Name: unlearning-cleanslate/generations-olmo-3-7b-simnpo-baseline
Creator: unlearning-cleanslate
Published: 2026-04-29 22:40:29
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/unlearning-cleanslate/generations-olmo-3-7b-simnpo-baseline

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: 1902936 num_examples: 1172 download_size: 1728703 dataset_size: 1902936 - 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: 625751 num_examples: 250 download_size: 613519 dataset_size: 625751 - 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: 1223830 num_examples: 187 download_size: 1215472 dataset_size: 1223830 - 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: 522109 num_examples: 250 download_size: 509665 dataset_size: 522109 - 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: 1349515 num_examples: 250 download_size: 1350365 dataset_size: 1349515 - 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: 786290 num_examples: 250 download_size: 782245 dataset_size: 786290 - 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: 1713719 num_examples: 250 download_size: 1697475 dataset_size: 1713719 - 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: 1683633 num_examples: 250 download_size: 1669284 dataset_size: 1683633 - 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: 1173262 num_examples: 250 download_size: 1170932 dataset_size: 1173262 - 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: 1139907 num_examples: 250 download_size: 1136944 dataset_size: 1139907 - 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: 1263300 num_examples: 250 download_size: 1263026 dataset_size: 1263300 - 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: 1010133 num_examples: 250 download_size: 1005764 dataset_size: 1010133 - 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: 814990 num_examples: 250 download_size: 806152 dataset_size: 814990 - 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: 790446 num_examples: 250 download_size: 794689 dataset_size: 790446 - 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: 755009 num_examples: 250 download_size: 747071 dataset_size: 755009 - 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: 545497 num_examples: 250 download_size: 533592 dataset_size: 545497 - 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: 580982 num_examples: 146 download_size: 588043 dataset_size: 580982 - 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: 912981 num_examples: 250 download_size: 907045 dataset_size: 912981 - 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: 1215820 num_examples: 250 download_size: 1214858 dataset_size: 1215820 - 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: 2373610 num_examples: 250 download_size: 2360847 dataset_size: 2373610 - 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: 797161 num_examples: 178 download_size: 800663 dataset_size: 797161 - 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: 371599 num_examples: 250 download_size: 356334 dataset_size: 371599 - 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: 1202335 num_examples: 250 download_size: 1200488 dataset_size: 1202335 - 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: 1236144 num_examples: 250 download_size: 1234597 dataset_size: 1236144 - 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: 1439843 num_examples: 250 download_size: 1441749 dataset_size: 1439843 - 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: 1075636 num_examples: 250 download_size: 1071985 dataset_size: 1075636 - 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: 1072551 num_examples: 250 download_size: 1069126 dataset_size: 1072551 - 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: 1023723 num_examples: 250 download_size: 1034066 dataset_size: 1023723 - 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: 7872660 num_examples: 12088 download_size: 6982224 dataset_size: 7872660 - 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: 6466536 num_examples: 500 download_size: 6478876 dataset_size: 6466536 - 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: 28107796 num_examples: 9536 download_size: 26364421 dataset_size: 28107796 - 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: 12570818 num_examples: 2638 download_size: 11640414 dataset_size: 12570818 - 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: 39608237 num_examples: 10042 download_size: 38119035 dataset_size: 39608237 - 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: 22107082 num_examples: 164 download_size: 14100588 dataset_size: 22107082 - 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: 5117615 num_examples: 5153 download_size: 4755651 dataset_size: 5117615 - 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: 187404 num_examples: 100 download_size: 189131 dataset_size: 187404 - 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: 282115 num_examples: 135 download_size: 280285 dataset_size: 282115 - 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: 366469 num_examples: 152 download_size: 363595 dataset_size: 366469 - 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: 256540 num_examples: 100 download_size: 259912 dataset_size: 256540 - 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: 557193 num_examples: 265 download_size: 535460 dataset_size: 557193 - 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: 374011 num_examples: 144 download_size: 370913 dataset_size: 374011 - 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: 214786 num_examples: 100 download_size: 219109 dataset_size: 