
=== Start adding workers ===
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=12,rank=0,shuffle=True)'}
=> Add worker SGDMWorker(index=0, momentum=0.9)
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=12,rank=1,shuffle=True)'}
=> Add worker SGDMWorker(index=1, momentum=0.9)
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=12,rank=2,shuffle=True)'}
=> Add worker SGDMWorker(index=2, momentum=0.9)
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=12,rank=3,shuffle=True)'}
=> Add worker SGDMWorker(index=3, momentum=0.9)
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=12,rank=4,shuffle=True)'}
=> Add worker SGDMWorker(index=4, momentum=0.9)
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=12,rank=5,shuffle=True)'}
=> Add worker SGDMWorker(index=5, momentum=0.9)
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=12,rank=6,shuffle=True)'}
=> Add worker SGDMWorker(index=6, momentum=0.9)
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=12,rank=7,shuffle=True)'}
=> Add worker SGDMWorker(index=7, momentum=0.9)
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=12,rank=8,shuffle=True)'}
=> Add worker SGDMWorker(index=8, momentum=0.9)
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=12,rank=9,shuffle=True)'}
=> Add worker SGDMWorker(index=9, momentum=0.9)
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=12,rank=10,shuffle=True)'}
=> Add worker SGDMWorker(index=10, momentum=0.9)
{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': True, 'download': True, 'batch_size': 64, 'shuffle': None, 'sampler': 'DistributedSampler(num_replicas=12,rank=11,shuffle=True)'}
=> Add worker ByzantineWorker(index=11)

=== Start adding graph ===
TwoCliquesWithByzantine(m=5,b=1)

{'Type': 'Setup', 'Dataset': 'cifar10', 'data_dir': '/home/he/dero/datasets/', 'train': False, 'download': True, 'batch_size': 128, 'shuffle': False, 'sampler': None}
Train epoch 1
[E 1B0  |    768/50000 (  2%) ] Loss: 2.3066 top1=  9.3750

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



=== 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 0.642 0.025]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.025 0.975]]


[E 1B10 |   8448/50000 ( 17%) ] Loss: 2.2809 top1= 19.3182

=== Log global consensus distance @ E1B10 ===
consensus_distance=0.009



=== Log clique consensus distance @ E1B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=0.037


[E 1B20 |  16128/50000 ( 32%) ] Loss: 2.2475 top1= 18.6080

=== Log global consensus distance @ E1B20 ===
consensus_distance=0.065



=== Log clique consensus distance @ E1B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=0.261


[E 1B30 |  23808/50000 ( 48%) ] Loss: 2.1399 top1= 20.4545

=== Log global consensus distance @ E1B30 ===
consensus_distance=0.185



=== Log clique consensus distance @ E1B30 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=0.742


[E 1B40 |  31488/50000 ( 63%) ] Loss: 2.1159 top1= 20.1705

=== Log global consensus distance @ E1B40 ===
consensus_distance=0.258



=== Log clique consensus distance @ E1B40 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=1.039


[E 1B50 |  39168/50000 ( 78%) ] Loss: 2.1426 top1= 21.3068

=== Log global consensus distance @ E1B50 ===
consensus_distance=0.251



=== Log clique consensus distance @ E1B50 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=1.000


[E 1B60 |  46848/50000 ( 94%) ] Loss: 2.0629 top1= 21.5909

=== Log global consensus distance @ E1B60 ===
consensus_distance=0.291



=== Log clique consensus distance @ E1B60 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=1.174



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3058 top1= 10.0361


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5005 top1= 10.2364


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4648 top1=  9.9659

Train epoch 2
[E 2B0  |    768/50000 (  2%) ] Loss: 2.1409 top1= 21.1648

=== Log global consensus distance @ E2B0 ===
consensus_distance=0.307



=== Log clique consensus distance @ E2B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=1.237


[E 2B10 |   8448/50000 ( 17%) ] Loss: 2.0972 top1= 19.6023

=== Log global consensus distance @ E2B10 ===
consensus_distance=0.279



=== Log clique consensus distance @ E2B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=1.121


[E 2B20 |  16128/50000 ( 32%) ] Loss: 2.1389 top1= 20.1705

=== Log global consensus distance @ E2B20 ===
consensus_distance=0.300



=== Log clique consensus distance @ E2B20 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=1.220


[E 2B30 |  23808/50000 ( 48%) ] Loss: 2.0471 top1= 24.1477

=== Log global consensus distance @ E2B30 ===
consensus_distance=0.289



=== Log clique consensus distance @ E2B30 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=1.169


[E 2B40 |  31488/50000 ( 63%) ] Loss: 2.0435 top1= 23.4375

=== Log global consensus distance @ E2B40 ===
consensus_distance=0.311



=== Log clique consensus distance @ E2B40 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=1.270


[E 2B50 |  39168/50000 ( 78%) ] Loss: 2.0261 top1= 27.5568

=== Log global consensus distance @ E2B50 ===
consensus_distance=0.319



=== Log clique consensus distance @ E2B50 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=1.309


[E 2B60 |  46848/50000 ( 94%) ] Loss: 1.8971 top1= 28.6932

=== Log global consensus distance @ E2B60 ===
consensus_distance=0.368



=== Log clique consensus distance @ E2B60 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=1.489



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.1636 top1= 16.9671


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3575 top1= 14.1126


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2396 top1= 20.3626

Train epoch 3
[E 3B0  |    768/50000 (  2%) ] Loss: 2.0207 top1= 26.9886

=== Log global consensus distance @ E3B0 ===
consensus_distance=0.379



=== Log clique consensus distance @ E3B0 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=1.532


[E 3B10 |   8448/50000 ( 17%) ] Loss: 1.9386 top1= 30.9659

=== Log global consensus distance @ E3B10 ===
consensus_distance=0.408



=== Log clique consensus distance @ E3B10 ===
clique1_consensus_distance=0.000
clique2_consensus_distance=1.649


