
=== 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=20,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=20,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=20,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=20,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=20,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=20,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=20,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=20,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=20,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=20,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=20,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=20,rank=11,shuffle=True)'}
=> Add worker SGDMWorker(index=11, 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=20,rank=12,shuffle=True)'}
=> Add worker SGDMWorker(index=12, 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=20,rank=13,shuffle=True)'}
=> Add worker SGDMWorker(index=13, 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=20,rank=14,shuffle=True)'}
=> Add worker SGDMWorker(index=14, 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=20,rank=15,shuffle=True)'}
=> Add worker SGDMWorker(index=15, 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=20,rank=16,shuffle=True)'}
=> Add worker SGDMWorker(index=16, 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=20,rank=17,shuffle=True)'}
=> Add worker SGDMWorker(index=17, 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=20,rank=18,shuffle=True)'}
=> Add worker SGDMWorker(index=18, 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=20,rank=19,shuffle=True)'}
=> Add worker SGDMWorker(index=19, momentum=0.9)

=== Start adding graph ===
<codes.graph_utils.Dumbbell object at 0x7eff8892c730>

{'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  |   1280/50000 (  3%) ] Loss: 2.3046 top1= 10.0781

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([2, 4, 4, 3, 2], device='cuda:0')
Worker 1 has targets: tensor([1, 2, 0, 2, 3], device='cuda:0')
Worker 2 has targets: tensor([4, 4, 2, 4, 3], device='cuda:0')
Worker 3 has targets: tensor([0, 1, 3, 0, 2], device='cuda:0')
Worker 4 has targets: tensor([2, 4, 2, 1, 3], device='cuda:0')
Worker 5 has targets: tensor([2, 1, 4, 1, 4], device='cuda:0')
Worker 6 has targets: tensor([3, 4, 2, 1, 2], device='cuda:0')
Worker 7 has targets: tensor([0, 0, 4, 2, 2], device='cuda:0')
Worker 8 has targets: tensor([0, 4, 3, 0, 2], device='cuda:0')
Worker 9 has targets: tensor([3, 4, 3, 3, 1], device='cuda:0')
Worker 10 has targets: tensor([6, 7, 6, 9, 6], device='cuda:0')
Worker 11 has targets: tensor([9, 8, 6, 8, 8], device='cuda:0')
Worker 12 has targets: tensor([5, 8, 7, 6, 5], device='cuda:0')
Worker 13 has targets: tensor([7, 5, 9, 8, 9], device='cuda:0')
Worker 14 has targets: tensor([5, 9, 7, 7, 5], device='cuda:0')
Worker 15 has targets: tensor([8, 8, 5, 7, 9], device='cuda:0')
Worker 16 has targets: tensor([7, 7, 9, 6, 8], device='cuda:0')
Worker 17 has targets: tensor([5, 6, 9, 9, 5], device='cuda:0')
Worker 18 has targets: tensor([5, 9, 9, 9, 9], device='cuda:0')
Worker 19 has targets: tensor([7, 5, 8, 8, 9], device='cuda:0')



=== Log mixing matrix @ E1B0 ===
[[0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.    0.
  0.    0.    0.    0.    0.    0.    0.    0.091]
 [0.091 0.182 0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.    0.
  0.    0.    0.    0.    0.    0.    0.    0.   ]
 [0.091 0.091 0.182 0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.    0.
  0.    0.    0.    0.    0.    0.    0.    0.   ]
 [0.091 0.091 0.091 0.182 0.091 0.091 0.091 0.091 0.091 0.091 0.    0.
  0.    0.    0.    0.    0.    0.    0.    0.   ]
 [0.091 0.091 0.091 0.091 0.182 0.091 0.091 0.091 0.091 0.091 0.    0.
  0.    0.    0.    0.    0.    0.    0.    0.   ]
 [0.091 0.091 0.091 0.091 0.091 0.182 0.091 0.091 0.091 0.091 0.    0.
  0.    0.    0.    0.    0.    0.    0.    0.   ]
 [0.091 0.091 0.091 0.091 0.091 0.091 0.182 0.091 0.091 0.091 0.    0.
  0.    0.    0.    0.    0.    0.    0.    0.   ]
 [0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.182 0.091 0.091 0.    0.
  0.    0.    0.    0.    0.    0.    0.    0.   ]
 [0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.182 0.091 0.    0.
  0.    0.    0.    0.    0.    0.    0.    0.   ]
 [0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.182 0.    0.
  0.    0.    0.    0.    0.    0.    0.    0.   ]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.182 0.091
  0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.091]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.091 0.182
  0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.091]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.091 0.091
  0.182 0.091 0.091 0.091 0.091 0.091 0.091 0.091]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.091 0.091
  0.091 0.182 0.091 0.091 0.091 0.091 0.091 0.091]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.091 0.091
  0.091 0.091 0.182 0.091 0.091 0.091 0.091 0.091]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.091 0.091
  0.091 0.091 0.091 0.182 0.091 0.091 0.091 0.091]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.091 0.091
  0.091 0.091 0.091 0.091 0.182 0.091 0.091 0.091]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.091 0.091
  0.091 0.091 0.091 0.091 0.091 0.182 0.091 0.091]
 [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.091 0.091
  0.091 0.091 0.091 0.091 0.091 0.091 0.182 0.091]
 [0.091 0.    0.    0.    0.    0.    0.    0.    0.    0.    0.091 0.091
  0.091 0.091 0.091 0.091 0.091 0.091 0.091 0.091]]


[E 1B10 |  14080/50000 ( 28%) ] Loss: 2.1022 top1= 18.6719
[E 1B20 |  26880/50000 ( 54%) ] Loss: 1.8292 top1= 20.0781
[E 1B30 |  39680/50000 ( 79%) ] Loss: 1.7104 top1= 19.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3076 top1=  9.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1174 top1= 10.7472


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3167 top1= 12.4299

Train epoch 2
[E 2B0  |   1280/50000 (  3%) ] Loss: 1.6436 top1= 20.5469
[E 2B10 |  14080/50000 ( 28%) ] Loss: 1.6680 top1= 25.3906
[E 2B20 |  26880/50000 ( 54%) ] Loss: 1.5834 top1= 25.6250
[E 2B30 |  39680/50000 ( 79%) ] Loss: 1.5624 top1= 29.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3139 top1= 10.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0846 top1= 15.1342


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2262 top1= 18.8802

Train epoch 3
[E 3B0  |   1280/50000 (  3%) ] Loss: 1.5078 top1= 34.4531
[E 3B10 |  14080/50000 ( 28%) ] Loss: 1.5184 top1= 34.8438
[E 3B20 |  26880/50000 ( 54%) ] Loss: 1.4884 top1= 33.9844
[E 3B30 |  39680/50000 ( 79%) ] Loss: 1.4419 top1= 36.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3187 top1= 10.0861


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5567 top1= 21.6146


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8967 top1= 20.2724

Train epoch 4
[E 4B0  |   1280/50000 (  3%) ] Loss: 1.4030 top1= 39.2188
[E 4B10 |  14080/50000 ( 28%) ] Loss: 1.3371 top1= 43.0469
[E 4B20 |  26880/50000 ( 54%) ] Loss: 1.5446 top1= 32.2656
[E 4B30 |  39680/50000 ( 79%) ] Loss: 1.4572 top1= 32.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3475 top1= 11.7788


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4765 top1= 16.9171


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6309 top1= 25.2504

Train epoch 5
[E 5B0  |   1280/50000 (  3%) ] Loss: 1.3755 top1= 42.2656
[E 5B10 |  14080/50000 ( 28%) ] Loss: 1.3216 top1= 44.8438
[E 5B20 |  26880/50000 ( 54%) ] Loss: 1.2636 top1= 44.0625
[E 5B30 |  39680/50000 ( 79%) ] Loss: 1.3130 top1= 42.4219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.3306 top1= 13.1110


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7940 top1= 16.1759


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9039 top1= 24.4091

Train epoch 6
[E 6B0  |   1280/50000 (  3%) ] Loss: 1.3753 top1= 40.3125
[E 6B10 |  14080/50000 ( 28%) ] Loss: 1.2896 top1= 45.1562
[E 6B20 |  26880/50000 ( 54%) ] Loss: 1.2400 top1= 46.0938
[E 6B30 |  39680/50000 ( 79%) ] Loss: 1.1424 top1= 53.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.2473 top1= 15.2043


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8933 top1= 22.6262


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4803 top1= 30.8794

Train epoch 7
[E 7B0  |   1280/50000 (  3%) ] Loss: 1.1942 top1= 51.9531
[E 7B10 |  14080/50000 ( 28%) ] Loss: 1.1973 top1= 50.3125
[E 7B20 |  26880/50000 ( 54%) ] Loss: 1.2471 top1= 48.3594
[E 7B30 |  39680/50000 ( 79%) ] Loss: 1.0815 top1= 55.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0581 top1= 23.5176


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4314 top1= 26.7628


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2455 top1= 31.6807

Train epoch 8
[E 8B0  |   1280/50000 (  3%) ] Loss: 1.0677 top1= 55.6250
[E 8B10 |  14080/50000 ( 28%) ] Loss: 1.1328 top1= 52.8125
[E 8B20 |  26880/50000 ( 54%) ] Loss: 1.0843 top1= 55.1562
[E 8B30 |  39680/50000 ( 79%) ] Loss: 0.9256 top1= 64.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9522 top1= 28.7159


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2345 top1= 29.0465


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9813 top1= 34.1546

Train epoch 9
[E 9B0  |   1280/50000 (  3%) ] Loss: 0.9534 top1= 61.3281
[E 9B10 |  14080/50000 ( 28%) ] Loss: 0.9604 top1= 62.0312
[E 9B20 |  26880/50000 ( 54%) ] Loss: 0.9913 top1= 60.3125
[E 9B30 |  39680/50000 ( 79%) ] Loss: 0.8488 top1= 66.1719

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9110 top1= 31.5204


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2270 top1= 30.3085


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6650 top1= 36.7688

Train epoch 10
[E10B0  |   1280/50000 (  3%) ] Loss: 0.8639 top1= 67.0312
[E10B10 |  14080/50000 ( 28%) ] Loss: 0.8743 top1= 65.0781
[E10B20 |  26880/50000 ( 54%) ] Loss: 1.0219 top1= 59.9219
[E10B30 |  39680/50000 ( 79%) ] Loss: 0.8311 top1= 67.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7948 top1= 34.7256


