: nan top1= 86.0795

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



=== Log clique consensus distance @ E2B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.271


[E 2B10 |   4224/60000 (  7%) ] Loss: nan top1= 85.7955

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



=== Log clique consensus distance @ E2B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.153


[E 2B20 |   8064/60000 ( 13%) ] Loss: nan top1= 86.6477

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



=== Log clique consensus distance @ E2B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=7.695



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8577 top1= 45.1823


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.9706 top1= 45.1322

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: nan top1= 86.9318

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



=== Log clique consensus distance @ E3B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=8.072


[E 3B10 |   4224/60000 (  7%) ] Loss: nan top1= 89.2045

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



=== Log clique consensus distance @ E3B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=8.424


[E 3B20 |   8064/60000 ( 13%) ] Loss: nan top1= 88.6364

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



=== Log clique consensus distance @ E3B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=8.733



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8780 top1= 45.4026


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8674 top1= 45.1022

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: nan top1= 89.7727

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



=== Log clique consensus distance @ E4B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=9.093


[E 4B10 |   4224/60000 (  7%) ] Loss: nan top1= 89.4886

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



=== Log clique consensus distance @ E4B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=9.394


[E 4B20 |   8064/60000 ( 13%) ] Loss: nan top1= 89.2045

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



=== Log clique consensus distance @ E4B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=9.687



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1188 top1= 46.5345


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1000 top1= 45.2624

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: nan top1= 90.6250

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



=== Log clique consensus distance @ E5B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=10.018


[E 5B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.6250

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



=== Log clique consensus distance @ E5B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=10.337


[E 5B20 |   8064/60000 ( 13%) ] Loss: nan top1= 89.4886

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



=== Log clique consensus distance @ E5B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=10.626



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5294 top1= 47.7364


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0095 top1= 44.3409

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: nan top1= 89.7727

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



=== Log clique consensus distance @ E6B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=10.965


[E 6B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.0568

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



=== Log clique consensus distance @ E6B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=11.291


[E 6B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.0568

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



=== Log clique consensus distance @ E6B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=11.566



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9277 top1= 47.7564


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1961 top1= 44.5513

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: nan top1= 90.3409

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



=== Log clique consensus distance @ E7B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=11.935


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

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



=== Log clique consensus distance @ E7B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=12.304


[E 7B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.0568

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



=== Log clique consensus distance @ E7B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=12.638



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4638 top1= 47.2857


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8890 top1= 46.1438

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: nan top1= 90.3409

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



=== Log clique consensus distance @ E8B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=12.981


[E 8B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.6250

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



=== Log clique consensus distance @ E8B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=13.261


[E 8B20 |   8064/60000 ( 13%) ] Loss: nan top1= 89.2045

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



=== Log clique consensus distance @ E8B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=13.582



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0894 top1= 47.7364


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1073 top1= 45.4828

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: nan top1= 90.6250

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



=== Log clique consensus distance @ E9B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=13.902


[E 9B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.3409

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



=== Log clique consensus distance @ E9B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=14.233


[E 9B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

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



=== Log clique consensus distance @ E9B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=14.515



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4725 top1= 48.5777


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5800 top1= 45.7933

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: nan top1= 90.6250

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



=== Log clique consensus distance @ E10B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=14.753


[E10B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.6250

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



=== Log clique consensus distance @ E10B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=14.988


[E10B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.6250

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



=== Log clique consensus distance @ E10B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=15.173



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0876 top1= 47.9567


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8730 top1= 46.4443

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=15.309


[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=15.412


[E11B20 |   8064/60000 ( 13%) ] Loss: nan top1= 90.9091

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



=== Log clique consensus distance @ E11B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=15.503



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5992 top1= 48.2672


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1515 top1= 46.4343

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=15.579


[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=15.646


[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=15.705



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0813 top1= 48.0669


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3641 top1= 46.5044

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=15.759


[E13B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

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



=== Log clique consensus distance @ E13B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=15.808


[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=15.854



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2550 top1= 48.3974


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5891 top1= 46.5244

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=15.895


[E14B10 |   4224/60000 (  7%) ] Loss: nan top1= 90.9091

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



=== Log clique consensus distance @ E14B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=15.930


[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=15.965



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4818 top1= 48.3674


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.7943 top1= 46.5445

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

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



=== Log clique consensus distance @ E15B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=15.997


