Epoch: 0001 train_loss= 0.70994 train_acc= 0.47792 val_loss= 0.68463 val_acc= 0.62295 time= 0.82818
Epoch: 0002 train_loss= 0.70575 train_acc= 0.48182 val_loss= 0.68607 val_acc= 0.62295 time= 0.01563
Epoch: 0003 train_loss= 0.70565 train_acc= 0.47532 val_loss= 0.68763 val_acc= 0.62295 time= 0.00000
Epoch: 0004 train_loss= 0.70229 train_acc= 0.47273 val_loss= 0.68930 val_acc= 0.62295 time= 0.00000
Epoch: 0005 train_loss= 0.70028 train_acc= 0.47532 val_loss= 0.69105 val_acc= 0.62295 time= 0.01563
Epoch: 0006 train_loss= 0.69918 train_acc= 0.48831 val_loss= 0.69286 val_acc= 0.62295 time= 0.00000
Epoch: 0007 train_loss= 0.69747 train_acc= 0.47143 val_loss= 0.69469 val_acc= 0.60656 time= 0.01563
Epoch: 0008 train_loss= 0.69716 train_acc= 0.47662 val_loss= 0.69651 val_acc= 0.39344 time= 0.00000
Epoch: 0009 train_loss= 0.69436 train_acc= 0.52468 val_loss= 0.69832 val_acc= 0.37705 time= 0.00000
Epoch: 0010 train_loss= 0.69562 train_acc= 0.50130 val_loss= 0.70011 val_acc= 0.37705 time= 0.01563
Epoch: 0011 train_loss= 0.69335 train_acc= 0.51818 val_loss= 0.70190 val_acc= 0.37705 time= 0.00000
Epoch: 0012 train_loss= 0.69374 train_acc= 0.51948 val_loss= 0.70362 val_acc= 0.37705 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.69774 accuracy= 0.48361 time= 0.01563 
