Minor correction: Number of validation sets

The number of validation sets shown in the output is 141, but 140 in the text.

Lesson2.md

@@ -270,7 +270,7 @@ data.show_batch(rows=3, figsize=(7,8))
 
 ![](lesson2/bears.png)
 
-You can kind of double check here. Remember, `data.c` is the attribute which the classifiers tell us how many possible labels there are. We'll learn about some other more specific meanings of `c` later. We can see how many things are now training set, how many things are in validation set. So we've got 473 training set, 141 validation set.  
+You can kind of double check here. Remember, `data.c` is the attribute which the classifiers tell us how many possible labels there are. We'll learn about some other more specific meanings of `c` later. We can see how many things are now training set, how many things are in validation set. So we've got 473 training set, 140 validation set.  
 
 ```python
 data.classes, data.c, len(data.train_ds), len(data.valid_ds)
@@ -1305,4 +1305,4 @@ What happens with the validation set is that we do our mini-batch SGD training l
 
 Even for people that don't go through this course and don't learn about the details of deep learning, if you've got managers or colleagues at work who are wanting to learn about AI, the only thing that you really need to be teaching them is about the idea of a validation set. Because that's the thing they can then use to figure out if somebody's telling them snake oil or not. They hold back some data and they get told "oh, here's a model that we're going to roll out" and then you say "okay, fine. I'm just going to check it on this held out data to see whether it generalizes." There's a lot of details to get right when you design your validation set. We will talk about them briefly next week, but a more full version would be in Rachel's piece on the fast.ai blog called [How (and why) to create a good validation set](https://www.fast.ai/2017/11/13/validation-sets/). And this is also one of the things we go into in a lot of detail in the intro to machine learning course. So we're going to try and give you enough to get by for this course, but it is certainly something that's worth deeper study as well.
 
-Thanks everybody! I hope you have a great time building your web applications. See you next week.
+Thanks everybody! I hope you have a great time building your web applications. See you next week.