Fix the loss initialization in intermediate_source/char_rnn_generation_tutorial.py (#2380)

* changed the loss init to make it less confusing
---------

Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>
Co-authored-by: Svetlana Karslioglu <svekars@fb.com>

Author: 3 people

intermediate_source/char_rnn_generation_tutorial.py

@@ -278,7 +278,7 @@ def train(category_tensor, input_line_tensor, target_line_tensor):
 
     rnn.zero_grad()
 
-    loss = 0
+    loss = torch.Tensor([0]) # you can also just simply use ``loss = 0``
 
     for i in range(input_line_tensor.size(0)):
         output, hidden = rnn(category_tensor, input_line_tensor[i], hidden)