
=== Start adding workers ===
=> Add worker SGDMWorker(index=0, momentum=0.0)
=> Add worker SGDMWorker(index=1, momentum=0.0)
=> Add worker SGDMWorker(index=2, momentum=0.0)
=> Add worker SGDMWorker(index=3, momentum=0.0)
=> Add worker SGDMWorker(index=4, momentum=0.0)
=> Add worker SGDMWorker(index=5, momentum=0.0)
=> Add worker SGDMWorker(index=6, momentum=0.0)
=> Add worker SGDMWorker(index=7, momentum=0.0)
=> Add worker SGDMWorker(index=8, momentum=0.0)
=> Add worker SGDMWorker(index=9, momentum=0.0)
=> Add worker SGDMWorker(index=10, momentum=0.0)
=> Add worker ByzantineWorker(index=11)
=> Add worker ByzantineWorker(index=12)
=> Add worker ByzantineWorker(index=13)

=== Start adding graph ===
TwoCliquesWithByzantine(m=5,b=3)

Train epoch 1
[E 1B0  |    448/60000 (  1%) ] Loss: 2.3005 top1=  9.0909

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([9, 4, 6, 0, 0], device='cuda:0')
Worker 1 has targets: tensor([3, 0, 5, 1, 7], device='cuda:0')
Worker 2 has targets: tensor([5, 6, 5, 4, 9], device='cuda:0')
Worker 3 has targets: tensor([4, 8, 4, 4, 2], device='cuda:0')
Worker 4 has targets: tensor([7, 9, 7, 0, 6], device='cuda:0')
Worker 5 has targets: tensor([4, 9, 4, 0, 8], device='cuda:0')
Worker 6 has targets: tensor([9, 3, 1, 7, 7], device='cuda:0')
Worker 7 has targets: tensor([6, 1, 8, 0, 7], device='cuda:0')
Worker 8 has targets: tensor([8, 3, 7, 6, 2], device='cuda:0')
Worker 9 has targets: tensor([8, 2, 3, 7, 8], device='cuda:0')
Worker 10 has targets: tensor([7, 5, 3, 8, 8], device='cuda:0')
Worker 11 has targets: tensor([4, 0, 5, 9, 5], device='cuda:0')
Worker 12 has targets: tensor([8, 2, 1, 2, 7], device='cuda:0')
Worker 13 has targets: tensor([9, 1, 6, 1, 1], device='cuda:0')



=== Log global consensus distance @ E1B0 ===
consensus_distance=0.000



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


[E 1B10 |   4928/60000 (  8%) ] Loss: 2.2809 top1= 14.4886

=== Log global consensus distance @ E1B10 ===
consensus_distance=0.000



=== Log clique consensus distance @ E1B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=0.000


[E 1B20 |   9408/60000 ( 16%) ] Loss: 2.2901 top1= 11.6477

=== Log global consensus distance @ E1B20 ===
consensus_distance=0.000



=== Log clique consensus distance @ E1B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=0.000



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2796 top1= 17.4379


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2774 top1= 17.9487


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2773 top1= 17.5080

Train epoch 2
[E 2B0  |    448/60000 (  1%) ] Loss: 2.2633 top1= 15.9091

=== Log global consensus distance @ E2B0 ===
consensus_distance=0.003



=== Log clique consensus distance @ E2B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=0.000


[E 2B10 |   4928/60000 (  8%) ] Loss: 2.2748 top1= 21.0227

=== Log global consensus distance @ E2B10 ===
consensus_distance=0.030



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


[E 2B20 |   9408/60000 ( 16%) ] Loss: 2.2714 top1= 19.6023

=== Log global consensus distance @ E2B20 ===
consensus_distance=0.275



=== Log clique consensus distance @ E2B20 ===
clique1_consensus_distance=0.012
clique2_consensus_distance=0.012



