Epoch: 0001 train_loss= 0.69984 train_acc= 0.49351 val_loss= 0.69829 val_acc= 0.59677 time= 0.84470
Epoch: 0002 train_loss= 0.70028 train_acc= 0.47662 val_loss= 0.69929 val_acc= 0.41935 time= 0.01563
Epoch: 0003 train_loss= 0.69919 train_acc= 0.48052 val_loss= 0.70056 val_acc= 0.43548 time= 0.00000
Epoch: 0004 train_loss= 0.69680 train_acc= 0.52078 val_loss= 0.70203 val_acc= 0.43548 time= 0.01562
Epoch: 0005 train_loss= 0.69677 train_acc= 0.52987 val_loss= 0.70307 val_acc= 0.43548 time= 0.01238
Epoch: 0006 train_loss= 0.69759 train_acc= 0.52468 val_loss= 0.70328 val_acc= 0.43548 time= 0.00350
Epoch: 0007 train_loss= 0.69378 train_acc= 0.54286 val_loss= 0.70303 val_acc= 0.43548 time= 0.00000
Epoch: 0008 train_loss= 0.69559 train_acc= 0.53636 val_loss= 0.70231 val_acc= 0.43548 time= 0.01563
Epoch: 0009 train_loss= 0.69534 train_acc= 0.53247 val_loss= 0.70164 val_acc= 0.43548 time= 0.00000
Epoch: 0010 train_loss= 0.69586 train_acc= 0.52208 val_loss= 0.70083 val_acc= 0.43548 time= 0.00000
Epoch: 0011 train_loss= 0.69577 train_acc= 0.52597 val_loss= 0.69993 val_acc= 0.43548 time= 0.01563
Epoch: 0012 train_loss= 0.69472 train_acc= 0.52857 val_loss= 0.69915 val_acc= 0.41935 time= 0.00000
Epoch: 0013 train_loss= 0.69357 train_acc= 0.53117 val_loss= 0.69841 val_acc= 0.41935 time= 0.01563
Epoch: 0014 train_loss= 0.69262 train_acc= 0.52597 val_loss= 0.69775 val_acc= 0.41935 time= 0.00000
Epoch: 0015 train_loss= 0.69287 train_acc= 0.52468 val_loss= 0.69700 val_acc= 0.41935 time= 0.00000
Epoch: 0016 train_loss= 0.69292 train_acc= 0.54026 val_loss= 0.69628 val_acc= 0.43548 time= 0.01563
Epoch: 0017 train_loss= 0.69216 train_acc= 0.53377 val_loss= 0.69587 val_acc= 0.43548 time= 0.00000
Epoch: 0018 train_loss= 0.69149 train_acc= 0.52727 val_loss= 0.69557 val_acc= 0.43548 time= 0.01563
Epoch: 0019 train_loss= 0.69265 train_acc= 0.53247 val_loss= 0.69558 val_acc= 0.43548 time= 0.00000
Epoch: 0020 train_loss= 0.69135 train_acc= 0.53247 val_loss= 0.69582 val_acc= 0.43548 time= 0.00000
Epoch: 0021 train_loss= 0.69218 train_acc= 0.52078 val_loss= 0.69615 val_acc= 0.43548 time= 0.01563
Epoch: 0022 train_loss= 0.69144 train_acc= 0.53117 val_loss= 0.69645 val_acc= 0.43548 time= 0.00000
Epoch: 0023 train_loss= 0.69118 train_acc= 0.53766 val_loss= 0.69681 val_acc= 0.43548 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.68755 accuracy= 0.57258 time= 0.00000 
