Epoch: 0001 train_loss= 2.43232 train_acc= 0.47922 val_loss= 1.41851 val_acc= 0.45161 time= 0.77670
Epoch: 0002 train_loss= 1.47754 train_acc= 0.49610 val_loss= 1.40459 val_acc= 0.45161 time= 0.01100
Epoch: 0003 train_loss= 2.94260 train_acc= 0.52078 val_loss= 1.12370 val_acc= 0.46774 time= 0.01200
Epoch: 0004 train_loss= 1.48108 train_acc= 0.48961 val_loss= 1.01692 val_acc= 0.46774 time= 0.01300
Epoch: 0005 train_loss= 2.21703 train_acc= 0.52338 val_loss= 0.88670 val_acc= 0.46774 time= 0.00247
Epoch: 0006 train_loss= 1.86077 train_acc= 0.51948 val_loss= 0.84940 val_acc= 0.40323 time= 0.02284
Epoch: 0007 train_loss= 1.88390 train_acc= 0.52468 val_loss= 0.96943 val_acc= 0.35484 time= 0.00139
Epoch: 0008 train_loss= 1.50661 train_acc= 0.47143 val_loss= 1.05960 val_acc= 0.41935 time= 0.01563
Epoch: 0009 train_loss= 2.00702 train_acc= 0.47922 val_loss= 1.06065 val_acc= 0.46774 time= 0.00000
Epoch: 0010 train_loss= 1.12741 train_acc= 0.48961 val_loss= 1.03121 val_acc= 0.48387 time= 0.02720
Epoch: 0011 train_loss= 1.67567 train_acc= 0.49351 val_loss= 1.04169 val_acc= 0.48387 time= 0.00569
Epoch: 0012 train_loss= 1.96606 train_acc= 0.52338 val_loss= 1.08519 val_acc= 0.46774 time= 0.01520
Early stopping...
Optimization Finished!
Test set results: cost= 1.02575 accuracy= 0.41935 time= 0.00500 
