Name: unlearning-cleanslate/generations-06-llama-3_1-8b-simnpo-gentle-bm25-10b-target-100-checkpoint-398
Creator: unlearning-cleanslate
Published: 2026-04-29 22:33:51
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/unlearning-cleanslate/generations-06-llama-3_1-8b-simnpo-gentle-bm25-10b-target-100-checkpoint-398

下载链接

链接失效反馈

官方服务：

资源简介：

--- dataset_info: - config_name: arc_challenge features: - name: doc_id dtype: int64 - name: doc struct: - name: answerKey dtype: string - name: choices struct: - name: label list: string - name: text list: string - name: id dtype: string - name: question dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_4 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 1903182 num_examples: 1172 download_size: 1728940 dataset_size: 1903182 - config_name: bbh_cot_fewshot_boolean_expressions features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 704199 num_examples: 250 download_size: 693528 dataset_size: 704199 - config_name: bbh_cot_fewshot_causal_judgement features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 1215486 num_examples: 187 download_size: 1207434 dataset_size: 1215486 - config_name: bbh_cot_fewshot_date_understanding features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 525833 num_examples: 250 download_size: 513623 dataset_size: 525833 - config_name: bbh_cot_fewshot_disambiguation_qa features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 1345017 num_examples: 250 download_size: 1346219 dataset_size: 1345017 - config_name: bbh_cot_fewshot_dyck_languages features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 1026906 num_examples: 250 download_size: 1024184 dataset_size: 1026906 - config_name: bbh_cot_fewshot_formal_fallacies features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 1781902 num_examples: 250 download_size: 1766490 dataset_size: 1781902 - config_name: bbh_cot_fewshot_geometric_shapes features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 1726067 num_examples: 250 download_size: 1711742 dataset_size: 1726067 - config_name: bbh_cot_fewshot_hyperbaton features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 1177405 num_examples: 250 download_size: 1175025 dataset_size: 1177405 - config_name: bbh_cot_fewshot_logical_deduction_five_objects features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 1153015 num_examples: 250 download_size: 1149980 dataset_size: 1153015 - config_name: bbh_cot_fewshot_logical_deduction_seven_objects features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 1290711 num_examples: 250 download_size: 1290914 dataset_size: 1290711 - config_name: bbh_cot_fewshot_logical_deduction_three_objects features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 1019799 num_examples: 250 download_size: 1015621 dataset_size: 1019799 - config_name: bbh_cot_fewshot_movie_recommendation features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 819498 num_examples: 250 download_size: 811125 dataset_size: 819498 - config_name: bbh_cot_fewshot_multistep_arithmetic_two features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 891996 num_examples: 250 download_size: 897714 dataset_size: 891996 - config_name: bbh_cot_fewshot_navigate features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 835542 num_examples: 250 download_size: 828329 dataset_size: 835542 - config_name: bbh_cot_fewshot_object_counting features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 565823 num_examples: 250 download_size: 554834 dataset_size: 565823 - config_name: bbh_cot_fewshot_penguins_in_a_table features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 587527 num_examples: 146 download_size: 595398 dataset_size: 587527 - config_name: bbh_cot_fewshot_reasoning_about_colored_objects features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 927618 num_examples: 250 download_size: 921986 dataset_size: 927618 - config_name: bbh_cot_fewshot_ruin_names features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 1227459 num_examples: 250 download_size: 1226376 dataset_size: 1227459 - config_name: bbh_cot_fewshot_salient_translation_error_detection features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 2372653 num_examples: 250 download_size: 2360123 dataset_size: 2372653 - config_name: bbh_cot_fewshot_snarks features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 799152 num_examples: 178 download_size: 804220 dataset_size: 799152 - config_name: bbh_cot_fewshot_sports_understanding features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 363049 num_examples: 250 download_size: 347774 dataset_size: 363049 - config_name: bbh_cot_fewshot_temporal_sequences features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 1203761 num_examples: 250 download_size: 1201917 dataset_size: 1203761 - config_name: bbh_cot_fewshot_tracking_shuffled_objects_five_objects features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 1248324 num_examples: 250 download_size: 1246569 dataset_size: 1248324 - config_name: bbh_cot_fewshot_tracking_shuffled_objects_seven_objects features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 1469646 num_examples: 250 download_size: 1471608 dataset_size: 1469646 - config_name: