
=== 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 0.417 0.25 ]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.25  0.75 ]]


[E 1B10 |   4224/60000 (  7%) ] Loss: 0.9390 top1= 69.0341

=== Log global consensus distance @ E1B10 ===
consensus_distance=1.125



=== Log clique consensus distance @ E1B10 ===
clique1_consensus_distance=0.036
clique2_consensus_distance=1.624


[E 1B20 |   8064/60000 ( 13%) ] Loss: 1.0216 top1= 82.6705

=== Log global consensus distance @ E1B20 ===
consensus_distance=6.378



=== Log clique consensus distance @ E1B20 ===
clique1_consensus_distance=0.294
clique2_consensus_distance=6.232



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2953 top1= 12.6803


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4381 top1= 39.7937


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0853 top1= 41.4163

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.5793 top1= 88.0682

=== Log global consensus distance @ E2B0 ===
consensus_distance=8.239



=== Log clique consensus distance @ E2B0 ===
clique1_consensus_distance=0.376
clique2_consensus_distance=9.833


[E 2B10 |   4224/60000 (  7%) ] Loss: 0.4061 top1= 89.2045

=== Log global consensus distance @ E2B10 ===
consensus_distance=8.629



=== Log clique consensus distance @ E2B10 ===
clique1_consensus_distance=0.367
clique2_consensus_distance=11.876


[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.3373 top1= 89.2045

=== Log global consensus distance @ E2B20 ===
consensus_distance=8.392



=== Log clique consensus distance @ E2B20 ===
clique1_consensus_distance=0.343
clique2_consensus_distance=11.898



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4300 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3442 top1= 37.7504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6583 top1= 37.5100

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.3152 top1= 92.0455

=== Log global consensus distance @ E3B0 ===
consensus_distance=8.111



=== Log clique consensus distance @ E3B0 ===
clique1_consensus_distance=0.328
clique2_consensus_distance=11.294


[E 3B10 |   4224/60000 (  7%) ] Loss: 0.3090 top1= 88.9205

=== Log global consensus distance @ E3B10 ===
consensus_distance=7.988



=== Log clique consensus distance @ E3B10 ===
clique1_consensus_distance=0.321
clique2_consensus_distance=10.980


[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.4253 top1= 86.3636

=== Log global consensus distance @ E3B20 ===
consensus_distance=7.970



=== Log clique consensus distance @ E3B20 ===
clique1_consensus_distance=0.320
clique2_consensus_distance=10.912



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5865 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2107 top1= 37.6402


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4020 top1= 35.6671

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.3740 top1= 88.9205

=== Log global consensus distance @ E4B0 ===
consensus_distance=8.234



=== Log clique consensus distance @ E4B0 ===
clique1_consensus_distance=0.332
clique2_consensus_distance=11.419


[E 4B10 |   4224/60000 (  7%) ] Loss: 0.3277 top1= 90.6250

=== Log global consensus distance @ E4B10 ===
consensus_distance=8.260



=== Log clique consensus distance @ E4B10 ===
clique1_consensus_distance=0.329
clique2_consensus_distance=11.536


[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.5775 top1= 84.6591

=== Log global consensus distance @ E4B20 ===
consensus_distance=23.820



=== Log clique consensus distance @ E4B20 ===
clique1_consensus_distance=0.667
clique2_consensus_distance=12.632



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.6155 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3970 top1= 18.1190


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7308 top1= 26.6927

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 4.7642 top1= 54.2614

=== Log global consensus distance @ E5B0 ===
consensus_distance=52.664



=== Log clique consensus distance @ E5B0 ===
clique1_consensus_distance=0.656
clique2_consensus_distance=20.539


[E 5B10 |   4224/60000 (  7%) ] Loss: 2.9528 top1= 25.2841

=== Log global consensus distance @ E5B10 ===
consensus_distance=62.693



=== Log clique consensus distance @ E5B10 ===
clique1_consensus_distance=0.647
clique2_consensus_distance=40.967


[E 5B20 |   8064/60000 ( 13%) ] Loss: 2.2352 top1= 18.7500

=== Log global consensus distance @ E5B20 ===
consensus_distance=60.926



=== Log clique consensus distance @ E5B20 ===
clique1_consensus_distance=0.642
clique2_consensus_distance=113.526



