Update README.md

README.md

@@ -78,15 +78,15 @@ The Correct answer:-Option 1
 
 ##Preprocessing
 
-The text are tokenized using the GPT2 tokenizer.To feed the inputs of multiple choice we concatenated context and question with all the 4 possible choices.We used the first sentence as context+question and the second sentence as choices to feed 2 inputs to our tokenizer.
+The text are tokenized using the GPT2 tokenizer.To feed the inputs of multiple choice we concatenated context and question as first input and   all the 4 possible choices as the second input to our tokenizer.
 
 ## Evaluation
 
-The following tables summarize the scores obtained by the **GPT2-CosmosQA**.
+The following tables summarize the scores obtained by the **GPT2-CosmosQA**.The ones  marked as (*) are the baseline models.
 
 |      Model      |  Dev Acc | Test Acc  | 
 |:---------------:|:-----:|:-----:|
-|  GPT-FT        |  54.0 | 54.4. |
+|  GPT-FT   *    |  54.0 | 54.4. |
 | GPT2-CosmosQA  | 60.3 | 59.7 |