fix to issue #23 (CUDA out of memory at 1000th epoch) as suggested by…

[wilsonjwcsu]

Fix to issue #23 (CUDA out of memory at 1000th epoch) as suggested by @07hyx06. Surrounded print output with torch.no_grad().

Tested by running on an internal large dataset. Before the fix, it stopped at 1000th epoch, complaining that it was out of memory. After fix, it's still running at 128,000 epochs. Memory initially 22157MB on GPU, and has not increased during training.