Epoch: 0001 train_loss= 0.69619 train_acc= 0.48961 val_loss= 0.70509 val_acc= 0.37705 time= 0.89068
Epoch: 0002 train_loss= 0.69471 train_acc= 0.49481 val_loss= 0.69807 val_acc= 0.39344 time= 0.00000
Epoch: 0003 train_loss= 0.69396 train_acc= 0.51039 val_loss= 0.69274 val_acc= 0.54098 time= 0.01563
Epoch: 0004 train_loss= 0.69268 train_acc= 0.53636 val_loss= 0.68817 val_acc= 0.60656 time= 0.00000
Epoch: 0005 train_loss= 0.69423 train_acc= 0.53117 val_loss= 0.68471 val_acc= 0.62295 time= 0.01563
Epoch: 0006 train_loss= 0.69238 train_acc= 0.53117 val_loss= 0.68208 val_acc= 0.62295 time= 0.00000
Epoch: 0007 train_loss= 0.69520 train_acc= 0.50909 val_loss= 0.68105 val_acc= 0.63934 time= 0.00000
Epoch: 0008 train_loss= 0.69407 train_acc= 0.50779 val_loss= 0.68136 val_acc= 0.62295 time= 0.01563
Epoch: 0009 train_loss= 0.69242 train_acc= 0.50909 val_loss= 0.68234 val_acc= 0.62295 time= 0.00000
Epoch: 0010 train_loss= 0.69302 train_acc= 0.52078 val_loss= 0.68376 val_acc= 0.62295 time= 0.01563
Epoch: 0011 train_loss= 0.69387 train_acc= 0.52338 val_loss= 0.68578 val_acc= 0.60656 time= 0.00000
Epoch: 0012 train_loss= 0.69523 train_acc= 0.50519 val_loss= 0.68769 val_acc= 0.60656 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.69228 accuracy= 0.54098 time= 0.01563 
