Epoch: 0001 train_loss= 2.24720 train_acc= 0.49221 val_loss= 1.07640 val_acc= 0.54098 time= 0.92565
Epoch: 0002 train_loss= 1.68378 train_acc= 0.48831 val_loss= 0.93498 val_acc= 0.55738 time= 0.03125
Epoch: 0003 train_loss= 1.03860 train_acc= 0.50130 val_loss= 0.85048 val_acc= 0.54098 time= 0.01563
Epoch: 0004 train_loss= 0.85949 train_acc= 0.51818 val_loss= 0.80179 val_acc= 0.57377 time= 0.03125
Epoch: 0005 train_loss= 0.84013 train_acc= 0.49351 val_loss= 0.77711 val_acc= 0.54098 time= 0.01563
Epoch: 0006 train_loss= 1.03026 train_acc= 0.49610 val_loss= 0.75311 val_acc= 0.54098 time= 0.03125
Epoch: 0007 train_loss= 0.82969 train_acc= 0.52338 val_loss= 0.73014 val_acc= 0.50820 time= 0.01563
Epoch: 0008 train_loss= 0.73380 train_acc= 0.52078 val_loss= 0.71638 val_acc= 0.55738 time= 0.03125
Epoch: 0009 train_loss= 0.76038 train_acc= 0.50130 val_loss= 0.70505 val_acc= 0.55738 time= 0.01563
Epoch: 0010 train_loss= 0.83241 train_acc= 0.50909 val_loss= 0.69913 val_acc= 0.54098 time= 0.03125
Epoch: 0011 train_loss= 1.00186 train_acc= 0.47922 val_loss= 0.69631 val_acc= 0.54098 time= 0.03125
Epoch: 0012 train_loss= 0.89363 train_acc= 0.51429 val_loss= 0.69495 val_acc= 0.55738 time= 0.01563
Epoch: 0013 train_loss= 0.70904 train_acc= 0.52078 val_loss= 0.69456 val_acc= 0.60656 time= 0.03125
Epoch: 0014 train_loss= 0.81561 train_acc= 0.50130 val_loss= 0.69438 val_acc= 0.59016 time= 0.03125
Epoch: 0015 train_loss= 0.75255 train_acc= 0.48961 val_loss= 0.69394 val_acc= 0.59016 time= 0.03125
Epoch: 0016 train_loss= 0.74972 train_acc= 0.52078 val_loss= 0.69340 val_acc= 0.59016 time= 0.01563
Epoch: 0017 train_loss= 0.75353 train_acc= 0.48312 val_loss= 0.69284 val_acc= 0.60656 time= 0.03125
Epoch: 0018 train_loss= 0.72395 train_acc= 0.47792 val_loss= 0.69238 val_acc= 0.60656 time= 0.01562
Epoch: 0019 train_loss= 0.71052 train_acc= 0.54026 val_loss= 0.69211 val_acc= 0.62295 time= 0.01563
Epoch: 0020 train_loss= 0.73371 train_acc= 0.49351 val_loss= 0.69186 val_acc= 0.62295 time= 0.03125
Epoch: 0021 train_loss= 0.71904 train_acc= 0.51429 val_loss= 0.69164 val_acc= 0.62295 time= 0.01563
Epoch: 0022 train_loss= 0.71770 train_acc= 0.53117 val_loss= 0.69155 val_acc= 0.62295 time= 0.03125
Epoch: 0023 train_loss= 0.72855 train_acc= 0.48831 val_loss= 0.69154 val_acc= 0.62295 time= 0.01562
Epoch: 0024 train_loss= 0.71164 train_acc= 0.51818 val_loss= 0.69166 val_acc= 0.62295 time= 0.01563
Epoch: 0025 train_loss= 0.72687 train_acc= 0.50779 val_loss= 0.69184 val_acc= 0.62295 time= 0.03125
Epoch: 0026 train_loss= 0.71916 train_acc= 0.49870 val_loss= 0.69214 val_acc= 0.60656 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.72057 accuracy= 0.50000 time= 0.01563 
