Name: unlearning-cleanslate/generations-simnpo_gemma-3-12b-pt_20260416_171305-corpus_sweep_post_eval
Creator: unlearning-cleanslate
Published: 2026-04-20 02:44:11
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/unlearning-cleanslate/generations-simnpo_gemma-3-12b-pt_20260416_171305-corpus_sweep_post_eval

下载链接

链接失效反馈

官方服务：

资源简介：

--- dataset_info: - config_name: arc_challenge features: - name: doc_id dtype: int64 - name: doc struct: - name: answerKey dtype: string - name: choices struct: - name: label list: string - name: text list: string - name: id dtype: string - name: question dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_4 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 1903114 num_examples: 1172 download_size: 1728873 dataset_size: 1903114 - config_name: arc_easy features: - name: doc_id dtype: int64 - name: doc struct: - name: answerKey dtype: string - name: choices struct: - name: label list: string - name: text list: string - name: id dtype: string - name: question dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_2 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_3 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_4 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 3520361 num_examples: 2376 download_size: 3153710 dataset_size: 3520361 - 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: 683825 num_examples: 250 download_size: 672583 dataset_size: 683825 - 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: 1207775 num_examples: 187 download_size: 1199625 dataset_size: 1207775 - 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: 533128 num_examples: 250 download_size: 520724 dataset_size: 533128 - 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: 1346072 num_examples: 250 download_size: 1347002 dataset_size: 1346072 - 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: 939160 num_examples: 250 download_size: 937081 dataset_size: 939160 - 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: 1824217 num_examples: 250 download_size: 1810421 dataset_size: 1824217 - 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: 1744480 num_examples: 250 download_size: 1733226 dataset_size: 1744480 - 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: 1177269 num_examples: 250 download_size: 1174893 dataset_size: 1177269 - 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: 1143552 num_examples: 250 download_size: 1140790 dataset_size: 1143552 - 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: 1285336 num_examples: 250 download_size: 1285520 dataset_size: 1285336 - 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: 1016668 num_examples: 250 download_size: 1012422 dataset_size: 1016668 - 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: 822595 num_examples: 250 download_size: 814353 dataset_size: 822595 - 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: 871220 num_examples: 250 download_size: 876444 dataset_size: 871220 - 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: 836675 num_examples: 250 download_size: 829447 dataset_size: 836675 - 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: 565322 num_examples: 250 download_size: 554372 dataset_size: 565322 - 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: 589262 num_examples: 146 download_size: 597399 dataset_size: 589262 - 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: 916236 num_examples: 250 download_size: 910441 dataset_size: 916236 - 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: 1283986 num_examples: 250 download_size: 1283463 dataset_size: 1283986 - 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: 2431210 num_examples: 250 download_size: 2418323 dataset_size: 2431210 - 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: 782637 num_examples: 178 download_size: 787886 dataset_size: 782637 - 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: 365098 num_examples: 250 download_size: 349841 dataset_size: 365098 - 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: 1203234 num_examples: 250 download_size: 1201382 dataset_size: 1203234 - 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: 1248661 num_examples: 250 download_size: 1247408 dataset_size: 1248661 - 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: 1470665 num_examples: 250 download_size: 1472977 dataset_size: 1470665 - 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: 1079801 num_examples: 250 download_size: 1076164 dataset_size: 1079801 - 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: 1099172 num_examples: 250 download_size: 1096247 dataset_size: 1099172 - 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: 1135173 num_examples: 250 download_size: 1143121 dataset_size: 1135173 - 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: 7964656 num_examples: 12088 download_size: 7073707 dataset_size: 7964656 - 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: 5702442 num_examples: 500 download_size: 5709767 dataset_size: 5702442 - 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: 29351400 num_examples: 9536 download_size: 27607010 dataset_size: 29351400 - 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: 11580124 num_examples: 2638 download_size: 10644685 dataset_size: 11580124 - 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: 39601549 num_examples: 10042 download_size: 38112388 dataset_size: 39601549 - 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: 22128772 num_examples: 164 download_size: 14122333 dataset_size: 22128772 - 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: 5115431 num_examples: 5153 download_size: 4753487 dataset_size: 5115431 - 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: 187262 num_examples: 100 download_size: 188981 dataset_size: 187262 - 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: 282021 num_examples: 135 download_size: 280181 dataset_size: 282021 - 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: 366307 num_examples: 152 download_size: 363433 dataset_size: 366307 - 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: 256414 num_examples: 100 download_size: 259780 dataset_size: 