fixed small but potentially confusing typo "the a" --> "the"

jpgard · jpgard · commit c325b2a0cbdf · 2019-06-07T16:43:59.000-07:00
diff --git a/beginner_source/examples_autograd/two_layer_net_autograd.py b/beginner_source/examples_autograd/two_layer_net_autograd.py
@@ -46,7 +46,7 @@
 
     # Compute and print loss using operations on Tensors.
     # Now loss is a Tensor of shape (1,)
-    # loss.item() gets the a scalar value held in the loss.
+    # loss.item() gets the scalar value held in the loss.
     loss = (y_pred - y).pow(2).sum()
     print(t, loss.item())
 
