Epoch: 0001 train_loss= 1.39233 train_acc= 0.20810 val_loss= 1.39250 val_acc= 0.25000 time= 0.34377
Epoch: 0002 train_loss= 1.39037 train_acc= 0.32542 val_loss= 1.39237 val_acc= 0.25000 time= 0.01563
Epoch: 0003 train_loss= 1.38856 train_acc= 0.32542 val_loss= 1.39235 val_acc= 0.25000 time= 0.01563
Epoch: 0004 train_loss= 1.38727 train_acc= 0.32542 val_loss= 1.39242 val_acc= 0.25000 time= 0.01563
Epoch: 0005 train_loss= 1.38558 train_acc= 0.32542 val_loss= 1.39252 val_acc= 0.25000 time= 0.01563
Epoch: 0006 train_loss= 1.38455 train_acc= 0.32542 val_loss= 1.39271 val_acc= 0.25000 time= 0.01563
Epoch: 0007 train_loss= 1.38300 train_acc= 0.32542 val_loss= 1.39299 val_acc= 0.25000 time= 0.01563
Epoch: 0008 train_loss= 1.38221 train_acc= 0.32542 val_loss= 1.39339 val_acc= 0.25000 time= 0.01563
Epoch: 0009 train_loss= 1.38079 train_acc= 0.32542 val_loss= 1.39392 val_acc= 0.25000 time= 0.01563
Epoch: 0010 train_loss= 1.37927 train_acc= 0.32542 val_loss= 1.39459 val_acc= 0.25000 time= 0.01563
Epoch: 0011 train_loss= 1.37818 train_acc= 0.32542 val_loss= 1.39541 val_acc= 0.25000 time= 0.01563
Epoch: 0012 train_loss= 1.37780 train_acc= 0.32542 val_loss= 1.39638 val_acc= 0.25000 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.37816 accuracy= 0.30973 time= 0.01563 
