Epoch: 0001 train_loss= 1.40091 train_acc= 0.26059 val_loss= 1.43797 val_acc= 0.21429 time= 0.10938
Epoch: 0002 train_loss= 1.41541 train_acc= 0.26059 val_loss= 1.41575 val_acc= 0.25000 time= 0.01563
Epoch: 0003 train_loss= 1.39719 train_acc= 0.26710 val_loss= 1.39803 val_acc= 0.37500 time= 0.01563
Epoch: 0004 train_loss= 1.39169 train_acc= 0.26710 val_loss= 1.38220 val_acc= 0.41071 time= 0.01563
Epoch: 0005 train_loss= 1.38608 train_acc= 0.29316 val_loss= 1.36966 val_acc= 0.39286 time= 0.01562
Epoch: 0006 train_loss= 1.38970 train_acc= 0.28664 val_loss= 1.35976 val_acc= 0.42857 time= 0.01563
Epoch: 0007 train_loss= 1.38725 train_acc= 0.27362 val_loss= 1.35165 val_acc= 0.42857 time= 0.03125
Epoch: 0008 train_loss= 1.39933 train_acc= 0.28664 val_loss= 1.34663 val_acc= 0.42857 time= 0.01563
Epoch: 0009 train_loss= 1.39335 train_acc= 0.28990 val_loss= 1.34213 val_acc= 0.42857 time= 0.01563
Epoch: 0010 train_loss= 1.39098 train_acc= 0.29316 val_loss= 1.33903 val_acc= 0.42857 time= 0.01563
Epoch: 0011 train_loss= 1.39122 train_acc= 0.29316 val_loss= 1.33645 val_acc= 0.42857 time= 0.01563
Epoch: 0012 train_loss= 1.38893 train_acc= 0.28339 val_loss= 1.33490 val_acc= 0.42857 time= 0.01563
Epoch: 0013 train_loss= 1.38437 train_acc= 0.28990 val_loss= 1.33424 val_acc= 0.44643 time= 0.01563
Epoch: 0014 train_loss= 1.38633 train_acc= 0.27362 val_loss= 1.33415 val_acc= 0.44643 time= 0.01563
Epoch: 0015 train_loss= 1.38499 train_acc= 0.28339 val_loss= 1.33435 val_acc= 0.44643 time= 0.01563
Epoch: 0016 train_loss= 1.38556 train_acc= 0.28664 val_loss= 1.33502 val_acc= 0.44643 time= 0.01563
Epoch: 0017 train_loss= 1.38370 train_acc= 0.29316 val_loss= 1.33621 val_acc= 0.44643 time= 0.01563
Epoch: 0018 train_loss= 1.38367 train_acc= 0.31596 val_loss= 1.33709 val_acc= 0.44643 time= 0.01563
Epoch: 0019 train_loss= 1.38501 train_acc= 0.29967 val_loss= 1.33822 val_acc= 0.44643 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.36630 accuracy= 0.35398 time= 0.01563 
