Epoch: 0001 train_loss= 1.99057 train_acc= 0.48442 val_loss= 0.72597 val_acc= 0.37705 time= 0.96881
Epoch: 0002 train_loss= 0.85792 train_acc= 0.48312 val_loss= 0.69074 val_acc= 0.59016 time= 0.03125
Epoch: 0003 train_loss= 1.07545 train_acc= 0.49481 val_loss= 0.67607 val_acc= 0.60656 time= 0.01563
Epoch: 0004 train_loss= 0.86830 train_acc= 0.50519 val_loss= 0.68053 val_acc= 0.60656 time= 0.03125
Epoch: 0005 train_loss= 0.83401 train_acc= 0.52078 val_loss= 0.69028 val_acc= 0.60656 time= 0.01563
Epoch: 0006 train_loss= 0.86977 train_acc= 0.51299 val_loss= 0.69029 val_acc= 0.60656 time= 0.03125
Epoch: 0007 train_loss= 0.95091 train_acc= 0.54286 val_loss= 0.69322 val_acc= 0.60656 time= 0.01562
Epoch: 0008 train_loss= 1.40645 train_acc= 0.51039 val_loss= 0.68618 val_acc= 0.60656 time= 0.03125
Epoch: 0009 train_loss= 0.77482 train_acc= 0.51558 val_loss= 0.68003 val_acc= 0.60656 time= 0.01563
Epoch: 0010 train_loss= 0.72190 train_acc= 0.54286 val_loss= 0.67768 val_acc= 0.60656 time= 0.01562
Epoch: 0011 train_loss= 0.73948 train_acc= 0.52078 val_loss= 0.67621 val_acc= 0.59016 time= 0.03125
Epoch: 0012 train_loss= 0.95246 train_acc= 0.52338 val_loss= 0.67749 val_acc= 0.59016 time= 0.01563
Epoch: 0013 train_loss= 0.93900 train_acc= 0.51818 val_loss= 0.68024 val_acc= 0.60656 time= 0.03125
Epoch: 0014 train_loss= 0.73828 train_acc= 0.53117 val_loss= 0.68437 val_acc= 0.63934 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.71327 accuracy= 0.56557 time= 0.01563 
