Epoch: 0001 train_loss= 1.42442 train_acc= 0.22656 val_loss= 1.39641 val_acc= 0.25000 time= 0.45592
Epoch: 0002 train_loss= 1.42255 train_acc= 0.21094 val_loss= 1.39067 val_acc= 0.25000 time= 0.01700
Epoch: 0003 train_loss= 1.40471 train_acc= 0.23438 val_loss= 1.38687 val_acc= 0.25000 time= 0.01700
Epoch: 0004 train_loss= 1.39522 train_acc= 0.24805 val_loss= 1.38417 val_acc= 0.21429 time= 0.01600
Epoch: 0005 train_loss= 1.39426 train_acc= 0.25000 val_loss= 1.38386 val_acc= 0.19643 time= 0.01700
Epoch: 0006 train_loss= 1.38583 train_acc= 0.27344 val_loss= 1.38426 val_acc= 0.28571 time= 0.01800
Epoch: 0007 train_loss= 1.38924 train_acc= 0.23242 val_loss= 1.38543 val_acc= 0.26786 time= 0.01600
Epoch: 0008 train_loss= 1.37838 train_acc= 0.32422 val_loss= 1.38709 val_acc= 0.26786 time= 0.01900
Epoch: 0009 train_loss= 1.39580 train_acc= 0.32812 val_loss= 1.38937 val_acc= 0.25000 time= 0.01700
Epoch: 0010 train_loss= 1.38029 train_acc= 0.33789 val_loss= 1.39175 val_acc= 0.25000 time= 0.01800
Epoch: 0011 train_loss= 1.37852 train_acc= 0.33789 val_loss= 1.39380 val_acc= 0.25000 time= 0.01700
Epoch: 0012 train_loss= 1.37737 train_acc= 0.33984 val_loss= 1.39622 val_acc= 0.25000 time= 0.01700
Early stopping...
Optimization Finished!
Test set results: cost= 1.34069 accuracy= 0.36283 time= 0.00800 
