Epoch: 0001 train_loss= 1.40007 train_acc= 0.29492 val_loss= 1.42369 val_acc= 0.23214 time= 0.18751
Epoch: 0002 train_loss= 1.40971 train_acc= 0.21680 val_loss= 1.41221 val_acc= 0.21429 time= 0.01563
Epoch: 0003 train_loss= 1.39481 train_acc= 0.24023 val_loss= 1.40292 val_acc= 0.21429 time= 0.01563
Epoch: 0004 train_loss= 1.39321 train_acc= 0.29492 val_loss= 1.39268 val_acc= 0.21429 time= 0.01563
Epoch: 0005 train_loss= 1.38686 train_acc= 0.30273 val_loss= 1.38577 val_acc= 0.21429 time= 0.01563
Epoch: 0006 train_loss= 1.39060 train_acc= 0.30078 val_loss= 1.37946 val_acc= 0.23214 time= 0.01563
Epoch: 0007 train_loss= 1.38585 train_acc= 0.30469 val_loss= 1.37346 val_acc= 0.25000 time= 0.01563
Epoch: 0008 train_loss= 1.38366 train_acc= 0.30469 val_loss= 1.36915 val_acc= 0.23214 time= 0.01563
Epoch: 0009 train_loss= 1.38584 train_acc= 0.31641 val_loss= 1.36578 val_acc= 0.23214 time= 0.01563
Epoch: 0010 train_loss= 1.38551 train_acc= 0.30078 val_loss= 1.36304 val_acc= 0.21429 time= 0.01563
Epoch: 0011 train_loss= 1.38402 train_acc= 0.30664 val_loss= 1.36178 val_acc= 0.21429 time= 0.01563
Epoch: 0012 train_loss= 1.38154 train_acc= 0.30664 val_loss= 1.36206 val_acc= 0.21429 time= 0.01563
Epoch: 0013 train_loss= 1.37835 train_acc= 0.34180 val_loss= 1.36317 val_acc= 0.25000 time= 0.01563
Epoch: 0014 train_loss= 1.38218 train_acc= 0.29688 val_loss= 1.36389 val_acc= 0.25000 time= 0.01563
Epoch: 0015 train_loss= 1.38060 train_acc= 0.31250 val_loss= 1.36515 val_acc= 0.28571 time= 0.01563
Epoch: 0016 train_loss= 1.38256 train_acc= 0.30469 val_loss= 1.36746 val_acc= 0.26786 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.37861 accuracy= 0.30973 time= 0.01563 
