Update README.md

README.md

@@ -36,4 +36,5 @@ inference:
 ## training 
 
 - for inputs, the model was presented with the post title and the post selftext encoded as: `question: <post title> context: <post selftext>`. You may see better results if queries are posed in this fashion.
-- The top two replies were aggregated and presented to the model as the output text.
+- The top two replies were aggregated and presented to the model as the output text.
+- Training for longer will be explored, but given that the dataset has 127k examples and the loss flatlines at 0.5 epochs this should be fairly viable.