Epoch: 0001 train_loss= 0.71072 train_acc= 0.43636 val_loss= 0.70267 val_acc= 0.49180 time= 0.20197
Epoch: 0002 train_loss= 0.70636 train_acc= 0.43939 val_loss= 0.70080 val_acc= 0.49180 time= 0.01562
Epoch: 0003 train_loss= 0.70425 train_acc= 0.43030 val_loss= 0.69933 val_acc= 0.49180 time= 0.00000
Epoch: 0004 train_loss= 0.69957 train_acc= 0.43939 val_loss= 0.69820 val_acc= 0.49180 time= 0.01563
Epoch: 0005 train_loss= 0.69985 train_acc= 0.47273 val_loss= 0.69734 val_acc= 0.37705 time= 0.00000
Epoch: 0006 train_loss= 0.69823 train_acc= 0.46970 val_loss= 0.69670 val_acc= 0.50820 time= 0.00000
Epoch: 0007 train_loss= 0.69483 train_acc= 0.55152 val_loss= 0.69629 val_acc= 0.50820 time= 0.01563
Epoch: 0008 train_loss= 0.69252 train_acc= 0.53636 val_loss= 0.69610 val_acc= 0.50820 time= 0.00000
Epoch: 0009 train_loss= 0.69404 train_acc= 0.55152 val_loss= 0.69610 val_acc= 0.50820 time= 0.00000
Epoch: 0010 train_loss= 0.69299 train_acc= 0.54848 val_loss= 0.69627 val_acc= 0.50820 time= 0.01563
Epoch: 0011 train_loss= 0.68968 train_acc= 0.55152 val_loss= 0.69660 val_acc= 0.50820 time= 0.00000
Epoch: 0012 train_loss= 0.68928 train_acc= 0.55152 val_loss= 0.69708 val_acc= 0.50820 time= 0.01563
Epoch: 0013 train_loss= 0.69064 train_acc= 0.55152 val_loss= 0.69765 val_acc= 0.50820 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.70361 accuracy= 0.48361 time= 0.00000 
