Epoch: 0001 train_loss= 0.83993 train_acc= 0.50364 val_loss= 0.64056 val_acc= 0.62295 time= 0.39389
Epoch: 0002 train_loss= 0.90790 train_acc= 0.51273 val_loss= 0.65244 val_acc= 0.54098 time= 0.01563
Epoch: 0003 train_loss= 0.99832 train_acc= 0.47818 val_loss= 0.63882 val_acc= 0.59016 time= 0.01562
Epoch: 0004 train_loss= 0.87788 train_acc= 0.52182 val_loss= 0.64554 val_acc= 0.62295 time= 0.00000
Epoch: 0005 train_loss= 1.02134 train_acc= 0.46364 val_loss= 0.66812 val_acc= 0.59016 time= 0.01563
Epoch: 0006 train_loss= 0.99230 train_acc= 0.49091 val_loss= 0.68323 val_acc= 0.54098 time= 0.01563
Epoch: 0007 train_loss= 0.84786 train_acc= 0.48545 val_loss= 0.70424 val_acc= 0.57377 time= 0.01563
Epoch: 0008 train_loss= 1.01172 train_acc= 0.48909 val_loss= 0.72782 val_acc= 0.50820 time= 0.01562
Epoch: 0009 train_loss= 0.94696 train_acc= 0.47455 val_loss= 0.74336 val_acc= 0.44262 time= 0.01563
Epoch: 0010 train_loss= 0.78218 train_acc= 0.48727 val_loss= 0.75639 val_acc= 0.44262 time= 0.00000
Epoch: 0011 train_loss= 0.91585 train_acc= 0.50909 val_loss= 0.75627 val_acc= 0.44262 time= 0.01563
Epoch: 0012 train_loss= 0.81535 train_acc= 0.50545 val_loss= 0.74888 val_acc= 0.47541 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.70338 accuracy= 0.49180 time= 0.00000 
