Epoch: 0001 train_loss= 0.70036 train_acc= 0.46364 val_loss= 0.69852 val_acc= 0.55738 time= 0.09362
Epoch: 0002 train_loss= 0.69896 train_acc= 0.46970 val_loss= 0.69964 val_acc= 0.44262 time= 0.01563
Epoch: 0003 train_loss= 0.69799 train_acc= 0.53636 val_loss= 0.70072 val_acc= 0.44262 time= 0.01563
Epoch: 0004 train_loss= 0.69735 train_acc= 0.53636 val_loss= 0.70186 val_acc= 0.44262 time= 0.01563
Epoch: 0005 train_loss= 0.69684 train_acc= 0.53636 val_loss= 0.70310 val_acc= 0.44262 time= 0.00000
Epoch: 0006 train_loss= 0.69626 train_acc= 0.53636 val_loss= 0.70439 val_acc= 0.44262 time= 0.01563
Epoch: 0007 train_loss= 0.69568 train_acc= 0.53636 val_loss= 0.70571 val_acc= 0.44262 time= 0.01563
Epoch: 0008 train_loss= 0.69553 train_acc= 0.53636 val_loss= 0.70693 val_acc= 0.44262 time= 0.01563
Epoch: 0009 train_loss= 0.69470 train_acc= 0.53636 val_loss= 0.70806 val_acc= 0.44262 time= 0.00000
Epoch: 0010 train_loss= 0.69499 train_acc= 0.53636 val_loss= 0.70880 val_acc= 0.44262 time= 0.01563
Epoch: 0011 train_loss= 0.69491 train_acc= 0.53636 val_loss= 0.70905 val_acc= 0.44262 time= 0.01563
Epoch: 0012 train_loss= 0.69453 train_acc= 0.53636 val_loss= 0.70886 val_acc= 0.44262 time= 0.01562
Early stopping...
Optimization Finished!
Test set results: cost= 0.69574 accuracy= 0.52459 time= 0.00000 
