Epoch: 0001 train_loss= 1.39651 train_acc= 0.17590 val_loss= 1.39449 val_acc= 0.26786 time= 0.09376
Epoch: 0002 train_loss= 1.39441 train_acc= 0.17264 val_loss= 1.39422 val_acc= 0.16071 time= 0.00000
Epoch: 0003 train_loss= 1.39254 train_acc= 0.22801 val_loss= 1.39409 val_acc= 0.16071 time= 0.01563
Epoch: 0004 train_loss= 1.39107 train_acc= 0.32899 val_loss= 1.39424 val_acc= 0.26786 time= 0.01562
Epoch: 0005 train_loss= 1.39060 train_acc= 0.32248 val_loss= 1.39481 val_acc= 0.16071 time= 0.01563
Epoch: 0006 train_loss= 1.38964 train_acc= 0.32573 val_loss= 1.39543 val_acc= 0.16071 time= 0.00000
Epoch: 0007 train_loss= 1.38887 train_acc= 0.32573 val_loss= 1.39611 val_acc= 0.16071 time= 0.01563
Epoch: 0008 train_loss= 1.38823 train_acc= 0.32573 val_loss= 1.39683 val_acc= 0.16071 time= 0.01563
Epoch: 0009 train_loss= 1.38730 train_acc= 0.32248 val_loss= 1.39759 val_acc= 0.16071 time= 0.01562
Epoch: 0010 train_loss= 1.38608 train_acc= 0.32573 val_loss= 1.39841 val_acc= 0.16071 time= 0.01563
Epoch: 0011 train_loss= 1.38546 train_acc= 0.32573 val_loss= 1.39927 val_acc= 0.16071 time= 0.00000
Epoch: 0012 train_loss= 1.38547 train_acc= 0.32573 val_loss= 1.40017 val_acc= 0.16071 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.38935 accuracy= 0.30088 time= 0.01563 
