Name: unlearning-cleanslate/generations-02-qwen3-8b-simnpo-gentle-baseline-target-100-checkpoint-539
Creator: unlearning-cleanslate
Published: 2026-04-29 22:10:24
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/unlearning-cleanslate/generations-02-qwen3-8b-simnpo-gentle-baseline-target-100-checkpoint-539

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: 1903474 num_examples: 1172 download_size: 1729235 dataset_size: 1903474 - 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: 692662 num_examples: 250 download_size: 681916 dataset_size: 692662 - 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: 1305165 num_examples: 187 download_size: 1298991 dataset_size: 1305165 - 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: 595780 num_examples: 250 download_size: 587678 dataset_size: 595780 - 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: 1477208 num_examples: 250 download_size: 1478966 dataset_size: 1477208 - 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: 993696 num_examples: 250 download_size: 992191 dataset_size: 993696 - 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: 1794281 num_examples: 250 download_size: 1779087 dataset_size: 1794281 - 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: 1897762 num_examples: 250 download_size: 1889646 dataset_size: 1897762 - 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: 1195174 num_examples: 250 download_size: 1192829 dataset_size: 1195174 - 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: 1278495 num_examples: 250 download_size: 1276688 dataset_size: 1278495 - 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: 1566105 num_examples: 250 download_size: 1578131 dataset_size: 1566105 - 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: 1091618 num_examples: 250 download_size: 1088140 dataset_size: 1091618 - 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: 882779 num_examples: 250 download_size: 875586 dataset_size: 882779 - 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: 876249 num_examples: 250 download_size: 881713 dataset_size: 876249 - 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: 844513 num_examples: 250 download_size: 837608 dataset_size: 844513 - 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: 565362 num_examples: 250 download_size: 554417 dataset_size: 565362 - 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: 602988 num_examples: 146 download_size: 610390 dataset_size: 602988 - 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: 1053287 num_examples: 250 download_size: 1048391 dataset_size: 1053287 - 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: 1279149 num_examples: 250 download_size: 1278717 dataset_size: 1279149 - 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: 2560200 num_examples: 250 download_size: 2549284 dataset_size: 2560200 - 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: 835675 num_examples: 178 download_size: 839958 dataset_size: 835675 - 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: 373465 num_examples: 250 download_size: 358207 dataset_size: 373465 - 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: 1255426 num_examples: 250 download_size: 1254676 dataset_size: 1255426 - 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: 1306770 num_examples: 250 download_size: 1306374 dataset_size: 1306770 - 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: 1527927 num_examples: 250 download_size: 1531014 dataset_size: 1527927 - 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: 1093626 num_examples: 250 download_size: 1090000 dataset_size: 1093626 - 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: 1118279 num_examples: 250 download_size: 1115493 dataset_size: 1118279 - 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: 1153694 num_examples: 250 download_size: 1161681 dataset_size: 1153694 - 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: 12075048 num_examples: 12088 download_size: 11186865 dataset_size: 12075048 - 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: 5745164 num_examples: 500 download_size: 5748252 dataset_size: 5745164 - 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: 28902580 num_examples: 9536 download_size: 27158321 dataset_size: 28902580 - 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: 11666619 num_examples: 2638 download_size: 10732082 dataset_size: 11666619 - 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: 39601125 num_examples: 10042 download_size: 38111939 dataset_size: 39601125 - 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: 22207160 num_examples: 164 download_size: 14203539 dataset_size: 22207160 - 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: 5116993 num_examples: 5153 download_size: 4755036 dataset_size: 5116993 - 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: 187286 num_examples: 100 download_size: 189009 dataset_size: 187286 - 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: 282029 num_examples: 135 download_size: 280193 dataset_size: 282029 - 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: 366415 num_examples: 152 download_size: 363548 dataset_size: 366415 - 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: 256402 num_examples: 100 download_size: 259773 dataset_size: 256402 - 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: 556875 num_examples: 265 download_size: 535142 dataset_size: 556875 - 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: 373885 num_examples: 144 download_size: 370781 dataset_size: 373885 - 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: 214728 num_examples: 100 download_size: 219051 dataset_size: 214728 - 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: 307929 num_examples: 100 download_size: 316765 dataset_size: 307929 - 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: 215679 num_examples: 100 download_size: 217040 dataset_size: 215679 - 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: 568950 num_examples: 173 download_size: 564416 dataset_size: 568950 - 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: 242859 num_examples: 102 download_size: 