Closed hideodeo closed 1 year ago
Question 3 (related to Question 1): If this error happened with Codex, how often it happened? Says you have 100 test instances, roughly how many instances do you get this error?
Hey @hideodeo, in general, codex was better at follow few-shot prompts than chatgpt, and threw these exceptions less frequently. Our implementation ignores these exceptions, but perhaps one could do better.
Hello! I'm running
python -u src/gsm/run.py
with "gpt-3.5-turbo" and has the following error. This is happening because "def solution():" not in entire_output in feedback.py.