Epoch: 0001 train_loss= 1.39402 train_acc= 0.32248 val_loss= 1.39130 val_acc= 0.15000 time= 0.23439
Epoch: 0002 train_loss= 1.39075 train_acc= 0.32899 val_loss= 1.38960 val_acc= 0.15000 time= 0.00000
Epoch: 0003 train_loss= 1.38788 train_acc= 0.32899 val_loss= 1.38892 val_acc= 0.15000 time= 0.01563
Epoch: 0004 train_loss= 1.38564 train_acc= 0.32899 val_loss= 1.38907 val_acc= 0.15000 time= 0.01563
Epoch: 0005 train_loss= 1.38384 train_acc= 0.32899 val_loss= 1.38990 val_acc= 0.15000 time= 0.01563
Epoch: 0006 train_loss= 1.38237 train_acc= 0.32899 val_loss= 1.39131 val_acc= 0.15000 time= 0.01563
Epoch: 0007 train_loss= 1.38138 train_acc= 0.32899 val_loss= 1.39305 val_acc= 0.15000 time= 0.00000
Epoch: 0008 train_loss= 1.37995 train_acc= 0.32899 val_loss= 1.39529 val_acc= 0.15000 time= 0.01563
Epoch: 0009 train_loss= 1.37952 train_acc= 0.32899 val_loss= 1.39783 val_acc= 0.15000 time= 0.01563
Epoch: 0010 train_loss= 1.37867 train_acc= 0.32899 val_loss= 1.40061 val_acc= 0.15000 time= 0.01563
Epoch: 0011 train_loss= 1.37779 train_acc= 0.32899 val_loss= 1.40358 val_acc= 0.15000 time= 0.01563
Epoch: 0012 train_loss= 1.37750 train_acc= 0.32899 val_loss= 1.40656 val_acc= 0.15000 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 1.38563 accuracy= 0.31667 time= 0.01563 