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4852 top1= 19.1907


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3023 top1= 24.1987


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3034 top1= 24.1186

Train epoch 3
[E 3B0  |    448/60000 (  1%) ] Loss: 2.3983 top1= 19.3182

=== Log global consensus distance @ E3B0 ===
consensus_distance=2.510



=== Log clique consensus distance @ E3B0 ===
clique1_consensus_distance=0.110
clique2_consensus_distance=0.110


[E 3B10 |   4928/60000 (  8%) ] Loss: 3.3411 top1= 19.6023

=== Log global consensus distance @ E3B10 ===
consensus_distance=20.954



=== Log clique consensus distance @ E3B10 ===
clique1_consensus_distance=0.639
clique2_consensus_distance=0.640


[E 3B20 |   9408/60000 ( 16%) ] Loss: 3.6945 top1= 24.4318

=== Log global consensus distance @ E3B20 ===
consensus_distance=70.174



=== Log clique consensus distance @ E3B20 ===
clique1_consensus_distance=0.640
clique2_consensus_distance=0.640



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=4.4579 top1= 26.6627


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9986 top1= 36.4283


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9978 top1= 36.4383

Train epoch 4
[E 4B0  |    448/60000 (  1%) ] Loss: 6.0903 top1= 19.0341

=== Log global consensus distance @ E4B0 ===
consensus_distance=148.695



=== Log clique consensus distance @ E4B0 ===
clique1_consensus_distance=0.640
clique2_consensus_distance=0.640


[E 4B10 |   4928/60000 (  8%) ] Loss: 6.1881 top1= 22.7273

=== Log global consensus distance @ E4B10 ===
consensus_distance=256.584



=== Log clique consensus distance @ E4B10 ===
clique1_consensus_distance=0.640
clique2_consensus_distance=0.641


[E 4B20 |   9408/60000 ( 16%) ] Loss: 4.6710 top1= 29.2614

=== Log global consensus distance @ E4B20 ===
consensus_distance=393.807



=== Log clique consensus distance @ E4B20 ===
clique1_consensus_distance=0.640
clique2_consensus_distance=0.641



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=7.3257 top1= 29.2067


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8131 top1= 42.5881


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8351 top1= 42.0873

Train epoch 5
[E 5B0  |    448/60000 (  1%) ] Loss: 6.7245 top1= 23.0114

=== Log global consensus distance @ E5B0 ===
consensus_distance=560.399



=== Log clique consensus distance @ E5B0 ===
clique1_consensus_distance=0.640
clique2_consensus_distance=0.642


[E 5B10 |   4928/60000 (  8%) ] Loss: 4.9549 top1= 28.1250

=== Log global consensus distance @ E5B10 ===
consensus_distance=756.431



=== Log clique consensus distance @ E5B10 ===
clique1_consensus_distance=0.640
clique2_consensus_distance=0.643


[E 5B20 |   9408/60000 ( 16%) ] Loss: 4.4786 top1= 34.0909

=== Log global consensus distance @ E5B20 ===
consensus_distance=981.792



=== Log clique consensus distance @ E5B20 ===
clique1_consensus_distance=0.640
clique2_consensus_distance=0.645



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=5.4867 top1= 41.8169


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7250 top1= 46.6146


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7534 top1= 45.8534

Train epoch 6
[E 6B0  |    448/60000 (  1%) ] Loss: 7.1597 top1= 26.9886

=== Log global consensus distance @ E6B0 ===
consensus_distance=1236.535



=== Log clique consensus distance @ E6B0 ===
clique1_consensus_distance=0.640
clique2_consensus_distance=0.646


[E 6B10 |   4928/60000 (  8%) ] Loss: 15.4734 top1= 32.1023

=== Log global consensus distance @ E6B10 ===
consensus_distance=1520.933



=== Log clique consensus distance @ E6B10 ===
clique1_consensus_distance=0.640
clique2_consensus_distance=0.648


[E 6B20 |   9408/60000 ( 16%) ] Loss: 35.6599 top1= 34.9432

=== Log global consensus distance @ E6B20 ===
consensus_distance=1834.310



=== Log clique consensus distance @ E6B20 ===
clique1_consensus_distance=0.640
clique2_consensus_distance=0.650