245875 dataset_size: 242859 - 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: 226908 num_examples: 100 download_size: 228462 dataset_size: 226908 - 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: 419122 num_examples: 235 download_size: 400128 dataset_size: 419122 - 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: 333839 num_examples: 114 download_size: 335147 dataset_size: 333839 - 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: 261471 num_examples: 145 download_size: 255521 dataset_size: 261471 - 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: 704704 num_examples: 378 download_size: 661362 dataset_size: 704704 - 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: 360391 num_examples: 126 download_size: 361544 dataset_size: 360391 - 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: 180693 num_examples: 100 download_size: 181905 dataset_size: 180693 - 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: 834600 num_examples: 310 download_size: 806347 dataset_size: 834600 - 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: 481516 num_examples: 203 download_size: 467800 dataset_size: 481516 - 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: 319072 num_examples: 100 download_size: 325409 dataset_size: 319072 - 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: 1511035 num_examples: 165 download_size: 1524679 dataset_size: 1511035 - 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: 394884 num_examples: 198 download_size: 381499 dataset_size: 394884 - 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: 523906 num_examples: 193 download_size: 513477 dataset_size: 523906 - 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: 961887 num_examples: 390 download_size: 921707 dataset_size: 961887 - 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: 528654 num_examples: 270 download_size: 507152 dataset_size: 528654 - 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: 606443 num_examples: 238 download_size: 588885 dataset_size: 606443 - 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: 436906 num_examples: 151 download_size: 439523 dataset_size: 436906 - 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: 1308108 num_examples: 545 download_size: 1240949 dataset_size: 1308108 - 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: 755890 num_examples: 216 download_size: 743228 dataset_size: 755890 - 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: 1674814 num_examples: 204 download_size: 1685956 dataset_size: 1674814 - 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: 2118659 num_examples: 237 download_size: 2123564 dataset_size: 2118659 - 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: 427288 num_examples: 223 download_size: 410185 dataset_size: 427288 - 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: 278700 num_examples: 131 download_size: 275864 dataset_size: 278700 - 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: 378001 num_examples: 121 download_size: 383642 dataset_size: 378001 - 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: 266330 num_examples: 108 download_size: 266213 dataset_size: 266330 - 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: 399359 num_examples: 163 download_size: 394080 dataset_size: 399359 - 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: 271004 num_examples: 112 download_size: 270854 dataset_size: 271004 - 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: 190397 num_examples: 103 download_size: 191147 dataset_size: 190397 - 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: 518755 num_examples: 234 download_size: 502096 dataset_size: 518755 - 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: 195010 num_examples: 100 download_size: 198535 dataset_size: 195010 - 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: 1437924 num_examples: 783 download_size: 1340272 dataset_size: 1437924 - 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: 848430 num_examples: 346 download_size: 813534 dataset_size: 848430 - 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: 2677556 num_examples: 895 download_size: 2561798 dataset_size: 2677556 - 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: 727826 num_examples: 306 download_size: 702585 dataset_size: 727826 - 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: 673284 num_examples: 311 download_size: 645898 dataset_size: 673284 - 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: 732386 num_examples: 324 download_size: 702449 dataset_size: 732386 - 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: 888516 num_examples: 282 download_size: 865153 dataset_size: 888516 - 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: 10851424 num_examples: 1534 download_size: 10726741 dataset_size: 10851424 - 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: 1341499 num_examples: 272 download_size: 1336921 dataset_size: 1341499 - 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: 1706369 num_examples: 612 download_size: 1632765 dataset_size: 1706369 - 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: 243602 num_examples: 110 download_size: 244608 dataset_size: 243602 - 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: 1246521 num_examples: 245 download_size: 1235276 dataset_size: 1246521 - 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: 506699 num_examples: 201 download_size: 494028 dataset_size: 506699 - 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: 233457 num_examples: 100 download_size: 235073 dataset_size: 233457 - 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: 337737 num_examples: 166 download_size: 331534 dataset_size: 337737 - 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: 280374 num_examples: 171 download_size: 270597 dataset_size: 280374 - 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: 28130341 num_examples: 17944 download_size: 21407931 dataset_size: 28130341 - 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: 981847 num_examples: 1267 download_size: 884763 dataset_size: 981847 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：