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4335 top1= 30.9495


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2867 top1= 37.1294

Train epoch 11
[E11B0  |   1280/50000 (  3%) ] Loss: 0.8428 top1= 67.6562
[E11B10 |  14080/50000 ( 28%) ] Loss: 0.8311 top1= 68.5156
[E11B20 |  26880/50000 ( 54%) ] Loss: 0.8493 top1= 66.8750
[E11B30 |  39680/50000 ( 79%) ] Loss: 0.7026 top1= 73.2031

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8174 top1= 35.9675


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4361 top1= 32.6122


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8931 top1= 38.4115

Train epoch 12
[E12B0  |   1280/50000 (  3%) ] Loss: 0.7593 top1= 71.1719
[E12B10 |  14080/50000 ( 28%) ] Loss: 0.8190 top1= 67.8125
[E12B20 |  26880/50000 ( 54%) ] Loss: 0.7951 top1= 68.8281
[E12B30 |  39680/50000 ( 79%) ] Loss: 0.7301 top1= 71.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7007 top1= 36.6687


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2419 top1= 33.8842


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9735 top1= 38.8021

Train epoch 13
[E13B0  |   1280/50000 (  3%) ] Loss: 0.7124 top1= 72.5781
[E13B10 |  14080/50000 ( 28%) ] Loss: 0.7840 top1= 71.0938
[E13B20 |  26880/50000 ( 54%) ] Loss: 0.7797 top1= 70.2344
[E13B30 |  39680/50000 ( 79%) ] Loss: 0.6803 top1= 73.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7138 top1= 40.3646


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4986 top1= 35.5769


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6643 top1= 39.4231

Train epoch 14
[E14B0  |   1280/50000 (  3%) ] Loss: 0.6661 top1= 75.0781
[E14B10 |  14080/50000 ( 28%) ] Loss: 0.6835 top1= 73.1250
[E14B20 |  26880/50000 ( 54%) ] Loss: 0.7054 top1= 74.2969
[E14B30 |  39680/50000 ( 79%) ] Loss: 0.6415 top1= 76.6406

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.5895 top1= 43.6198


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4028 top1= 36.1078


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0594 top1= 39.0325

Train epoch 15
[E15B0  |   1280/50000 (  3%) ] Loss: 0.6342 top1= 77.1875
[E15B10 |  14080/50000 ( 28%) ] Loss: 0.6887 top1= 74.6875
[E15B20 |  26880/50000 ( 54%) ] Loss: 0.6550 top1= 76.4062
[E15B30 |  39680/50000 ( 79%) ] Loss: 0.5988 top1= 78.2031

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.5296 top1= 45.0020


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4771 top1= 36.1779


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4942 top1= 39.6735

Train epoch 16
[E16B0  |   1280/50000 (  3%) ] Loss: 0.6075 top1= 77.4219
[E16B10 |  14080/50000 ( 28%) ] Loss: 0.6096 top1= 76.3281
[E16B20 |  26880/50000 ( 54%) ] Loss: 0.6402 top1= 76.8750
[E16B30 |  39680/50000 ( 79%) ] Loss: 0.5790 top1= 77.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.5080 top1= 48.1070


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2124 top1= 36.9091


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4287 top1= 39.9940

Train epoch 17
[E17B0  |   1280/50000 (  3%) ] Loss: 0.5990 top1= 79.0625
[E17B10 |  14080/50000 ( 28%) ] Loss: 0.5643 top1= 78.9844
[E17B20 |  26880/50000 ( 54%) ] Loss: 0.6147 top1= 78.5938
[E17B30 |  39680/50000 ( 79%) ] Loss: 0.4997 top1= 80.7031

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4795 top1= 48.7580


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8216 top1= 37.5601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7879 top1= 40.2544

Train epoch 18
[E18B0  |   1280/50000 (  3%) ] Loss: 0.5784 top1= 78.9844
[E18B10 |  14080/50000 ( 28%) ] Loss: 0.5804 top1= 78.8281
[E18B20 |  26880/50000 ( 54%) ] Loss: 0.5520 top1= 79.5312
[E18B30 |  39680/50000 ( 79%) ] Loss: 0.5570 top1= 78.9844

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4423 top1= 52.1034


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0664 top1= 39.2027


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1305 top1= 41.9371

Train epoch 19
[E19B0  |   1280/50000 (  3%) ] Loss: 0.4800 top1= 82.5781
[E19B10 |  14080/50000 ( 28%) ] Loss: 0.5182 top1= 81.7969
[E19B20 |  26880/50000 ( 54%) ] Loss: 0.4823 top1= 82.5000
[E19B30 |  39680/50000 ( 79%) ] Loss: 0.4574 top1= 83.2031

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4508 top1= 52.8646


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2392 top1= 39.2328


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1817 top1= 42.8886

Train epoch 20
[E20B0  |   1280/50000 (  3%) ] Loss: 0.4452 top1= 84.0625
[E20B10 |  14080/50000 ( 28%) ] Loss: 0.4891 top1= 82.5000
[E20B20 |  26880/50000 ( 54%) ] Loss: 0.4684 top1= 83.5938
[E20B30 |  39680/50000 ( 79%) ] Loss: 0.4598 top1= 83.3594

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3581 top1= 55.0982


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9588 top1= 39.0825


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2918 top1= 42.8586

Train epoch 21
[E21B0  |   1280/50000 (  3%) ] Loss: 0.4709 top1= 82.5781
[E21B10 |  14080/50000 ( 28%) ] Loss: 0.4958 top1= 81.9531
[E21B20 |  26880/50000 ( 54%) ] Loss: 0.4306 top1= 84.4531
[E21B30 |  39680/50000 ( 79%) ] Loss: 0.4469 top1= 83.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3479 top1= 55.9796


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9397 top1= 39.0425


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3260 top1= 43.2993

Train epoch 22
[E22B0  |   1280/50000 (  3%) ] Loss: 0.4316 top1= 84.0625
[E22B10 |  14080/50000 ( 28%) ] Loss: 0.4511 top1= 82.6562
[E22B20 |  26880/50000 ( 54%) ] Loss: 0.4342 top1= 83.9844
[E22B30 |  39680/50000 ( 79%) ] Loss: 0.4129 top1= 85.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3434 top1= 57.6823


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6040 top1= 39.4431


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5671 top1= 43.9603

Train epoch 23
[E23B0  |   1280/50000 (  3%) ] Loss: 0.4036 top1= 86.5625
[E23B10 |  14080/50000 ( 28%) ] Loss: 0.4259 top1= 85.4688
[E23B20 |  26880/50000 ( 54%) ] Loss: 0.4004 top1= 85.8594
[E23B30 |  39680/50000 ( 79%) ] Loss: 0.3713 top1= 86.6406

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3368 top1= 59.2448


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4282 top1= 40.5148


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9663 top1= 43.4495

Train epoch 24
[E24B0  |   1280/50000 (  3%) ] Loss: 0.3919 top1= 86.7969
[E24B10 |  14080/50000 ( 28%) ] Loss: 0.4078 top1= 85.3906
[E24B20 |  26880/50000 ( 54%) ] Loss: 0.3592 top1= 87.1875
[E24B30 |  39680/50000 ( 79%) ] Loss: 0.3489 top1= 86.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2163 top1= 60.8073


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8802 top1= 40.4547


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5606 top1= 43.4195

Train epoch 25
[E25B0  |   1280/50000 (  3%) ] Loss: 0.3943 top1= 86.4844
[E25B10 |  14080/50000 ( 28%) ] Loss: 0.4130 top1= 85.7031
[E25B20 |  26880/50000 ( 54%) ] Loss: 0.3939 top1= 86.0156
[E25B30 |  39680/50000 ( 79%) ] Loss: 0.3418 top1= 87.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2865 top1= 60.8674


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8239 top1= 40.7452


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3307 top1= 42.3478

Train epoch 26
[E26B0  |   1280/50000 (  3%) ] Loss: 0.3860 top1= 86.9531
[E26B10 |  14080/50000 ( 28%) ] Loss: 0.3731 top1= 85.3125
[E26B20 |  26880/50000 ( 54%) ] Loss: 0.3627 top1= 87.8125
[E26B30 |  39680/50000 ( 79%) ] Loss: 0.3454 top1= 87.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1731 top1= 63.6218


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6215 top1= 41.0657


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8313 top1= 44.0805

Train epoch 27
[E27B0  |   1280/50000 (  3%) ] Loss: 0.3358 top1= 87.8125
[E27B10 |  14080/50000 ( 28%) ] Loss: 0.3453 top1= 87.9688
[E27B20 |  26880/50000 ( 54%) ] Loss: 0.3576 top1= 86.9531
[E27B30 |  39680/50000 ( 79%) ] Loss: 0.3234 top1= 87.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1192 top1= 65.7051


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2750 top1= 41.4163


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3672 top1= 44.2708

Train epoch 28
[E28B0  |   1280/50000 (  3%) ] Loss: 0.3306 top1= 89.4531
[E28B10 |  14080/50000 ( 28%) ] Loss: 0.3098 top1= 88.5938
[E28B20 |  26880/50000 ( 54%) ] Loss: 0.3280 top1= 88.9844
[E28B30 |  39680/50000 ( 79%) ] Loss: 0.2832 top1= 89.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2108 top1= 63.9523


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7478 top1= 41.2059


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9714 top1= 42.1575

Train epoch 29
[E29B0  |   1280/50000 (  3%) ] Loss: 0.3669 top1= 87.5781
[E29B10 |  14080/50000 ( 28%) ] Loss: 0.3378 top1= 87.5781
[E29B20 |  26880/50000 ( 54%) ] Loss: 0.3366 top1= 87.6562
[E29B30 |  39680/50000 ( 79%) ] Loss: 0.3194 top1= 88.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1946 top1= 65.4147


