Epoch: 0001 train_loss= 1.61252 train_acc= 0.52987 val_loss= 0.79301 val_acc= 0.47541 time= 0.96909
Epoch: 0002 train_loss= 1.12608 train_acc= 0.53636 val_loss= 0.68286 val_acc= 0.59016 time= 0.01563
Epoch: 0003 train_loss= 1.01329 train_acc= 0.48961 val_loss= 0.77874 val_acc= 0.59016 time= 0.03125
Epoch: 0004 train_loss= 1.63573 train_acc= 0.48961 val_loss= 0.78300 val_acc= 0.59016 time= 0.01563
Epoch: 0005 train_loss= 1.10739 train_acc= 0.51299 val_loss= 0.74342 val_acc= 0.59016 time= 0.01563
Epoch: 0006 train_loss= 1.81037 train_acc= 0.46883 val_loss= 0.68703 val_acc= 0.59016 time= 0.03125
Epoch: 0007 train_loss= 0.95180 train_acc= 0.49481 val_loss= 0.67267 val_acc= 0.59016 time= 0.01563
Epoch: 0008 train_loss= 1.23078 train_acc= 0.53506 val_loss= 0.69136 val_acc= 0.52459 time= 0.03125
Epoch: 0009 train_loss= 1.19454 train_acc= 0.50000 val_loss= 0.76738 val_acc= 0.45902 time= 0.01563
Epoch: 0010 train_loss= 4.34381 train_acc= 0.53377 val_loss= 0.79801 val_acc= 0.45902 time= 0.03125
Epoch: 0011 train_loss= 1.74557 train_acc= 0.52597 val_loss= 0.78592 val_acc= 0.45902 time= 0.01563
Epoch: 0012 train_loss= 1.27200 train_acc= 0.54026 val_loss= 0.75622 val_acc= 0.45902 time= 0.03125
Early stopping...
Optimization Finished!
Test set results: cost= 0.73825 accuracy= 0.49180 time= 0.00000 
