Epoch: 0001 train_loss= 1.39678 train_acc= 0.25586 val_loss= 1.39369 val_acc= 0.23214 time= 0.21877
Epoch: 0002 train_loss= 1.39560 train_acc= 0.25391 val_loss= 1.38683 val_acc= 0.21429 time= 0.01563
Epoch: 0003 train_loss= 1.39248 train_acc= 0.26953 val_loss= 1.38141 val_acc= 0.26786 time= 0.01563
Epoch: 0004 train_loss= 1.38569 train_acc= 0.26953 val_loss= 1.37792 val_acc= 0.26786 time= 0.01563
Epoch: 0005 train_loss= 1.38859 train_acc= 0.26172 val_loss= 1.37529 val_acc= 0.26786 time= 0.01563
Epoch: 0006 train_loss= 1.38566 train_acc= 0.27344 val_loss= 1.37330 val_acc= 0.26786 time= 0.01563
Epoch: 0007 train_loss= 1.38976 train_acc= 0.27148 val_loss= 1.37310 val_acc= 0.26786 time= 0.01563
Epoch: 0008 train_loss= 1.38072 train_acc= 0.28516 val_loss= 1.37283 val_acc= 0.25000 time= 0.01563
Epoch: 0009 train_loss= 1.37968 train_acc= 0.27734 val_loss= 1.37288 val_acc= 0.25000 time= 0.01563
Epoch: 0010 train_loss= 1.38502 train_acc= 0.28320 val_loss= 1.37333 val_acc= 0.23214 time= 0.01563
Epoch: 0011 train_loss= 1.38875 train_acc= 0.28125 val_loss= 1.37425 val_acc= 0.25000 time= 0.01563
Epoch: 0012 train_loss= 1.38203 train_acc= 0.29102 val_loss= 1.37543 val_acc= 0.30357 time= 0.01563
Epoch: 0013 train_loss= 1.38140 train_acc= 0.26953 val_loss= 1.37688 val_acc= 0.28571 time= 0.01562
Early stopping...
Optimization Finished!
Test set results: cost= 1.38877 accuracy= 0.23894 time= 0.01563 