bbh_cot_fewshot_tracking_shuffled_objects_three_objects features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 1081455 num_examples: 250 download_size: 1077812 dataset_size: 1081455 - config_name: bbh_cot_fewshot_web_of_lies features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 1099612 num_examples: 250 download_size: 1096676 dataset_size: 1099612 - config_name: bbh_cot_fewshot_word_sorting features: - name: doc_id dtype: int64 - name: doc struct: - name: input dtype: string - name: target dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 1087331 num_examples: 250 download_size: 1094959 dataset_size: 1087331 - config_name: cleanslate_qa features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: string - name: content_id dtype: string - name: content_title dtype: string - name: question dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 8296268 num_examples: 12088 download_size: 7405463 dataset_size: 8296268 - config_name: coqa features: - name: doc_id dtype: int64 - name: doc struct: - name: additional_answers struct: - name: '0' struct: - name: input_text list: string - name: span_end list: int64 - name: span_start list: int64 - name: span_text list: string - name: turn_id list: int64 - name: '1' struct: - name: input_text list: string - name: span_end list: int64 - name: span_start list: int64 - name: span_text list: string - name: turn_id list: int64 - name: '2' struct: - name: input_text list: string - name: span_end list: int64 - name: span_start list: int64 - name: span_text list: string - name: turn_id list: int64 - name: answers struct: - name: input_text list: string - name: span_end list: int64 - name: span_start list: int64 - name: span_text list: string - name: turn_id list: int64 - name: id dtype: string - name: questions struct: - name: input_text list: string - name: turn_id list: int64 - name: source dtype: string - name: story dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: float64 - name: score dtype: float64 splits: - name: train num_bytes: 5578142 num_examples: 500 download_size: 5581287 dataset_size: 5578142 - config_name: drop features: - name: doc_id dtype: int64 - name: doc struct: - name: answer struct: - name: date struct: - name: day dtype: string - name: month dtype: string - name: year dtype: string - name: hit_id dtype: string - name: number dtype: string - name: spans list: string - name: worker_id dtype: string - name: answers list: list: string - name: id dtype: string - name: passage dtype: string - name: query_id dtype: string - name: question dtype: string - name: section_id dtype: string - name: validated_answers struct: - name: date list: - name: day dtype: string - name: month dtype: string - name: year dtype: string - name: hit_id list: string - name: number list: string - name: spans list: list: string - name: worker_id list: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 29315830 num_examples: 9536 download_size: 27571498 dataset_size: 29315830 - config_name: gsm8k features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: string - name: question dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 11677758 num_examples: 2638 download_size: 10743191 dataset_size: 11677758 - config_name: hellaswag features: - name: doc_id dtype: int64 - name: doc struct: - name: activity_label dtype: string - name: choices list: string - name: ctx dtype: string - name: ctx_a dtype: string - name: ctx_b dtype: string - name: endings list: string - name: gold dtype: int64 - name: ind dtype: int64 - name: label dtype: string - name: query dtype: string - name: source_id dtype: string - name: split dtype: string - name: split_type dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 39602023 num_examples: 10042 download_size: 38112853 dataset_size: 39602023 - config_name: humaneval_plus features: - name: doc_id dtype: int64 - name: doc struct: - name: canonical_solution dtype: string - name: entry_point dtype: string - name: prompt dtype: string - name: task_id dtype: string - name: test dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: max_gen_toks dtype: int64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: 'null' - name: score dtype: float64 splits: - name: train num_bytes: 22085134 num_examples: 164 download_size: 14079551 dataset_size: 22085134 - config_name: lambada_openai features: - name: doc_id dtype: int64 - name: doc struct: - name: text dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 5116687 num_examples: 5153 download_size: 4754769 dataset_size: 5116687 - config_name: mmlu_abstract_algebra features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 187506 num_examples: 100 download_size: 189225 dataset_size: 187506 - config_name: mmlu_anatomy features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 282181 num_examples: 135 download_size: 280352 dataset_size: 282181 - config_name: mmlu_astronomy features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 366563 num_examples: 152 download_size: 363695 dataset_size: 366563 - config_name: mmlu_business_ethics features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 256468 num_examples: 100 download_size: 259840 dataset_size: 256468 - config_name: mmlu_clinical_knowledge