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=9.4786 top1= 26.9531


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6706 top1= 49.0385


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7033 top1= 47.3357

Train epoch 7
[E 7B0  |    448/60000 (  1%) ] Loss: 12.6668 top1= 28.1250

=== Log global consensus distance @ E7B0 ===
consensus_distance=2176.920



=== Log clique consensus distance @ E7B0 ===
clique1_consensus_distance=0.640
clique2_consensus_distance=0.652


[E 7B10 |   4928/60000 (  8%) ] Loss: 8.0123 top1= 32.1023

=== Log global consensus distance @ E7B10 ===
consensus_distance=2549.052



=== Log clique consensus distance @ E7B10 ===
clique1_consensus_distance=0.640
clique2_consensus_distance=0.654


[E 7B20 |   9408/60000 ( 16%) ] Loss: 6.3487 top1= 38.0682

=== Log global consensus distance @ E7B20 ===
consensus_distance=2950.563



=== Log clique consensus distance @ E7B20 ===
clique1_consensus_distance=0.640
clique2_consensus_distance=0.656



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=102.5749 top1= 14.3730


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5408 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5544 top1= 48.9984

Train epoch 8
[E 8B0  |    448/60000 (  1%) ] Loss: 160.3513 top1= 27.2727

=== Log global consensus distance @ E8B0 ===
consensus_distance=3381.262



=== Log clique consensus distance @ E8B0 ===
clique1_consensus_distance=0.640
clique2_consensus_distance=0.658


[E 8B10 |   4928/60000 (  8%) ] Loss: 9.0178 top1= 33.8068

=== Log global consensus distance @ E8B10 ===
consensus_distance=3841.357



=== Log clique consensus distance @ E8B10 ===
clique1_consensus_distance=0.640
clique2_consensus_distance=0.659


[E 8B20 |   9408/60000 ( 16%) ] Loss: nan top1= 26.9886

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



=== Log clique consensus distance @ E8B20 ===
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=nan top1=  9.8057

Train epoch 9
[E 9B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



=== Log clique consensus distance @ E9B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E 9B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



=== Log clique consensus distance @ E9B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E 9B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

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



=== Log clique consensus distance @ E9B20 ===
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=nan top1=  9.8057

Train epoch 10
[E10B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



=== Log clique consensus distance @ E10B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E10B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



=== Log clique consensus distance @ E10B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E10B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

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



=== Log clique consensus distance @ E10B20 ===
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=nan top1=  9.8057

Train epoch 11
[E11B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



=== Log clique consensus distance @ E11B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E11B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



=== Log clique consensus distance @ E11B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E11B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

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



=== Log clique consensus distance @ E11B20 ===
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=nan top1=  9.8057

Train epoch 12
[E12B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



=== Log clique consensus distance @ E12B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E12B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



=== Log clique consensus distance @ E12B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E12B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

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



=== Log clique consensus distance @ E12B20 ===
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=nan top1=  9.8057

Train epoch 13
[E13B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



=== Log clique consensus distance @ E13B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E13B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



=== Log clique consensus distance @ E13B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E13B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

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



=== Log clique consensus distance @ E13B20 ===
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=nan top1=  9.8057

Train epoch 14
[E14B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



=== Log clique consensus distance @ E14B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E14B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



=== Log clique consensus distance @ E14B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E14B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

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



=== Log clique consensus distance @ E14B20 ===
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=nan top1=  9.8057

Train epoch 15
[E15B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



=== Log clique consensus distance @ E15B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E15B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



=== Log clique consensus distance @ E15B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E15B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

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



=== Log clique consensus distance @ E15B20 ===
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=nan top1=  9.8057

Train epoch 16
[E16B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



=== Log clique consensus distance @ E16B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E16B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



=== Log clique consensus distance @ E16B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E16B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

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



=== Log clique consensus distance @ E16B20 ===
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=nan top1=  9.8057

Train epoch 17
[E17B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



=== Log clique consensus distance @ E17B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E17B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