214786 - 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: 308007 num_examples: 100 download_size: 316843 dataset_size: 308007 - 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: 215809 num_examples: 100 download_size: 217170 dataset_size: 215809 - 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: 568984 num_examples: 173 download_size: 564452 dataset_size: 568984 - 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: 243031 num_examples: 102 download_size: 246057 dataset_size: 243031 - 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: 226932 num_examples: 100 download_size: 228489 dataset_size: 226932 - 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: 419186 num_examples: 235 download_size: 400192 dataset_size: 419186 - 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: 333845 num_examples: 114 download_size: 335157 dataset_size: 333845 - 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: 261589 num_examples: 145 download_size: 255639 dataset_size: 261589 - 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: 704990 num_examples: 378 download_size: 661647 dataset_size: 704990 - 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: 360485 num_examples: 126 download_size: 361638 dataset_size: 360485 - 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: 180821 num_examples: 100 download_size: 182029 dataset_size: 180821 - 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: 834792 num_examples: 310 download_size: 806545 dataset_size: 834792 - 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: 481710 num_examples: 203 download_size: 467990 dataset_size: 481710 - 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: 319144 num_examples: 100 download_size: 325480 dataset_size: 319144 - 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: 1511207 num_examples: 165 download_size: 1524845 dataset_size: 1511207 - 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: 394982 num_examples: 198 download_size: 381593 dataset_size: 394982 - 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: 523974 num_examples: 193 download_size: 513552 dataset_size: 523974 - 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: 962105 num_examples: 390 download_size: 921912 dataset_size: 962105 - 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: 528906 num_examples: 270 download_size: 507408 dataset_size: 528906 - 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: 606411 num_examples: 238 download_size: 588860 dataset_size: 606411 - 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: 437030 num_examples: 151 download_size: 439641 dataset_size: 437030 - 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: 1308382 num_examples: 545 download_size: 1241243 dataset_size: 1308382 - 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: 756062 num_examples: 216 download_size: 743395 dataset_size: 756062 - 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: 1675030 num_examples: 204 download_size: 1686178 dataset_size: 1675030 - 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: 2118897 num_examples: 237 download_size: 2123800 dataset_size: 2118897 - 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: 427354 num_examples: 223 download_size: 410254 dataset_size: 427354 - 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: 278824 num_examples: 131 download_size: 275988 dataset_size: 278824 - 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: 378111 num_examples: 121 download_size: 383759 dataset_size: 378111 - 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: 266376 num_examples: 108 download_size: 266263 dataset_size: 266376 - 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: 399393 num_examples: 163 download_size: 394119 dataset_size: 399393 - 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: 271034 num_examples: 112 download_size: 270880 dataset_size: 271034 - 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: 190447 num_examples: 103 download_size: 191191 dataset_size: 190447 - 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: 519059 num_examples: 234 download_size: 502411 dataset_size: 519059 - 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: 195092 num_examples: 100 download_size: 198622 dataset_size: 195092 - 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: 1438080 num_examples: 783 download_size: 1340422 dataset_size: 1438080 - 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: 848506 num_examples: 346 download_size: 813611 dataset_size: 848506 - 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: 2678038 num_examples: 895 download_size: 2562286 dataset_size: 2678038 - 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: 727988 num_examples: 306 download_size: 702748 dataset_size: 727988 - 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: 673604 num_examples: 311 download_size: 646216 dataset_size: 673604 - 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: 732470 num_examples: 324 download_size: 702530 dataset_size: 732470 - 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: 888862 num_examples: 282 download_size: 865503 dataset_size: 888862 - 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: 10852296 num_examples: 1534 download_size: 10727615 dataset_size: 10852296 - 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: 1341645 num_examples: 272 download_size: 1337066 dataset_size: 1341645 - 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: 1706847 num_examples: 612 download_size: 1633244 dataset_size: 1706847 - 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: 