From 6e667b17cc56418bde3932f9983c5be999972cd9 Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Sun, 21 Dec 2025 04:28:33 +0000 Subject: [PATCH] fix: address dataset generation review feedback Co-authored-by: acon96 <35843486+acon96@users.noreply.github.com> --- data/generate_data.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/data/generate_data.py b/data/generate_data.py index 919ec5f..f7f6810 100644 --- a/data/generate_data.py +++ b/data/generate_data.py @@ -650,7 +650,6 @@ def generate_refusal_example(refusal_case: dict, persona: str, language: str, ma "available_tools": available_tools, "question": question, "answers": [response_text], - "answer_starting": "", "tool_calls": [] } @@ -853,7 +852,10 @@ def generate_sft_file( missing_responses.add(str(ex)) for refusal_case in tqdm(piles.pile_of_refusals): - run_factor_times(generate_refusal_example, generated_examples, refusal_case, person, refusal_factor, language) + try: + run_factor_times(generate_refusal_example, generated_examples, refusal_case, person, refusal_factor, language) + except NoResponseAvailableException as ex: + missing_responses.add(str(ex)) for status_request in tqdm(piles.pile_of_status_requests): run_factor_times(generate_status_request, generated_examples, status_request, "assistant", status_request_factor, language)