| tag: | |
| - llama | |
| task: arc_challenge_chat | |
| dataset_path: allenai/ai2_arc | |
| dataset_name: ARC-Challenge | |
| output_type: generate_until | |
| training_split: train | |
| validation_split: validation | |
| test_split: test | |
| fewshot_split: train | |
| doc_to_text: 'Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices.text[0]}}\nB. {{choices.text[1]}}\nC. {{choices.text[2]}}{% if choices.text|length > 3 %}\nD. {{choices.text[3]}}{% endif %}\nYour response should end with "The best answer is [the_answer_letter]" where the [the_answer_letter] is one of A, B, C or D.' | |
| gen_prefix: 'The best answer is' | |
| fewshot_delimiter: "\n\n" | |
| doc_to_target: "{{ 'ABCD'[answerKey|int - 1] if answerKey|string in '1234' else answerKey }}" | |
| num_fewshot: 0 | |
| generation_kwargs: | |
| max_gen_toks: 100 | |
| until: | |
| - "\n\n" | |
| - "." | |
| metric_list: | |
| - metric: exact_match | |
| aggregation: mean | |
| higher_is_better: true | |
| ignore_case: true | |
| ignore_punctuation: true | |
| filter_list: | |
| - name: remove_whitespace | |
| filter: | |
| - function: remove_whitespace | |
| - function: take_first | |
| metadata: | |
| version: 1.0 | |