Epoch: 0001 train_loss= 3.81167 train_acc= 0.48182 val_loss= 0.70874 val_acc= 0.52459 time= 0.66704
Epoch: 0002 train_loss= 0.95653 train_acc= 0.51636 val_loss= 0.70207 val_acc= 0.59016 time= 0.01563
Epoch: 0003 train_loss= 0.71806 train_acc= 0.48727 val_loss= 0.69723 val_acc= 0.54098 time= 0.01563
Epoch: 0004 train_loss= 1.88749 train_acc= 0.50364 val_loss= 0.69632 val_acc= 0.52459 time= 0.03125
Epoch: 0005 train_loss= 0.93413 train_acc= 0.52909 val_loss= 0.69697 val_acc= 0.44262 time= 0.01563
Epoch: 0006 train_loss= 1.14787 train_acc= 0.50000 val_loss= 0.69844 val_acc= 0.42623 time= 0.03125
Epoch: 0007 train_loss= 0.70908 train_acc= 0.51818 val_loss= 0.70005 val_acc= 0.45902 time= 0.01563
Epoch: 0008 train_loss= 0.70197 train_acc= 0.52000 val_loss= 0.70146 val_acc= 0.45902 time= 0.03125
Epoch: 0009 train_loss= 0.70082 train_acc= 0.53273 val_loss= 0.70255 val_acc= 0.42623 time= 0.01563
Epoch: 0010 train_loss= 0.69879 train_acc= 0.53091 val_loss= 0.70312 val_acc= 0.42623 time= 0.01562
Epoch: 0011 train_loss= 0.70128 train_acc= 0.54182 val_loss= 0.70342 val_acc= 0.42623 time= 0.03125
Epoch: 0012 train_loss= 0.70163 train_acc= 0.51091 val_loss= 0.70422 val_acc= 0.42623 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69584 accuracy= 0.55738 time= 0.01562 