=== Log clique consensus distance @ E17B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E17B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

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



=== Log clique consensus distance @ E17B20 ===
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=nan top1=  9.8057

Train epoch 18
[E18B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



=== Log clique consensus distance @ E18B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E18B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



=== Log clique consensus distance @ E18B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E18B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

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



=== Log clique consensus distance @ E18B20 ===
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=nan top1=  9.8057

Train epoch 19
[E19B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



=== Log clique consensus distance @ E19B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E19B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



=== Log clique consensus distance @ E19B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E19B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

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



=== Log clique consensus distance @ E19B20 ===
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=nan top1=  9.8057

Train epoch 20
[E20B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



=== Log clique consensus distance @ E20B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E20B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



=== Log clique consensus distance @ E20B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E20B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

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



=== Log clique consensus distance @ E20B20 ===
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=nan top1=  9.8057

Train epoch 21
[E21B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



=== Log clique consensus distance @ E21B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E21B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



=== Log clique consensus distance @ E21B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E21B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

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



=== Log clique consensus distance @ E21B20 ===
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=nan top1=  9.8057

Train epoch 22
[E22B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



=== Log clique consensus distance @ E22B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E22B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



=== Log clique consensus distance @ E22B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E22B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

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



=== Log clique consensus distance @ E22B20 ===
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=nan top1=  9.8057

Train epoch 23
[E23B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



=== Log clique consensus distance @ E23B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E23B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



=== Log clique consensus distance @ E23B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E23B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

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



=== Log clique consensus distance @ E23B20 ===
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=nan top1=  9.8057

Train epoch 24
[E24B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



=== Log clique consensus distance @ E24B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E24B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



=== Log clique consensus distance @ E24B10 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E24B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

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



=== Log clique consensus distance @ E24B20 ===
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=nan top1=  9.8057

Train epoch 25
[E25B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



=== Log clique consensus distance @ E25B0 ===
clique1_consensus_distance=nan
clique2_consensus_distance=nan


[E25B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



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


[E25B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

=== 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=nan top1=  9.8057

Train epoch 26
[E26B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



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


[E26B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



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


[E26B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

=== 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=nan top1=  9.8057

Train epoch 27
[E27B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



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


[E27B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



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


[E27B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

=== 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=nan top1=  9.8057

Train epoch 28
[E28B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



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


[E28B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



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


[E28B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

=== 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=nan top1=  9.8057

Train epoch 29
[E29B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



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


[E29B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



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


[E29B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

=== 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=nan top1=  9.8057

Train epoch 30
[E30B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



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


[E30B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



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


[E30B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

=== 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=nan top1=  9.8057

Train epoch 31
[E31B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



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


[E31B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



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


[E31B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

=== 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=nan top1=  9.8057

Train epoch 32
[E32B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



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


[E32B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



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


[E32B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

=== 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=nan top1=  9.8057

Train epoch 33
[E33B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



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


[E33B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



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


[E33B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

=== 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=nan top1=  9.8057

Train epoch 34
[E34B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



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


[E34B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



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


[E34B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

=== 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=nan top1=  9.8057

Train epoch 35
[E35B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



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


[E35B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



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


[E35B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

=== 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=nan top1=  9.8057

Train epoch 36
[E36B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



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


[E36B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



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


[E36B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

=== 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=nan top1=  9.8057

Train epoch 37
[E37B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



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


[E37B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



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


[E37B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

=== 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=nan top1=  9.8057

Train epoch 38
[E38B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



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


[E38B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



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


[E38B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

=== 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=nan top1=  9.8057

Train epoch 39
[E39B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



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


[E39B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



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


[E39B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

=== 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=nan top1=  9.8057

Train epoch 40
[E40B0  |    448/60000 (  1%) ] Loss: nan top1=  7.9545

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



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


[E40B10 |   4928/60000 (  8%) ] Loss: nan top1= 10.5114

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



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


[E40B20 |   9408/60000 ( 16%) ] Loss: nan top1=  9.6591

=== 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=nan top1=  9.8057

