Epoch: 0001 train_loss= 1.38939 train_acc= 0.27362 val_loss= 1.39304 val_acc= 0.26786 time= 0.29123
Epoch: 0002 train_loss= 1.38242 train_acc= 0.27362 val_loss= 1.39543 val_acc= 0.25000 time= 0.01107
Epoch: 0003 train_loss= 1.37963 train_acc= 0.28013 val_loss= 1.39855 val_acc= 0.23214 time= 0.01129
Epoch: 0004 train_loss= 1.37261 train_acc= 0.30945 val_loss= 1.40258 val_acc= 0.23214 time= 0.01094
Epoch: 0005 train_loss= 1.36921 train_acc= 0.33550 val_loss= 1.40742 val_acc= 0.23214 time= 0.01095
Epoch: 0006 train_loss= 1.37079 train_acc= 0.33876 val_loss= 1.41287 val_acc= 0.23214 time= 0.01121
Epoch: 0007 train_loss= 1.36403 train_acc= 0.33876 val_loss= 1.41883 val_acc= 0.23214 time= 0.01000
Epoch: 0008 train_loss= 1.36424 train_acc= 0.33550 val_loss= 1.42492 val_acc= 0.23214 time= 0.01119
Epoch: 0009 train_loss= 1.36228 train_acc= 0.33876 val_loss= 1.43050 val_acc= 0.23214 time= 0.00912
Epoch: 0010 train_loss= 1.36691 train_acc= 0.33876 val_loss= 1.43486 val_acc= 0.23214 time= 0.00918
Epoch: 0011 train_loss= 1.36246 train_acc= 0.33876 val_loss= 1.43776 val_acc= 0.23214 time= 0.01006
Epoch: 0012 train_loss= 1.36357 train_acc= 0.33876 val_loss= 1.43922 val_acc= 0.23214 time= 0.00891
Early stopping...
Optimization Finished!
Test set results: cost= 1.39483 accuracy= 0.30973 time= 0.00500 
