Epoch: 0001 train_loss= 1.39274 train_acc= 0.27148 val_loss= 1.38270 val_acc= 0.35714 time= 0.49590
Epoch: 0002 train_loss= 1.39948 train_acc= 0.23828 val_loss= 1.38299 val_acc= 0.33929 time= 0.01700
Epoch: 0003 train_loss= 1.40382 train_acc= 0.28125 val_loss= 1.38549 val_acc= 0.33929 time= 0.01900
Epoch: 0004 train_loss= 1.39065 train_acc= 0.30664 val_loss= 1.38808 val_acc= 0.33929 time= 0.01700
Epoch: 0005 train_loss= 1.39100 train_acc= 0.32227 val_loss= 1.39185 val_acc= 0.33929 time= 0.01700
Epoch: 0006 train_loss= 1.38256 train_acc= 0.32617 val_loss= 1.39581 val_acc= 0.30357 time= 0.01700
Epoch: 0007 train_loss= 1.37587 train_acc= 0.30859 val_loss= 1.39912 val_acc= 0.30357 time= 0.01900
Epoch: 0008 train_loss= 1.37828 train_acc= 0.32617 val_loss= 1.40124 val_acc= 0.32143 time= 0.01700
Epoch: 0009 train_loss= 1.37773 train_acc= 0.32227 val_loss= 1.40285 val_acc= 0.26786 time= 0.01900
Epoch: 0010 train_loss= 1.37314 train_acc= 0.33008 val_loss= 1.40341 val_acc= 0.25000 time= 0.01700
Epoch: 0011 train_loss= 1.38724 train_acc= 0.31445 val_loss= 1.40257 val_acc= 0.26786 time= 0.01600
Epoch: 0012 train_loss= 1.38736 train_acc= 0.31641 val_loss= 1.40067 val_acc= 0.28571 time= 0.01600
Early stopping...
Optimization Finished!
Test set results: cost= 1.41908 accuracy= 0.27434 time= 0.00800 
