Epoch: 0001 train_loss= 1.47299 train_acc= 0.19553 val_loss= 1.47608 val_acc= 0.12500 time= 0.70317
Epoch: 0002 train_loss= 1.45677 train_acc= 0.21648 val_loss= 1.45135 val_acc= 0.12500 time= 0.01563
Epoch: 0003 train_loss= 1.42242 train_acc= 0.23184 val_loss= 1.42950 val_acc= 0.12500 time= 0.01563
Epoch: 0004 train_loss= 1.42765 train_acc= 0.20391 val_loss= 1.41212 val_acc= 0.12500 time= 0.01563
Epoch: 0005 train_loss= 1.42890 train_acc= 0.22207 val_loss= 1.39675 val_acc= 0.16071 time= 0.01563
Epoch: 0006 train_loss= 1.40493 train_acc= 0.23184 val_loss= 1.38325 val_acc= 0.23214 time= 0.01563
Epoch: 0007 train_loss= 1.38967 train_acc= 0.27235 val_loss= 1.37184 val_acc= 0.25000 time= 0.01563
Epoch: 0008 train_loss= 1.39541 train_acc= 0.25279 val_loss= 1.36255 val_acc= 0.35714 time= 0.01563
Epoch: 0009 train_loss= 1.39180 train_acc= 0.27514 val_loss= 1.35536 val_acc= 0.37500 time= 0.01563
Epoch: 0010 train_loss= 1.39383 train_acc= 0.31145 val_loss= 1.35053 val_acc= 0.42857 time= 0.01563
Epoch: 0011 train_loss= 1.39901 train_acc= 0.26117 val_loss= 1.34676 val_acc= 0.41071 time= 0.01563
Epoch: 0012 train_loss= 1.39799 train_acc= 0.28911 val_loss= 1.34484 val_acc= 0.37500 time= 0.01563
Epoch: 0013 train_loss= 1.37730 train_acc= 0.30587 val_loss= 1.34339 val_acc= 0.37500 time= 0.01563
Epoch: 0014 train_loss= 1.39161 train_acc= 0.29469 val_loss= 1.34262 val_acc= 0.37500 time= 0.01563
Epoch: 0015 train_loss= 1.38477 train_acc= 0.30447 val_loss= 1.34243 val_acc= 0.37500 time= 0.01563
Epoch: 0016 train_loss= 1.38758 train_acc= 0.31145 val_loss= 1.34327 val_acc= 0.37500 time= 0.01563
Epoch: 0017 train_loss= 1.38408 train_acc= 0.32402 val_loss= 1.34438 val_acc= 0.37500 time= 0.01563
Epoch: 0018 train_loss= 1.38727 train_acc= 0.29609 val_loss= 1.34641 val_acc= 0.39286 time= 0.01563
Epoch: 0019 train_loss= 1.38301 train_acc= 0.31844 val_loss= 1.34796 val_acc= 0.39286 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 1.38779 accuracy= 0.29204 time= 0.01563 