[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=16.027


[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=16.056



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.6521 top1= 48.3774


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.9598 top1= 46.5545

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: nan top1= 90.9091

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



=== Log clique consensus distance @ E16B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=16.083


[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=16.109


[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=16.135



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7927 top1= 48.3974


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.1077 top1= 46.5645

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=16.160


[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=16.184


[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=16.207



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9195 top1= 48.3974


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.2396 top1= 46.5545

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=16.229


[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=16.251


[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=16.272



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0323 top1= 48.4375


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.3560 top1= 46.5645

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=16.292


[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=16.312


[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=16.332



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1356 top1= 48.4475


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.4706 top1= 46.5645

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=16.351


[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=16.369


[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=16.387



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2281 top1= 48.4375


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.5714 top1= 46.5645

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=16.404


[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=16.421


[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=16.438



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3168 top1= 48.4175


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.6697 top1= 46.5645

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=16.454


[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=16.470


[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=16.486



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3964 top1= 48.4475


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.7584 top1= 46.5645

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=16.501


[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=16.516


[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=16.531



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4695 top1= 48.4475


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.8426 top1= 46.5745

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=16.545


[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=16.559


[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=16.573



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5401 top1= 48.4475


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.9218 top1= 46.5745

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=16.586


[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=16.599


[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=16.613



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6063 top1= 48.4475


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.9973 top1= 46.5745

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=16.625


[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=16.638


[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=16.650



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6668 top1= 48.4475


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.0690 top1= 46.5745

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=16.663


[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=16.674


[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=16.686



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.7266 top1= 48.4475


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.1355 top1= 46.5745

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=16.698


[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=16.709


[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=16.721



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.7810 top1= 48.4475


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.2001 top1= 46.5745

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=16.732


[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=16.742


[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=16.753



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8347 top1= 48.4475


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.2628 top1= 46.5745

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=16.764


[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=16.774


[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=16.784



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8844 top1= 48.4475


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.3217 top1= 46.5745

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=16.795


[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=16.804


[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=16.814



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9338 top1= 48.4475


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.3773 top1= 46.5845

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=16.824


[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=16.834


[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=16.843



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9798 top1= 48.4375


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.4336 top1= 46.5845

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=16.852


[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=16.861


[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=16.871



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.0249 top1= 48.4375


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.4853 top1= 46.5845

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=16.880


[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=16.888


[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=16.897



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.0679 top1= 48.4375


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.5358 top1= 46.5845

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=16.906


[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=16.914


[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=16.923



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1092 top1= 48.4475


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.5836 top1= 46.5845

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=16.931


[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=16.939


[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=16.948



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1498 top1= 48.4475


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.6322 top1= 46.5845

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=16.956


[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=16.964


[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=16.972



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1871 top1= 48.4575


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.6786 top1= 46.5845

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=16.979


[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=16.987


[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=16.995



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2250 top1= 48.4675


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.7219 top1= 46.5845

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=17.002


[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=17.010


[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=17.017



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2601 top1= 48.4675


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.7662 top1= 46.5845

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=17.024


[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=17.032


[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=17.039



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2959 top1= 48.4675


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.8069 top1= 46.5845

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=17.046


[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=17.053


[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=17.060



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.3292 top1= 48.4675


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.8479 top1= 46.5845

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=17.067


[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=17.073


[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=17.080



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.3620 top1= 48.4675


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.8871 top1= 46.5845

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=17.087


[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=17.094


[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=17.100



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.3933 top1= 48.4675


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.9248 top1= 46.5845

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=17.107


[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=17.113


[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=17.120



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.4242 top1= 48.4876


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.9631 top1= 46.5845

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=17.126


[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=17.132


[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=17.138



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.4546 top1= 48.4876


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.9982 top1= 46.5845

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=17.145


[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=17.151


[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=17.157



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.4836 top1= 48.4876


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.0339 top1= 46.5845

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=17.163


[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=17.169


[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=17.175



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.5123 top1= 48.4876


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.0683 top1= 46.5845

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=17.181


[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=17.186


[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=17.192



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.5397 top1= 48.4876


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.1016 top1= 46.5845

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=17.198


[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=17.203


[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=17.209



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.5675 top1= 48.4876


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.1349 top1= 46.5845

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=17.215


[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=17.220


[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=17.226



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.5937 top1= 48.4876


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.1674 top1= 46.5845

