Epoch: 0001 train_loss= 1.41601 train_acc= 0.51948 val_loss= 0.75295 val_acc= 0.63934 time= 0.29690
Epoch: 0002 train_loss= 2.02414 train_acc= 0.52338 val_loss= 0.75578 val_acc= 0.42623 time= 0.01563
Epoch: 0003 train_loss= 1.06507 train_acc= 0.50779 val_loss= 0.90625 val_acc= 0.37705 time= 0.01563
Epoch: 0004 train_loss= 1.70530 train_acc= 0.49610 val_loss= 0.92974 val_acc= 0.37705 time= 0.01563
Epoch: 0005 train_loss= 1.55022 train_acc= 0.47922 val_loss= 0.89443 val_acc= 0.37705 time= 0.00000
Epoch: 0006 train_loss= 3.00467 train_acc= 0.46753 val_loss= 0.82962 val_acc= 0.39344 time= 0.01563
Epoch: 0007 train_loss= 1.96626 train_acc= 0.50649 val_loss= 0.77424 val_acc= 0.42623 time= 0.01563
Epoch: 0008 train_loss= 1.09618 train_acc= 0.51039 val_loss= 0.74955 val_acc= 0.42623 time= 0.01562
Epoch: 0009 train_loss= 0.80876 train_acc= 0.52208 val_loss= 0.73891 val_acc= 0.52459 time= 0.01563
Epoch: 0010 train_loss= 1.55575 train_acc= 0.51948 val_loss= 0.73767 val_acc= 0.52459 time= 0.01563
Epoch: 0011 train_loss= 0.82190 train_acc= 0.53896 val_loss= 0.73562 val_acc= 0.50820 time= 0.01563
Epoch: 0012 train_loss= 0.94352 train_acc= 0.48442 val_loss= 0.73341 val_acc= 0.50820 time= 0.01563
Epoch: 0013 train_loss= 0.84301 train_acc= 0.51039 val_loss= 0.72957 val_acc= 0.50820 time= 0.01563
Epoch: 0014 train_loss= 0.80447 train_acc= 0.51948 val_loss= 0.72747 val_acc= 0.50820 time= 0.01563
Epoch: 0015 train_loss= 0.89985 train_acc= 0.49481 val_loss= 0.72770 val_acc= 0.50820 time= 0.00000
Epoch: 0016 train_loss= 1.30366 train_acc= 0.52727 val_loss= 0.73390 val_acc= 0.50820 time= 0.01563
Epoch: 0017 train_loss= 0.97880 train_acc= 0.50390 val_loss= 0.74419 val_acc= 0.42623 time= 0.01562
Early stopping...
Optimization Finished!
Test set results: cost= 0.70182 accuracy= 0.54098 time= 0.01563 
