Epoch: 0001 train_loss= 1.39410 train_acc= 0.25733 val_loss= 1.39061 val_acc= 0.33333 time= 0.18751
Epoch: 0002 train_loss= 1.39120 train_acc= 0.25407 val_loss= 1.38800 val_acc= 0.33333 time= 0.01563
Epoch: 0003 train_loss= 1.38906 train_acc= 0.25407 val_loss= 1.38619 val_acc= 0.33333 time= 0.01563
Epoch: 0004 train_loss= 1.38743 train_acc= 0.25407 val_loss= 1.38497 val_acc= 0.33333 time= 0.01563
Epoch: 0005 train_loss= 1.38640 train_acc= 0.25407 val_loss= 1.38419 val_acc= 0.33333 time= 0.01563
Epoch: 0006 train_loss= 1.38588 train_acc= 0.25407 val_loss= 1.38382 val_acc= 0.33333 time= 0.01563
Epoch: 0007 train_loss= 1.38562 train_acc= 0.25733 val_loss= 1.38373 val_acc= 0.23333 time= 0.01563
Epoch: 0008 train_loss= 1.38558 train_acc= 0.26710 val_loss= 1.38378 val_acc= 0.23333 time= 0.01563
Epoch: 0009 train_loss= 1.38575 train_acc= 0.26710 val_loss= 1.38395 val_acc= 0.23333 time= 0.01563
Epoch: 0010 train_loss= 1.38564 train_acc= 0.25733 val_loss= 1.38414 val_acc= 0.23333 time= 0.01563
Epoch: 0011 train_loss= 1.38561 train_acc= 0.27687 val_loss= 1.38427 val_acc= 0.23333 time= 0.01563
Epoch: 0012 train_loss= 1.38577 train_acc= 0.26710 val_loss= 1.38442 val_acc= 0.23333 time= 0.01563
Epoch: 0013 train_loss= 1.38605 train_acc= 0.27036 val_loss= 1.38455 val_acc= 0.23333 time= 0.01562
Early stopping...
Optimization Finished!
Test set results: cost= 1.38454 accuracy= 0.31667 time= 0.00000 