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5061 top1= 41.4062


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9671 top1= 44.8017

Train epoch 30
[E30B0  |   1280/50000 (  3%) ] Loss: 0.3059 top1= 88.9844
[E30B10 |  14080/50000 ( 28%) ] Loss: 0.2753 top1= 89.3750
[E30B20 |  26880/50000 ( 54%) ] Loss: 0.3150 top1= 88.9844
[E30B30 |  39680/50000 ( 79%) ] Loss: 0.3050 top1= 88.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1376 top1= 66.5264


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8298 top1= 40.6851


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8393 top1= 45.1823

Train epoch 31
[E31B0  |   1280/50000 (  3%) ] Loss: 0.2976 top1= 89.4531
[E31B10 |  14080/50000 ( 28%) ] Loss: 0.3022 top1= 88.9844
[E31B20 |  26880/50000 ( 54%) ] Loss: 0.2944 top1= 88.7500
[E31B30 |  39680/50000 ( 79%) ] Loss: 0.2608 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1673 top1= 65.5749


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5504 top1= 41.2260


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2246 top1= 45.2023

Train epoch 32
[E32B0  |   1280/50000 (  3%) ] Loss: 0.2919 top1= 89.6875
[E32B10 |  14080/50000 ( 28%) ] Loss: 0.3233 top1= 89.1406
[E32B20 |  26880/50000 ( 54%) ] Loss: 0.2948 top1= 88.9844
[E32B30 |  39680/50000 ( 79%) ] Loss: 0.3021 top1= 89.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1412 top1= 67.1174


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7827 top1= 41.5565


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7216 top1= 45.0521

Train epoch 33
[E33B0  |   1280/50000 (  3%) ] Loss: 0.2626 top1= 89.6875
[E33B10 |  14080/50000 ( 28%) ] Loss: 0.2924 top1= 89.1406
[E33B20 |  26880/50000 ( 54%) ] Loss: 0.3030 top1= 88.6719
[E33B30 |  39680/50000 ( 79%) ] Loss: 0.2138 top1= 91.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1778 top1= 66.5465


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2265 top1= 41.7668


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3687 top1= 45.5829

Train epoch 34
[E34B0  |   1280/50000 (  3%) ] Loss: 0.2779 top1= 89.9219
[E34B10 |  14080/50000 ( 28%) ] Loss: 0.2544 top1= 90.1562
[E34B20 |  26880/50000 ( 54%) ] Loss: 0.2902 top1= 90.1562
[E34B30 |  39680/50000 ( 79%) ] Loss: 0.2598 top1= 90.2344

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1725 top1= 68.0088


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5461 top1= 41.7268


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8571 top1= 45.1022

Train epoch 35
[E35B0  |   1280/50000 (  3%) ] Loss: 0.2628 top1= 89.9219
[E35B10 |  14080/50000 ( 28%) ] Loss: 0.2474 top1= 90.7031
[E35B20 |  26880/50000 ( 54%) ] Loss: 0.2966 top1= 89.4531
[E35B30 |  39680/50000 ( 79%) ] Loss: 0.2676 top1= 89.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1011 top1= 68.9704


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8966 top1= 41.6767


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4400 top1= 45.3626

Train epoch 36
[E36B0  |   1280/50000 (  3%) ] Loss: 0.2552 top1= 90.7031
[E36B10 |  14080/50000 ( 28%) ] Loss: 0.2533 top1= 90.7812
[E36B20 |  26880/50000 ( 54%) ] Loss: 0.2536 top1= 90.8594
[E36B30 |  39680/50000 ( 79%) ] Loss: 0.2342 top1= 91.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2327 top1= 67.5180


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4558 top1= 41.4563


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7426 top1= 45.9435

Train epoch 37
[E37B0  |   1280/50000 (  3%) ] Loss: 0.2073 top1= 92.8906
[E37B10 |  14080/50000 ( 28%) ] Loss: 0.2506 top1= 90.6250
[E37B20 |  26880/50000 ( 54%) ] Loss: 0.2572 top1= 90.7031
[E37B30 |  39680/50000 ( 79%) ] Loss: 0.2470 top1= 90.5469

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2242 top1= 67.6983


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3104 top1= 41.8670


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2923 top1= 45.0921

Train epoch 38
[E38B0  |   1280/50000 (  3%) ] Loss: 0.2287 top1= 92.1094
[E38B10 |  14080/50000 ( 28%) ] Loss: 0.2421 top1= 91.4844
[E38B20 |  26880/50000 ( 54%) ] Loss: 0.2541 top1= 90.0000
[E38B30 |  39680/50000 ( 79%) ] Loss: 0.2430 top1= 91.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1327 top1= 68.4295


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4363 top1= 41.1358


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8503 top1= 45.4728

Train epoch 39
[E39B0  |   1280/50000 (  3%) ] Loss: 0.2665 top1= 90.4688
[E39B10 |  14080/50000 ( 28%) ] Loss: 0.2535 top1= 90.1562
[E39B20 |  26880/50000 ( 54%) ] Loss: 0.2206 top1= 92.1875
[E39B30 |  39680/50000 ( 79%) ] Loss: 0.2273 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1134 top1= 68.6198


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6896 top1= 42.1875


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2129 top1= 44.7015

Train epoch 40
[E40B0  |   1280/50000 (  3%) ] Loss: 0.2047 top1= 93.1250
[E40B10 |  14080/50000 ( 28%) ] Loss: 0.2456 top1= 91.0156
[E40B20 |  26880/50000 ( 54%) ] Loss: 0.2488 top1= 90.4688
[E40B30 |  39680/50000 ( 79%) ] Loss: 0.2072 top1= 91.7969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1430 top1= 67.9988


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2469 top1= 41.8670


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1405 top1= 45.4327

Train epoch 41
[E41B0  |   1280/50000 (  3%) ] Loss: 0.2554 top1= 90.9375
[E41B10 |  14080/50000 ( 28%) ] Loss: 0.2718 top1= 89.8438
[E41B20 |  26880/50000 ( 54%) ] Loss: 0.2981 top1= 88.6719
[E41B30 |  39680/50000 ( 79%) ] Loss: 0.2224 top1= 91.7969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1021 top1= 68.8602


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8722 top1= 40.4347


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1898 top1= 45.2324

Train epoch 42
[E42B0  |   1280/50000 (  3%) ] Loss: 0.2929 top1= 88.9062
[E42B10 |  14080/50000 ( 28%) ] Loss: 0.2337 top1= 91.2500
[E42B20 |  26880/50000 ( 54%) ] Loss: 0.2564 top1= 90.2344
[E42B30 |  39680/50000 ( 79%) ] Loss: 0.1929 top1= 93.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1537 top1= 68.2091


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3980 top1= 42.7183


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5170 top1= 45.8834

Train epoch 43
[E43B0  |   1280/50000 (  3%) ] Loss: 0.2063 top1= 92.7344
[E43B10 |  14080/50000 ( 28%) ] Loss: 0.2518 top1= 90.2344
[E43B20 |  26880/50000 ( 54%) ] Loss: 0.2453 top1= 89.9219
[E43B30 |  39680/50000 ( 79%) ] Loss: 0.2514 top1= 91.1719

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0697 top1= 69.2107


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3826 top1= 42.4579


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2407 top1= 44.6615

Train epoch 44
[E44B0  |   1280/50000 (  3%) ] Loss: 0.2236 top1= 92.4219
[E44B10 |  14080/50000 ( 28%) ] Loss: 0.2028 top1= 92.5000
[E44B20 |  26880/50000 ( 54%) ] Loss: 0.2147 top1= 91.7969
[E44B30 |  39680/50000 ( 79%) ] Loss: 0.1784 top1= 93.5156

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0726 top1= 69.7516


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4817 top1= 41.9671


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9337 top1= 45.4327

Train epoch 45
[E45B0  |   1280/50000 (  3%) ] Loss: 0.2126 top1= 92.7344
[E45B10 |  14080/50000 ( 28%) ] Loss: 0.1959 top1= 92.2656
[E45B20 |  26880/50000 ( 54%) ] Loss: 0.2088 top1= 92.2656
[E45B30 |  39680/50000 ( 79%) ] Loss: 0.1932 top1= 93.2031

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1637 top1= 68.7099


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0109 top1= 41.9071


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1960 top1= 45.2224

Train epoch 46
[E46B0  |   1280/50000 (  3%) ] Loss: 0.1957 top1= 93.1250
[E46B10 |  14080/50000 ( 28%) ] Loss: 0.2243 top1= 91.7969
[E46B20 |  26880/50000 ( 54%) ] Loss: 0.1920 top1= 92.8125
[E46B30 |  39680/50000 ( 79%) ] Loss: 0.2096 top1= 92.1094

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1687 top1= 68.8001


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2794 top1= 42.0974


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.0367 top1= 45.3826

Train epoch 47
[E47B0  |   1280/50000 (  3%) ] Loss: 0.1944 top1= 92.6562
[E47B10 |  14080/50000 ( 28%) ] Loss: 0.2389 top1= 91.4844
[E47B20 |  26880/50000 ( 54%) ] Loss: 0.1460 top1= 94.5312
[E47B30 |  39680/50000 ( 79%) ] Loss: 0.1784 top1= 93.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1987 top1= 68.4896


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0159 top1= 42.4379


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3611 top1= 45.6631

Train epoch 48
[E48B0  |   1280/50000 (  3%) ] Loss: 0.1744 top1= 93.9062
[E48B10 |  14080/50000 ( 28%) ] Loss: 0.1787 top1= 93.1250
[E48B20 |  26880/50000 ( 54%) ] Loss: 0.1561 top1= 93.9844
[E48B30 |  39680/50000 ( 79%) ] Loss: 0.1625 top1= 93.5156

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1744 top1= 69.7316


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2314 top1= 42.4579


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4511 top1= 45.8634

Train epoch 49
[E49B0  |   1280/50000 (  3%) ] Loss: 0.1521 top1= 94.2188
[E49B10 |  14080/50000 ( 28%) ] Loss: 0.1792 top1= 93.2812
[E49B20 |  26880/50000 ( 54%) ] Loss: 0.1950 top1= 92.8906
[E49B30 |  39680/50000 ( 79%) ] Loss: 0.1333 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1414 top1= 70.1522


