
=== 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=0.000



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


[E 1B10 |   4224/60000 (  7%) ] Loss: 1.9616 top1= 42.6136

=== Log global consensus distance @ E1B10 ===
consensus_distance=0.030



=== Log clique consensus distance @ E1B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=0.033


[E 1B20 |   8064/60000 ( 13%) ] Loss: 2.0196 top1= 26.9886

=== Log global consensus distance @ E1B20 ===
consensus_distance=0.384



=== Log clique consensus distance @ E1B20 ===
clique1_consensus_distance=0.016
clique2_consensus_distance=0.184



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=27.8291 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2120 top1= 15.8854


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4870 top1= 17.1675

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 5.3532 top1= 11.3636

=== Log global consensus distance @ E2B0 ===
consensus_distance=3.919



=== Log clique consensus distance @ E2B0 ===
clique1_consensus_distance=0.177
clique2_consensus_distance=0.786


[E 2B10 |   4224/60000 (  7%) ] Loss: 2.0967 top1= 23.8636

=== Log global consensus distance @ E2B10 ===
consensus_distance=5.801



=== Log clique consensus distance @ E2B10 ===
clique1_consensus_distance=0.301
clique2_consensus_distance=2.016


[E 2B20 |   8064/60000 ( 13%) ] Loss: 1.9091 top1= 28.4091

=== Log global consensus distance @ E2B20 ===
consensus_distance=5.920



=== Log clique consensus distance @ E2B20 ===
clique1_consensus_distance=0.305
clique2_consensus_distance=2.255



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=4.9260 top1= 16.1558


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4354 top1=  2.1334


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7546 top1=  8.8341

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 1.7063 top1= 28.9773

=== Log global consensus distance @ E3B0 ===
consensus_distance=5.839



=== Log clique consensus distance @ E3B0 ===
clique1_consensus_distance=0.303
clique2_consensus_distance=1.975


[E 3B10 |   4224/60000 (  7%) ] Loss: 1.7777 top1= 31.2500

=== Log global consensus distance @ E3B10 ===
consensus_distance=5.749



=== Log clique consensus distance @ E3B10 ===
clique1_consensus_distance=0.301
clique2_consensus_distance=1.646


[E 3B20 |   8064/60000 ( 13%) ] Loss: 1.7134 top1= 39.4886

=== Log global consensus distance @ E3B20 ===
consensus_distance=5.685



=== Log clique consensus distance @ E3B20 ===
clique1_consensus_distance=0.299
clique2_consensus_distance=1.434



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=11.1901 top1= 18.2592


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6859 top1= 12.9908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0406 top1=  9.0845

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 1.7358 top1= 38.9205

=== Log global consensus distance @ E4B0 ===
consensus_distance=5.655



=== Log clique consensus distance @ E4B0 ===
clique1_consensus_distance=0.298
clique2_consensus_distance=1.373


[E 4B10 |   4224/60000 (  7%) ] Loss: 1.8998 top1= 40.3409

=== Log global consensus distance @ E4B10 ===
consensus_distance=5.662



=== Log clique consensus distance @ E4B10 ===
clique1_consensus_distance=0.298
clique2_consensus_distance=1.410


[E 4B20 |   8064/60000 ( 13%) ] Loss: 2.1254 top1= 35.7955

=== Log global consensus distance @ E4B20 ===
consensus_distance=5.679



=== Log clique consensus distance @ E4B20 ===
clique1_consensus_distance=0.298
clique2_consensus_distance=1.497



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=30.6398 top1= 18.7500


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2316 top1= 19.1807


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8048 top1= 11.2881

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 2.3315 top1= 35.5114

=== Log global consensus distance @ E5B0 ===
consensus_distance=5.700



=== Log clique consensus distance @ E5B0 ===
clique1_consensus_distance=0.297
clique2_consensus_distance=1.647


[E 5B10 |   4224/60000 (  7%) ] Loss: 39.1304 top1= 34.3750

=== Log global consensus distance @ E5B10 ===
consensus_distance=7.798



=== Log clique consensus distance @ E5B10 ===
clique1_consensus_distance=0.362
clique2_consensus_distance=9.835


[E 5B20 |   8064/60000 ( 13%) ] Loss: 338.4654 top1= 30.3977

=== Log global consensus distance @ E5B20 ===
consensus_distance=26.795



=== Log clique consensus distance @ E5B20 ===
clique1_consensus_distance=0.768
clique2_consensus_distance=87.581



