Update README.md

README.md

@@ -8,7 +8,8 @@
 
 ##Dataset
 
-[Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning](https://huggingface.co/datasets/cosmos_qa).This dataset contains a set of 35,600 problems that require commonsense-based reading comprehension, formulated as multiple-choice questions.Understanding narratives requires reading between the lines, which in turn, requires interpreting the likely causes and effects of events, even when they are not mentioned explicitly.
+[Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning](https://huggingface.co/datasets/cosmos_qa).This dataset contains a set of 35,600 problems that require commonsense-based reading comprehension, formulated as multiple-choice questions.Understanding narratives requires reading between the lines, which in turn, requires interpreting the likely causes and effects of events, even when they are not mentioned explicitly.The questions focus on factual and literal understanding of the context paragraph, our dataset focuses on reading between the lines over a diverse collection of people's everyday narratives.
+
 
 ###Example
 
@@ -78,7 +79,7 @@ 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 as first input and   all the 4 possible choices as the second input to our tokenizer.
+The texts 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
 
@@ -86,9 +87,14 @@ The following tables summarize the scores obtained by the **GPT2-CosmosQA**.The
 
 |      Model      |  Dev Acc | Test Acc  | 
 |:---------------:|:-----:|:-----:|
+| BERT-FT Multiway| 68.3.| 68.4  |
 |  GPT-FT   *    |  54.0 | 54.4. |
 | GPT2-CosmosQA  | 60.3 | 59.7 | 
 
+##Inference
+
+This project was mainly dedicated to test the  common sense understanding of the  GPT2-model.We used a Dataset known as CosmosQ requires reasoning beyond the exact text spans in the context.The above results shows that even so GPT2 model is a model that was pre-trained to predict the next word it can remember long term dependencies 
+
 
 ## Credits
   Huge thanks to Huggingface 🤗 & Google Jax/Flax team for such a wonderful community week. Especially for providing such massive computing resource. Big thanks to [@patil-suraj](https://github.com/patil-suraj) & [@patrickvonplaten](https://github.com/patrickvonplaten) for mentoring during whole week.