[E 3B20 |  16128/50000 ( 32%) ] Loss: 1.9752 top1= 25.7102

=== Log global consensus distance @ E3B20 ===
consensus_distance=0.437



=== Log clique consensus distance @ E3B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=1.760


[E 3B30 |  23808/50000 ( 48%) ] Loss: 1.8921 top1= 33.5227

=== Log global consensus distance @ E3B30 ===
consensus_distance=0.459



=== Log clique consensus distance @ E3B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=1.847


[E 3B40 |  31488/50000 ( 63%) ] Loss: 1.8399 top1= 31.3920

=== Log global consensus distance @ E3B40 ===
consensus_distance=0.494



=== Log clique consensus distance @ E3B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=1.994


[E 3B50 |  39168/50000 ( 78%) ] Loss: 1.8617 top1= 31.5341

=== Log global consensus distance @ E3B50 ===
consensus_distance=0.514



=== Log clique consensus distance @ E3B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=2.071


[E 3B60 |  46848/50000 ( 94%) ] Loss: 1.7412 top1= 35.2273

=== Log global consensus distance @ E3B60 ===
consensus_distance=0.560



=== Log clique consensus distance @ E3B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=2.252



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9758 top1= 23.0669


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1026 top1= 18.7600


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0670 top1= 22.7764

Train epoch 4
[E 4B0  |    768/50000 (  2%) ] Loss: 1.8743 top1= 31.8182

=== Log global consensus distance @ E4B0 ===
consensus_distance=0.568



=== Log clique consensus distance @ E4B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=2.294


[E 4B10 |   8448/50000 ( 17%) ] Loss: 1.8644 top1= 31.9602

=== Log global consensus distance @ E4B10 ===
consensus_distance=0.586



=== Log clique consensus distance @ E4B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=2.366


[E 4B20 |  16128/50000 ( 32%) ] Loss: 1.8643 top1= 30.3977

=== Log global consensus distance @ E4B20 ===
consensus_distance=0.615



=== Log clique consensus distance @ E4B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=2.482


[E 4B30 |  23808/50000 ( 48%) ] Loss: 1.7920 top1= 33.8068

=== Log global consensus distance @ E4B30 ===
consensus_distance=0.640



=== Log clique consensus distance @ E4B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=2.578


[E 4B40 |  31488/50000 ( 63%) ] Loss: 1.7080 top1= 37.5000

=== Log global consensus distance @ E4B40 ===
consensus_distance=0.679



=== Log clique consensus distance @ E4B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=2.735


[E 4B50 |  39168/50000 ( 78%) ] Loss: 1.7277 top1= 35.2273

=== Log global consensus distance @ E4B50 ===
consensus_distance=0.695



=== Log clique consensus distance @ E4B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=2.801


[E 4B60 |  46848/50000 ( 94%) ] Loss: 1.6115 top1= 40.9091

=== Log global consensus distance @ E4B60 ===
consensus_distance=0.736



=== Log clique consensus distance @ E4B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=2.963



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8976 top1= 26.0417


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9980 top1= 20.4227


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9721 top1= 25.6410

Train epoch 5
[E 5B0  |    768/50000 (  2%) ] Loss: 1.7737 top1= 33.8068

=== Log global consensus distance @ E5B0 ===
consensus_distance=0.735



=== Log clique consensus distance @ E5B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=2.964


[E 5B10 |   8448/50000 ( 17%) ] Loss: 1.7409 top1= 39.7727

=== Log global consensus distance @ E5B10 ===
consensus_distance=0.738



=== Log clique consensus distance @ E5B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=2.974


[E 5B20 |  16128/50000 ( 32%) ] Loss: 1.7481 top1= 32.9545

=== Log global consensus distance @ E5B20 ===
consensus_distance=0.761



=== Log clique consensus distance @ E5B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=3.066


[E 5B30 |  23808/50000 ( 48%) ] Loss: 1.7092 top1= 37.9261

=== Log global consensus distance @ E5B30 ===
consensus_distance=0.782



=== Log clique consensus distance @ E5B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=3.152


[E 5B40 |  31488/50000 ( 63%) ] Loss: 1.6525 top1= 40.4830

=== Log global consensus distance @ E5B40 ===
consensus_distance=0.814



=== Log clique consensus distance @ E5B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=3.280


[E 5B50 |  39168/50000 ( 78%) ] Loss: 1.6510 top1= 37.7841

=== Log global consensus distance @ E5B50 ===
consensus_distance=0.829



=== Log clique consensus distance @ E5B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=3.346


[E 5B60 |  46848/50000 ( 94%) ] Loss: 1.5773 top1= 42.1875

=== Log global consensus distance @ E5B60 ===
consensus_distance=0.855



=== Log clique consensus distance @ E5B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=3.437



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8258 top1= 29.7175


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0419 top1= 20.2424


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8645 top1= 28.8462

Train epoch 6
[E 6B0  |    768/50000 (  2%) ] Loss: 1.7361 top1= 34.6591

=== Log global consensus distance @ E6B0 ===
consensus_distance=0.857



=== Log clique consensus distance @ E6B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=3.451


[E 6B10 |   8448/50000 ( 17%) ] Loss: 1.6328 top1= 41.1932

=== Log global consensus distance @ E6B10 ===
consensus_distance=0.865



=== Log clique consensus distance @ E6B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=3.489


[E 6B20 |  16128/50000 ( 32%) ] Loss: 1.6825 top1= 37.9261

=== Log global consensus distance @ E6B20 ===
consensus_distance=0.899



=== Log clique consensus distance @ E6B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=3.623


[E 6B30 |  23808/50000 ( 48%) ] Loss: 1.6087 top1= 41.9034

=== Log global consensus distance @ E6B30 ===
consensus_distance=0.926



=== Log clique consensus distance @ E6B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=3.727