243714 num_examples: 110 download_size: 244726 dataset_size: 243714 - 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: 1246653 num_examples: 245 download_size: 1235404 dataset_size: 1246653 - 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: 506707 num_examples: 201 download_size: 494038 dataset_size: 506707 - 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: 233547 num_examples: 100 download_size: 235164 dataset_size: 233547 - 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: 337971 num_examples: 166 download_size: 331772 dataset_size: 337971 - 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: 280484 num_examples: 171 download_size: 270713 dataset_size: 280484 - 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: 27488172 num_examples: 17944 download_size: 20765520 dataset_size: 27488172 - 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: 981239 num_examples: 1267 download_size: 884150 dataset_size: 981239 configs: - config_name: arc_challenge data_files: - split: train path: arc_challenge/train-* - config_name: bbh_cot_fewshot_boolean_expressions data_files: - split: train path: bbh_cot_fewshot_boolean_expressions/train-* - config_name: bbh_cot_fewshot_causal_judgement data_files: - split: train path: bbh_cot_fewshot_causal_judgement/train-* - config_name: bbh_cot_fewshot_date_understanding data_files: - split: train path: bbh_cot_fewshot_date_understanding/train-* - config_name: bbh_cot_fewshot_disambiguation_qa data_files: - split: train path: bbh_cot_fewshot_disambiguation_qa/train-* - config_name: bbh_cot_fewshot_dyck_languages data_files: - split: train path: bbh_cot_fewshot_dyck_languages/train-* - config_name: bbh_cot_fewshot_formal_fallacies data_files: - split: train path: bbh_cot_fewshot_formal_fallacies/train-* - config_name: bbh_cot_fewshot_geometric_shapes data_files: - split: train path: bbh_cot_fewshot_geometric_shapes/train-* - config_name: bbh_cot_fewshot_hyperbaton data_files: - split: train path: bbh_cot_fewshot_hyperbaton/train-* - config_name: bbh_cot_fewshot_logical_deduction_five_objects data_files: - split: train path: bbh_cot_fewshot_logical_deduction_five_objects/train-* - config_name: bbh_cot_fewshot_logical_deduction_seven_objects data_files: - split: train path: bbh_cot_fewshot_logical_deduction_seven_objects/train-* - config_name: bbh_cot_fewshot_logical_deduction_three_objects data_files: - split: train path: bbh_cot_fewshot_logical_deduction_three_objects/train-* - config_name: bbh_cot_fewshot_movie_recommendation data_files: - split: train path: bbh_cot_fewshot_movie_recommendation/train-* - config_name: bbh_cot_fewshot_multistep_arithmetic_two data_files: - split: train path: bbh_cot_fewshot_multistep_arithmetic_two/train-* - config_name: bbh_cot_fewshot_navigate data_files: - split: train path: bbh_cot_fewshot_navigate/train-* - config_name: bbh_cot_fewshot_object_counting data_files: - split: train path: bbh_cot_fewshot_object_counting/train-* - config_name: bbh_cot_fewshot_penguins_in_a_table data_files: - split: train path: bbh_cot_fewshot_penguins_in_a_table/train-* - config_name: bbh_cot_fewshot_reasoning_about_colored_objects data_files: - split: train path: bbh_cot_fewshot_reasoning_about_colored_objects/train-* - config_name: bbh_cot_fewshot_ruin_names data_files: - split: train path: bbh_cot_fewshot_ruin_names/train-* - config_name: bbh_cot_fewshot_salient_translation_error_detection data_files: - split: train path: bbh_cot_fewshot_salient_translation_error_detection/train-* - config_name: bbh_cot_fewshot_snarks data_files: - split: train path: bbh_cot_fewshot_snarks/train-* - config_name: bbh_cot_fewshot_sports_understanding data_files: - split: train path: bbh_cot_fewshot_sports_understanding/train-* - config_name: bbh_cot_fewshot_temporal_sequences data_files: - split: train path: bbh_cot_fewshot_temporal_sequences/train-* - config_name: bbh_cot_fewshot_tracking_shuffled_objects_five_objects data_files: - split: train path: bbh_cot_fewshot_tracking_shuffled_objects_five_objects/train-* - config_name: bbh_cot_fewshot_tracking_shuffled_objects_seven_objects data_files: - split: train path: bbh_cot_fewshot_tracking_shuffled_objects_seven_objects/train-* - config_name: bbh_cot_fewshot_tracking_shuffled_objects_three_objects data_files: - split: train path: bbh_cot_fewshot_tracking_shuffled_objects_three_objects/train-* - config_name: bbh_cot_fewshot_web_of_lies data_files: - split: train path: bbh_cot_fewshot_web_of_lies/train-* - config_name: bbh_cot_fewshot_word_sorting data_files: - split: train path: bbh_cot_fewshot_word_sorting/train-* - config_name: cleanslate_qa data_files: - split: train path: cleanslate_qa/train-* - config_name: coqa data_files: - split: train path: coqa/train-* - config_name: drop data_files: - split: train path: drop/train-* - config_name: gsm8k data_files: - split: train path: gsm8k/train-* - config_name: hellaswag data_files: - split: train path: hellaswag/train-* - config_name: humaneval_plus data_files: - split: train path: humaneval_plus/train-* - config_name: lambada_openai data_files: - split: train path: lambada_openai/train-* - config_name: mmlu_abstract_algebra data_files: - split: train path: mmlu_abstract_algebra/train-* - config_name: mmlu_anatomy data_files: - split: train path: mmlu_anatomy/train-* - config_name: mmlu_astronomy data_files: - split: train path: mmlu_astronomy/train-* - config_name: mmlu_business_ethics data_files: - split: train path: mmlu_business_ethics/train-* - config_name: mmlu_clinical_knowledge data_files: - split: