Epoch: 0001 train_loss= 1.39204 train_acc= 0.27344 val_loss= 1.38915 val_acc= 0.39286 time= 0.25002
Epoch: 0002 train_loss= 1.39101 train_acc= 0.29492 val_loss= 1.38690 val_acc= 0.39286 time= 0.01563
Epoch: 0003 train_loss= 1.38961 train_acc= 0.29297 val_loss= 1.38478 val_acc= 0.39286 time= 0.01563
Epoch: 0004 train_loss= 1.38861 train_acc= 0.29297 val_loss= 1.38283 val_acc= 0.39286 time= 0.01563
Epoch: 0005 train_loss= 1.38733 train_acc= 0.29297 val_loss= 1.38098 val_acc= 0.39286 time= 0.03125
Epoch: 0006 train_loss= 1.38652 train_acc= 0.29297 val_loss= 1.37921 val_acc= 0.39286 time= 0.01563
Epoch: 0007 train_loss= 1.38518 train_acc= 0.29297 val_loss= 1.37753 val_acc= 0.39286 time= 0.01562
Epoch: 0008 train_loss= 1.38495 train_acc= 0.29297 val_loss= 1.37593 val_acc= 0.39286 time= 0.01563
Epoch: 0009 train_loss= 1.38380 train_acc= 0.29297 val_loss= 1.37445 val_acc= 0.39286 time= 0.01563
Epoch: 0010 train_loss= 1.38297 train_acc= 0.29297 val_loss= 1.37311 val_acc= 0.39286 time= 0.03125
Epoch: 0011 train_loss= 1.38212 train_acc= 0.29297 val_loss= 1.37194 val_acc= 0.39286 time= 0.01563
Epoch: 0012 train_loss= 1.38084 train_acc= 0.29297 val_loss= 1.37094 val_acc= 0.39286 time= 0.01563
Epoch: 0013 train_loss= 1.37963 train_acc= 0.29297 val_loss= 1.37020 val_acc= 0.39286 time= 0.01562
Epoch: 0014 train_loss= 1.37959 train_acc= 0.29297 val_loss= 1.36987 val_acc= 0.39286 time= 0.01563
Epoch: 0015 train_loss= 1.37864 train_acc= 0.29297 val_loss= 1.36992 val_acc= 0.39286 time= 0.03125
Epoch: 0016 train_loss= 1.37800 train_acc= 0.29297 val_loss= 1.37038 val_acc= 0.39286 time= 0.01563
Epoch: 0017 train_loss= 1.37790 train_acc= 0.29297 val_loss= 1.37120 val_acc= 0.39286 time= 0.01563
Epoch: 0018 train_loss= 1.37754 train_acc= 0.29297 val_loss= 1.37234 val_acc= 0.39286 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.38875 accuracy= 0.31858 time= 0.01563 
