Epoch: 0001 train_loss= 1.47803 train_acc= 0.17590 val_loss= 1.44126 val_acc= 0.17857 time= 0.06251
Epoch: 0002 train_loss= 1.46103 train_acc= 0.17915 val_loss= 1.43062 val_acc= 0.17857 time= 0.01562
Epoch: 0003 train_loss= 1.43496 train_acc= 0.18567 val_loss= 1.42289 val_acc= 0.17857 time= 0.01562
Epoch: 0004 train_loss= 1.42168 train_acc= 0.16938 val_loss= 1.41709 val_acc= 0.16071 time= 0.01563
Epoch: 0005 train_loss= 1.43075 train_acc= 0.15961 val_loss= 1.41265 val_acc= 0.19643 time= 0.01563
Epoch: 0006 train_loss= 1.41148 train_acc= 0.22150 val_loss= 1.40935 val_acc= 0.25000 time= 0.01563
Epoch: 0007 train_loss= 1.39798 train_acc= 0.24756 val_loss= 1.40689 val_acc= 0.26786 time= 0.01563
Epoch: 0008 train_loss= 1.38963 train_acc= 0.27687 val_loss= 1.40530 val_acc= 0.30357 time= 0.01563
Epoch: 0009 train_loss= 1.39270 train_acc= 0.25081 val_loss= 1.40467 val_acc= 0.30357 time= 0.01563
Epoch: 0010 train_loss= 1.38345 train_acc= 0.25407 val_loss= 1.40464 val_acc= 0.30357 time= 0.01563
Epoch: 0011 train_loss= 1.39175 train_acc= 0.26384 val_loss= 1.40518 val_acc= 0.30357 time= 0.01562
Epoch: 0012 train_loss= 1.37090 train_acc= 0.28339 val_loss= 1.40582 val_acc= 0.26786 time= 0.01563
Epoch: 0013 train_loss= 1.37652 train_acc= 0.31922 val_loss= 1.40614 val_acc= 0.32143 time= 0.01563
Epoch: 0014 train_loss= 1.37764 train_acc= 0.27036 val_loss= 1.40702 val_acc= 0.25000 time= 0.01563
Epoch: 0015 train_loss= 1.36505 train_acc= 0.28664 val_loss= 1.40823 val_acc= 0.23214 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.40428 accuracy= 0.30088 time= 0.00000 
