Epoch: 0001 train_loss= 1.40881 train_acc= 0.27687 val_loss= 1.38754 val_acc= 0.21667 time= 0.15626
Epoch: 0002 train_loss= 1.40222 train_acc= 0.26710 val_loss= 1.38590 val_acc= 0.21667 time= 0.01563
Epoch: 0003 train_loss= 1.38995 train_acc= 0.28664 val_loss= 1.38595 val_acc= 0.23333 time= 0.01563
Epoch: 0004 train_loss= 1.39637 train_acc= 0.28339 val_loss= 1.38606 val_acc= 0.25000 time= 0.00000
Epoch: 0005 train_loss= 1.38527 train_acc= 0.27687 val_loss= 1.38651 val_acc= 0.38333 time= 0.01563
Epoch: 0006 train_loss= 1.39388 train_acc= 0.25407 val_loss= 1.38765 val_acc= 0.36667 time= 0.01563
Epoch: 0007 train_loss= 1.39301 train_acc= 0.27362 val_loss= 1.38917 val_acc= 0.35000 time= 0.01563
Epoch: 0008 train_loss= 1.37333 train_acc= 0.32573 val_loss= 1.39089 val_acc= 0.35000 time= 0.00000
Epoch: 0009 train_loss= 1.38770 train_acc= 0.26710 val_loss= 1.39257 val_acc= 0.33333 time= 0.01563
Epoch: 0010 train_loss= 1.39176 train_acc= 0.28664 val_loss= 1.39405 val_acc= 0.33333 time= 0.01563
Epoch: 0011 train_loss= 1.37757 train_acc= 0.28664 val_loss= 1.39513 val_acc= 0.31667 time= 0.01563
Epoch: 0012 train_loss= 1.37385 train_acc= 0.27362 val_loss= 1.39620 val_acc= 0.31667 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.37298 accuracy= 0.32500 time= 0.00000 
