Epoch: 0001 train_loss= 1.41523 train_acc= 0.25279 val_loss= 1.37046 val_acc= 0.30357 time= 0.70317
Epoch: 0002 train_loss= 1.39821 train_acc= 0.25000 val_loss= 1.37068 val_acc= 0.21429 time= 0.01562
Epoch: 0003 train_loss= 1.39742 train_acc= 0.28492 val_loss= 1.37361 val_acc= 0.25000 time= 0.00000
Epoch: 0004 train_loss= 1.39063 train_acc= 0.25279 val_loss= 1.37648 val_acc= 0.23214 time= 0.01563
Epoch: 0005 train_loss= 1.38416 train_acc= 0.29609 val_loss= 1.37957 val_acc= 0.23214 time= 0.01562
Epoch: 0006 train_loss= 1.41954 train_acc= 0.30028 val_loss= 1.38228 val_acc= 0.23214 time= 0.01563
Epoch: 0007 train_loss= 1.40677 train_acc= 0.30028 val_loss= 1.38383 val_acc= 0.23214 time= 0.01563
Epoch: 0008 train_loss= 1.41164 train_acc= 0.28631 val_loss= 1.38537 val_acc= 0.23214 time= 0.00000
Epoch: 0009 train_loss= 1.39630 train_acc= 0.31285 val_loss= 1.38637 val_acc= 0.25000 time= 0.01563
Epoch: 0010 train_loss= 1.38694 train_acc= 0.31145 val_loss= 1.38733 val_acc= 0.25000 time= 0.01563
Epoch: 0011 train_loss= 1.38760 train_acc= 0.27514 val_loss= 1.38825 val_acc= 0.30357 time= 0.01563
Epoch: 0012 train_loss= 1.38397 train_acc= 0.31006 val_loss= 1.38886 val_acc= 0.33929 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 1.36697 accuracy= 0.33628 time= 0.01563 
