
=== 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 0.042 0.625]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.625 0.375]]


[E 1B10 |   4224/60000 (  7%) ] Loss: 0.9134 top1= 71.3068

=== Log global consensus distance @ E1B10 ===
consensus_distance=1.262



=== Log clique consensus distance @ E1B10 ===
clique1_consensus_distance=0.020
clique2_consensus_distance=1.648


[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.3770 top1= 93.4659

=== Log global consensus distance @ E1B20 ===
consensus_distance=8.902



=== Log clique consensus distance @ E1B20 ===
clique1_consensus_distance=0.023
clique2_consensus_distance=4.864



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=13.2824 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0384 top1= 41.1959


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9262 top1= 38.0709

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1779 top1= 94.6023

=== Log global consensus distance @ E2B0 ===
consensus_distance=21.625



=== Log clique consensus distance @ E2B0 ===
clique1_consensus_distance=0.024
clique2_consensus_distance=7.189


[E 2B10 |   4224/60000 (  7%) ] Loss: 0.1555 top1= 95.1705

=== Log global consensus distance @ E2B10 ===
consensus_distance=39.445



=== Log clique consensus distance @ E2B10 ===
clique1_consensus_distance=0.024
clique2_consensus_distance=8.882


[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.2164 top1= 94.3182

=== Log global consensus distance @ E2B20 ===
consensus_distance=61.820



=== Log clique consensus distance @ E2B20 ===
clique1_consensus_distance=0.025
clique2_consensus_distance=10.377



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=9.7363 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7337 top1= 42.8686


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2772 top1= 43.1490

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1449 top1= 96.0227

=== Log global consensus distance @ E3B0 ===
consensus_distance=89.209



=== Log clique consensus distance @ E3B0 ===
clique1_consensus_distance=0.025
clique2_consensus_distance=12.141


[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1384 top1= 96.0227

=== Log global consensus distance @ E3B10 ===
consensus_distance=122.583



=== Log clique consensus distance @ E3B10 ===
clique1_consensus_distance=0.025
clique2_consensus_distance=13.984


[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1684 top1= 95.7386

=== Log global consensus distance @ E3B20 ===
consensus_distance=161.816



=== Log clique consensus distance @ E3B20 ===
clique1_consensus_distance=0.025
clique2_consensus_distance=15.688



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=4.8078 top1= 14.3129


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2088 top1= 47.4960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1859 top1= 45.8133

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1400 top1= 96.3068

=== Log global consensus distance @ E4B0 ===
consensus_distance=205.423



=== Log clique consensus distance @ E4B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=17.513


[E 4B10 |   4224/60000 (  7%) ] Loss: 0.1125 top1= 96.3068

=== Log global consensus distance @ E4B10 ===
consensus_distance=252.517



=== Log clique consensus distance @ E4B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=19.354


[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.1172 top1= 96.5909

=== Log global consensus distance @ E4B20 ===
consensus_distance=303.432



=== Log clique consensus distance @ E4B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=21.066



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.6303 top1= 13.0008


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4230 top1= 48.8281


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2248 top1= 46.2039

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.1278 top1= 96.3068

=== Log global consensus distance @ E5B0 ===
consensus_distance=358.687



=== Log clique consensus distance @ E5B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=22.858


[E 5B10 |   4224/60000 (  7%) ] Loss: 0.1157 top1= 95.7386

=== Log global consensus distance @ E5B10 ===
consensus_distance=418.509



=== Log clique consensus distance @ E5B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=24.807


[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0987 top1= 97.4432

=== Log global consensus distance @ E5B20 ===
consensus_distance=482.656



=== Log clique consensus distance @ E5B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=26.694



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.3674 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7339 top1= 48.5577


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1515 top1= 46.0236

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.1368 top1= 95.4545

=== Log global consensus distance @ E6B0 ===
consensus_distance=551.134



=== Log clique consensus distance @ E6B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=28.441


[E 6B10 |   4224/60000 (  7%) ] Loss: 0.1295 top1= 95.1705

=== Log global consensus distance @ E6B10 ===
consensus_distance=624.207



=== Log clique consensus distance @ E6B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=30.450


[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.1299 top1= 96.0227

=== Log global consensus distance @ E6B20 ===
consensus_distance=701.579



=== Log clique consensus distance @ E6B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=32.305



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.3457 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9017 top1= 46.4844