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0260 top1= 42.5180


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1567 top1= 46.0337

Train epoch 50
[E50B0  |   1280/50000 (  3%) ] Loss: 0.1606 top1= 94.3750
[E50B10 |  14080/50000 ( 28%) ] Loss: 0.1984 top1= 93.7500
[E50B20 |  26880/50000 ( 54%) ] Loss: 0.1756 top1= 93.1250
[E50B30 |  39680/50000 ( 79%) ] Loss: 0.1512 top1= 93.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2702 top1= 66.6166


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.7895 top1= 40.9756


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4892 top1= 44.7516

Train epoch 51
[E51B0  |   1280/50000 (  3%) ] Loss: 0.2427 top1= 91.4844
[E51B10 |  14080/50000 ( 28%) ] Loss: 0.2507 top1= 90.7031
[E51B20 |  26880/50000 ( 54%) ] Loss: 0.1942 top1= 93.0469
[E51B30 |  39680/50000 ( 79%) ] Loss: 0.1376 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1319 top1= 70.7232


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3220 top1= 42.9187


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3395 top1= 45.7732

Train epoch 52
[E52B0  |   1280/50000 (  3%) ] Loss: 0.1512 top1= 94.8438
[E52B10 |  14080/50000 ( 28%) ] Loss: 0.1323 top1= 94.8438
[E52B20 |  26880/50000 ( 54%) ] Loss: 0.1503 top1= 94.5312
[E52B30 |  39680/50000 ( 79%) ] Loss: 0.1360 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2949 top1= 68.4395


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2177 top1= 42.0373


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8034 top1= 45.9135

Train epoch 53
[E53B0  |   1280/50000 (  3%) ] Loss: 0.1745 top1= 94.3750
[E53B10 |  14080/50000 ( 28%) ] Loss: 0.1555 top1= 94.2969
[E53B20 |  26880/50000 ( 54%) ] Loss: 0.1476 top1= 94.4531
[E53B30 |  39680/50000 ( 79%) ] Loss: 0.1305 top1= 94.2969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2078 top1= 68.7200


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1795 top1= 41.6567


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3744 top1= 46.5545

Train epoch 54
[E54B0  |   1280/50000 (  3%) ] Loss: 0.1567 top1= 94.2188
[E54B10 |  14080/50000 ( 28%) ] Loss: 0.1318 top1= 94.9219
[E54B20 |  26880/50000 ( 54%) ] Loss: 0.1457 top1= 93.9844
[E54B30 |  39680/50000 ( 79%) ] Loss: 0.1421 top1= 94.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3027 top1= 68.4095


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.8229 top1= 41.9271


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9753 top1= 45.7632

Train epoch 55
[E55B0  |   1280/50000 (  3%) ] Loss: 0.1636 top1= 93.6719
[E55B10 |  14080/50000 ( 28%) ] Loss: 0.1542 top1= 95.0781
[E55B20 |  26880/50000 ( 54%) ] Loss: 0.1165 top1= 95.7031
[E55B30 |  39680/50000 ( 79%) ] Loss: 0.1521 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2962 top1= 68.1891


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.0479 top1= 42.2376


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0600 top1= 45.9034

Train epoch 56
[E56B0  |   1280/50000 (  3%) ] Loss: 0.1426 top1= 95.9375
[E56B10 |  14080/50000 ( 28%) ] Loss: 0.1346 top1= 95.0000
[E56B20 |  26880/50000 ( 54%) ] Loss: 0.1323 top1= 95.0000
[E56B30 |  39680/50000 ( 79%) ] Loss: 0.1326 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2762 top1= 69.1406


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.4958 top1= 42.0573


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9760 top1= 45.4928

Train epoch 57
[E57B0  |   1280/50000 (  3%) ] Loss: 0.1251 top1= 94.8438
[E57B10 |  14080/50000 ( 28%) ] Loss: 0.1163 top1= 96.1719
[E57B20 |  26880/50000 ( 54%) ] Loss: 0.1682 top1= 93.9062
[E57B30 |  39680/50000 ( 79%) ] Loss: 0.1669 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4203 top1= 67.9587


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.7063 top1= 42.6983


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7584 top1= 45.9435

Train epoch 58
[E58B0  |   1280/50000 (  3%) ] Loss: 0.1253 top1= 95.9375
[E58B10 |  14080/50000 ( 28%) ] Loss: 0.1168 top1= 95.4688
[E58B20 |  26880/50000 ( 54%) ] Loss: 0.1158 top1= 95.7812
[E58B30 |  39680/50000 ( 79%) ] Loss: 0.1350 top1= 95.3906

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1905 top1= 69.3209


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5522 top1= 41.6166


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5789 top1= 45.6330

Train epoch 59
[E59B0  |   1280/50000 (  3%) ] Loss: 0.1644 top1= 93.4375
[E59B10 |  14080/50000 ( 28%) ] Loss: 0.1358 top1= 95.3125
[E59B20 |  26880/50000 ( 54%) ] Loss: 0.1174 top1= 95.7031
[E59B30 |  39680/50000 ( 79%) ] Loss: 0.1514 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1489 top1= 71.5745


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.8118 top1= 41.9271


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0558 top1= 45.5529

Train epoch 60
[E60B0  |   1280/50000 (  3%) ] Loss: 0.1578 top1= 94.3750
[E60B10 |  14080/50000 ( 28%) ] Loss: 0.1510 top1= 94.8438
[E60B20 |  26880/50000 ( 54%) ] Loss: 0.1118 top1= 95.8594
[E60B30 |  39680/50000 ( 79%) ] Loss: 0.1244 top1= 94.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4285 top1= 67.9487


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.3663 top1= 41.7768


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1128 top1= 45.3826

Train epoch 61
[E61B0  |   1280/50000 (  3%) ] Loss: 0.1909 top1= 93.8281
[E61B10 |  14080/50000 ( 28%) ] Loss: 0.1215 top1= 95.3906
[E61B20 |  26880/50000 ( 54%) ] Loss: 0.1389 top1= 95.2344
[E61B30 |  39680/50000 ( 79%) ] Loss: 0.1093 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1126 top1= 70.8133


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9590 top1= 42.0072


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3898 top1= 45.5028

Train epoch 62
[E62B0  |   1280/50000 (  3%) ] Loss: 0.1260 top1= 95.4688
[E62B10 |  14080/50000 ( 28%) ] Loss: 0.1282 top1= 95.6250
[E62B20 |  26880/50000 ( 54%) ] Loss: 0.1329 top1= 95.0000
[E62B30 |  39680/50000 ( 79%) ] Loss: 0.1581 top1= 93.9844

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4239 top1= 68.3694


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.7466 top1= 41.7067


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.0902 top1= 45.1522

Train epoch 63
[E63B0  |   1280/50000 (  3%) ] Loss: 0.1441 top1= 94.7656
[E63B10 |  14080/50000 ( 28%) ] Loss: 0.1619 top1= 94.9219
[E63B20 |  26880/50000 ( 54%) ] Loss: 0.1447 top1= 94.4531
[E63B30 |  39680/50000 ( 79%) ] Loss: 0.1408 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2741 top1= 69.0505


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9335 top1= 42.1975


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0209 top1= 46.1238

Train epoch 64
[E64B0  |   1280/50000 (  3%) ] Loss: 0.1070 top1= 96.2500
[E64B10 |  14080/50000 ( 28%) ] Loss: 0.1378 top1= 94.6094
[E64B20 |  26880/50000 ( 54%) ] Loss: 0.1426 top1= 94.6875
[E64B30 |  39680/50000 ( 79%) ] Loss: 0.1190 top1= 95.3906

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1815 top1= 70.2224


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.6454 top1= 42.4379


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8682 top1= 46.0938

Train epoch 65
[E65B0  |   1280/50000 (  3%) ] Loss: 0.1200 top1= 95.3906
[E65B10 |  14080/50000 ( 28%) ] Loss: 0.1701 top1= 95.1562
[E65B20 |  26880/50000 ( 54%) ] Loss: 0.1278 top1= 95.8594
[E65B30 |  39680/50000 ( 79%) ] Loss: 0.1192 top1= 95.8594

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0654 top1= 71.7748


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.0553 top1= 43.0689


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.2495 top1= 45.7332

Train epoch 66
[E66B0  |   1280/50000 (  3%) ] Loss: 0.1060 top1= 96.3281
[E66B10 |  14080/50000 ( 28%) ] Loss: 0.1161 top1= 95.7812
[E66B20 |  26880/50000 ( 54%) ] Loss: 0.1615 top1= 94.5312
[E66B30 |  39680/50000 ( 79%) ] Loss: 0.1323 top1= 94.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1845 top1= 71.1338


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9797 top1= 42.8786


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.6480 top1= 45.9335

Train epoch 67
[E67B0  |   1280/50000 (  3%) ] Loss: 0.1174 top1= 95.6250
[E67B10 |  14080/50000 ( 28%) ] Loss: 0.1414 top1= 95.0000
[E67B20 |  26880/50000 ( 54%) ] Loss: 0.1384 top1= 95.6250
[E67B30 |  39680/50000 ( 79%) ] Loss: 0.1196 top1= 95.5469

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1454 top1= 70.2224


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2666 top1= 42.6683


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.9036 top1= 45.7432

Train epoch 68
[E68B0  |   1280/50000 (  3%) ] Loss: 0.1115 top1= 96.0156
[E68B10 |  14080/50000 ( 28%) ] Loss: 0.1054 top1= 96.6406
[E68B20 |  26880/50000 ( 54%) ] Loss: 0.1244 top1= 95.7031
[E68B30 |  39680/50000 ( 79%) ] Loss: 0.0990 top1= 96.6406

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1427 top1= 70.6731


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9979 top1= 43.0489


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.6304 top1= 45.3526

Train epoch 69
[E69B0  |   1280/50000 (  3%) ] Loss: 0.1077 top1= 96.7188
[E69B10 |  14080/50000 ( 28%) ] Loss: 0.1094 top1= 96.4062
[E69B20 |  26880/50000 ( 54%) ] Loss: 0.1270 top1= 95.3906
[E69B30 |  39680/50000 ( 79%) ] Loss: 0.0878 top1= 96.4844

