Name: unlearning-cleanslate/generations-simnpo_olmo-3-1125-32b_20260416_164134-corpus_sweep_post_eval
Creator: unlearning-cleanslate
Published: 2026-04-20 02:50:51
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/unlearning-cleanslate/generations-simnpo_olmo-3-1125-32b_20260416_164134-corpus_sweep_post_eval

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: 1903170 num_examples: 1172 download_size: 1728925 dataset_size: 1903170 - config_name: arc_easy 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: 3520759 num_examples: 2376 download_size: 3154109 dataset_size: 3520759 - 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: 694626 num_examples: 250 download_size: 683672 dataset_size: 694626 - 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: 1225744 num_examples: 187 download_size: 1217634 dataset_size: 1225744 - 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: 518133 num_examples: 250 download_size: 505688 dataset_size: 518133 - 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: 1348084 num_examples: 250 download_size: 1349444 dataset_size: 1348084 - 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: 955386 num_examples: 250 download_size: 953287 dataset_size: 955386 - 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: 1781437 num_examples: 250 download_size: 1766090 dataset_size: 1781437 - 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: 1707962 num_examples: 250 download_size: 1693001 dataset_size: 1707962 - 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: 1176625 num_examples: 250 download_size: 1174114 dataset_size: 1176625 - 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: 1260817 num_examples: 250 download_size: 1258731 dataset_size: 1260817 - 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: 1523114 num_examples: 250 download_size: 1524793 dataset_size: 1523114 - 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: 1030378 num_examples: 250 download_size: 1026230 dataset_size: 1030378 - 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: 821373 num_examples: 250 download_size: 812974 dataset_size: 821373 - 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: 879167 num_examples: 250 download_size: 884668 dataset_size: 879167 - 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: 835576 num_examples: 250 download_size: 828338 dataset_size: 835576 - 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: 565224 num_examples: 250 download_size: 554266 dataset_size: 565224 - 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: 586136 num_examples: 146 download_size: 593567 dataset_size: 586136 - 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: 923541 num_examples: 250 download_size: 917297 dataset_size: 923541 - 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: 1231567 num_examples: 250 download_size: 1230445 dataset_size: 1231567 - 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: 2384262 num_examples: 250 download_size: 2371665 dataset_size: 2384262 - 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: 793942 num_examples: 178 download_size: 799018 dataset_size: 793942 - 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: 360680 num_examples: 250 download_size: 345361 dataset_size: 360680 - 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: 1202723 num_examples: 250 download_size: 1200855 dataset_size: 1202723 - 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: 1248554 num_examples: 250 download_size: 1247295 dataset_size: 1248554 - 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: 1467991 num_examples: 250 download_size: 1470287 dataset_size: 1467991 - 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: 1080791 num_examples: 250 download_size: 1077091 dataset_size: 1080791 - 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: 1099506 num_examples: 250 download_size: 1096536 dataset_size: 1099506 - 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: 1111586 num_examples: 250 download_size: 1119455 dataset_size: 1111586 - 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: 8004072 num_examples: 12088 download_size: 7112980 dataset_size: 8004072 - 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: 5526066 num_examples: 500 download_size: 5531638 dataset_size: 5526066 - 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: 28133736 num_examples: 9536 download_size: 26390110 dataset_size: 28133736 - 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: 11598709 num_examples: 2638 download_size: 10663601 dataset_size: 11598709 - 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: 39600261 num_examples: 10042 download_size: 38111068 dataset_size: 39600261 - 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: 22072980 num_examples: 164 download_size: 14066412 dataset_size: 22072980 - 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: 5115999 num_examples: 5153 download_size: 4754086 dataset_size: 5115999 - 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: 187414 num_examples: 100 download_size: 189133 dataset_size: 187414 - 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: 281991 num_examples: 135 download_size: 280149 dataset_size: 281991 - 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: 366507 num_examples: 152 download_size: 363633 dataset_size: 366507 - 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: 256400 num_examples: 100 download_size: 259766 dataset_size: 256400 - 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: 556901 num_examples: 265 download_size: 535164 dataset_size: 556901 - 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: 373827 num_examples: 144 download_size: 370721 dataset_size: 373827 - 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: 214826 num_examples: 100 download_size: 219145 dataset_size: 214826 - 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: 307951 num_examples: 100 download_size: 316783 dataset_size: 307951 - 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: 215823 num_examples: 100 download_size: 217184 dataset_size: 215823 - 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: 568994 num_examples: 173 download_size: 564456 dataset_size: 568994 - 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: 242973 num_examples: 102 download_size: 245995 dataset_size: 242973 - 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: 226774 num_examples: 100 download_size: 228325 dataset_size: 226774 - 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: 