update description to be more user friendly

app.py

@@ -23,6 +23,8 @@ f1.compute()
 
 where the `average` parameter can be chosen to configure the way f1 scores across labels are averaged. Acceptable values include `[None, 'micro', 'macro', 'weighted']` (
 or `binary` if there exist only two labels). \n
+
+Play around with the interface below to see how the F1 score changes based on predictions, references, and method of averaging!
 """
 
 metric = FixedF1()