[E 6B40 |  31488/50000 ( 63%) ] Loss: 1.5689 top1= 43.8920

=== Log global consensus distance @ E6B40 ===
consensus_distance=0.960



=== Log clique consensus distance @ E6B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=3.865


[E 6B50 |  39168/50000 ( 78%) ] Loss: 1.5921 top1= 39.4886

=== Log global consensus distance @ E6B50 ===
consensus_distance=0.987



=== Log clique consensus distance @ E6B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=3.977


[E 6B60 |  46848/50000 ( 94%) ] Loss: 1.4283 top1= 46.7330

=== Log global consensus distance @ E6B60 ===
consensus_distance=1.026



=== Log clique consensus distance @ E6B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=4.122



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7076 top1= 34.1947


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9195 top1= 22.9467


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7952 top1= 32.5020

Train epoch 7
[E 7B0  |    768/50000 (  2%) ] Loss: 1.6378 top1= 40.1989

=== Log global consensus distance @ E7B0 ===
consensus_distance=1.035



=== Log clique consensus distance @ E7B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=4.163


[E 7B10 |   8448/50000 ( 17%) ] Loss: 1.5596 top1= 45.7386

=== Log global consensus distance @ E7B10 ===
consensus_distance=1.033



=== Log clique consensus distance @ E7B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=4.157


[E 7B20 |  16128/50000 ( 32%) ] Loss: 1.5881 top1= 42.8977

=== Log global consensus distance @ E7B20 ===
consensus_distance=1.047



=== Log clique consensus distance @ E7B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=4.220


[E 7B30 |  23808/50000 ( 48%) ] Loss: 1.5581 top1= 43.0398

=== Log global consensus distance @ E7B30 ===
consensus_distance=1.090



=== Log clique consensus distance @ E7B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=4.388


[E 7B40 |  31488/50000 ( 63%) ] Loss: 1.5483 top1= 45.0284

=== Log global consensus distance @ E7B40 ===
consensus_distance=1.138



=== Log clique consensus distance @ E7B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=4.582


[E 7B50 |  39168/50000 ( 78%) ] Loss: 1.5478 top1= 44.4602

=== Log global consensus distance @ E7B50 ===
consensus_distance=1.193



=== Log clique consensus distance @ E7B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=4.805


[E 7B60 |  46848/50000 ( 94%) ] Loss: 1.4026 top1= 49.4318

=== Log global consensus distance @ E7B60 ===
consensus_distance=1.232



=== Log clique consensus distance @ E7B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=4.950



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6064 top1= 37.9908


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7672 top1= 29.3369


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7351 top1= 35.8874

Train epoch 8
[E 8B0  |    768/50000 (  2%) ] Loss: 1.4973 top1= 45.4545

=== Log global consensus distance @ E8B0 ===
consensus_distance=1.225



=== Log clique consensus distance @ E8B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=4.930


[E 8B10 |   8448/50000 ( 17%) ] Loss: 1.4904 top1= 46.5909

=== Log global consensus distance @ E8B10 ===
consensus_distance=1.200



=== Log clique consensus distance @ E8B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=4.829


[E 8B20 |  16128/50000 ( 32%) ] Loss: 1.5540 top1= 43.4659

=== Log global consensus distance @ E8B20 ===
consensus_distance=1.207



=== Log clique consensus distance @ E8B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=4.865


[E 8B30 |  23808/50000 ( 48%) ] Loss: 1.4437 top1= 51.7045

=== Log global consensus distance @ E8B30 ===
consensus_distance=1.240



=== Log clique consensus distance @ E8B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=4.990


[E 8B40 |  31488/50000 ( 63%) ] Loss: 1.4010 top1= 49.5739

=== Log global consensus distance @ E8B40 ===
consensus_distance=1.266



=== Log clique consensus distance @ E8B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.097


[E 8B50 |  39168/50000 ( 78%) ] Loss: 1.4556 top1= 48.0114

=== Log global consensus distance @ E8B50 ===
consensus_distance=1.284



=== Log clique consensus distance @ E8B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.175


[E 8B60 |  46848/50000 ( 94%) ] Loss: 1.3427 top1= 50.9943

=== Log global consensus distance @ E8B60 ===
consensus_distance=1.296



=== Log clique consensus distance @ E8B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.210



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.5476 top1= 40.7352


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7444 top1= 30.3786


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6403 top1= 39.4231

Train epoch 9
[E 9B0  |    768/50000 (  2%) ] Loss: 1.4434 top1= 46.5909

=== Log global consensus distance @ E9B0 ===
consensus_distance=1.278



=== Log clique consensus distance @ E9B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.148


[E 9B10 |   8448/50000 ( 17%) ] Loss: 1.4612 top1= 47.0170

=== Log global consensus distance @ E9B10 ===
consensus_distance=1.236



=== Log clique consensus distance @ E9B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=4.975


[E 9B20 |  16128/50000 ( 32%) ] Loss: 1.4835 top1= 47.1591

=== Log global consensus distance @ E9B20 ===
consensus_distance=1.234



=== Log clique consensus distance @ E9B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=4.970


[E 9B30 |  23808/50000 ( 48%) ] Loss: 1.3944 top1= 50.8523

=== Log global consensus distance @ E9B30 ===
consensus_distance=1.257



=== Log clique consensus distance @ E9B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.059


[E 9B40 |  31488/50000 ( 63%) ] Loss: 1.3881 top1= 49.5739

=== Log global consensus distance @ E9B40 ===
consensus_distance=1.285



=== Log clique consensus distance @ E9B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.177


[E 9B50 |  39168/50000 ( 78%) ] Loss: 1.3552 top1= 50.1420

=== Log global consensus distance @ E9B50 ===
consensus_distance=1.304



=== Log clique consensus distance @ E9B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.252