features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 557061 num_examples: 265 download_size: 535332 dataset_size: 557061 - config_name: mmlu_college_biology features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 374031 num_examples: 144 download_size: 370927 dataset_size: 374031 - config_name: mmlu_college_chemistry features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 214830 num_examples: 100 download_size: 219153 dataset_size: 214830 - config_name: mmlu_college_computer_science features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 307943 num_examples: 100 download_size: 316779 dataset_size: 307943 - config_name: mmlu_college_mathematics features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 215831 num_examples: 100 download_size: 217196 dataset_size: 215831 - config_name: mmlu_college_medicine features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 569122 num_examples: 173 download_size: 564584 dataset_size: 569122 - config_name: mmlu_college_physics features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 242921 num_examples: 102 download_size: 245947 dataset_size: 242921 - config_name: mmlu_computer_security features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 226884 num_examples: 100 download_size: 228436 dataset_size: 226884 - config_name: mmlu_conceptual_physics features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 419244 num_examples: 235 download_size: 400252 dataset_size: 419244 - config_name: mmlu_econometrics features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 333935 num_examples: 114 download_size: 335249 dataset_size: 333935 - config_name: mmlu_electrical_engineering features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 261709 num_examples: 145 download_size: 255759 dataset_size: 261709 - config_name: mmlu_elementary_mathematics features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 705210 num_examples: 378 download_size: 661863 dataset_size: 705210 - config_name: mmlu_formal_logic features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 360589 num_examples: 126 download_size: 361742 dataset_size: 360589 - config_name: mmlu_global_facts features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 180819 num_examples: 100 download_size: 182032 dataset_size: 180819 - config_name: mmlu_high_school_biology features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 834866 num_examples: 310 download_size: 806624 dataset_size: 834866 - config_name: mmlu_high_school_chemistry features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 481732 num_examples: 203 download_size: 468016 dataset_size: 481732 - config_name: mmlu_high_school_computer_science features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 319160 num_examples: 100 download_size: 325500 dataset_size: 319160 - config_name: mmlu_high_school_european_history features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 1511261 num_examples: 165 download_size: 1524903 dataset_size: 1511261 - config_name: mmlu_high_school_geography features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 395008 num_examples: 198 download_size: 381626 dataset_size: 395008 - config_name: mmlu_high_school_government_and_politics features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 524136 num_examples: 193 download_size: 513711 dataset_size: 524136 - config_name: mmlu_high_school_macroeconomics features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 962231 num_examples: 390 download_size: 922042 dataset_size: 962231 - config_name: mmlu_high_school_mathematics features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 528958 num_examples: 270 download_size: 507456 dataset_size: 528958 - config_name: mmlu_high_school_microeconomics features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 606585 num_examples: 238 download_size: 589035 dataset_size: 606585 - config_name: mmlu_high_school_physics features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 437086 num_examples: 151 download_size: 439699 dataset_size: 437086 - config_name: mmlu_high_school_psychology features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 1308632 num_examples: 545 download_size: 1241485 dataset_size: 1308632 - config_name: mmlu_high_school_statistics features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 756192 num_examples: 216 download_size: 743531 dataset_size: 756192 - config_name: mmlu_high_school_us_history features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 1675060 num_examples: 204 download_size: 1686211 dataset_size: 1675060 - config_name: mmlu_high_school_world_history features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 2118997 num_examples: 237 download_size: 2123905 dataset_size: 2118997 - config_name: mmlu_human_aging features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 427410 num_examples: 223 download_size: 410309 dataset_size: 427410 - config_name: mmlu_human_sexuality features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 278820 num_examples: 131 download_size: 275984 dataset_size: 278820 - config_name: mmlu_international_law features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 378145 num_examples: 