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2409 top1= 71.1438


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.7743 top1= 42.8686


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.0471 top1= 45.5929

Train epoch 70
[E70B0  |   1280/50000 (  3%) ] Loss: 0.1081 top1= 96.4844
[E70B10 |  14080/50000 ( 28%) ] Loss: 0.1000 top1= 96.2500
[E70B20 |  26880/50000 ( 54%) ] Loss: 0.1413 top1= 94.9219
[E70B30 |  39680/50000 ( 79%) ] Loss: 0.1036 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1689 top1= 70.5829


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9781 top1= 43.0689


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5535 top1= 45.8534

Train epoch 71
[E71B0  |   1280/50000 (  3%) ] Loss: 0.1156 top1= 96.0156
[E71B10 |  14080/50000 ( 28%) ] Loss: 0.0966 top1= 96.9531
[E71B20 |  26880/50000 ( 54%) ] Loss: 0.1038 top1= 95.9375
[E71B30 |  39680/50000 ( 79%) ] Loss: 0.1008 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1890 top1= 70.0120


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.3359 top1= 42.3177


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1837 top1= 46.2240

Train epoch 72
[E72B0  |   1280/50000 (  3%) ] Loss: 0.1111 top1= 95.9375
[E72B10 |  14080/50000 ( 28%) ] Loss: 0.1141 top1= 96.6406
[E72B20 |  26880/50000 ( 54%) ] Loss: 0.1062 top1= 96.4062
[E72B30 |  39680/50000 ( 79%) ] Loss: 0.1130 top1= 96.0156

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2020 top1= 70.8834


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.4036 top1= 41.8069


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.2077 top1= 45.7031

Train epoch 73
[E73B0  |   1280/50000 (  3%) ] Loss: 0.1278 top1= 96.2500
[E73B10 |  14080/50000 ( 28%) ] Loss: 0.0904 top1= 96.2500
[E73B20 |  26880/50000 ( 54%) ] Loss: 0.1079 top1= 96.0156
[E73B30 |  39680/50000 ( 79%) ] Loss: 0.0976 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.5268 top1= 67.3878


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1515 top1= 42.0473


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7924 top1= 45.6430

Train epoch 74
[E74B0  |   1280/50000 (  3%) ] Loss: 0.1246 top1= 95.7812
[E74B10 |  14080/50000 ( 28%) ] Loss: 0.1020 top1= 96.2500
[E74B20 |  26880/50000 ( 54%) ] Loss: 0.1017 top1= 96.4062
[E74B30 |  39680/50000 ( 79%) ] Loss: 0.0778 top1= 97.5781

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2157 top1= 71.1538


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.1717 top1= 41.6466


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.9551 top1= 46.0537

Train epoch 75
[E75B0  |   1280/50000 (  3%) ] Loss: 0.1072 top1= 96.7188
[E75B10 |  14080/50000 ( 28%) ] Loss: 0.0960 top1= 96.5625
[E75B20 |  26880/50000 ( 54%) ] Loss: 0.0961 top1= 96.2500
[E75B30 |  39680/50000 ( 79%) ] Loss: 0.0939 top1= 96.6406

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2618 top1= 70.1222


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.8954 top1= 41.8169


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5046 top1= 45.8934

Train epoch 76
[E76B0  |   1280/50000 (  3%) ] Loss: 0.0964 top1= 96.1719
[E76B10 |  14080/50000 ( 28%) ] Loss: 0.0921 top1= 96.3281
[E76B20 |  26880/50000 ( 54%) ] Loss: 0.1140 top1= 96.0156
[E76B30 |  39680/50000 ( 79%) ] Loss: 0.0813 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2959 top1= 69.9920


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9314 top1= 42.9287


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.8494 top1= 45.7432

Train epoch 77
[E77B0  |   1280/50000 (  3%) ] Loss: 0.0704 top1= 97.6562
[E77B10 |  14080/50000 ( 28%) ] Loss: 0.0834 top1= 97.4219
[E77B20 |  26880/50000 ( 54%) ] Loss: 0.0733 top1= 96.9531
[E77B30 |  39680/50000 ( 79%) ] Loss: 0.0625 top1= 97.7344

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3482 top1= 69.3409


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.3464 top1= 42.9788


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.7478 top1= 45.9235

Train epoch 78
[E78B0  |   1280/50000 (  3%) ] Loss: 0.0736 top1= 97.4219
[E78B10 |  14080/50000 ( 28%) ] Loss: 0.0834 top1= 97.4219
[E78B20 |  26880/50000 ( 54%) ] Loss: 0.0690 top1= 97.8125
[E78B30 |  39680/50000 ( 79%) ] Loss: 0.0824 top1= 97.4219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3632 top1= 70.3926


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.1392 top1= 42.8185


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.1650 top1= 46.3041

Train epoch 79
[E79B0  |   1280/50000 (  3%) ] Loss: 0.0914 top1= 96.7969
[E79B10 |  14080/50000 ( 28%) ] Loss: 0.0682 top1= 97.5000
[E79B20 |  26880/50000 ( 54%) ] Loss: 0.0686 top1= 97.5781
[E79B30 |  39680/50000 ( 79%) ] Loss: 0.0872 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1746 top1= 72.0653


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.4870 top1= 43.1991


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.7298 top1= 46.3041

Train epoch 80
[E80B0  |   1280/50000 (  3%) ] Loss: 0.0722 top1= 97.7344
[E80B10 |  14080/50000 ( 28%) ] Loss: 0.0762 top1= 97.0312
[E80B20 |  26880/50000 ( 54%) ] Loss: 0.1015 top1= 96.1719
[E80B30 |  39680/50000 ( 79%) ] Loss: 0.0776 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3017 top1= 71.8750


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.2749 top1= 43.1791


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.1938 top1= 45.7432

Train epoch 81
[E81B0  |   1280/50000 (  3%) ] Loss: 0.0729 top1= 97.4219
[E81B10 |  14080/50000 ( 28%) ] Loss: 0.0552 top1= 98.4375
[E81B20 |  26880/50000 ( 54%) ] Loss: 0.0419 top1= 98.6719
[E81B30 |  39680/50000 ( 79%) ] Loss: 0.0406 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3204 top1= 72.2957


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5152 top1= 45.0321


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2789 top1= 49.0284

Train epoch 82
[E82B0  |   1280/50000 (  3%) ] Loss: 0.0455 top1= 98.5156
[E82B10 |  14080/50000 ( 28%) ] Loss: 0.0332 top1= 98.8281
[E82B20 |  26880/50000 ( 54%) ] Loss: 0.0218 top1= 99.3750
[E82B30 |  39680/50000 ( 79%) ] Loss: 0.0263 top1= 99.1406

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2809 top1= 73.1671


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2879 top1= 45.7432


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9476 top1= 48.7580

Train epoch 83
[E83B0  |   1280/50000 (  3%) ] Loss: 0.0330 top1= 99.1406
[E83B10 |  14080/50000 ( 28%) ] Loss: 0.0343 top1= 98.6719
[E83B20 |  26880/50000 ( 54%) ] Loss: 0.0155 top1= 99.7656
[E83B30 |  39680/50000 ( 79%) ] Loss: 0.0233 top1= 99.2969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3093 top1= 73.4475


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5425 top1= 45.7933


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5022 top1= 48.5276

Train epoch 84
[E84B0  |   1280/50000 (  3%) ] Loss: 0.0206 top1= 99.5312
[E84B10 |  14080/50000 ( 28%) ] Loss: 0.0179 top1= 99.5312
[E84B20 |  26880/50000 ( 54%) ] Loss: 0.0203 top1= 99.3750
[E84B30 |  39680/50000 ( 79%) ] Loss: 0.0181 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3753 top1= 73.1871


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8425 top1= 45.9135


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9176 top1= 50.0200

Train epoch 85
[E85B0  |   1280/50000 (  3%) ] Loss: 0.0294 top1= 99.1406
[E85B10 |  14080/50000 ( 28%) ] Loss: 0.0187 top1= 99.2969
[E85B20 |  26880/50000 ( 54%) ] Loss: 0.0164 top1= 99.5312
[E85B30 |  39680/50000 ( 79%) ] Loss: 0.0275 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3526 top1= 73.8181


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.7296 top1= 46.2039


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4701 top1= 49.4091

Train epoch 86
[E86B0  |   1280/50000 (  3%) ] Loss: 0.0265 top1= 99.0625
[E86B10 |  14080/50000 ( 28%) ] Loss: 0.0239 top1= 99.2969
[E86B20 |  26880/50000 ( 54%) ] Loss: 0.0214 top1= 99.3750
[E86B30 |  39680/50000 ( 79%) ] Loss: 0.0203 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3741 top1= 73.9483


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5218 top1= 46.4643


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0965 top1= 49.0485

Train epoch 87
[E87B0  |   1280/50000 (  3%) ] Loss: 0.0120 top1= 99.7656
[E87B10 |  14080/50000 ( 28%) ] Loss: 0.0200 top1= 99.5312
[E87B20 |  26880/50000 ( 54%) ] Loss: 0.0166 top1= 99.4531
[E87B30 |  39680/50000 ( 79%) ] Loss: 0.0190 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3870 top1= 74.1987


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5453 top1= 46.8950


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8086 top1= 49.6895

Train epoch 88
[E88B0  |   1280/50000 (  3%) ] Loss: 0.0200 top1= 99.1406
[E88B10 |  14080/50000 ( 28%) ] Loss: 0.0180 top1= 99.6094
[E88B20 |  26880/50000 ( 54%) ] Loss: 0.0205 top1= 99.5312
[E88B30 |  39680/50000 ( 79%) ] Loss: 0.0163 top1= 99.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4370 top1= 73.8081


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9565 top1= 46.4944


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5695 top1= 49.4591

Train epoch 89
[E89B0  |   1280/50000 (  3%) ] Loss: 0.0151 top1= 99.4531
[E89B10 |  14080/50000 ( 28%) ] Loss: 0.0117 top1= 99.6875
[E89B20 |  26880/50000 ( 54%) ] Loss: 0.0159 top1= 99.5312
[E89B30 |  39680/50000 ( 79%) ] Loss: 0.0209 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4849 top1= 73.5577


