Typo fix and reformatting (pytorch#266)

Author: davidefiocco

beginner_source/nlp/pytorch_tutorial.py

@@ -272,8 +272,8 @@
 # In essence, we have broken the Tensor away from its past history
 
 ###############################################################
-# You can also stops autograd from tracking history on Tensors
-# with requires_grad=True by wrapping the code block in
+# You can also stop autograd from tracking history on Tensors
+# with ``.requires_grad``=True by wrapping the code block in
 # ``with torch.no_grad():``
 print(x.requires_grad)
 print((x ** 2).requires_grad)