Epoch: 0001 train_loss= 1.39632 train_acc= 0.28911 val_loss= 1.38001 val_acc= 0.30357 time= 0.70317
Epoch: 0002 train_loss= 1.40052 train_acc= 0.30028 val_loss= 1.37652 val_acc= 0.32143 time= 0.01563
Epoch: 0003 train_loss= 1.38671 train_acc= 0.29749 val_loss= 1.37403 val_acc= 0.35714 time= 0.01563
Epoch: 0004 train_loss= 1.38650 train_acc= 0.30587 val_loss= 1.37219 val_acc= 0.32143 time= 0.01563
Epoch: 0005 train_loss= 1.39122 train_acc= 0.29888 val_loss= 1.37127 val_acc= 0.30357 time= 0.01563
Epoch: 0006 train_loss= 1.38261 train_acc= 0.29190 val_loss= 1.37044 val_acc= 0.30357 time= 0.00000
Epoch: 0007 train_loss= 1.37891 train_acc= 0.30866 val_loss= 1.36906 val_acc= 0.30357 time= 0.01563
Epoch: 0008 train_loss= 1.38062 train_acc= 0.29888 val_loss= 1.36726 val_acc= 0.30357 time= 0.01563
Epoch: 0009 train_loss= 1.38866 train_acc= 0.29609 val_loss= 1.36542 val_acc= 0.30357 time= 0.01563
Epoch: 0010 train_loss= 1.38759 train_acc= 0.29888 val_loss= 1.36372 val_acc= 0.26786 time= 0.01563
Epoch: 0011 train_loss= 1.38524 train_acc= 0.29330 val_loss= 1.36262 val_acc= 0.26786 time= 0.00000
Epoch: 0012 train_loss= 1.37185 train_acc= 0.31564 val_loss= 1.36206 val_acc= 0.32143 time= 0.01563
Epoch: 0013 train_loss= 1.37727 train_acc= 0.32263 val_loss= 1.36243 val_acc= 0.35714 time= 0.01563
Epoch: 0014 train_loss= 1.38020 train_acc= 0.30726 val_loss= 1.36313 val_acc= 0.33929 time= 0.01563
Epoch: 0015 train_loss= 1.37214 train_acc= 0.29888 val_loss= 1.36375 val_acc= 0.33929 time= 0.01563
Epoch: 0016 train_loss= 1.37283 train_acc= 0.30587 val_loss= 1.36439 val_acc= 0.35714 time= 0.00000
Epoch: 0017 train_loss= 1.36747 train_acc= 0.33520 val_loss= 1.36499 val_acc= 0.33929 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.39181 accuracy= 0.31858 time= 0.00000 