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.0455 top1= 46.3341


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6594 top1= 50.9014

Train epoch 90
[E90B0  |   1280/50000 (  3%) ] Loss: 0.0205 top1= 99.0625
[E90B10 |  14080/50000 ( 28%) ] Loss: 0.0255 top1= 99.2188
[E90B20 |  26880/50000 ( 54%) ] Loss: 0.0159 top1= 99.6094
[E90B30 |  39680/50000 ( 79%) ] Loss: 0.0084 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.5467 top1= 73.6278


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.1897 top1= 45.6831


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0422 top1= 50.3205

Train epoch 91
[E91B0  |   1280/50000 (  3%) ] Loss: 0.0129 top1= 99.8438
[E91B10 |  14080/50000 ( 28%) ] Loss: 0.0128 top1= 99.4531
[E91B20 |  26880/50000 ( 54%) ] Loss: 0.0077 top1= 99.9219
[E91B30 |  39680/50000 ( 79%) ] Loss: 0.0133 top1= 99.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.5072 top1= 73.8782


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9817 top1= 45.7031


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.8298 top1= 49.5994

Train epoch 92
[E92B0  |   1280/50000 (  3%) ] Loss: 0.0110 top1= 99.6875
[E92B10 |  14080/50000 ( 28%) ] Loss: 0.0217 top1= 99.2969
[E92B20 |  26880/50000 ( 54%) ] Loss: 0.0112 top1= 99.6094
[E92B30 |  39680/50000 ( 79%) ] Loss: 0.0131 top1= 99.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.5568 top1= 73.5677


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.6455 top1= 46.0637


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9028 top1= 51.0116

Train epoch 93
[E93B0  |   1280/50000 (  3%) ] Loss: 0.0274 top1= 99.1406
[E93B10 |  14080/50000 ( 28%) ] Loss: 0.0106 top1= 99.6875
[E93B20 |  26880/50000 ( 54%) ] Loss: 0.0098 top1= 99.4531
[E93B30 |  39680/50000 ( 79%) ] Loss: 0.0137 top1= 99.2969

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6218 top1= 73.2372


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.7996 top1= 46.4643


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3048 top1= 51.0417

Train epoch 94
[E94B0  |   1280/50000 (  3%) ] Loss: 0.0178 top1= 99.4531
[E94B10 |  14080/50000 ( 28%) ] Loss: 0.0156 top1= 99.5312
[E94B20 |  26880/50000 ( 54%) ] Loss: 0.0132 top1= 99.6094
[E94B30 |  39680/50000 ( 79%) ] Loss: 0.0106 top1= 99.6094

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.5629 top1= 73.6879


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.5809 top1= 45.5228


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.9502 top1= 50.3606

Train epoch 95
[E95B0  |   1280/50000 (  3%) ] Loss: 0.0147 top1= 99.3750
[E95B10 |  14080/50000 ( 28%) ] Loss: 0.0085 top1= 99.7656
[E95B20 |  26880/50000 ( 54%) ] Loss: 0.0109 top1= 99.7656
[E95B30 |  39680/50000 ( 79%) ] Loss: 0.0087 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.5789 top1= 73.7580


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9595 top1= 46.1939


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.2349 top1= 49.7897

Train epoch 96
[E96B0  |   1280/50000 (  3%) ] Loss: 0.0099 top1= 99.8438
[E96B10 |  14080/50000 ( 28%) ] Loss: 0.0207 top1= 99.4531
[E96B20 |  26880/50000 ( 54%) ] Loss: 0.0089 top1= 99.6094
[E96B30 |  39680/50000 ( 79%) ] Loss: 0.0191 top1= 99.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6209 top1= 73.8582


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.0401 top1= 46.3942


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.0522 top1= 50.6811

Train epoch 97
[E97B0  |   1280/50000 (  3%) ] Loss: 0.0144 top1= 99.6875
[E97B10 |  14080/50000 ( 28%) ] Loss: 0.0157 top1= 99.6094
[E97B20 |  26880/50000 ( 54%) ] Loss: 0.0146 top1= 99.6875
[E97B30 |  39680/50000 ( 79%) ] Loss: 0.0153 top1= 99.6094

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6263 top1= 73.8482


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.2230 top1= 46.1739


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.9414 top1= 50.0901

Train epoch 98
[E98B0  |   1280/50000 (  3%) ] Loss: 0.0084 top1= 99.6875
[E98B10 |  14080/50000 ( 28%) ] Loss: 0.0161 top1= 99.3750
[E98B20 |  26880/50000 ( 54%) ] Loss: 0.0157 top1= 99.3750
[E98B30 |  39680/50000 ( 79%) ] Loss: 0.0060 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7092 top1= 73.5477


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.4359 top1= 45.8233


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.3638 top1= 50.4407

Train epoch 99
[E99B0  |   1280/50000 (  3%) ] Loss: 0.0120 top1= 99.5312
[E99B10 |  14080/50000 ( 28%) ] Loss: 0.0117 top1= 99.4531
[E99B20 |  26880/50000 ( 54%) ] Loss: 0.0118 top1= 99.6094
[E99B30 |  39680/50000 ( 79%) ] Loss: 0.0120 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6954 top1= 73.5877


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.8037 top1= 46.3642


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.9976 top1= 49.2688

Train epoch 100
[E100B0  |   1280/50000 (  3%) ] Loss: 0.0100 top1= 99.7656
[E100B10 |  14080/50000 ( 28%) ] Loss: 0.0089 top1= 99.5312
[E100B20 |  26880/50000 ( 54%) ] Loss: 0.0079 top1= 99.7656
[E100B30 |  39680/50000 ( 79%) ] Loss: 0.0076 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7567 top1= 73.3073


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.2029 top1= 46.9351


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.3795 top1= 50.6711

Train epoch 101
[E101B0  |   1280/50000 (  3%) ] Loss: 0.0051 top1= 99.9219
[E101B10 |  14080/50000 ( 28%) ] Loss: 0.0180 top1= 99.4531
[E101B20 |  26880/50000 ( 54%) ] Loss: 0.0071 top1= 99.8438
[E101B30 |  39680/50000 ( 79%) ] Loss: 0.0088 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7553 top1= 73.5577


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.9004 top1= 46.0036


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.4277 top1= 50.8514

Train epoch 102
[E102B0  |   1280/50000 (  3%) ] Loss: 0.0090 top1= 99.8438
[E102B10 |  14080/50000 ( 28%) ] Loss: 0.0088 top1= 99.9219
[E102B20 |  26880/50000 ( 54%) ] Loss: 0.0090 top1= 99.6875
[E102B30 |  39680/50000 ( 79%) ] Loss: 0.0088 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8065 top1= 73.3874


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.9046 top1= 46.4243


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.7683 top1= 50.4006

Train epoch 103
[E103B0  |   1280/50000 (  3%) ] Loss: 0.0094 top1= 99.6094
[E103B10 |  14080/50000 ( 28%) ] Loss: 0.0124 top1= 99.7656
[E103B20 |  26880/50000 ( 54%) ] Loss: 0.0068 top1= 99.8438
[E103B30 |  39680/50000 ( 79%) ] Loss: 0.0069 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8314 top1= 73.4275


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.9589 top1= 46.7047


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.1094 top1= 50.5308

Train epoch 104
[E104B0  |   1280/50000 (  3%) ] Loss: 0.0135 top1= 99.6094
[E104B10 |  14080/50000 ( 28%) ] Loss: 0.0196 top1= 99.2188
[E104B20 |  26880/50000 ( 54%) ] Loss: 0.0079 top1= 99.6875
[E104B30 |  39680/50000 ( 79%) ] Loss: 0.0132 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8125 top1= 73.1571


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.9020 top1= 46.6446


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.4578 top1= 49.2087

Train epoch 105
[E105B0  |   1280/50000 (  3%) ] Loss: 0.0127 top1= 99.4531
[E105B10 |  14080/50000 ( 28%) ] Loss: 0.0112 top1= 99.6875
[E105B20 |  26880/50000 ( 54%) ] Loss: 0.0059 top1= 99.7656
[E105B30 |  39680/50000 ( 79%) ] Loss: 0.0065 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8104 top1= 73.3874


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.9374 top1= 46.3942


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7107 top1= 49.0785

Train epoch 106
[E106B0  |   1280/50000 (  3%) ] Loss: 0.0077 top1= 99.7656
[E106B10 |  14080/50000 ( 28%) ] Loss: 0.0072 top1= 99.6094
[E106B20 |  26880/50000 ( 54%) ] Loss: 0.0047 top1= 99.8438
[E106B30 |  39680/50000 ( 79%) ] Loss: 0.0087 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8914 top1= 72.9968


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.5330 top1= 46.2039


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.1241 top1= 52.0333

Train epoch 107
[E107B0  |   1280/50000 (  3%) ] Loss: 0.0062 top1= 99.7656
[E107B10 |  14080/50000 ( 28%) ] Loss: 0.0121 top1= 99.4531
[E107B20 |  26880/50000 ( 54%) ] Loss: 0.0038 top1= 99.9219
[E107B30 |  39680/50000 ( 79%) ] Loss: 0.0043 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8656 top1= 73.2672


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.9129 top1= 46.6146


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.5317 top1= 49.4792

Train epoch 108
[E108B0  |   1280/50000 (  3%) ] Loss: 0.0074 top1= 99.7656
[E108B10 |  14080/50000 ( 28%) ] Loss: 0.0066 top1= 99.8438
[E108B20 |  26880/50000 ( 54%) ] Loss: 0.0042 top1= 99.7656
[E108B30 |  39680/50000 ( 79%) ] Loss: 0.0148 top1= 99.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8208 top1= 73.6879


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.8715 top1= 46.6446


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.8279 top1= 50.3606

Train epoch 109
[E109B0  |   1280/50000 (  3%) ] Loss: 0.0054 top1= 99.8438
[E109B10 |  14080/50000 ( 28%) ] Loss: 0.0108 top1= 99.5312
[E109B20 |  26880/50000 ( 54%) ] Loss: 0.0081 top1= 99.8438
[E109B30 |  39680/50000 ( 79%) ] Loss: 0.0059 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9077 top1= 73.2772


