Add more descriptive error message in eval_runner.py (#552)

- Fixed a small typo in the BFCL readme
- Added a more descriptive error message in eval_runner.py

berkeley-function-call-leaderboard/README.md

@@ -64,7 +64,7 @@ export YI_API_KEY=XXXXXX
 
 If decided to run OSS model, the generation script uses vllm and therefore requires GPU for hosting and inferencing. If you have questions or concerns about evaluating OSS models, please reach out to us in our [discord channel](https://discord.gg/grXXvj9Whz).
 
-### Genrating LLM Responses
+### Generating LLM Responses
 
 Use the following command for LLM inference of the evaluation dataset with specific models
 

berkeley-function-call-leaderboard/eval_checker/eval_runner.py

@@ -172,7 +172,7 @@ def single_ast_file_runner(
 ):
     assert (
         len(model_result) == len(prompt) == len(possible_answer)
-    ), "The length of the model result does not match the length of the prompt or possible answer. Please check the input files for completeness."
+    ), f"The length of the model result ({len(model_result)}) does not match the length of the prompt ({len(prompt)}) or possible answer ({len(possible_answer)}). Please check the input files for completeness."
 
     result = []
     correct_count = 0