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=58.9158 top1= 12.1294


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6611 top1=  9.3750


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=44.3237 top1= 10.3866

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 7.4173 top1= 35.7955

=== Log global consensus distance @ E6B0 ===
consensus_distance=184.434



=== Log clique consensus distance @ E6B0 ===
clique1_consensus_distance=0.895
clique2_consensus_distance=705.213


[E 6B10 |   4224/60000 (  7%) ] Loss: 11.6264 top1= 34.9432

=== Log global consensus distance @ E6B10 ===
consensus_distance=297.574



=== Log clique consensus distance @ E6B10 ===
clique1_consensus_distance=0.725
clique2_consensus_distance=1146.302


[E 6B20 |   8064/60000 ( 13%) ] Loss: 3.5926 top1= 34.6591

=== Log global consensus distance @ E6B20 ===
consensus_distance=309.933



=== Log clique consensus distance @ E6B20 ===
clique1_consensus_distance=0.667
clique2_consensus_distance=1213.668



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.9491 top1= 18.1891


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.4341 top1= 14.2127


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7763 top1= 33.0929

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 1.4351 top1= 51.9886

=== Log global consensus distance @ E7B0 ===
consensus_distance=278.707



=== Log clique consensus distance @ E7B0 ===
clique1_consensus_distance=0.649
clique2_consensus_distance=1073.644


[E 7B10 |   4224/60000 (  7%) ] Loss: 1.3959 top1= 57.1023

=== Log global consensus distance @ E7B10 ===
consensus_distance=232.940



=== Log clique consensus distance @ E7B10 ===
clique1_consensus_distance=0.643
clique2_consensus_distance=899.603


[E 7B20 |   8064/60000 ( 13%) ] Loss: 1.2334 top1= 59.6591

=== Log global consensus distance @ E7B20 ===
consensus_distance=199.927



=== Log clique consensus distance @ E7B20 ===
clique1_consensus_distance=0.641
clique2_consensus_distance=761.946



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.9702 top1=  9.7857


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1451 top1=  9.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2160 top1= 28.4856

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 1.4326 top1= 51.9886

=== Log global consensus distance @ E8B0 ===
consensus_distance=173.289



=== Log clique consensus distance @ E8B0 ===
clique1_consensus_distance=0.640
clique2_consensus_distance=651.694


[E 8B10 |   4224/60000 (  7%) ] Loss: 1.4370 top1= 50.5682

=== Log global consensus distance @ E8B10 ===
consensus_distance=148.977



=== Log clique consensus distance @ E8B10 ===
clique1_consensus_distance=0.640
clique2_consensus_distance=554.725


[E 8B20 |   8064/60000 ( 13%) ] Loss: 1.7294 top1= 45.1705

=== Log global consensus distance @ E8B20 ===
consensus_distance=126.519



=== Log clique consensus distance @ E8B20 ===
clique1_consensus_distance=0.640
clique2_consensus_distance=466.676



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.9317 top1= 11.8890


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1198 top1=  7.1014


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8853 top1= 32.7023

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 1.5668 top1= 55.3977

=== Log global consensus distance @ E9B0 ===
consensus_distance=105.906



=== Log clique consensus distance @ E9B0 ===
clique1_consensus_distance=0.640
clique2_consensus_distance=386.507


[E 9B10 |   4224/60000 (  7%) ] Loss: 1.9332 top1= 41.4773

=== Log global consensus distance @ E9B10 ===
consensus_distance=87.150



=== Log clique consensus distance @ E9B10 ===
clique1_consensus_distance=0.639
clique2_consensus_distance=313.981


[E 9B20 |   8064/60000 ( 13%) ] Loss: 2.0047 top1= 35.5114

=== Log global consensus distance @ E9B20 ===
consensus_distance=70.252



=== Log clique consensus distance @ E9B20 ===
clique1_consensus_distance=0.639
clique2_consensus_distance=248.965



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.6053 top1= 17.7083


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2877 top1= 13.8622


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8890 top1= 24.3189

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 1.9414 top1= 38.6364

=== Log global consensus distance @ E10B0 ===
consensus_distance=55.185



=== Log clique consensus distance @ E10B0 ===
clique1_consensus_distance=0.639
clique2_consensus_distance=191.417


[E10B10 |   4224/60000 (  7%) ] Loss: 1.9166 top1= 44.6023

=== Log global consensus distance @ E10B10 ===
consensus_distance=41.975



=== Log clique consensus distance @ E10B10 ===
clique1_consensus_distance=0.639
clique2_consensus_distance=141.279


