Epoch: 0001 train_loss= 1.57233 train_acc= 0.47636 val_loss= 0.66230 val_acc= 0.57377 time= 0.60942
Epoch: 0002 train_loss= 1.14498 train_acc= 0.54545 val_loss= 0.65586 val_acc= 0.57377 time= 0.01563
Epoch: 0003 train_loss= 0.93379 train_acc= 0.51273 val_loss= 0.67130 val_acc= 0.59016 time= 0.03125
Epoch: 0004 train_loss= 0.84705 train_acc= 0.51818 val_loss= 0.67607 val_acc= 0.54098 time= 0.01563
Epoch: 0005 train_loss= 0.84375 train_acc= 0.50182 val_loss= 0.66535 val_acc= 0.55738 time= 0.01562
Epoch: 0006 train_loss= 1.08681 train_acc= 0.54364 val_loss= 0.66671 val_acc= 0.54098 time= 0.03125
Epoch: 0007 train_loss= 0.74510 train_acc= 0.52000 val_loss= 0.66996 val_acc= 0.54098 time= 0.01563
Epoch: 0008 train_loss= 1.03691 train_acc= 0.52182 val_loss= 0.68061 val_acc= 0.54098 time= 0.03125
Epoch: 0009 train_loss= 0.97753 train_acc= 0.54364 val_loss= 0.70665 val_acc= 0.49180 time= 0.01563
Epoch: 0010 train_loss= 0.77088 train_acc= 0.50364 val_loss= 0.72601 val_acc= 0.49180 time= 0.01562
Epoch: 0011 train_loss= 0.97590 train_acc= 0.52000 val_loss= 0.72263 val_acc= 0.45902 time= 0.03125
Epoch: 0012 train_loss= 0.97371 train_acc= 0.47636 val_loss= 0.70515 val_acc= 0.47541 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.71214 accuracy= 0.49180 time= 0.01562 
