Epoch: 0001 train_loss= 2.08160 train_acc= 0.14825 val_loss= 2.07882 val_acc= 0.06897 time= 0.69516
Epoch: 0002 train_loss= 2.07896 train_acc= 0.18329 val_loss= 2.07797 val_acc= 0.06897 time= 0.00900
Epoch: 0003 train_loss= 2.07575 train_acc= 0.18598 val_loss= 2.07681 val_acc= 0.06897 time= 0.00900
Epoch: 0004 train_loss= 2.07446 train_acc= 0.18598 val_loss= 2.07570 val_acc= 0.06897 time= 0.00700
Epoch: 0005 train_loss= 2.07221 train_acc= 0.18598 val_loss= 2.07466 val_acc= 0.06897 time= 0.00800
Epoch: 0006 train_loss= 2.06971 train_acc= 0.18598 val_loss= 2.07376 val_acc= 0.06897 time= 0.00800
Epoch: 0007 train_loss= 2.06654 train_acc= 0.18598 val_loss= 2.07327 val_acc= 0.06897 time= 0.01000
Epoch: 0008 train_loss= 2.06527 train_acc= 0.18598 val_loss= 2.07336 val_acc= 0.06897 time= 0.00800
Epoch: 0009 train_loss= 2.06273 train_acc= 0.18598 val_loss= 2.07403 val_acc= 0.06897 time= 0.01100
Epoch: 0010 train_loss= 2.06184 train_acc= 0.18598 val_loss= 2.07538 val_acc= 0.06897 time= 0.01000
Epoch: 0011 train_loss= 2.06016 train_acc= 0.18598 val_loss= 2.07752 val_acc= 0.06897 time= 0.00800
Epoch: 0012 train_loss= 2.05673 train_acc= 0.18598 val_loss= 2.08029 val_acc= 0.06897 time= 0.00700
Early stopping...
Optimization Finished!
Test set results: cost= 2.06639 accuracy= 0.16949 time= 0.00400 