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.4321 top1= 46.5946


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.7049 top1= 49.5092

Train epoch 110
[E110B0  |   1280/50000 (  3%) ] Loss: 0.0039 top1= 99.8438
[E110B10 |  14080/50000 ( 28%) ] Loss: 0.0166 top1= 99.6094
[E110B20 |  26880/50000 ( 54%) ] Loss: 0.0075 top1= 99.6875
[E110B30 |  39680/50000 ( 79%) ] Loss: 0.0049 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9166 top1= 73.4876


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.9617 top1= 46.0537


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.0999 top1= 51.1919

Train epoch 111
[E111B0  |   1280/50000 (  3%) ] Loss: 0.0103 top1= 99.8438
[E111B10 |  14080/50000 ( 28%) ] Loss: 0.0053 top1= 99.9219
[E111B20 |  26880/50000 ( 54%) ] Loss: 0.0051 top1= 99.8438
[E111B30 |  39680/50000 ( 79%) ] Loss: 0.0098 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0507 top1= 72.4359


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.8299 top1= 46.2841


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.3922 top1= 52.1835

Train epoch 112
[E112B0  |   1280/50000 (  3%) ] Loss: 0.0062 top1= 99.8438
[E112B10 |  14080/50000 ( 28%) ] Loss: 0.0063 top1= 99.7656
[E112B20 |  26880/50000 ( 54%) ] Loss: 0.0040 top1= 99.9219
[E112B30 |  39680/50000 ( 79%) ] Loss: 0.0066 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9494 top1= 73.0869


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.6956 top1= 46.1338


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.4745 top1= 50.0901

Train epoch 113
[E113B0  |   1280/50000 (  3%) ] Loss: 0.0068 top1= 99.6875
[E113B10 |  14080/50000 ( 28%) ] Loss: 0.0061 top1= 99.7656
[E113B20 |  26880/50000 ( 54%) ] Loss: 0.0037 top1= 99.9219
[E113B30 |  39680/50000 ( 79%) ] Loss: 0.0129 top1= 99.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9500 top1= 73.1170


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.3216 top1= 46.6046


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.5006 top1= 50.1703

Train epoch 114
[E114B0  |   1280/50000 (  3%) ] Loss: 0.0114 top1= 99.6094
[E114B10 |  14080/50000 ( 28%) ] Loss: 0.0045 top1= 99.8438
[E114B20 |  26880/50000 ( 54%) ] Loss: 0.0104 top1= 99.6875
[E114B30 |  39680/50000 ( 79%) ] Loss: 0.0125 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9529 top1= 73.1871


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.3992 top1= 45.9635


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.9189 top1= 49.8397

Train epoch 115
[E115B0  |   1280/50000 (  3%) ] Loss: 0.0100 top1= 99.5312
[E115B10 |  14080/50000 ( 28%) ] Loss: 0.0040 top1= 99.8438
[E115B20 |  26880/50000 ( 54%) ] Loss: 0.0065 top1= 99.8438
[E115B30 |  39680/50000 ( 79%) ] Loss: 0.0057 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0039 top1= 72.8466


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.7146 top1= 46.5946


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.9826 top1= 51.7929

Train epoch 116
[E116B0  |   1280/50000 (  3%) ] Loss: 0.0084 top1= 99.8438
[E116B10 |  14080/50000 ( 28%) ] Loss: 0.0105 top1= 99.4531
[E116B20 |  26880/50000 ( 54%) ] Loss: 0.0038 top1= 99.8438
[E116B30 |  39680/50000 ( 79%) ] Loss: 0.0053 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9451 top1= 73.2973


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.0522 top1= 46.1238


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.4585 top1= 49.6194

Train epoch 117
[E117B0  |   1280/50000 (  3%) ] Loss: 0.0062 top1= 99.9219
[E117B10 |  14080/50000 ( 28%) ] Loss: 0.0097 top1= 99.7656
[E117B20 |  26880/50000 ( 54%) ] Loss: 0.0082 top1= 99.7656
[E117B30 |  39680/50000 ( 79%) ] Loss: 0.0086 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0455 top1= 72.7965


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.3816 top1= 45.9836


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=11.1061 top1= 50.5609

Train epoch 118
[E118B0  |   1280/50000 (  3%) ] Loss: 0.0060 top1= 99.6094
[E118B10 |  14080/50000 ( 28%) ] Loss: 0.0056 top1= 99.6875
[E118B20 |  26880/50000 ( 54%) ] Loss: 0.0094 top1= 99.8438
[E118B30 |  39680/50000 ( 79%) ] Loss: 0.0056 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.1689 top1= 71.7849


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.8977 top1= 45.8033


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=10.6643 top1= 51.1418

Train epoch 119
[E119B0  |   1280/50000 (  3%) ] Loss: 0.0227 top1= 99.5312
[E119B10 |  14080/50000 ( 28%) ] Loss: 0.0102 top1= 99.6094
[E119B20 |  26880/50000 ( 54%) ] Loss: 0.0055 top1= 99.9219
[E119B30 |  39680/50000 ( 79%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9854 top1= 73.6378


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.1345 top1= 46.2340


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=12.0118 top1= 50.3105

Train epoch 120
[E120B0  |   1280/50000 (  3%) ] Loss: 0.0067 top1= 99.6094
[E120B10 |  14080/50000 ( 28%) ] Loss: 0.0112 top1= 99.5312
[E120B20 |  26880/50000 ( 54%) ] Loss: 0.0075 top1= 99.7656
[E120B30 |  39680/50000 ( 79%) ] Loss: 0.0065 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0217 top1= 73.1971


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=11.2729 top1= 46.0737


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=13.6195 top1= 49.0685

Train epoch 121
[E121B0  |   1280/50000 (  3%) ] Loss: 0.0072 top1= 99.6875
[E121B10 |  14080/50000 ( 28%) ] Loss: 0.0054 top1= 99.8438
[E121B20 |  26880/50000 ( 54%) ] Loss: 0.0096 top1= 99.8438
[E121B30 |  39680/50000 ( 79%) ] Loss: 0.0128 top1= 99.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0093 top1= 73.1771


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8303 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2901 top1= 54.4972

Train epoch 122
[E122B0  |   1280/50000 (  3%) ] Loss: 0.0184 top1= 99.5312
[E122B10 |  14080/50000 ( 28%) ] Loss: 0.0087 top1= 99.6875
[E122B20 |  26880/50000 ( 54%) ] Loss: 0.0124 top1= 99.5312
[E122B30 |  39680/50000 ( 79%) ] Loss: 0.0081 top1= 99.6094

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9904 top1= 73.3574


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1934 top1= 49.6294


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.6750 top1= 53.7861

Train epoch 123
[E123B0  |   1280/50000 (  3%) ] Loss: 0.0117 top1= 99.7656
[E123B10 |  14080/50000 ( 28%) ] Loss: 0.0094 top1= 99.6094
[E123B20 |  26880/50000 ( 54%) ] Loss: 0.0088 top1= 99.5312
[E123B30 |  39680/50000 ( 79%) ] Loss: 0.0208 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9884 top1= 73.2372


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.0688 top1= 49.9199


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3757 top1= 54.2568

Train epoch 124
[E124B0  |   1280/50000 (  3%) ] Loss: 0.0075 top1= 99.6875
[E124B10 |  14080/50000 ( 28%) ] Loss: 0.0096 top1= 99.6875
[E124B20 |  26880/50000 ( 54%) ] Loss: 0.0125 top1= 99.6094
[E124B30 |  39680/50000 ( 79%) ] Loss: 0.0052 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9709 top1= 73.5076


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.7610 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3416 top1= 54.2969

Train epoch 125
[E125B0  |   1280/50000 (  3%) ] Loss: 0.0156 top1= 99.5312
[E125B10 |  14080/50000 ( 28%) ] Loss: 0.0093 top1= 99.8438
[E125B20 |  26880/50000 ( 54%) ] Loss: 0.0142 top1= 99.6875
[E125B30 |  39680/50000 ( 79%) ] Loss: 0.0081 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0108 top1= 73.3674


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9598 top1= 50.1002


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.9218 top1= 53.4355

Train epoch 126
[E126B0  |   1280/50000 (  3%) ] Loss: 0.0225 top1= 99.5312
[E126B10 |  14080/50000 ( 28%) ] Loss: 0.0074 top1= 99.6875
[E126B20 |  26880/50000 ( 54%) ] Loss: 0.0066 top1= 99.8438
[E126B30 |  39680/50000 ( 79%) ] Loss: 0.0167 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9894 top1= 73.3574


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.0884 top1= 49.9800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9322 top1= 55.2284

Train epoch 127
[E127B0  |   1280/50000 (  3%) ] Loss: 0.0259 top1= 99.3750
[E127B10 |  14080/50000 ( 28%) ] Loss: 0.0089 top1= 99.7656
[E127B20 |  26880/50000 ( 54%) ] Loss: 0.0070 top1= 99.7656
[E127B30 |  39680/50000 ( 79%) ] Loss: 0.0123 top1= 99.6094

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0122 top1= 73.0569


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1553 top1= 49.8698


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8471 top1= 55.5389

Train epoch 128
[E128B0  |   1280/50000 (  3%) ] Loss: 0.0074 top1= 99.6094
[E128B10 |  14080/50000 ( 28%) ] Loss: 0.0076 top1= 99.9219
[E128B20 |  26880/50000 ( 54%) ] Loss: 0.0114 top1= 99.6094
[E128B30 |  39680/50000 ( 79%) ] Loss: 0.0178 top1= 99.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9962 top1= 73.2472


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4942 top1= 50.9816


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.4989 top1= 54.3369

Train epoch 129
[E129B0  |   1280/50000 (  3%) ] Loss: 0.0150 top1= 99.6094
[E129B10 |  14080/50000 ( 28%) ] Loss: 0.0139 top1= 99.5312
[E129B20 |  26880/50000 ( 54%) ] Loss: 0.0106 top1= 99.5312
[E129B30 |  39680/50000 ( 79%) ] Loss: 0.0098 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9957 top1= 73.2171


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9776 top1= 50.1302


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2669 top1= 54.9679

Train epoch 130
[E130B0  |   1280/50000 (  3%) ] Loss: 0.0108 top1= 99.5312
[E130B10 |  14080/50000 ( 28%) ] Loss: 0.0135 top1= 99.6094
[E130B20 |  26880/50000 ( 54%) ] Loss: 0.0128 top1= 99.6094
[E130B30 |  39680/50000 ( 79%) ] Loss: 0.0142 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9793 top1= 73.3073