121 download_size: 383793 dataset_size: 378145 - config_name: mmlu_jurisprudence features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 266352 num_examples: 108 download_size: 266237 dataset_size: 266352 - config_name: mmlu_logical_fallacies features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 399415 num_examples: 163 download_size: 394139 dataset_size: 399415 - config_name: mmlu_machine_learning features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 271078 num_examples: 112 download_size: 270924 dataset_size: 271078 - config_name: mmlu_management features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 190411 num_examples: 103 download_size: 191165 dataset_size: 190411 - config_name: mmlu_marketing features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 518931 num_examples: 234 download_size: 502284 dataset_size: 518931 - config_name: mmlu_medical_genetics features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 195102 num_examples: 100 download_size: 198632 dataset_size: 195102 - config_name: mmlu_miscellaneous features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 1437860 num_examples: 783 download_size: 1340214 dataset_size: 1437860 - config_name: mmlu_moral_disputes features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 848464 num_examples: 346 download_size: 813574 dataset_size: 848464 - config_name: mmlu_moral_scenarios features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 2679134 num_examples: 895 download_size: 2563374 dataset_size: 2679134 - config_name: mmlu_nutrition features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 727970 num_examples: 306 download_size: 702726 dataset_size: 727970 - config_name: mmlu_philosophy features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 673494 num_examples: 311 download_size: 646104 dataset_size: 673494 - config_name: mmlu_prehistory features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 732552 num_examples: 324 download_size: 702615 dataset_size: 732552 - config_name: mmlu_professional_accounting features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 888814 num_examples: 282 download_size: 865447 dataset_size: 888814 - config_name: mmlu_professional_law features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 10852232 num_examples: 1534 download_size: 10727548 dataset_size: 10852232 - config_name: mmlu_professional_medicine features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 1341745 num_examples: 272 download_size: 1337170 dataset_size: 1341745 - config_name: mmlu_professional_psychology features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 1706893 num_examples: 612 download_size: 1633293 dataset_size: 1706893 - config_name: mmlu_public_relations features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 243736 num_examples: 110 download_size: 244747 dataset_size: 243736 - config_name: mmlu_security_studies features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 1246715 num_examples: 245 download_size: 1235462 dataset_size: 1246715 - config_name: mmlu_sociology features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 506745 num_examples: 201 download_size: 494079 dataset_size: 506745 - config_name: mmlu_us_foreign_policy features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 233509 num_examples: 100 download_size: 235125 dataset_size: 233509 - config_name: mmlu_virology features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 337869 num_examples: 166 download_size: 331670 dataset_size: 337869 - config_name: mmlu_world_religions features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: int64 - name: choices list: string - name: question dtype: string - name: subject dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 280450 num_examples: 171 download_size: 270681 dataset_size: 280450 - config_name: triviaqa features: - name: doc_id dtype: int64 - name: doc struct: - name: answer struct: - name: aliases list: string - name: matched_wiki_entity_name dtype: string - name: normalized_aliases list: string - name: normalized_matched_wiki_entity_name dtype: string - name: normalized_value dtype: string - name: type dtype: string - name: value dtype: string - name: entity_pages struct: - name: doc_source list: 'null' - name: filename list: 'null' - name: title list: 'null' - name: wiki_context list: 'null' - name: question dtype: string - name: question_id dtype: string - name: question_source dtype: string - name: search_results struct: - name: description list: 'null' - name: filename list: 'null' - name: rank list: 'null' - name: search_context list: 'null' - name: title list: 'null' - name: url list: 'null' - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 struct: - name: do_sample dtype: bool - name: temperature dtype: float64 - name: until list: string - name: resps list: list: string - name: filtered_resps list: string - name: filter dtype: string - name: metrics list: string - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: bypass dtype: float64 - name: score dtype: float64 splits: - name: train num_bytes: 27608598 num_examples: 17944 download_size: 20886491 dataset_size: 27608598 - config_name: winogrande features: - name: doc_id dtype: int64 - name: doc struct: - name: answer dtype: string - name: option1 dtype: string - name: option2 dtype: string - name: sentence dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 981783 num_examples: 1267 download_size: 884695 dataset_size: 981783 configs: - config_name: arc_challenge data_files: - split: train path: arc_challenge/train-* - config_name: bbh_cot_fewshot_boolean_expressions data_files: - split: train path: bbh_cot_fewshot_boolean_expressions/train-* - config_name: bbh_cot_fewshot_causal_judgement data_files: - split: train path: bbh_cot_fewshot_causal_judgement/train-* - config_name: bbh_cot_fewshot_date_understanding data_files: - split: train path: bbh_cot_fewshot_date_understanding/train-* - config_name: bbh_cot_fewshot_disambiguation_qa data_files: - split: train path: bbh_cot_fewshot_disambiguation_qa/train-* - config_name: bbh_cot_fewshot_dyck_languages data_files: - split: train path: bbh_cot_fewshot_dyck_languages/train-* - config_name: bbh_cot_fewshot_formal_fallacies data_files: - split: train path: bbh_cot_fewshot_formal_fallacies/train-* - config_name: bbh_cot_fewshot_geometric_shapes data_files: - split: train path: bbh_cot_fewshot_geometric_shapes/train-* - config_name: bbh_cot_fewshot_hyperbaton data_files: - split: train path: bbh_cot_fewshot_hyperbaton/train-* - config_name: bbh_cot_fewshot_logical_deduction_five_objects data_files: - split: train path: bbh_cot_fewshot_logical_deduction_five_objects/train-* - config_name: bbh_cot_fewshot_logical_deduction_seven_objects data_files: - split: train path: bbh_cot_fewshot_logical_deduction_seven_objects/train-* - config_name: bbh_cot_fewshot_logical_deduction_three_objects data_files: - split: train path: bbh_cot_fewshot_logical_deduction_three_objects/train-* - config_name: bbh_cot_fewshot_movie_recommendation data_files: - split: train path: bbh_cot_fewshot_movie_recommendation/train-* - config_name: bbh_cot_fewshot_multistep_arithmetic_two data_files: - split: train path: bbh_cot_fewshot_multistep_arithmetic_two/train-* - config_name: bbh_cot_fewshot_navigate data_files: - split: train path: bbh_cot_fewshot_navigate/train-* - config_name: bbh_cot_fewshot_object_counting data_files: - split: train path: bbh_cot_fewshot_object_counting/train-* - config_name: bbh_cot_fewshot_penguins_in_a_table data_files: - split: train path: bbh_cot_fewshot_penguins_in_a_table/train-* - config_name: bbh_cot_fewshot_reasoning_about_colored_objects data_files: - split: train path: bbh_cot_fewshot_reasoning_about_colored_objects/train-* - config_name: bbh_cot_fewshot_ruin_names data_files: - split: train path: bbh_cot_fewshot_ruin_names/train-* - config_name: bbh_cot_fewshot_salient_translation_error_detection data_files: - split: train path: bbh_cot_fewshot_salient_translation_error_detection/train-* - config_name: bbh_cot_fewshot_snarks data_files: - split: train path: bbh_cot_fewshot_snarks/train-* - config_name: bbh_cot_fewshot_sports_understanding data_files: - split: train path: bbh_cot_fewshot_sports_understanding/train-* - config_name: bbh_cot_fewshot_temporal_sequences data_files: - split: train path: bbh_cot_fewshot_temporal_sequences/train-* - config_name: bbh_cot_fewshot_tracking_shuffled_objects_five_objects data_files: - split: train path: bbh_cot_fewshot_tracking_shuffled_objects_five_objects/train-* - config_name: bbh_cot_fewshot_tracking_shuffled_objects_seven_objects data_files: - split: train path: bbh_cot_fewshot_tracking_shuffled_objects_seven_objects/train-* - config_name: bbh_cot_fewshot_tracking_shuffled_objects_three_objects data_files: - split: train path: bbh_cot_fewshot_tracking_shuffled_objects_three_objects/train-* - config_name: bbh_cot_fewshot_web_of_lies data_files: - split: train path: bbh_cot_fewshot_web_of_lies/train-* - config_name: bbh_cot_fewshot_word_sorting data_files: - split: train path: bbh_cot_fewshot_word_sorting/train-* - config_name: cleanslate_qa data_files: - split: train path: cleanslate_qa/train-* - config_name: coqa data_files: - split: train path: coqa/train-* - config_name: drop data_files: - split: train path: drop/train-* - config_name: gsm8k data_files: - split: train path: gsm8k/train-* - config_name: hellaswag data_files: - split: train path: hellaswag/train-* - config_name: humaneval_plus data_files: - split: train path: humaneval_plus/train-* - config_name: lambada_openai data_files: - split: train path: lambada_openai/train-* - config_name: mmlu_abstract_algebra data_files: - split: train path: mmlu_abstract_algebra/train-* - config_name: mmlu_anatomy data_files: - split: train path: mmlu_anatomy/train-* - config_name: mmlu_astronomy data_files: - split: train path: mmlu_astronomy/train-* - config_name: mmlu_business_ethics data_files: - split: train path: mmlu_business_ethics/train-* - config_name: mmlu_clinical_knowledge data_files: - split: train path: mmlu_clinical_knowledge/train-* - config_name: mmlu_college_biology data_files: - split: train path: mmlu_college_biology/train-* - config_name: mmlu_college_chemistry data_files: - split: train path: mmlu_college_chemistry/train-* - config_name: mmlu_college_computer_science data_files: - split: train path: mmlu_college_computer_science/train-* - config_name: mmlu_college_mathematics data_files: - split: train path: mmlu_college_mathematics/train-* - config_name: mmlu_college_medicine data_files: - split: train path: mmlu_college_medicine/train-* - config_name: mmlu_college_physics data_files: - split: train path: mmlu_college_physics/train-* - config_name: mmlu_computer_security data_files: - split: train path: mmlu_computer_security/train-* - config_name: mmlu_conceptual_physics data_files: - split: train path: mmlu_conceptual_physics/train-* - config_name: mmlu_econometrics data_files: - split: train path: mmlu_econometrics/train-* - config_name: mmlu_electrical_engineering data_files: - split: train path: mmlu_electrical_engineering/train-* - config_name: mmlu_elementary_mathematics data_files: - split: train path: mmlu_elementary_mathematics/train-* - config_name: mmlu_formal_logic data_files: - split: train path: mmlu_formal_logic/train-* - config_name: mmlu_global_facts data_files: - split: train path: mmlu_global_facts/train-* - config_name: mmlu_high_school_biology data_files: - split: train path: mmlu_high_school_biology/train-* - config_name: mmlu_high_school_chemistry data_files: - split: train path: mmlu_high_school_chemistry/train-* - config_name: mmlu_high_school_computer_science data_files: - split: train path: mmlu_high_school_computer_science/train-* - config_name: mmlu_high_school_european_history data_files: - split: train path: mmlu_high_school_european_history/train-* - config_name: mmlu_high_school_geography data_files: - split: train path: mmlu_high_school_geography/train-* - config_name: mmlu_high_school_government_and_politics data_files: - split: train path: mmlu_high_school_government_and_politics/train-* - config_name: mmlu_high_school_macroeconomics data_files: - split: train path: mmlu_high_school_macroeconomics/train-* - config_name: mmlu_high_school_mathematics data_files: - split: train path: mmlu_high_school_mathematics/train-* - config_name: mmlu_high_school_microeconomics data_files: - split: train path: mmlu_high_school_microeconomics/train-* - config_name: mmlu_high_school_physics data_files: - split: train path: mmlu_high_school_physics/train-* - config_name: mmlu_high_school_psychology data_files: - split: train path: mmlu_high_school_psychology/train-* - config_name: mmlu_high_school_statistics data_files: - split: train path: mmlu_high_school_statistics/train-* - config_name: mmlu_high_school_us_history data_files: - split: train path: mmlu_high_school_us_history/train-* - config_name: mmlu_high_school_world_history data_files: - split: train path: mmlu_high_school_world_history/train-* - config_name: mmlu_human_aging data_files: - split: train path: mmlu_human_aging/train-* - config_name: mmlu_human_sexuality data_files: - split: train path: mmlu_human_sexuality/train-* - config_name: mmlu_international_law data_files: - split: train path: mmlu_international_law/train-* - config_name: mmlu_jurisprudence data_files: - split: train path: mmlu_jurisprudence/train-* - config_name: mmlu_logical_fallacies data_files: - split: train path: mmlu_logical_fallacies/train-* - config_name: mmlu_machine_learning data_files: - split: train path: mmlu_machine_learning/train-* - config_name: mmlu_management data_files: - split: train path: mmlu_management/train-* - config_name: mmlu_marketing data_files: - split: train path: mmlu_marketing/train-* - config_name: mmlu_medical_genetics data_files: - split: train path: mmlu_medical_genetics/train-* - config_name: mmlu_miscellaneous data_files: - split: train path: mmlu_miscellaneous/train-* - config_name: mmlu_moral_disputes data_files: - split: train path: mmlu_moral_disputes/train-* - config_name: mmlu_moral_scenarios data_files: - split: train path: mmlu_moral_scenarios/train-* - config_name: mmlu_nutrition data_files: - split: train path: mmlu_nutrition/train-* - config_name: mmlu_philosophy data_files: - split: train path: mmlu_philosophy/train-* - config_name: mmlu_prehistory data_files: - split: train path: mmlu_prehistory/train-* - config_name: mmlu_professional_accounting data_files: - split: train path: mmlu_professional_accounting/train-* - config_name: mmlu_professional_law data_files: - split: train path: mmlu_professional_law/train-* - config_name: mmlu_professional_medicine data_files: - split: train path: mmlu_professional_medicine/train-* - config_name: mmlu_professional_psychology data_files: - split: train path: mmlu_professional_psychology/train-* - config_name: mmlu_public_relations data_files: - split: train path: mmlu_public_relations/train-* - config_name: mmlu_security_studies data_files: - split: train path: mmlu_security_studies/train-* - config_name: mmlu_sociology data_files: - split: train path: mmlu_sociology/train-* - config_name: mmlu_us_foreign_policy data_files: - split: train path: mmlu_us_foreign_policy/train-* - config_name: mmlu_virology data_files: - split: train path: mmlu_virology/train-* - config_name: mmlu_world_religions data_files: - split: train path: mmlu_world_religions/train-* - config_name: triviaqa data_files: - split: train path: triviaqa/train-* - config_name: winogrande data_files: - split: train path: winogrande/train-* ---

应用场景：