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9081 top1= 45.6330

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.1388 top1= 95.7386

=== Log global consensus distance @ E7B0 ===
consensus_distance=783.712



=== Log clique consensus distance @ E7B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=34.324


[E 7B10 |   4224/60000 (  7%) ] Loss: 0.1516 top1= 94.0341

=== Log global consensus distance @ E7B10 ===
consensus_distance=870.285



=== Log clique consensus distance @ E7B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=36.349


[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0923 top1= 97.1591

=== Log global consensus distance @ E7B20 ===
consensus_distance=961.047



=== Log clique consensus distance @ E7B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=38.070



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.3340 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8267 top1= 48.4475


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7305 top1= 44.4712

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0859 top1= 97.1591

=== Log global consensus distance @ E8B0 ===
consensus_distance=1056.128



=== Log clique consensus distance @ E8B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=39.588


[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0792 top1= 97.4432

=== Log global consensus distance @ E8B10 ===
consensus_distance=1155.617



=== Log clique consensus distance @ E8B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=40.983


[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0867 top1= 97.1591

=== Log global consensus distance @ E8B20 ===
consensus_distance=1259.442



=== Log clique consensus distance @ E8B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=42.247



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.5929 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0856 top1= 48.7580


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6104 top1= 45.6030

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0867 top1= 97.7273

=== Log global consensus distance @ E9B0 ===
consensus_distance=1367.796



=== Log clique consensus distance @ E9B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=43.627


[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0746 top1= 97.1591

=== Log global consensus distance @ E9B10 ===
consensus_distance=1480.654



=== Log clique consensus distance @ E9B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=45.143


[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0844 top1= 97.7273

=== Log global consensus distance @ E9B20 ===
consensus_distance=1597.819



=== Log clique consensus distance @ E9B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=46.460



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.6940 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0998 top1= 48.9383


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4481 top1= 45.0220

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.1206 top1= 97.1591

=== Log global consensus distance @ E10B0 ===
consensus_distance=1719.583



=== Log clique consensus distance @ E10B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=48.388


[E10B10 |   4224/60000 (  7%) ] Loss: 0.0993 top1= 96.8750

=== Log global consensus distance @ E10B10 ===
consensus_distance=1845.996



=== Log clique consensus distance @ E10B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=50.361


[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0892 top1= 98.0114

=== Log global consensus distance @ E10B20 ===
consensus_distance=1976.488



=== Log clique consensus distance @ E10B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=51.835



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.4864 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4967 top1= 48.4776


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7577 top1= 43.4395

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0892 top1= 96.5909

=== Log global consensus distance @ E11B0 ===
consensus_distance=2111.357



=== Log clique consensus distance @ E11B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=53.043


[E11B10 |   4224/60000 (  7%) ] Loss: 0.0820 top1= 96.8750

=== Log global consensus distance @ E11B10 ===
consensus_distance=2250.689



=== Log clique consensus distance @ E11B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=54.400


[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0754 top1= 98.0114

=== Log global consensus distance @ E11B20 ===
consensus_distance=2394.359



=== Log clique consensus distance @ E11B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=55.578



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.6410 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0430 top1= 47.6663


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6650 top1= 42.5982

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.1063 top1= 97.4432

=== Log global consensus distance @ E12B0 ===
consensus_distance=2542.489



=== Log clique consensus distance @ E12B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=56.683


[E12B10 |   4224/60000 (  7%) ] Loss: 0.0921 top1= 97.4432

=== Log global consensus distance @ E12B10 ===
consensus_distance=2695.115



=== Log clique consensus distance @ E12B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=57.925


[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0915 top1= 97.4432

=== Log global consensus distance @ E12B20 ===
consensus_distance=2852.094



=== Log clique consensus distance @ E12B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=59.053



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.8411 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3612 top1= 46.3442


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9306 top1= 41.0457

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.1092 top1= 96.3068

=== Log global consensus distance @ E13B0 ===
consensus_distance=3013.584



=== Log clique consensus distance @ E13B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=60.251


[E13B10 |   4224/60000 (  7%) ] Loss: 0.1007 top1= 96.3068

=== Log global consensus distance @ E13B10 ===
consensus_distance=3179.729



=== Log clique consensus distance @ E13B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=61.812


[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0786 top1= 96.8750

=== Log global consensus distance @ E13B20 ===
consensus_distance=3350.201



=== Log clique consensus distance @ E13B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=63.203



