Epoch: 0001 train_loss= 0.71067 train_acc= 0.47818 val_loss= 0.69372 val_acc= 0.53226 time= 0.59513
Epoch: 0002 train_loss= 0.70506 train_acc= 0.48727 val_loss= 0.69467 val_acc= 0.53226 time= 0.00700
Epoch: 0003 train_loss= 0.70178 train_acc= 0.46727 val_loss= 0.69646 val_acc= 0.54839 time= 0.00600
Epoch: 0004 train_loss= 0.69777 train_acc= 0.51818 val_loss= 0.69902 val_acc= 0.46774 time= 0.00500
Epoch: 0005 train_loss= 0.69575 train_acc= 0.52727 val_loss= 0.70206 val_acc= 0.46774 time= 0.00600
Epoch: 0006 train_loss= 0.69729 train_acc= 0.51273 val_loss= 0.70536 val_acc= 0.46774 time= 0.00600
Epoch: 0007 train_loss= 0.69361 train_acc= 0.53091 val_loss= 0.70852 val_acc= 0.46774 time= 0.00600
Epoch: 0008 train_loss= 0.69493 train_acc= 0.51818 val_loss= 0.71099 val_acc= 0.46774 time= 0.00600
Epoch: 0009 train_loss= 0.69543 train_acc= 0.52364 val_loss= 0.71252 val_acc= 0.46774 time= 0.00600
Epoch: 0010 train_loss= 0.69586 train_acc= 0.52364 val_loss= 0.71286 val_acc= 0.46774 time= 0.00600
Epoch: 0011 train_loss= 0.69347 train_acc= 0.52727 val_loss= 0.71239 val_acc= 0.46774 time= 0.00500
Epoch: 0012 train_loss= 0.69638 train_acc= 0.52182 val_loss= 0.71108 val_acc= 0.46774 time= 0.00700
Early stopping...
Optimization Finished!
Test set results: cost= 0.68290 accuracy= 0.55645 time= 0.00200 
