Epoch: 0001 train_loss= 1.02756 train_acc= 0.47922 val_loss= 0.75777 val_acc= 0.57377 time= 0.95319
Epoch: 0002 train_loss= 1.22831 train_acc= 0.48442 val_loss= 0.68883 val_acc= 0.60656 time= 0.01562
Epoch: 0003 train_loss= 1.08639 train_acc= 0.48701 val_loss= 0.67525 val_acc= 0.59016 time= 0.03125
Epoch: 0004 train_loss= 1.82823 train_acc= 0.52727 val_loss= 0.67844 val_acc= 0.62295 time= 0.01563
Epoch: 0005 train_loss= 0.98542 train_acc= 0.47013 val_loss= 0.67686 val_acc= 0.55738 time= 0.03125
Epoch: 0006 train_loss= 1.10552 train_acc= 0.50390 val_loss= 0.67801 val_acc= 0.59016 time= 0.03125
Epoch: 0007 train_loss= 0.77382 train_acc= 0.47532 val_loss= 0.67810 val_acc= 0.57377 time= 0.03125
Epoch: 0008 train_loss= 0.88009 train_acc= 0.50000 val_loss= 0.67950 val_acc= 0.57377 time= 0.01563
Epoch: 0009 train_loss= 1.16999 train_acc= 0.54545 val_loss= 0.68299 val_acc= 0.55738 time= 0.03125
Epoch: 0010 train_loss= 2.04830 train_acc= 0.53117 val_loss= 0.68754 val_acc= 0.57377 time= 0.03125
Epoch: 0011 train_loss= 0.76853 train_acc= 0.51299 val_loss= 0.69140 val_acc= 0.57377 time= 0.01563
Epoch: 0012 train_loss= 0.94763 train_acc= 0.51429 val_loss= 0.69577 val_acc= 0.57377 time= 0.03125
Early stopping...
Optimization Finished!
Test set results: cost= 0.68960 accuracy= 0.57377 time= 0.00000 