419058 num_examples: 235 download_size: 400065 dataset_size: 419058 - 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: 333939 num_examples: 114 download_size: 335251 dataset_size: 333939 - 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: 261593 num_examples: 145 download_size: 255641 dataset_size: 261593 - 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: 705148 num_examples: 378 download_size: 661808 dataset_size: 705148 - 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: 360527 num_examples: 126 download_size: 361676 dataset_size: 360527 - 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: 180759 num_examples: 100 download_size: 181967 dataset_size: 180759 - 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: 834564 num_examples: 310 download_size: 806313 dataset_size: 834564 - 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: 481652 num_examples: 203 download_size: 467932 dataset_size: 481652 - 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: 319066 num_examples: 100 download_size: 325401 dataset_size: 319066 - 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: 1511095 num_examples: 165 download_size: 1524734 dataset_size: 1511095 - 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: 394680 num_examples: 198 download_size: 381291 dataset_size: 394680 - 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: 523738 num_examples: 193 download_size: 513300 dataset_size: 523738 - 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: 961959 num_examples: 390 download_size: 921761 dataset_size: 961959 - 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: 528982 num_examples: 270 download_size: 507480 dataset_size: 528982 - 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: 606403 num_examples: 238 download_size: 588848 dataset_size: 606403 - 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: 437056 num_examples: 151 download_size: 439663 dataset_size: 437056 - 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: 1307860 num_examples: 545 download_size: 1240706 dataset_size: 1307860 - 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: 756040 num_examples: 216 download_size: 743377 dataset_size: 756040 - 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: 1674790 num_examples: 204 download_size: 1685933 dataset_size: 1674790 - 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: 2118775 num_examples: 237 download_size: 2123679 dataset_size: 2118775 - 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: 427344 num_examples: 223 download_size: 410243 dataset_size: 427344 - 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: 278750 num_examples: 131 download_size: 275911 dataset_size: 278750 - 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: 378019 num_examples: 121 download_size: 383670 dataset_size: 378019 - 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: 266290 num_examples: 108 download_size: 266171 dataset_size: 266290 - 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: 399289 num_examples: 163 download_size: 394009 dataset_size: 399289 - 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: 271076 num_examples: 112 download_size: 270918 dataset_size: 271076 - 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: 190371 num_examples: 103 download_size: 191114 dataset_size: 190371 - 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: 518759 num_examples: 234 download_size: 502099 dataset_size: 518759 - 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: 195054 num_examples: 100 download_size: 198582 dataset_size: 195054 - 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: 1437078 num_examples: 783 download_size: 1339417 dataset_size: 1437078 - 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: 848320 num_examples: 346 download_size: 813437 dataset_size: 848320 - 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: 2678720 num_examples: 895 download_size: 2562971 dataset_size: 2678720 - 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: 727782 num_examples: 306 download_size: 702535 dataset_size: 727782 - 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: 673438 num_examples: 311 download_size: 646048 dataset_size: 673438 - 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: 732282 num_examples: 324 download_size: 702340 dataset_size: 732282 - 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: 888746 num_examples: 282 download_size: 865383 dataset_size: 888746 - 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: 10852454 num_examples: 1534 download_size: 10727766 dataset_size: 10852454 - 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: 1341627 num_examples: 272 download_size: 1337046 dataset_size: 1341627 - 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: 1706615 num_examples: 612 download_size: 1633008 dataset_size: 1706615 - 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: 243550 num_examples: 110 download_size: 244552 dataset_size: 243550 - 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: 1246509 num_examples: 245 download_size: 1235254 dataset_size: 1246509 - 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: 506507 num_examples: 201 download_size: 493834 dataset_size: 506507 - 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: 233385 num_examples: 100 download_size: 234995 dataset_size: 233385 - 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: 337811 num_examples: 166 download_size: 331604 dataset_size: 337811 - 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: 280206 num_examples: 171 download_size: 270429 dataset_size: 280206 - config_name: piqa features: - name: doc_id dtype: int64 - name: doc struct: - name: goal dtype: string - name: label dtype: int64 - name: sol1 dtype: string - name: sol2 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: 1782332 num_examples: 1838 download_size: 1554796 dataset_size: 1782332 - 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: 27491345 num_examples: 17944 download_size: 20768762 dataset_size: 27491345 - 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: 981921 num_examples: 1267 download_size: 884835 dataset_size: 981921 configs: - config_name: arc_challenge data_files: - split: train path: arc_challenge/train-* - config_name: arc_easy data_files: - split: train path: arc_easy/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: piqa data_files: - split: train path: piqa/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：