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=4.0340 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9671 top1= 49.0184


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4925 top1= 44.6114

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.1038 top1= 96.5909

=== Log global consensus distance @ E14B0 ===
consensus_distance=3524.943



=== Log clique consensus distance @ E14B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=64.381


[E14B10 |   4224/60000 (  7%) ] Loss: 0.0966 top1= 96.8750

=== Log global consensus distance @ E14B10 ===
consensus_distance=3704.286



=== Log clique consensus distance @ E14B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=65.740


[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0947 top1= 96.8750

=== Log global consensus distance @ E14B20 ===
consensus_distance=3887.882



=== Log clique consensus distance @ E14B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=66.872



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=4.3799 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0877 top1= 48.4976


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2219 top1= 46.0637

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0568 top1= 98.2955

=== Log global consensus distance @ E15B0 ===
consensus_distance=4075.979



=== Log clique consensus distance @ E15B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=67.933


[E15B10 |   4224/60000 (  7%) ] Loss: 0.0755 top1= 97.1591

=== Log global consensus distance @ E15B10 ===
consensus_distance=4279.360



=== Log clique consensus distance @ E15B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=68.878


[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0713 top1= 98.2955

=== Log global consensus distance @ E15B20 ===
consensus_distance=4485.645



=== Log clique consensus distance @ E15B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=69.515



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=4.5494 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3034 top1= 49.1486


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3733 top1= 45.4928

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0666 top1= 97.7273

=== Log global consensus distance @ E16B0 ===
consensus_distance=4691.444



=== Log clique consensus distance @ E16B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=70.525


[E16B10 |   4224/60000 (  7%) ] Loss: 0.0862 top1= 97.1591

=== Log global consensus distance @ E16B10 ===
consensus_distance=4899.267



=== Log clique consensus distance @ E16B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=71.493


[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0677 top1= 97.4432

=== Log global consensus distance @ E16B20 ===
consensus_distance=5110.395



=== Log clique consensus distance @ E16B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=72.182



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=4.8871 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7286 top1= 48.7981


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4819 top1= 45.1723

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0764 top1= 97.4432

=== Log global consensus distance @ E17B0 ===
consensus_distance=5325.746



=== Log clique consensus distance @ E17B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=73.226


[E17B10 |   4224/60000 (  7%) ] Loss: 0.0649 top1= 98.0114

=== Log global consensus distance @ E17B10 ===
consensus_distance=5545.375



=== Log clique consensus distance @ E17B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=74.158


[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0588 top1= 98.0114

=== Log global consensus distance @ E17B20 ===
consensus_distance=5769.268



=== Log clique consensus distance @ E17B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=74.923



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=5.2130 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2465 top1= 48.1771


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7334 top1= 44.7316

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0632 top1= 97.7273

=== Log global consensus distance @ E18B0 ===
consensus_distance=5997.669



=== Log clique consensus distance @ E18B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=75.817


[E18B10 |   4224/60000 (  7%) ] Loss: 0.0600 top1= 97.4432

=== Log global consensus distance @ E18B10 ===
consensus_distance=6230.448



=== Log clique consensus distance @ E18B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=76.693


[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0640 top1= 98.0114

=== Log global consensus distance @ E18B20 ===
consensus_distance=6467.797



=== Log clique consensus distance @ E18B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=77.838



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=5.5549 top1=  9.7556


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8216 top1= 48.0669


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5995 top1= 44.8518

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0778 top1= 97.4432

=== Log global consensus distance @ E19B0 ===
consensus_distance=6709.729



=== Log clique consensus distance @ E19B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=79.061


[E19B10 |   4224/60000 (  7%) ] Loss: 0.0576 top1= 98.0114

=== Log global consensus distance @ E19B10 ===
consensus_distance=6955.982



=== Log clique consensus distance @ E19B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=80.131


[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0711 top1= 97.1591

=== Log global consensus distance @ E19B20 ===
consensus_distance=7206.382



=== Log clique consensus distance @ E19B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=80.910



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=5.8361 top1=  9.7556


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.4213 top1= 48.5978


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2230 top1= 43.8502

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0513 top1= 98.2955

=== Log global consensus distance @ E20B0 ===
consensus_distance=7461.362



=== Log clique consensus distance @ E20B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=81.846


