Epoch: 0001 train_loss= 1.40146 train_acc= 0.22207 val_loss= 1.38813 val_acc= 0.28571 time= 0.32815
Epoch: 0002 train_loss= 1.38716 train_acc= 0.28352 val_loss= 1.38064 val_acc= 0.28571 time= 0.01563
Epoch: 0003 train_loss= 1.39033 train_acc= 0.27235 val_loss= 1.37550 val_acc= 0.35714 time= 0.01563
Epoch: 0004 train_loss= 1.38888 train_acc= 0.30587 val_loss= 1.37200 val_acc= 0.35714 time= 0.01563
Epoch: 0005 train_loss= 1.38452 train_acc= 0.29469 val_loss= 1.36920 val_acc= 0.37500 time= 0.01563
Epoch: 0006 train_loss= 1.38863 train_acc= 0.30447 val_loss= 1.36713 val_acc= 0.37500 time= 0.01563
Epoch: 0007 train_loss= 1.38563 train_acc= 0.30028 val_loss= 1.36473 val_acc= 0.37500 time= 0.01563
Epoch: 0008 train_loss= 1.38633 train_acc= 0.31425 val_loss= 1.36294 val_acc= 0.37500 time= 0.01563
Epoch: 0009 train_loss= 1.38294 train_acc= 0.30587 val_loss= 1.36200 val_acc= 0.37500 time= 0.03125
Epoch: 0010 train_loss= 1.38372 train_acc= 0.30587 val_loss= 1.36158 val_acc= 0.37500 time= 0.01563
Epoch: 0011 train_loss= 1.38244 train_acc= 0.31145 val_loss= 1.36150 val_acc= 0.37500 time= 0.01563
Epoch: 0012 train_loss= 1.38081 train_acc= 0.30447 val_loss= 1.36142 val_acc= 0.37500 time= 0.01563
Epoch: 0013 train_loss= 1.38459 train_acc= 0.31145 val_loss= 1.36233 val_acc= 0.37500 time= 0.01563
Epoch: 0014 train_loss= 1.38305 train_acc= 0.30726 val_loss= 1.36385 val_acc= 0.37500 time= 0.03125
Epoch: 0015 train_loss= 1.38448 train_acc= 0.29888 val_loss= 1.36612 val_acc= 0.35714 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.38534 accuracy= 0.31858 time= 0.00000 
