Epoch: 0001 train_loss= 1.41309 train_acc= 0.22266 val_loss= 1.37032 val_acc= 0.35714 time= 0.44938
Epoch: 0002 train_loss= 1.40542 train_acc= 0.24609 val_loss= 1.37296 val_acc= 0.41071 time= 0.01700
Epoch: 0003 train_loss= 1.40056 train_acc= 0.23047 val_loss= 1.37694 val_acc= 0.39286 time= 0.01700
Epoch: 0004 train_loss= 1.38855 train_acc= 0.27539 val_loss= 1.37964 val_acc= 0.37500 time= 0.01800
Epoch: 0005 train_loss= 1.38717 train_acc= 0.28906 val_loss= 1.38287 val_acc= 0.37500 time= 0.01700
Epoch: 0006 train_loss= 1.40391 train_acc= 0.25977 val_loss= 1.38546 val_acc= 0.37500 time= 0.01700
Epoch: 0007 train_loss= 1.38168 train_acc= 0.29492 val_loss= 1.38823 val_acc= 0.37500 time= 0.01600
Epoch: 0008 train_loss= 1.38879 train_acc= 0.31250 val_loss= 1.39172 val_acc= 0.37500 time= 0.01701
Epoch: 0009 train_loss= 1.38160 train_acc= 0.29492 val_loss= 1.39489 val_acc= 0.37500 time= 0.01500
Epoch: 0010 train_loss= 1.38141 train_acc= 0.30469 val_loss= 1.39725 val_acc= 0.37500 time= 0.01900
Epoch: 0011 train_loss= 1.38489 train_acc= 0.29492 val_loss= 1.39922 val_acc= 0.37500 time= 0.01600
Epoch: 0012 train_loss= 1.37998 train_acc= 0.28906 val_loss= 1.40055 val_acc= 0.37500 time= 0.01600
Early stopping...
Optimization Finished!
Test set results: cost= 1.38675 accuracy= 0.29204 time= 0.00700 