[E20B10 |   4224/60000 (  7%) ] Loss: 0.0674 top1= 97.4432

=== Log global consensus distance @ E20B10 ===
consensus_distance=7720.885



=== Log clique consensus distance @ E20B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=82.960


[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0677 top1= 98.0114

=== Log global consensus distance @ E20B20 ===
consensus_distance=7984.823



=== Log clique consensus distance @ E20B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=83.919



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=6.1505 top1=  9.7556


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.6280 top1= 48.9683


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.1228 top1= 45.5329

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0616 top1= 97.7273

=== Log global consensus distance @ E21B0 ===
consensus_distance=8253.173



=== Log clique consensus distance @ E21B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=85.094


[E21B10 |   4224/60000 (  7%) ] Loss: 0.0720 top1= 97.4432

=== Log global consensus distance @ E21B10 ===
consensus_distance=8526.049



=== Log clique consensus distance @ E21B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=86.331


[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0873 top1= 97.7273

=== Log global consensus distance @ E21B20 ===
consensus_distance=8803.005



=== Log clique consensus distance @ E21B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=87.144



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=6.6756 top1=  9.7556


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.8785 top1= 48.0569


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.0724 top1= 43.7800

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0617 top1= 97.4432

=== Log global consensus distance @ E22B0 ===
consensus_distance=9084.591



=== Log clique consensus distance @ E22B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=88.207


[E22B10 |   4224/60000 (  7%) ] Loss: 0.0983 top1= 96.0227

=== Log global consensus distance @ E22B10 ===
consensus_distance=9370.586



=== Log clique consensus distance @ E22B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=89.403


[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0524 top1= 98.2955

=== Log global consensus distance @ E22B20 ===
consensus_distance=9661.479



=== Log clique consensus distance @ E22B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=91.014



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=7.3362 top1=  9.7556


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.2077 top1= 48.1771


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.3237 top1= 44.3910

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0672 top1= 98.0114

=== Log global consensus distance @ E23B0 ===
consensus_distance=9956.552



=== Log clique consensus distance @ E23B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=92.424


[E23B10 |   4224/60000 (  7%) ] Loss: 0.0643 top1= 97.4432

=== Log global consensus distance @ E23B10 ===
consensus_distance=10255.915



=== Log clique consensus distance @ E23B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=93.678


[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0893 top1= 96.5909

=== Log global consensus distance @ E23B20 ===
consensus_distance=10559.646



=== Log clique consensus distance @ E23B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=94.826



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=8.1794 top1=  9.7556


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.7620 top1= 48.8682


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.2268 top1= 45.2424

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.1236 top1= 95.7386

=== Log global consensus distance @ E24B0 ===
consensus_distance=10867.964



=== Log clique consensus distance @ E24B0 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=96.222


[E24B10 |   4224/60000 (  7%) ] Loss: 0.0665 top1= 97.4432

=== Log global consensus distance @ E24B10 ===
consensus_distance=11180.765



=== Log clique consensus distance @ E24B10 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=97.781


[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0588 top1= 97.7273

=== Log global consensus distance @ E24B20 ===
consensus_distance=11497.914



=== Log clique consensus distance @ E24B20 ===
clique1_consensus_distance=0.026
clique2_consensus_distance=99.100



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=8.7912 top1=  9.7556


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=24.6480 top1= 48.4275


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.7108 top1= 45.6330

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.8778 top1= 95.4545

=== Log global consensus distance @ E25B0 ===
consensus_distance=11821.613



=== Log clique consensus distance @ E25B0 ===
clique1_consensus_distance=0.293
clique2_consensus_distance=103.133


[E25B10 |   4224/60000 (  7%) ] Loss: nan top1= 62.2159

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



=== Log clique consensus distance @ E25B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E25B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E25B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.5171 top1= 45.3125

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E26B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E26B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.6818

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



=== Log clique consensus distance @ E26B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E26B20 |   8064/60000 ( 13%) ] Loss: nan top1= 54.8295

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



=== Log clique consensus distance @ E26B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.4170 top1= 45.8133

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: nan top1= 56.5341

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



=== Log clique consensus distance @ E27B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E27B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.3977

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



=== Log clique consensus distance @ E27B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E27B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E27B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=13.2658 top1= 46.4844

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: nan top1= 57.1023

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



=== Log clique consensus distance @ E28B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E28B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.3977

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



=== Log clique consensus distance @ E28B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E28B20 |   8064/60000 ( 13%) ] Loss: nan top1= 54.8295