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.4959 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3387 top1= 17.9587


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5205 top1=  9.7456

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 2.2110 top1= 15.6250

=== Log global consensus distance @ E6B0 ===
consensus_distance=43.529



=== Log clique consensus distance @ E6B0 ===
clique1_consensus_distance=0.636
clique2_consensus_distance=124.692


[E 6B10 |   4224/60000 (  7%) ] Loss: 2.1758 top1= 15.3409

=== Log global consensus distance @ E6B10 ===
consensus_distance=27.813



=== Log clique consensus distance @ E6B10 ===
clique1_consensus_distance=0.318
clique2_consensus_distance=91.829


[E 6B20 |   8064/60000 ( 13%) ] Loss: 2.1215 top1= 15.3409

=== Log global consensus distance @ E6B20 ===
consensus_distance=18.513



=== Log clique consensus distance @ E6B20 ===
clique1_consensus_distance=0.244
clique2_consensus_distance=56.893



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.5000 top1= 10.3666


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3089 top1= 18.3093


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5202 top1=  9.7456

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 2.1392 top1= 14.7727

=== Log global consensus distance @ E7B0 ===
consensus_distance=13.271



=== Log clique consensus distance @ E7B0 ===
clique1_consensus_distance=0.244
clique2_consensus_distance=34.389


[E 7B10 |   4224/60000 (  7%) ] Loss: 2.2301 top1= 15.6250

=== Log global consensus distance @ E7B10 ===
consensus_distance=10.278



=== Log clique consensus distance @ E7B10 ===
clique1_consensus_distance=0.257
clique2_consensus_distance=21.124


[E 7B20 |   8064/60000 ( 13%) ] Loss: 2.4306 top1= 10.7955

=== Log global consensus distance @ E7B20 ===
consensus_distance=8.638



=== Log clique consensus distance @ E7B20 ===
clique1_consensus_distance=0.280
clique2_consensus_distance=13.588



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.8972 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7900 top1=  9.7456


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8160 top1=  9.7456

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 8.0850 top1=  9.6591

=== Log global consensus distance @ E8B0 ===
consensus_distance=9.044



=== Log clique consensus distance @ E8B0 ===
clique1_consensus_distance=0.411
clique2_consensus_distance=9.486


[E 8B10 |   4224/60000 (  7%) ] Loss: 3.0326 top1= 11.3636

=== Log global consensus distance @ E8B10 ===
consensus_distance=57.301



=== Log clique consensus distance @ E8B10 ===
clique1_consensus_distance=0.637
clique2_consensus_distance=9.058


[E 8B20 |   8064/60000 ( 13%) ] Loss: nan top1=  3.1250

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



=== Log clique consensus distance @ E8B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=10.976



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5389 top1=  9.7456


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5525 top1=  9.7456

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: nan top1=  2.5568

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



=== Log clique consensus distance @ E9B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=14.069


[E 9B10 |   4224/60000 (  7%) ] Loss: nan top1=  3.9773

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



=== Log clique consensus distance @ E9B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=17.356


[E 9B20 |   8064/60000 ( 13%) ] Loss: nan top1= 16.1932

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



=== Log clique consensus distance @ E9B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=20.662



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5455 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5279 top1=  9.7456

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: nan top1= 15.0568

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



=== Log clique consensus distance @ E10B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=23.938


[E10B10 |   4224/60000 (  7%) ] Loss: nan top1= 22.7273

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



=== Log clique consensus distance @ E10B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=27.094


[E10B20 |   8064/60000 ( 13%) ] Loss: nan top1= 24.4318

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



=== Log clique consensus distance @ E10B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=30.093



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6381 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6105 top1= 10.2865

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: nan top1= 23.5795

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



=== Log clique consensus distance @ E11B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=32.994


[E11B10 |   4224/60000 (  7%) ] Loss: nan top1= 22.7273

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



=== Log clique consensus distance @ E11B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=35.751


