Epoch: 0001 train_loss= 0.69626 train_acc= 0.52987 val_loss= 0.69730 val_acc= 0.49180 time= 0.85073
Epoch: 0002 train_loss= 0.69474 train_acc= 0.52078 val_loss= 0.69652 val_acc= 0.50820 time= 0.00000
Epoch: 0003 train_loss= 0.69362 train_acc= 0.52208 val_loss= 0.69602 val_acc= 0.50820 time= 0.00000
Epoch: 0004 train_loss= 0.69252 train_acc= 0.52468 val_loss= 0.69588 val_acc= 0.52459 time= 0.01563
Epoch: 0005 train_loss= 0.69389 train_acc= 0.50779 val_loss= 0.69601 val_acc= 0.57377 time= 0.00000
Epoch: 0006 train_loss= 0.69314 train_acc= 0.51299 val_loss= 0.69616 val_acc= 0.49180 time= 0.01563
Epoch: 0007 train_loss= 0.69119 train_acc= 0.52597 val_loss= 0.69652 val_acc= 0.49180 time= 0.00000
Epoch: 0008 train_loss= 0.69373 train_acc= 0.48442 val_loss= 0.69689 val_acc= 0.50820 time= 0.00000
Epoch: 0009 train_loss= 0.69241 train_acc= 0.51169 val_loss= 0.69746 val_acc= 0.57377 time= 0.01563
Epoch: 0010 train_loss= 0.69264 train_acc= 0.50130 val_loss= 0.69817 val_acc= 0.50820 time= 0.00000
Epoch: 0011 train_loss= 0.69277 train_acc= 0.50909 val_loss= 0.69897 val_acc= 0.50820 time= 0.00000
Epoch: 0012 train_loss= 0.69158 train_acc= 0.52857 val_loss= 0.69972 val_acc= 0.49180 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69274 accuracy= 0.54918 time= 0.00000 
