Epoch: 0001 train_loss= 1.39420 train_acc= 0.18017 val_loss= 1.39144 val_acc= 0.28571 time= 0.79721
Epoch: 0002 train_loss= 1.39126 train_acc= 0.27514 val_loss= 1.38947 val_acc= 0.25000 time= 0.01562
Epoch: 0003 train_loss= 1.38881 train_acc= 0.31425 val_loss= 1.38811 val_acc= 0.25000 time= 0.01563
Epoch: 0004 train_loss= 1.38667 train_acc= 0.31285 val_loss= 1.38730 val_acc= 0.25000 time= 0.01563
Epoch: 0005 train_loss= 1.38516 train_acc= 0.31145 val_loss= 1.38691 val_acc= 0.25000 time= 0.00000
Epoch: 0006 train_loss= 1.38373 train_acc= 0.30866 val_loss= 1.38687 val_acc= 0.25000 time= 0.01563
Epoch: 0007 train_loss= 1.38284 train_acc= 0.30726 val_loss= 1.38714 val_acc= 0.25000 time= 0.01563
Epoch: 0008 train_loss= 1.38222 train_acc= 0.31145 val_loss= 1.38759 val_acc= 0.25000 time= 0.01563
Epoch: 0009 train_loss= 1.38176 train_acc= 0.31425 val_loss= 1.38812 val_acc= 0.25000 time= 0.01562
Epoch: 0010 train_loss= 1.38116 train_acc= 0.30866 val_loss= 1.38868 val_acc= 0.25000 time= 0.01563
Epoch: 0011 train_loss= 1.38128 train_acc= 0.31285 val_loss= 1.38921 val_acc= 0.25000 time= 0.00000
Epoch: 0012 train_loss= 1.38105 train_acc= 0.31006 val_loss= 1.38966 val_acc= 0.25000 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.39191 accuracy= 0.28319 time= 0.01563 