[E 9B60 |  46848/50000 ( 94%) ] Loss: 1.3202 top1= 52.1307

=== Log global consensus distance @ E9B60 ===
consensus_distance=1.313



=== Log clique consensus distance @ E9B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.280



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4629 top1= 44.8818


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6289 top1= 34.2949


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5508 top1= 43.1390

Train epoch 10
[E10B0  |    768/50000 (  2%) ] Loss: 1.3854 top1= 49.4318

=== Log global consensus distance @ E10B0 ===
consensus_distance=1.292



=== Log clique consensus distance @ E10B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.200


[E10B10 |   8448/50000 ( 17%) ] Loss: 1.3488 top1= 51.8466

=== Log global consensus distance @ E10B10 ===
consensus_distance=1.262



=== Log clique consensus distance @ E10B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.083


[E10B20 |  16128/50000 ( 32%) ] Loss: 1.3678 top1= 51.9886

=== Log global consensus distance @ E10B20 ===
consensus_distance=1.260



=== Log clique consensus distance @ E10B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.079


[E10B30 |  23808/50000 ( 48%) ] Loss: 1.3279 top1= 52.6989

=== Log global consensus distance @ E10B30 ===
consensus_distance=1.282



=== Log clique consensus distance @ E10B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.153


[E10B40 |  31488/50000 ( 63%) ] Loss: 1.2813 top1= 54.2614

=== Log global consensus distance @ E10B40 ===
consensus_distance=1.295



=== Log clique consensus distance @ E10B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.209


[E10B50 |  39168/50000 ( 78%) ] Loss: 1.3032 top1= 53.2670

=== Log global consensus distance @ E10B50 ===
consensus_distance=1.307



=== Log clique consensus distance @ E10B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.263


[E10B60 |  46848/50000 ( 94%) ] Loss: 1.2238 top1= 57.2443

=== Log global consensus distance @ E10B60 ===
consensus_distance=1.301



=== Log clique consensus distance @ E10B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.234



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4027 top1= 47.1054


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5514 top1= 39.8037


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5245 top1= 45.1522

Train epoch 11
[E11B0  |    768/50000 (  2%) ] Loss: 1.3275 top1= 54.4034

=== Log global consensus distance @ E11B0 ===
consensus_distance=1.284



=== Log clique consensus distance @ E11B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.170


[E11B10 |   8448/50000 ( 17%) ] Loss: 1.3786 top1= 51.2784

=== Log global consensus distance @ E11B10 ===
consensus_distance=1.261



=== Log clique consensus distance @ E11B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.080


[E11B20 |  16128/50000 ( 32%) ] Loss: 1.2755 top1= 57.6705

=== Log global consensus distance @ E11B20 ===
consensus_distance=1.272



=== Log clique consensus distance @ E11B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.126


[E11B30 |  23808/50000 ( 48%) ] Loss: 1.2835 top1= 55.6818

=== Log global consensus distance @ E11B30 ===
consensus_distance=1.295



=== Log clique consensus distance @ E11B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.209


[E11B40 |  31488/50000 ( 63%) ] Loss: 1.2709 top1= 56.3920

=== Log global consensus distance @ E11B40 ===
consensus_distance=1.303



=== Log clique consensus distance @ E11B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.245


[E11B50 |  39168/50000 ( 78%) ] Loss: 1.2061 top1= 55.6818

=== Log global consensus distance @ E11B50 ===
consensus_distance=1.308



=== Log clique consensus distance @ E11B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.264


[E11B60 |  46848/50000 ( 94%) ] Loss: 1.2197 top1= 57.1023

=== Log global consensus distance @ E11B60 ===
consensus_distance=1.303



=== Log clique consensus distance @ E11B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.236



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3563 top1= 49.4091


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4784 top1= 42.7684


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5511 top1= 44.2208

Train epoch 12
[E12B0  |    768/50000 (  2%) ] Loss: 1.3568 top1= 51.1364

=== Log global consensus distance @ E12B0 ===
consensus_distance=1.299



=== Log clique consensus distance @ E12B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.228


[E12B10 |   8448/50000 ( 17%) ] Loss: 1.2759 top1= 53.4091

=== Log global consensus distance @ E12B10 ===
consensus_distance=1.298



=== Log clique consensus distance @ E12B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.225


[E12B20 |  16128/50000 ( 32%) ] Loss: 1.2202 top1= 57.9545

=== Log global consensus distance @ E12B20 ===
consensus_distance=1.303



=== Log clique consensus distance @ E12B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.249


[E12B30 |  23808/50000 ( 48%) ] Loss: 1.1996 top1= 58.8068

=== Log global consensus distance @ E12B30 ===
consensus_distance=1.315



=== Log clique consensus distance @ E12B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.290


[E12B40 |  31488/50000 ( 63%) ] Loss: 1.1703 top1= 58.5227

=== Log global consensus distance @ E12B40 ===
consensus_distance=1.321



=== Log clique consensus distance @ E12B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.318


[E12B50 |  39168/50000 ( 78%) ] Loss: 1.1958 top1= 57.1023

=== Log global consensus distance @ E12B50 ===
consensus_distance=1.326



=== Log clique consensus distance @ E12B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.334


[E12B60 |  46848/50000 ( 94%) ] Loss: 1.1623 top1= 58.9489

=== Log global consensus distance @ E12B60 ===
consensus_distance=1.327



=== Log clique consensus distance @ E12B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.339



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2527 top1= 53.6458


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3184 top1= 49.6294


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4011 top1= 50.6410

Train epoch 13
[E13B0  |    768/50000 (  2%) ] Loss: 1.2281 top1= 57.5284

=== Log global consensus distance @ E13B0 ===
consensus_distance=1.323



=== Log clique consensus distance @ E13B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.327


[E13B10 |   8448/50000 ( 17%) ] Loss: 1.2007 top1= 56.1080

=== Log global consensus distance @ E13B10 ===
consensus_distance=1.323



=== Log clique consensus distance @ E13B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.326