[E11B20 |   8064/60000 ( 13%) ] Loss: nan top1= 24.4318

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



=== Log clique consensus distance @ E11B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=38.354



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7325 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7000 top1= 10.2865

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: nan top1= 23.5795

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



=== Log clique consensus distance @ E12B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=40.883


[E12B10 |   4224/60000 (  7%) ] Loss: nan top1= 22.7273

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



=== Log clique consensus distance @ E12B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=43.294


[E12B20 |   8064/60000 ( 13%) ] Loss: nan top1= 24.4318

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



=== Log clique consensus distance @ E12B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=45.573



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8177 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7805 top1= 10.2865

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: nan top1= 23.5795

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



=== Log clique consensus distance @ E13B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=47.806


[E13B10 |   4224/60000 (  7%) ] Loss: nan top1= 22.7273

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



=== Log clique consensus distance @ E13B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=49.943


[E13B20 |   8064/60000 ( 13%) ] Loss: nan top1= 24.4318

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



=== Log clique consensus distance @ E13B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=51.968



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8933 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8508 top1= 10.2865

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: nan top1= 23.5795

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



=== Log clique consensus distance @ E14B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=53.968


[E14B10 |   4224/60000 (  7%) ] Loss: nan top1= 22.7273

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



=== Log clique consensus distance @ E14B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=55.889


[E14B20 |   8064/60000 ( 13%) ] Loss: nan top1= 24.4318

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



=== Log clique consensus distance @ E14B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=57.713



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9604 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9123 top1= 10.2865

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: nan top1= 23.5795

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



=== Log clique consensus distance @ E15B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=59.527


[E15B10 |   4224/60000 (  7%) ] Loss: nan top1= 22.7273

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



=== Log clique consensus distance @ E15B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=61.276


[E15B20 |   8064/60000 ( 13%) ] Loss: nan top1= 24.4318

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



=== Log clique consensus distance @ E15B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=62.937



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0203 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9667 top1= 10.2865

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: nan top1= 23.5795

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



=== Log clique consensus distance @ E16B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=64.599


[E16B10 |   4224/60000 (  7%) ] Loss: nan top1= 22.7273

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



=== Log clique consensus distance @ E16B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=66.206


[E16B20 |   8064/60000 ( 13%) ] Loss: nan top1= 24.4318

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



=== Log clique consensus distance @ E16B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=67.734



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0743 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0152 top1= 10.2865

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: nan top1= 23.5795

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



=== Log clique consensus distance @ E17B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=69.271


[E17B10 |   4224/60000 (  7%) ] Loss: nan top1= 22.7273

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



=== Log clique consensus distance @ E17B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=70.760


[E17B20 |   8064/60000 ( 13%) ] Loss: nan top1= 24.4318

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



=== Log clique consensus distance @ E17B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=72.176



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1232 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0589 top1= 10.2865

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: nan top1= 23.5795

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



=== Log clique consensus distance @ E18B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=73.607


[E18B10 |   4224/60000 (  7%) ] Loss: nan top1= 22.7273

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



=== Log clique consensus distance @ E18B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=74.996


[E18B20 |   8064/60000 ( 13%) ] Loss: nan top1= 24.4318

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



=== Log clique consensus distance @ E18B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=76.317



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1679 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0988 top1= 10.2865

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: nan top1= 23.5795

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



=== Log clique consensus distance @ E19B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=77.658


[E19B10 |   4224/60000 (  7%) ] Loss: nan top1= 22.7273

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



=== Log clique consensus distance @ E19B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=78.961


[E19B20 |   8064/60000 ( 13%) ] Loss: nan top1= 24.4318

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



=== Log clique consensus distance @ E19B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=80.200



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2090 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1353 top1= 10.2865

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: nan top1= 23.5795

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



=== Log clique consensus distance @ E20B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=81.463


[E20B10 |   4224/60000 (  7%) ] Loss: nan top1= 22.7273

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



=== Log clique consensus distance @ E20B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=82.692


[E20B20 |   8064/60000 ( 13%) ] Loss: nan top1= 24.4318

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



=== Log clique consensus distance @ E20B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=83.859



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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2469 top1= 11.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1691 top1= 10.2865