train path: mmlu_clinical_knowledge/train-* - config_name: mmlu_college_biology data_files: - split: train path: mmlu_college_biology/train-* - config_name: mmlu_college_chemistry data_files: - split: train path: mmlu_college_chemistry/train-* - config_name: mmlu_college_computer_science data_files: - split: train path: mmlu_college_computer_science/train-* - config_name: mmlu_college_mathematics data_files: - split: train path: mmlu_college_mathematics/train-* - config_name: mmlu_college_medicine data_files: - split: train path: mmlu_college_medicine/train-* - config_name: mmlu_college_physics data_files: - split: train path: mmlu_college_physics/train-* - config_name: mmlu_computer_security data_files: - split: train path: mmlu_computer_security/train-* - config_name: mmlu_conceptual_physics data_files: - split: train path: mmlu_conceptual_physics/train-* - config_name: mmlu_econometrics data_files: - split: train path: mmlu_econometrics/train-* - config_name: mmlu_electrical_engineering data_files: - split: train path: mmlu_electrical_engineering/train-* - config_name: mmlu_elementary_mathematics data_files: - split: train path: mmlu_elementary_mathematics/train-* - config_name: mmlu_formal_logic data_files: - split: train path: mmlu_formal_logic/train-* - config_name: mmlu_global_facts data_files: - split: train path: mmlu_global_facts/train-* - config_name: mmlu_high_school_biology data_files: - split: train path: mmlu_high_school_biology/train-* - config_name: mmlu_high_school_chemistry data_files: - split: train path: mmlu_high_school_chemistry/train-* - config_name: mmlu_high_school_computer_science data_files: - split: train path: mmlu_high_school_computer_science/train-* - config_name: mmlu_high_school_european_history data_files: - split: train path: mmlu_high_school_european_history/train-* - config_name: mmlu_high_school_geography data_files: - split: train path: mmlu_high_school_geography/train-* - config_name: mmlu_high_school_government_and_politics data_files: - split: train path: mmlu_high_school_government_and_politics/train-* - config_name: mmlu_high_school_macroeconomics data_files: - split: train path: mmlu_high_school_macroeconomics/train-* - config_name: mmlu_high_school_mathematics data_files: - split: train path: mmlu_high_school_mathematics/train-* - config_name: mmlu_high_school_microeconomics data_files: - split: train path: mmlu_high_school_microeconomics/train-* - config_name: mmlu_high_school_physics data_files: - split: train path: mmlu_high_school_physics/train-* - config_name: mmlu_high_school_psychology data_files: - split: train path: mmlu_high_school_psychology/train-* - config_name: mmlu_high_school_statistics data_files: - split: train path: mmlu_high_school_statistics/train-* - config_name: mmlu_high_school_us_history data_files: - split: train path: mmlu_high_school_us_history/train-* - config_name: mmlu_high_school_world_history data_files: - split: train path: mmlu_high_school_world_history/train-* - config_name: mmlu_human_aging data_files: - split: train path: mmlu_human_aging/train-* - config_name: mmlu_human_sexuality data_files: - split: train path: mmlu_human_sexuality/train-* - config_name: mmlu_international_law data_files: - split: train path: mmlu_international_law/train-* - config_name: mmlu_jurisprudence data_files: - split: train path: mmlu_jurisprudence/train-* - config_name: mmlu_logical_fallacies data_files: - split: train path: mmlu_logical_fallacies/train-* - config_name: mmlu_machine_learning data_files: - split: train path: mmlu_machine_learning/train-* - config_name: mmlu_management data_files: - split: train path: mmlu_management/train-* - config_name: mmlu_marketing data_files: - split: train path: mmlu_marketing/train-* - config_name: mmlu_medical_genetics data_files: - split: train path: mmlu_medical_genetics/train-* - config_name: mmlu_miscellaneous data_files: - split: train path: mmlu_miscellaneous/train-* - config_name: mmlu_moral_disputes data_files: - split: train path: mmlu_moral_disputes/train-* - config_name: mmlu_moral_scenarios data_files: - split: train path: mmlu_moral_scenarios/train-* - config_name: mmlu_nutrition data_files: - split: train path: mmlu_nutrition/train-* - config_name: mmlu_philosophy data_files: - split: train path: mmlu_philosophy/train-* - config_name: mmlu_prehistory data_files: - split: train path: mmlu_prehistory/train-* - config_name: mmlu_professional_accounting data_files: - split: train path: mmlu_professional_accounting/train-* - config_name: mmlu_professional_law data_files: - split: train path: mmlu_professional_law/train-* - config_name: mmlu_professional_medicine data_files: - split: train path: mmlu_professional_medicine/train-* - config_name: mmlu_professional_psychology data_files: - split: train path: mmlu_professional_psychology/train-* - config_name: mmlu_public_relations data_files: - split: train path: mmlu_public_relations/train-* - config_name: mmlu_security_studies data_files: - split: train path: mmlu_security_studies/train-* - config_name: mmlu_sociology data_files: - split: train path: mmlu_sociology/train-* - config_name: mmlu_us_foreign_policy data_files: - split: train path: mmlu_us_foreign_policy/train-* - config_name: mmlu_virology data_files: - split: train path: mmlu_virology/train-* - config_name: mmlu_world_religions data_files: - split: train path: mmlu_world_religions/train-* - config_name: triviaqa data_files: - split: train path: triviaqa/train-* - config_name: winogrande data_files: - split: train path: winogrande/train-* ---

应用场景：