[E13B20 |  16128/50000 ( 32%) ] Loss: 1.1188 top1= 61.9318

=== Log global consensus distance @ E13B20 ===
consensus_distance=1.334



=== Log clique consensus distance @ E13B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.375


[E13B30 |  23808/50000 ( 48%) ] Loss: 1.1695 top1= 60.5114

=== Log global consensus distance @ E13B30 ===
consensus_distance=1.345



=== Log clique consensus distance @ E13B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.409


[E13B40 |  31488/50000 ( 63%) ] Loss: 1.1854 top1= 58.9489

=== Log global consensus distance @ E13B40 ===
consensus_distance=1.355



=== Log clique consensus distance @ E13B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.456


[E13B50 |  39168/50000 ( 78%) ] Loss: 1.1283 top1= 58.9489

=== Log global consensus distance @ E13B50 ===
consensus_distance=1.362



=== Log clique consensus distance @ E13B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.479


[E13B60 |  46848/50000 ( 94%) ] Loss: 1.1173 top1= 60.5114

=== Log global consensus distance @ E13B60 ===
consensus_distance=1.374



=== Log clique consensus distance @ E13B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.528



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2056 top1= 56.0196


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3007 top1= 50.8614


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3807 top1= 51.2119

Train epoch 14
[E14B0  |    768/50000 (  2%) ] Loss: 1.2295 top1= 57.6705

=== Log global consensus distance @ E14B0 ===
consensus_distance=1.378



=== Log clique consensus distance @ E14B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.548


[E14B10 |   8448/50000 ( 17%) ] Loss: 1.1817 top1= 59.6591

=== Log global consensus distance @ E14B10 ===
consensus_distance=1.376



=== Log clique consensus distance @ E14B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.540


[E14B20 |  16128/50000 ( 32%) ] Loss: 1.1253 top1= 60.3693

=== Log global consensus distance @ E14B20 ===
consensus_distance=1.389



=== Log clique consensus distance @ E14B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.593


[E14B30 |  23808/50000 ( 48%) ] Loss: 1.1019 top1= 61.5057

=== Log global consensus distance @ E14B30 ===
consensus_distance=1.400



=== Log clique consensus distance @ E14B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.633


[E14B40 |  31488/50000 ( 63%) ] Loss: 1.0851 top1= 62.7841

=== Log global consensus distance @ E14B40 ===
consensus_distance=1.406



=== Log clique consensus distance @ E14B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.657


[E14B50 |  39168/50000 ( 78%) ] Loss: 1.1203 top1= 59.6591

=== Log global consensus distance @ E14B50 ===
consensus_distance=1.413



=== Log clique consensus distance @ E14B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.686


[E14B60 |  46848/50000 ( 94%) ] Loss: 1.0478 top1= 62.5000

=== Log global consensus distance @ E14B60 ===
consensus_distance=1.439



=== Log clique consensus distance @ E14B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.792



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1618 top1= 57.2316


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2975 top1= 50.9215


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3302 top1= 52.9046

Train epoch 15
[E15B0  |    768/50000 (  2%) ] Loss: 1.1565 top1= 59.3750

=== Log global consensus distance @ E15B0 ===
consensus_distance=1.445



=== Log clique consensus distance @ E15B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.818


[E15B10 |   8448/50000 ( 17%) ] Loss: 1.1244 top1= 60.3693

=== Log global consensus distance @ E15B10 ===
consensus_distance=1.444



=== Log clique consensus distance @ E15B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.812


[E15B20 |  16128/50000 ( 32%) ] Loss: 1.0594 top1= 64.0625

=== Log global consensus distance @ E15B20 ===
consensus_distance=1.454



=== Log clique consensus distance @ E15B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.856


[E15B30 |  23808/50000 ( 48%) ] Loss: 1.0811 top1= 60.7955

=== Log global consensus distance @ E15B30 ===
consensus_distance=1.462



=== Log clique consensus distance @ E15B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.880


[E15B40 |  31488/50000 ( 63%) ] Loss: 1.0610 top1= 61.7898

=== Log global consensus distance @ E15B40 ===
consensus_distance=1.460



=== Log clique consensus distance @ E15B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.876


[E15B50 |  39168/50000 ( 78%) ] Loss: 1.0644 top1= 59.5170

=== Log global consensus distance @ E15B50 ===
consensus_distance=1.471



=== Log clique consensus distance @ E15B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=5.921


[E15B60 |  46848/50000 ( 94%) ] Loss: 1.0119 top1= 63.6364

=== Log global consensus distance @ E15B60 ===
consensus_distance=1.495



=== Log clique consensus distance @ E15B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.015



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1174 top1= 59.1847


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2040 top1= 55.1683


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2841 top1= 54.5773

Train epoch 16
[E16B0  |    768/50000 (  2%) ] Loss: 1.0958 top1= 61.2216

=== Log global consensus distance @ E16B0 ===
consensus_distance=1.506



=== Log clique consensus distance @ E16B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.063


[E16B10 |   8448/50000 ( 17%) ] Loss: 1.0888 top1= 62.9261

=== Log global consensus distance @ E16B10 ===
consensus_distance=1.513



=== Log clique consensus distance @ E16B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.092


[E16B20 |  16128/50000 ( 32%) ] Loss: 0.9776 top1= 66.3352

=== Log global consensus distance @ E16B20 ===
consensus_distance=1.522



=== Log clique consensus distance @ E16B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.131


[E16B30 |  23808/50000 ( 48%) ] Loss: 1.0756 top1= 63.7784

=== Log global consensus distance @ E16B30 ===
consensus_distance=1.542



=== Log clique consensus distance @ E16B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.203


[E16B40 |  31488/50000 ( 63%) ] Loss: 1.0421 top1= 62.6420

=== Log global consensus distance @ E16B40 ===
consensus_distance=1.567



=== Log clique consensus distance @ E16B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.308