[E10B20 |   8064/60000 ( 13%) ] Loss: 1.9823 top1= 42.6136

=== Log global consensus distance @ E10B20 ===
consensus_distance=30.625



=== Log clique consensus distance @ E10B20 ===
clique1_consensus_distance=0.639
clique2_consensus_distance=98.419



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.0239 top1= 10.5769


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6438 top1=  9.9058


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8903 top1= 25.4307

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 2.4906 top1= 38.0682

=== Log global consensus distance @ E11B0 ===
consensus_distance=21.681



=== Log clique consensus distance @ E11B0 ===
clique1_consensus_distance=0.640
clique2_consensus_distance=63.938


[E11B10 |   4224/60000 (  7%) ] Loss: 2.4677 top1= 25.2841

=== Log global consensus distance @ E11B10 ===
consensus_distance=14.151



=== Log clique consensus distance @ E11B10 ===
clique1_consensus_distance=0.563
clique2_consensus_distance=37.127


[E11B20 |   8064/60000 ( 13%) ] Loss: 2.8340 top1= 20.1705

=== Log global consensus distance @ E11B20 ===
consensus_distance=10.306



=== Log clique consensus distance @ E11B20 ===
clique1_consensus_distance=0.468
clique2_consensus_distance=21.162



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.1192 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0557 top1=  9.7456


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8882 top1= 16.0357

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 3.0870 top1= 13.6364

=== Log global consensus distance @ E12B0 ===
consensus_distance=8.189



=== Log clique consensus distance @ E12B0 ===
clique1_consensus_distance=0.417
clique2_consensus_distance=12.052


[E12B10 |   4224/60000 (  7%) ] Loss: 3.1476 top1= 11.0795

=== Log global consensus distance @ E12B10 ===
consensus_distance=7.007



=== Log clique consensus distance @ E12B10 ===
clique1_consensus_distance=0.383
clique2_consensus_distance=6.903


[E12B20 |   8064/60000 ( 13%) ] Loss: 3.1926 top1= 10.7955

=== Log global consensus distance @ E12B20 ===
consensus_distance=6.366



=== Log clique consensus distance @ E12B20 ===
clique1_consensus_distance=0.361
clique2_consensus_distance=4.016



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.2447 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1496 top1=  9.7456


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1744 top1=  9.7456

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 3.2802 top1=  9.6591

=== Log global consensus distance @ E13B0 ===
consensus_distance=5.986



=== Log clique consensus distance @ E13B0 ===
clique1_consensus_distance=0.344
clique2_consensus_distance=2.395


[E13B10 |   4224/60000 (  7%) ] Loss: 3.2668 top1= 11.0795

=== Log global consensus distance @ E13B10 ===
consensus_distance=5.771



=== Log clique consensus distance @ E13B10 ===
clique1_consensus_distance=0.332
clique2_consensus_distance=1.488


[E13B20 |   8064/60000 ( 13%) ] Loss: 3.3471 top1= 10.7955

=== Log global consensus distance @ E13B20 ===
consensus_distance=5.924



=== Log clique consensus distance @ E13B20 ===
clique1_consensus_distance=0.345
clique2_consensus_distance=1.004



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.4442 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3264 top1=  9.7456


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3480 top1=  9.7456

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 3.4481 top1=  9.9432

=== Log global consensus distance @ E14B0 ===
consensus_distance=5.909



=== Log clique consensus distance @ E14B0 ===
clique1_consensus_distance=0.341
clique2_consensus_distance=0.728


[E14B10 |   4224/60000 (  7%) ] Loss: 3.4619 top1= 11.0795

=== Log global consensus distance @ E14B10 ===
consensus_distance=5.664



=== Log clique consensus distance @ E14B10 ===
clique1_consensus_distance=0.320
clique2_consensus_distance=0.555


[E14B20 |   8064/60000 ( 13%) ] Loss: 3.5516 top1= 10.7955

=== Log global consensus distance @ E14B20 ===
consensus_distance=5.540



=== Log clique consensus distance @ E14B20 ===
clique1_consensus_distance=0.309
clique2_consensus_distance=0.460



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.6841 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5366 top1=  9.7456


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5574 top1=  9.7456

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 3.6706 top1=  9.9432

=== Log global consensus distance @ E15B0 ===
consensus_distance=5.490



=== Log clique consensus distance @ E15B0 ===
clique1_consensus_distance=0.304
clique2_consensus_distance=0.409


