Epoch: 0001 train_loss= 1.42831 train_acc= 0.20531 val_loss= 1.40747 val_acc= 0.14286 time= 0.31252
Epoch: 0002 train_loss= 1.43474 train_acc= 0.20810 val_loss= 1.41237 val_acc= 0.14286 time= 0.01563
Epoch: 0003 train_loss= 1.42145 train_acc= 0.20810 val_loss= 1.41197 val_acc= 0.14286 time= 0.01563
Epoch: 0004 train_loss= 1.41618 train_acc= 0.21369 val_loss= 1.41477 val_acc= 0.08929 time= 0.01563
Epoch: 0005 train_loss= 1.40601 train_acc= 0.27374 val_loss= 1.41372 val_acc= 0.17857 time= 0.01563
Epoch: 0006 train_loss= 1.40494 train_acc= 0.25000 val_loss= 1.41546 val_acc= 0.19643 time= 0.03125
Epoch: 0007 train_loss= 1.39193 train_acc= 0.29609 val_loss= 1.41569 val_acc= 0.19643 time= 0.01563
Epoch: 0008 train_loss= 1.39309 train_acc= 0.31425 val_loss= 1.41277 val_acc= 0.19643 time= 0.01563
Epoch: 0009 train_loss= 1.39004 train_acc= 0.29609 val_loss= 1.40830 val_acc= 0.19643 time= 0.01563
Epoch: 0010 train_loss= 1.38721 train_acc= 0.31564 val_loss= 1.40303 val_acc= 0.19643 time= 0.01563
Epoch: 0011 train_loss= 1.38196 train_acc= 0.30726 val_loss= 1.39892 val_acc= 0.19643 time= 0.01563
Epoch: 0012 train_loss= 1.38603 train_acc= 0.30028 val_loss= 1.39511 val_acc= 0.19643 time= 0.01562
Epoch: 0013 train_loss= 1.38236 train_acc= 0.32542 val_loss= 1.39136 val_acc= 0.19643 time= 0.03125
Epoch: 0014 train_loss= 1.38086 train_acc= 0.27374 val_loss= 1.39000 val_acc= 0.21429 time= 0.01563
Epoch: 0015 train_loss= 1.38227 train_acc= 0.28631 val_loss= 1.38938 val_acc= 0.19643 time= 0.01563
Epoch: 0016 train_loss= 1.38008 train_acc= 0.29888 val_loss= 1.39168 val_acc= 0.19643 time= 0.01563
Epoch: 0017 train_loss= 1.38208 train_acc= 0.30168 val_loss= 1.39512 val_acc= 0.19643 time= 0.01563
Epoch: 0018 train_loss= 1.38556 train_acc= 0.31145 val_loss= 1.39629 val_acc= 0.19643 time= 0.01563
Epoch: 0019 train_loss= 1.37945 train_acc= 0.31983 val_loss= 1.39775 val_acc= 0.19643 time= 0.03125
Early stopping...
Optimization Finished!
Test set results: cost= 1.38651 accuracy= 0.31858 time= 0.00000 