[E16B50 |  39168/50000 ( 78%) ] Loss: 0.9974 top1= 66.1932

=== Log global consensus distance @ E16B50 ===
consensus_distance=1.587



=== Log clique consensus distance @ E16B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.392


[E16B60 |  46848/50000 ( 94%) ] Loss: 0.9684 top1= 66.0511

=== Log global consensus distance @ E16B60 ===
consensus_distance=1.607



=== Log clique consensus distance @ E16B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.466



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0811 top1= 60.8474


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1156 top1= 59.3450


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3036 top1= 54.9479

Train epoch 17
[E17B0  |    768/50000 (  2%) ] Loss: 1.0427 top1= 64.0625

=== Log global consensus distance @ E17B0 ===
consensus_distance=1.608



=== Log clique consensus distance @ E17B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.476


[E17B10 |   8448/50000 ( 17%) ] Loss: 1.0588 top1= 64.3466

=== Log global consensus distance @ E17B10 ===
consensus_distance=1.599



=== Log clique consensus distance @ E17B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.440


[E17B20 |  16128/50000 ( 32%) ] Loss: 0.9989 top1= 65.3409

=== Log global consensus distance @ E17B20 ===
consensus_distance=1.603



=== Log clique consensus distance @ E17B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.456


[E17B30 |  23808/50000 ( 48%) ] Loss: 0.9791 top1= 66.3352

=== Log global consensus distance @ E17B30 ===
consensus_distance=1.628



=== Log clique consensus distance @ E17B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.548


[E17B40 |  31488/50000 ( 63%) ] Loss: 0.9599 top1= 64.7727

=== Log global consensus distance @ E17B40 ===
consensus_distance=1.650



=== Log clique consensus distance @ E17B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.640


[E17B50 |  39168/50000 ( 78%) ] Loss: 0.9794 top1= 62.3580

=== Log global consensus distance @ E17B50 ===
consensus_distance=1.673



=== Log clique consensus distance @ E17B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.737


[E17B60 |  46848/50000 ( 94%) ] Loss: 0.9776 top1= 66.0511

=== Log global consensus distance @ E17B60 ===
consensus_distance=1.690



=== Log clique consensus distance @ E17B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.804



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0553 top1= 61.7288


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1905 top1= 55.9295


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2444 top1= 56.7708

Train epoch 18
[E18B0  |    768/50000 (  2%) ] Loss: 1.0150 top1= 64.4886

=== Log global consensus distance @ E18B0 ===
consensus_distance=1.694



=== Log clique consensus distance @ E18B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.822


[E18B10 |   8448/50000 ( 17%) ] Loss: 0.9854 top1= 65.3409

=== Log global consensus distance @ E18B10 ===
consensus_distance=1.688



=== Log clique consensus distance @ E18B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.798


[E18B20 |  16128/50000 ( 32%) ] Loss: 0.9615 top1= 67.6136

=== Log global consensus distance @ E18B20 ===
consensus_distance=1.709



=== Log clique consensus distance @ E18B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.884


[E18B30 |  23808/50000 ( 48%) ] Loss: 0.9571 top1= 66.3352

=== Log global consensus distance @ E18B30 ===
consensus_distance=1.726



=== Log clique consensus distance @ E18B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.948


[E18B40 |  31488/50000 ( 63%) ] Loss: 0.9653 top1= 64.4886

=== Log global consensus distance @ E18B40 ===
consensus_distance=1.726



=== Log clique consensus distance @ E18B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.947


[E18B50 |  39168/50000 ( 78%) ] Loss: 0.9507 top1= 64.7727

=== Log global consensus distance @ E18B50 ===
consensus_distance=1.734



=== Log clique consensus distance @ E18B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=6.983


[E18B60 |  46848/50000 ( 94%) ] Loss: 0.8894 top1= 67.8977

=== Log global consensus distance @ E18B60 ===
consensus_distance=1.746



=== Log clique consensus distance @ E18B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.028



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0225 top1= 63.2312


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1597 top1= 57.5721


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2280 top1= 57.8926

Train epoch 19
[E19B0  |    768/50000 (  2%) ] Loss: 0.9944 top1= 64.2045

=== Log global consensus distance @ E19B0 ===
consensus_distance=1.746



=== Log clique consensus distance @ E19B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.034


[E19B10 |   8448/50000 ( 17%) ] Loss: 0.9431 top1= 67.8977

=== Log global consensus distance @ E19B10 ===
consensus_distance=1.742



=== Log clique consensus distance @ E19B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.014


[E19B20 |  16128/50000 ( 32%) ] Loss: 0.9412 top1= 68.0398

=== Log global consensus distance @ E19B20 ===
consensus_distance=1.759



=== Log clique consensus distance @ E19B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.086


[E19B30 |  23808/50000 ( 48%) ] Loss: 0.9040 top1= 66.9034

=== Log global consensus distance @ E19B30 ===
consensus_distance=1.789



=== Log clique consensus distance @ E19B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.195


[E19B40 |  31488/50000 ( 63%) ] Loss: 0.9572 top1= 66.9034

=== Log global consensus distance @ E19B40 ===
consensus_distance=1.795



=== Log clique consensus distance @ E19B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.224


[E19B50 |  39168/50000 ( 78%) ] Loss: 0.9045 top1= 66.4773

=== Log global consensus distance @ E19B50 ===
consensus_distance=1.814



=== Log clique consensus distance @ E19B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.302


[E19B60 |  46848/50000 ( 94%) ] Loss: 0.8955 top1= 67.3295

=== Log global consensus distance @ E19B60 ===
consensus_distance=1.812



=== Log clique consensus distance @ E19B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.293



