Update README.md

README.md

@@ -142,9 +142,10 @@ missing values. I also use techniques like forward and backward filling to handl
 
 # Limitations
 
-This section should summarize the main
-limitations of your model. Limitations could be based on benchmark task
-performance, any observations you noticed when examining model
-responses, or any shortcomings your model has relative to your ideal use
-case.
+The main limitation of this model is that it does not perform well on benchmarks outside of the chosen task, indicating that the model suffered 
+catastrophic forgetting during the training process. The benchmark task performance of the trained model on HumanEval, Squadv2, and E2E NLG Challenge were all lower than the baseline model. 
+This means that using the model for anything outside of the interview preparation use-case is unlikely to work well. Additionally, some of the model responses were not as expected,
+as they included multiple questions and answers instead of the one that I asked for. While this technically works as long as the questions/answers are coherent and relevant,
+it is still a limitation because I did not want the model to generate more than one question/answer. Generating multiple has a higher risk of inaccurate generated outputs.
+