Epoch: 0001 train_loss= 0.70392 train_acc= 0.48788 val_loss= 0.69821 val_acc= 0.45902 time= 0.27306
Epoch: 0002 train_loss= 0.69749 train_acc= 0.49091 val_loss= 0.69661 val_acc= 0.45902 time= 0.00700
Epoch: 0003 train_loss= 0.69645 train_acc= 0.48182 val_loss= 0.69550 val_acc= 0.44262 time= 0.00600
Epoch: 0004 train_loss= 0.69742 train_acc= 0.50000 val_loss= 0.69483 val_acc= 0.39344 time= 0.00700
Epoch: 0005 train_loss= 0.69593 train_acc= 0.42727 val_loss= 0.69459 val_acc= 0.47541 time= 0.00700
Epoch: 0006 train_loss= 0.69353 train_acc= 0.49697 val_loss= 0.69468 val_acc= 0.54098 time= 0.00700
Epoch: 0007 train_loss= 0.69597 train_acc= 0.49091 val_loss= 0.69484 val_acc= 0.54098 time= 0.00900
Epoch: 0008 train_loss= 0.69276 train_acc= 0.49394 val_loss= 0.69507 val_acc= 0.54098 time= 0.00800
Epoch: 0009 train_loss= 0.69359 train_acc= 0.50000 val_loss= 0.69534 val_acc= 0.54098 time= 0.00700
Epoch: 0010 train_loss= 0.69477 train_acc= 0.52121 val_loss= 0.69554 val_acc= 0.54098 time= 0.00600
Epoch: 0011 train_loss= 0.69592 train_acc= 0.51212 val_loss= 0.69554 val_acc= 0.54098 time= 0.00600
Epoch: 0012 train_loss= 0.69556 train_acc= 0.50303 val_loss= 0.69537 val_acc= 0.54098 time= 0.00600
Early stopping...
Optimization Finished!
Test set results: cost= 0.69842 accuracy= 0.48361 time= 0.00200 