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9995 top1= 64.0725


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1638 top1= 58.1530


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1502 top1= 59.7857

Train epoch 20
[E20B0  |    768/50000 (  2%) ] Loss: 0.9517 top1= 67.4716

=== Log global consensus distance @ E20B0 ===
consensus_distance=1.809



=== Log clique consensus distance @ E20B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.287


[E20B10 |   8448/50000 ( 17%) ] Loss: 0.8968 top1= 68.6080

=== Log global consensus distance @ E20B10 ===
consensus_distance=1.796



=== Log clique consensus distance @ E20B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.227


[E20B20 |  16128/50000 ( 32%) ] Loss: 0.8826 top1= 68.4659

=== Log global consensus distance @ E20B20 ===
consensus_distance=1.801



=== Log clique consensus distance @ E20B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.252


[E20B30 |  23808/50000 ( 48%) ] Loss: 0.8793 top1= 69.1761

=== Log global consensus distance @ E20B30 ===
consensus_distance=1.817



=== Log clique consensus distance @ E20B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.310


[E20B40 |  31488/50000 ( 63%) ] Loss: 0.8765 top1= 68.1818

=== Log global consensus distance @ E20B40 ===
consensus_distance=1.811



=== Log clique consensus distance @ E20B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.292


[E20B50 |  39168/50000 ( 78%) ] Loss: 0.8929 top1= 68.1818

=== Log global consensus distance @ E20B50 ===
consensus_distance=1.811



=== Log clique consensus distance @ E20B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.292


[E20B60 |  46848/50000 ( 94%) ] Loss: 0.8780 top1= 68.6080

=== Log global consensus distance @ E20B60 ===
consensus_distance=1.813



=== Log clique consensus distance @ E20B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.296



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9947 top1= 64.5333


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1332 top1= 59.2147


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1689 top1= 60.1462

Train epoch 21
[E21B0  |    768/50000 (  2%) ] Loss: 0.9417 top1= 65.9091

=== Log global consensus distance @ E21B0 ===
consensus_distance=1.806



=== Log clique consensus distance @ E21B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.274


[E21B10 |   8448/50000 ( 17%) ] Loss: 0.8825 top1= 68.4659

=== Log global consensus distance @ E21B10 ===
consensus_distance=1.787



=== Log clique consensus distance @ E21B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.186


[E21B20 |  16128/50000 ( 32%) ] Loss: 0.8557 top1= 69.1761

=== Log global consensus distance @ E21B20 ===
consensus_distance=1.790



=== Log clique consensus distance @ E21B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.207


[E21B30 |  23808/50000 ( 48%) ] Loss: 0.8538 top1= 70.3125

=== Log global consensus distance @ E21B30 ===
consensus_distance=1.813



=== Log clique consensus distance @ E21B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.298


[E21B40 |  31488/50000 ( 63%) ] Loss: 0.8595 top1= 70.3125

=== Log global consensus distance @ E21B40 ===
consensus_distance=1.826



=== Log clique consensus distance @ E21B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.346


[E21B50 |  39168/50000 ( 78%) ] Loss: 0.8828 top1= 67.6136

=== Log global consensus distance @ E21B50 ===
consensus_distance=1.841



=== Log clique consensus distance @ E21B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.408


[E21B60 |  46848/50000 ( 94%) ] Loss: 0.8244 top1= 71.0227

=== Log global consensus distance @ E21B60 ===
consensus_distance=1.844



=== Log clique consensus distance @ E21B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.425



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9515 top1= 66.0357


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0569 top1= 62.0092


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1765 top1= 60.6871

Train epoch 22
[E22B0  |    768/50000 (  2%) ] Loss: 0.9284 top1= 67.3295

=== Log global consensus distance @ E22B0 ===
consensus_distance=1.841



=== Log clique consensus distance @ E22B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.416


[E22B10 |   8448/50000 ( 17%) ] Loss: 0.8712 top1= 67.8977

=== Log global consensus distance @ E22B10 ===
consensus_distance=1.832



=== Log clique consensus distance @ E22B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.376


[E22B20 |  16128/50000 ( 32%) ] Loss: 0.8370 top1= 70.0284

=== Log global consensus distance @ E22B20 ===
consensus_distance=1.845



=== Log clique consensus distance @ E22B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.429


[E22B30 |  23808/50000 ( 48%) ] Loss: 0.8574 top1= 70.8807

=== Log global consensus distance @ E22B30 ===
consensus_distance=1.870



=== Log clique consensus distance @ E22B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.520


[E22B40 |  31488/50000 ( 63%) ] Loss: 0.8098 top1= 72.0170

=== Log global consensus distance @ E22B40 ===
consensus_distance=1.876



=== Log clique consensus distance @ E22B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.546


[E22B50 |  39168/50000 ( 78%) ] Loss: 0.8788 top1= 68.1818

=== Log global consensus distance @ E22B50 ===
consensus_distance=1.893



=== Log clique consensus distance @ E22B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.621


[E22B60 |  46848/50000 ( 94%) ] Loss: 0.7775 top1= 73.4375

=== Log global consensus distance @ E22B60 ===
consensus_distance=1.903



=== Log clique consensus distance @ E22B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.658



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9338 top1= 66.7869


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9932 top1= 64.0024


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2190 top1= 60.4467

Train epoch 23
[E23B0  |    768/50000 (  2%) ] Loss: 0.8985 top1= 69.0341

=== Log global consensus distance @ E23B0 ===
consensus_distance=1.905



=== Log clique consensus distance @ E23B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.670


[E23B10 |   8448/50000 ( 17%) ] Loss: 0.8389 top1= 70.3125

=== Log global consensus distance @ E23B10 ===
consensus_distance=1.894



=== Log clique consensus distance @ E23B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.626


[E23B20 |  16128/50000 ( 32%) ] Loss: 0.8278 top1= 70.7386

=== Log global consensus distance @ E23B20 ===
consensus_distance=1.913



=== Log clique consensus distance @ E23B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.703