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.7977 top1= 50.4307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5228 top1= 54.3269

Train epoch 131
[E131B0  |   1280/50000 (  3%) ] Loss: 0.0131 top1= 99.6094
[E131B10 |  14080/50000 ( 28%) ] Loss: 0.0095 top1= 99.8438
[E131B20 |  26880/50000 ( 54%) ] Loss: 0.0061 top1= 99.7656
[E131B30 |  39680/50000 ( 79%) ] Loss: 0.0080 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9673 top1= 73.2873


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5467 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7916 top1= 55.7292

Train epoch 132
[E132B0  |   1280/50000 (  3%) ] Loss: 0.0081 top1= 99.6875
[E132B10 |  14080/50000 ( 28%) ] Loss: 0.0157 top1= 99.5312
[E132B20 |  26880/50000 ( 54%) ] Loss: 0.0063 top1= 99.8438
[E132B30 |  39680/50000 ( 79%) ] Loss: 0.0086 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9853 top1= 73.3474


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.7371 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5504 top1= 54.4772

Train epoch 133
[E133B0  |   1280/50000 (  3%) ] Loss: 0.0159 top1= 99.3750
[E133B10 |  14080/50000 ( 28%) ] Loss: 0.0149 top1= 99.5312
[E133B20 |  26880/50000 ( 54%) ] Loss: 0.0062 top1= 99.7656
[E133B30 |  39680/50000 ( 79%) ] Loss: 0.0070 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0132 top1= 73.3974


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1970 top1= 51.7027


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2512 top1= 55.0280

Train epoch 134
[E134B0  |   1280/50000 (  3%) ] Loss: 0.0165 top1= 99.6094
[E134B10 |  14080/50000 ( 28%) ] Loss: 0.0165 top1= 99.6094
[E134B20 |  26880/50000 ( 54%) ] Loss: 0.0109 top1= 99.6094
[E134B30 |  39680/50000 ( 79%) ] Loss: 0.0123 top1= 99.6094

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9964 top1= 73.3974


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6599 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.4107 top1= 54.6775

Train epoch 135
[E135B0  |   1280/50000 (  3%) ] Loss: 0.0099 top1= 99.6875
[E135B10 |  14080/50000 ( 28%) ] Loss: 0.0060 top1= 99.8438
[E135B20 |  26880/50000 ( 54%) ] Loss: 0.0351 top1= 99.0625
[E135B30 |  39680/50000 ( 79%) ] Loss: 0.0074 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0114 top1= 73.1671


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.7366 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2817 top1= 54.9479

Train epoch 136
[E136B0  |   1280/50000 (  3%) ] Loss: 0.0184 top1= 99.7656
[E136B10 |  14080/50000 ( 28%) ] Loss: 0.0070 top1= 99.9219
[E136B20 |  26880/50000 ( 54%) ] Loss: 0.0132 top1= 99.4531
[E136B30 |  39680/50000 ( 79%) ] Loss: 0.0082 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9992 top1= 73.4876


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3946 top1= 50.9014


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3916 top1= 54.7175

Train epoch 137
[E137B0  |   1280/50000 (  3%) ] Loss: 0.0200 top1= 99.5312
[E137B10 |  14080/50000 ( 28%) ] Loss: 0.0130 top1= 99.5312
[E137B20 |  26880/50000 ( 54%) ] Loss: 0.0045 top1= 99.9219
[E137B30 |  39680/50000 ( 79%) ] Loss: 0.0069 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9946 top1= 73.5477


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2992 top1= 51.1719


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.6501 top1= 54.2668

Train epoch 138
[E138B0  |   1280/50000 (  3%) ] Loss: 0.0073 top1= 99.6875
[E138B10 |  14080/50000 ( 28%) ] Loss: 0.0118 top1= 99.5312
[E138B20 |  26880/50000 ( 54%) ] Loss: 0.0069 top1= 99.9219
[E138B30 |  39680/50000 ( 79%) ] Loss: 0.0038 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9984 top1= 73.5377


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3547 top1= 51.1318


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3119 top1= 55.0381

Train epoch 139
[E139B0  |   1280/50000 (  3%) ] Loss: 0.0186 top1= 99.2969
[E139B10 |  14080/50000 ( 28%) ] Loss: 0.0098 top1= 99.7656
[E139B20 |  26880/50000 ( 54%) ] Loss: 0.0085 top1= 99.6094
[E139B30 |  39680/50000 ( 79%) ] Loss: 0.0098 top1= 99.6094

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0135 top1= 73.3073


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5070 top1= 50.7612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8486 top1= 56.0296

Train epoch 140
[E140B0  |   1280/50000 (  3%) ] Loss: 0.0169 top1= 99.5312
[E140B10 |  14080/50000 ( 28%) ] Loss: 0.0086 top1= 99.7656
[E140B20 |  26880/50000 ( 54%) ] Loss: 0.0049 top1= 99.8438
[E140B30 |  39680/50000 ( 79%) ] Loss: 0.0090 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9939 top1= 73.3674


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9934 top1= 50.1002


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.6156 top1= 54.3670

Train epoch 141
[E141B0  |   1280/50000 (  3%) ] Loss: 0.0056 top1= 99.8438
[E141B10 |  14080/50000 ( 28%) ] Loss: 0.0108 top1= 99.6875
[E141B20 |  26880/50000 ( 54%) ] Loss: 0.0065 top1= 99.6875
[E141B30 |  39680/50000 ( 79%) ] Loss: 0.0094 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0171 top1= 73.3173


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5620 top1= 50.8413


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.4289 top1= 54.7676

Train epoch 142
[E142B0  |   1280/50000 (  3%) ] Loss: 0.0188 top1= 99.2969
[E142B10 |  14080/50000 ( 28%) ] Loss: 0.0087 top1= 99.7656
[E142B20 |  26880/50000 ( 54%) ] Loss: 0.0160 top1= 99.4531
[E142B30 |  39680/50000 ( 79%) ] Loss: 0.0062 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0292 top1= 73.1571


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5258 top1= 50.8013


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.4526 top1= 54.9179

Train epoch 143
[E143B0  |   1280/50000 (  3%) ] Loss: 0.0093 top1= 99.4531
[E143B10 |  14080/50000 ( 28%) ] Loss: 0.0205 top1= 99.6094
[E143B20 |  26880/50000 ( 54%) ] Loss: 0.0089 top1= 99.6094
[E143B30 |  39680/50000 ( 79%) ] Loss: 0.0118 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0151 top1= 73.3073


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4041 top1= 50.9615


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.4571 top1= 54.7075

Train epoch 144
[E144B0  |   1280/50000 (  3%) ] Loss: 0.0115 top1= 99.6875
[E144B10 |  14080/50000 ( 28%) ] Loss: 0.0168 top1= 99.5312
[E144B20 |  26880/50000 ( 54%) ] Loss: 0.0092 top1= 99.5312
[E144B30 |  39680/50000 ( 79%) ] Loss: 0.0135 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0271 top1= 73.2672


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6689 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5546 top1= 54.8177

Train epoch 145
[E145B0  |   1280/50000 (  3%) ] Loss: 0.0072 top1= 99.7656
[E145B10 |  14080/50000 ( 28%) ] Loss: 0.0074 top1= 99.9219
[E145B20 |  26880/50000 ( 54%) ] Loss: 0.0152 top1= 99.6094
[E145B30 |  39680/50000 ( 79%) ] Loss: 0.0066 top1= 99.9219

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0196 top1= 73.2873


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5284 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.8451 top1= 54.2969

Train epoch 146
[E146B0  |   1280/50000 (  3%) ] Loss: 0.0115 top1= 99.7656
[E146B10 |  14080/50000 ( 28%) ] Loss: 0.0090 top1= 99.6094
[E146B20 |  26880/50000 ( 54%) ] Loss: 0.0119 top1= 99.7656
[E146B30 |  39680/50000 ( 79%) ] Loss: 0.0146 top1= 99.4531

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9926 top1= 73.4475


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3487 top1= 50.9816


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2390 top1= 55.2284

Train epoch 147
[E147B0  |   1280/50000 (  3%) ] Loss: 0.0115 top1= 99.6094
[E147B10 |  14080/50000 ( 28%) ] Loss: 0.0096 top1= 99.6094
[E147B20 |  26880/50000 ( 54%) ] Loss: 0.0058 top1= 99.8438
[E147B30 |  39680/50000 ( 79%) ] Loss: 0.0075 top1= 99.7656

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0021 top1= 73.4876


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3576 top1= 51.2821


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5102 top1= 54.8077

Train epoch 148
[E148B0  |   1280/50000 (  3%) ] Loss: 0.0109 top1= 99.6875
[E148B10 |  14080/50000 ( 28%) ] Loss: 0.0092 top1= 99.6875
[E148B20 |  26880/50000 ( 54%) ] Loss: 0.0068 top1= 99.7656
[E148B30 |  39680/50000 ( 79%) ] Loss: 0.0141 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0256 top1= 73.3073


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5092 top1= 50.8714


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3827 top1= 55.0581

Train epoch 149
[E149B0  |   1280/50000 (  3%) ] Loss: 0.0089 top1= 99.6875
[E149B10 |  14080/50000 ( 28%) ] Loss: 0.0176 top1= 99.5312
[E149B20 |  26880/50000 ( 54%) ] Loss: 0.0147 top1= 99.5312
[E149B30 |  39680/50000 ( 79%) ] Loss: 0.0153 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0379 top1= 73.3373


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6161 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5002 top1= 55.0881

Train epoch 150
[E150B0  |   1280/50000 (  3%) ] Loss: 0.0104 top1= 99.7656
[E150B10 |  14080/50000 ( 28%) ] Loss: 0.0082 top1= 99.7656
[E150B20 |  26880/50000 ( 54%) ] Loss: 0.0061 top1= 99.8438
[E150B30 |  39680/50000 ( 79%) ] Loss: 0.0074 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0252 top1= 73.4275


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2453 top1= 51.4623


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2326 top1= 55.3986