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



=== Log clique consensus distance @ E28B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.0812 top1= 45.7933

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: nan top1= 57.1023

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



=== Log clique consensus distance @ E29B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E29B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.3977

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



=== Log clique consensus distance @ E29B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E29B20 |   8064/60000 ( 13%) ] Loss: nan top1= 54.8295

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



=== Log clique consensus distance @ E29B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.0979 top1= 46.8750

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E30B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E30B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.6818

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



=== Log clique consensus distance @ E30B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E30B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E30B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=13.8145 top1= 46.9651

Train epoch 31
[E31B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E31B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E31B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.9659

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



=== Log clique consensus distance @ E31B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E31B20 |   8064/60000 ( 13%) ] Loss: nan top1= 54.8295

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



=== Log clique consensus distance @ E31B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7904 top1= 45.9435

Train epoch 32
[E32B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E32B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E32B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.9659

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



=== Log clique consensus distance @ E32B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E32B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E32B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.8882 top1= 46.6546

Train epoch 33
[E33B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E33B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E33B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.9659

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



=== Log clique consensus distance @ E33B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E33B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E33B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.6202 top1= 46.5044

Train epoch 34
[E34B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E34B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E34B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.9659

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



=== Log clique consensus distance @ E34B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E34B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E34B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.8901 top1= 46.6647

Train epoch 35
[E35B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E35B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E35B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.9659

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



=== Log clique consensus distance @ E35B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E35B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E35B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=13.3371 top1= 46.9852

Train epoch 36
[E36B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E36B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E36B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.9659

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



=== Log clique consensus distance @ E36B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E36B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E36B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=13.6151 top1= 46.8750

Train epoch 37
[E37B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E37B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E37B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.9659

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



=== Log clique consensus distance @ E37B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E37B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E37B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=13.7598 top1= 46.8450

Train epoch 38
[E38B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E38B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E38B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.9659

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



=== Log clique consensus distance @ E38B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E38B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E38B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=13.8514 top1= 46.8450

Train epoch 39
[E39B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E39B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E39B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.9659

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



=== Log clique consensus distance @ E39B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E39B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E39B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=13.9442 top1= 46.8550

Train epoch 40
[E40B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E40B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E40B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.9659

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



=== Log clique consensus distance @ E40B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E40B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E40B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=14.0268 top1= 46.8550

Train epoch 41
[E41B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E41B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E41B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.9659

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



=== Log clique consensus distance @ E41B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E41B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E41B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=14.1040 top1= 46.8550

Train epoch 42
[E42B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E42B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E42B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.9659

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



=== Log clique consensus distance @ E42B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E42B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E42B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=14.1746 top1= 46.8550

Train epoch 43
[E43B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E43B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E43B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.9659

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



=== Log clique consensus distance @ E43B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E43B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E43B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=14.2385 top1= 46.8550

Train epoch 44
[E44B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E44B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E44B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.9659

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



=== Log clique consensus distance @ E44B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E44B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E44B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=14.2905 top1= 46.8550

Train epoch 45
[E45B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E45B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E45B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.9659

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



=== Log clique consensus distance @ E45B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E45B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E45B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=14.3419 top1= 46.8550

Train epoch 46
[E46B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E46B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E46B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.9659

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



=== Log clique consensus distance @ E46B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E46B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E46B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=14.3913 top1= 46.8550

Train epoch 47
[E47B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E47B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E47B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.9659

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



=== Log clique consensus distance @ E47B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E47B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E47B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=14.4387 top1= 46.8550

Train epoch 48
[E48B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E48B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E48B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.9659

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



=== Log clique consensus distance @ E48B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E48B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E48B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=14.4851 top1= 46.8450

Train epoch 49
[E49B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E49B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E49B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.9659

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



=== Log clique consensus distance @ E49B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E49B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E49B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=14.5279 top1= 46.8450

Train epoch 50
[E50B0  |    384/60000 (  1%) ] Loss: nan top1= 57.3864

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



=== Log clique consensus distance @ E50B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E50B10 |   4224/60000 (  7%) ] Loss: nan top1= 55.9659

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



=== Log clique consensus distance @ E50B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E50B20 |   8064/60000 ( 13%) ] Loss: nan top1= 55.1136

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



=== Log clique consensus distance @ E50B20 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=nan top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=14.5694 top1= 46.8450