[E23B30 |  23808/50000 ( 48%) ] Loss: 0.8199 top1= 71.1648

=== Log global consensus distance @ E23B30 ===
consensus_distance=1.936



=== Log clique consensus distance @ E23B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.791


[E23B40 |  31488/50000 ( 63%) ] Loss: 0.8240 top1= 71.8750

=== Log global consensus distance @ E23B40 ===
consensus_distance=1.940



=== Log clique consensus distance @ E23B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.798


[E23B50 |  39168/50000 ( 78%) ] Loss: 0.8386 top1= 70.3125

=== Log global consensus distance @ E23B50 ===
consensus_distance=1.951



=== Log clique consensus distance @ E23B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.848


[E23B60 |  46848/50000 ( 94%) ] Loss: 0.7937 top1= 71.4489

=== Log global consensus distance @ E23B60 ===
consensus_distance=1.943



=== Log clique consensus distance @ E23B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.818



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9272 top1= 66.8269


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9554 top1= 65.7151


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2472 top1= 60.0260

Train epoch 24
[E24B0  |    768/50000 (  2%) ] Loss: 0.8746 top1= 68.8920

=== Log global consensus distance @ E24B0 ===
consensus_distance=1.936



=== Log clique consensus distance @ E24B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.793


[E24B10 |   8448/50000 ( 17%) ] Loss: 0.7850 top1= 72.3011

=== Log global consensus distance @ E24B10 ===
consensus_distance=1.923



=== Log clique consensus distance @ E24B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.745


[E24B20 |  16128/50000 ( 32%) ] Loss: 0.7932 top1= 70.7386

=== Log global consensus distance @ E24B20 ===
consensus_distance=1.939



=== Log clique consensus distance @ E24B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.810


[E24B30 |  23808/50000 ( 48%) ] Loss: 0.8014 top1= 72.8693

=== Log global consensus distance @ E24B30 ===
consensus_distance=1.963



=== Log clique consensus distance @ E24B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.893


[E24B40 |  31488/50000 ( 63%) ] Loss: 0.7926 top1= 74.1477

=== Log global consensus distance @ E24B40 ===
consensus_distance=1.961



=== Log clique consensus distance @ E24B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=7.889


[E24B50 |  39168/50000 ( 78%) ] Loss: 0.8137 top1= 72.0170

=== Log global consensus distance @ E24B50 ===
consensus_distance=1.991



=== Log clique consensus distance @ E24B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=8.014


[E24B60 |  46848/50000 ( 94%) ] Loss: 0.7845 top1= 73.8636

=== Log global consensus distance @ E24B60 ===
consensus_distance=2.001



=== Log clique consensus distance @ E24B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=8.048



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8841 top1= 68.4295


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9702 top1= 64.9239


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0788 top1= 63.5417

Train epoch 25
[E25B0  |    768/50000 (  2%) ] Loss: 0.8053 top1= 72.1591

=== Log global consensus distance @ E25B0 ===
consensus_distance=2.006



=== Log clique consensus distance @ E25B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=8.074


[E25B10 |   8448/50000 ( 17%) ] Loss: 0.7996 top1= 70.7386

=== Log global consensus distance @ E25B10 ===
consensus_distance=2.002



=== Log clique consensus distance @ E25B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=8.057


[E25B20 |  16128/50000 ( 32%) ] Loss: 0.7700 top1= 72.4432

=== Log global consensus distance @ E25B20 ===
consensus_distance=2.030



=== Log clique consensus distance @ E25B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=8.170


[E25B30 |  23808/50000 ( 48%) ] Loss: 0.7536 top1= 73.2955

=== Log global consensus distance @ E25B30 ===
consensus_distance=2.065



=== Log clique consensus distance @ E25B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=8.308


[E25B40 |  31488/50000 ( 63%) ] Loss: 0.7941 top1= 73.2955

=== Log global consensus distance @ E25B40 ===
consensus_distance=2.069



=== Log clique consensus distance @ E25B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=8.322


[E25B50 |  39168/50000 ( 78%) ] Loss: 0.7747 top1= 72.8693

=== Log global consensus distance @ E25B50 ===
consensus_distance=2.094



=== Log clique consensus distance @ E25B50 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=8.420


[E25B60 |  46848/50000 ( 94%) ] Loss: 0.7359 top1= 72.4432

=== Log global consensus distance @ E25B60 ===
consensus_distance=2.095



=== Log clique consensus distance @ E25B60 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=8.430



=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8688 top1= 69.4712


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9146 top1= 67.0573


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0724 top1= 64.4331

Train epoch 26
[E26B0  |    768/50000 (  2%) ] Loss: 0.8054 top1= 70.7386

=== Log global consensus distance @ E26B0 ===
consensus_distance=2.090



=== Log clique consensus distance @ E26B0 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=8.414


[E26B10 |   8448/50000 ( 17%) ] Loss: 0.7327 top1= 74.1477

=== Log global consensus distance @ E26B10 ===
consensus_distance=2.077



=== Log clique consensus distance @ E26B10 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=8.359


[E26B20 |  16128/50000 ( 32%) ] Loss: 0.7586 top1= 72.8693

=== Log global consensus distance @ E26B20 ===
consensus_distance=2.105



=== Log clique consensus distance @ E26B20 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=8.475


[E26B30 |  23808/50000 ( 48%) ] Loss: 0.7945 top1= 71.8750

=== Log global consensus distance @ E26B30 ===
consensus_distance=2.124



=== Log clique consensus distance @ E26B30 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=8.546


[E26B40 |  31488/50000 ( 63%) ] Loss: 0.7395 top1= 75.0000

=== Log global consensus distance @ E26B40 ===
consensus_distance=2.128



=== Log clique consensus distance @ E26B40 ===
clique1_consensus_distance=0.001
clique2_consensus_distance=8.550