[E15B10 |   4224/60000 (  7%) ] Loss: 3.7142 top1= 11.0795

=== Log global consensus distance @ E15B10 ===
consensus_distance=5.470



=== Log clique consensus distance @ E15B10 ===
clique1_consensus_distance=0.302
clique2_consensus_distance=0.381


[E15B20 |   8064/60000 ( 13%) ] Loss: 3.8483 top1= 10.7955

=== Log global consensus distance @ E15B20 ===
consensus_distance=5.724



=== Log clique consensus distance @ E15B20 ===
clique1_consensus_distance=0.300
clique2_consensus_distance=1.472



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=4.0660 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8631 top1=  9.7456


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8843 top1=  9.7456

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 4.8018 top1=  9.6591

=== Log global consensus distance @ E16B0 ===
consensus_distance=5.819



=== Log clique consensus distance @ E16B0 ===
clique1_consensus_distance=0.300
clique2_consensus_distance=1.842


[E16B10 |   4224/60000 (  7%) ] Loss: 4.1006 top1= 11.0795

=== Log global consensus distance @ E16B10 ===
consensus_distance=6.192



=== Log clique consensus distance @ E16B10 ===
clique1_consensus_distance=0.337
clique2_consensus_distance=1.523


[E16B20 |   8064/60000 ( 13%) ] Loss: 4.2517 top1= 10.7955

=== Log global consensus distance @ E16B20 ===
consensus_distance=5.968



=== Log clique consensus distance @ E16B20 ===
clique1_consensus_distance=0.327
clique2_consensus_distance=1.104



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=4.4254 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2332 top1=  9.7456


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2550 top1=  9.7456

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 4.8365 top1=  9.6591

=== Log global consensus distance @ E17B0 ===
consensus_distance=5.829



=== Log clique consensus distance @ E17B0 ===
clique1_consensus_distance=0.313
clique2_consensus_distance=1.260


[E17B10 |   4224/60000 (  7%) ] Loss: 4.4597 top1= 11.0795

=== Log global consensus distance @ E17B10 ===
consensus_distance=6.502



=== Log clique consensus distance @ E17B10 ===
clique1_consensus_distance=0.347
clique2_consensus_distance=1.556


[E17B20 |   8064/60000 ( 13%) ] Loss: 4.5611 top1= 10.7955

=== Log global consensus distance @ E17B20 ===
consensus_distance=23.714



=== Log clique consensus distance @ E17B20 ===
clique1_consensus_distance=0.627
clique2_consensus_distance=3.614



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=4.4958 top1=  9.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3796 top1=  9.7456


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4058 top1=  9.7456

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 9.7538 top1=  7.6705

=== Log global consensus distance @ E18B0 ===
consensus_distance=816.881



=== Log clique consensus distance @ E18B0 ===
clique1_consensus_distance=0.633
clique2_consensus_distance=8.118


[E18B10 |   4224/60000 (  7%) ] 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 |   8064/60000 ( 13%) ] 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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

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



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


[E19B10 |   4224/60000 (  7%) ] 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 |   8064/60000 ( 13%) ] 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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

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



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


[E20B10 |   4224/60000 (  7%) ] 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 |   8064/60000 ( 13%) ] 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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

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



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


[E21B10 |   4224/60000 (  7%) ] 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 |   8064/60000 ( 13%) ] 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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

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



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


[E22B10 |   4224/60000 (  7%) ] 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 |   8064/60000 ( 13%) ] 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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

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



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


[E23B10 |   4224/60000 (  7%) ] 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 |   8064/60000 ( 13%) ] 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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

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



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


[E24B10 |   4224/60000 (  7%) ] 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 |   8064/60000 ( 13%) ] 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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

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



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


[E25B10 |   4224/60000 (  7%) ] 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 |   8064/60000 ( 13%) ] 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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

=== 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= 10.5114

=== 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=  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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

=== 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= 10.5114

=== 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=  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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

=== 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= 10.5114

=== 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=  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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

=== 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= 10.5114

=== 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=  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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

=== 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= 10.5114

=== 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=  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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

=== 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= 10.5114

=== 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=  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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

=== 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= 10.5114

=== 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=  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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

=== 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= 10.5114

=== 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=  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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

=== 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= 10.5114

=== 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=  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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

=== 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= 10.5114

=== 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=  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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

=== 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= 10.5114

=== 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=  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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

=== 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= 10.5114

=== 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=  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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

=== 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= 10.5114

=== 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=  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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

=== 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= 10.5114

=== 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=  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  |    384/60000 (  1%) ] Loss: nan top1= 11.9318

=== 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= 10.5114

=== 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=  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