256414 - 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: 556747 num_examples: 265 download_size: 535011 dataset_size: 556747 - 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: 373769 num_examples: 144 download_size: 370660 dataset_size: 373769 - 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: 214784 num_examples: 100 download_size: 219103 dataset_size: 214784 - 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: 307941 num_examples: 100 download_size: 316769 dataset_size: 307941 - 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: 215773 num_examples: 100 download_size: 217134 dataset_size: 215773 - 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: 568854 num_examples: 173 download_size: 564310 dataset_size: 568854 - 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: 242917 num_examples: 102 download_size: 245939 dataset_size: 242917 - 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: 226750 num_examples: 100 download_size: 228290 dataset_size: 226750 - 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: 419004 num_examples: 235 download_size: 400006 dataset_size: 419004 - 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: 333921 num_examples: 114 download_size: 335229 dataset_size: 333921 - 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: 261567 num_examples: 145 download_size: 255609 dataset_size: 261567 - 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: 704802 num_examples: 378 download_size: 661458 dataset_size: 704802 - 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: 360451 num_examples: 126 download_size: 361600 dataset_size: 360451 - 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: 180769 num_examples: 100 download_size: 181973 dataset_size: 180769 - 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: 834352 num_examples: 310 download_size: 806101 dataset_size: 834352 - 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: 481524 num_examples: 203 download_size: 467802 dataset_size: 481524 - 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: 319098 num_examples: 100 download_size: 325430 dataset_size: 319098 - 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: 1511009 num_examples: 165 download_size: 1524645 dataset_size: 1511009 - 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: 394588 num_examples: 198 download_size: 381194 dataset_size: 394588 - 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: 523638 num_examples: 193 download_size: 513203 dataset_size: 523638 - 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: 961705 num_examples: 390 download_size: 921514 dataset_size: 961705 - 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: 528770 num_examples: 270 download_size: 507268 dataset_size: 528770 - 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: 606267 num_examples: 238 download_size: 588712 dataset_size: 606267 - 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: 436944 num_examples: 151 download_size: 439551 dataset_size: 436944 - 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: 1307512 num_examples: 545 download_size: 1240340 dataset_size: 1307512 - 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: 756004 num_examples: 216 download_size: 743337 dataset_size: 756004 - 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: 1674810 num_examples: 204 download_size: 1685956 dataset_size: 1674810 - 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: 2118763 num_examples: 237 download_size: 2123656 dataset_size: 2118763 - 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: 427180 num_examples: 223 download_size: 410072 dataset_size: 427180 - 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: 278690 num_examples: 131 download_size: 275848 dataset_size: 278690 - 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: 377993 num_examples: 121 download_size: 383637 dataset_size: 377993 - 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: 266202 num_examples: 108 download_size: 266080 dataset_size: 266202 - 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: 399169 num_examples: 163 download_size: 393885 dataset_size: 399169 - 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: 271016 num_examples: 112 download_size: 270854 dataset_size: 271016 - 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: 190353 num_examples: 103 download_size: 191100 dataset_size: 190353 - 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: 518557 num_examples: 234 download_size: 501891 dataset_size: 518557 - 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: 194950 num_examples: 100 download_size: 198473 dataset_size: 194950 - 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: 1436660 num_examples: 783 download_size: 1338995 dataset_size: 1436660 - 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: 848216 num_examples: 346 download_size: 813329 dataset_size: 848216 - 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: 2677844 num_examples: 895 download_size: 2562078 dataset_size: 2677844 - 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: 727614 num_examples: 306 download_size: 702361 dataset_size: 727614 - 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: 673222 num_examples: 311 download_size: 645829 dataset_size: 673222 - 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: 732096 num_examples: 324 download_size: 702158 dataset_size: 732096 - 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: 888648 num_examples: 282 download_size: 865275 dataset_size: 888648 - 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: 10851556 num_examples: 1534 download_size: 10726868 dataset_size: 10851556 - 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: 1341307 num_examples: 272 download_size: 1336724 dataset_size: 1341307 - 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: 1706197 num_examples: 612 download_size: 1632590 dataset_size: 1706197 - 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: 243562 num_examples: 110 download_size: 244566 dataset_size: 243562 - 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: 1246451 num_examples: 245 download_size: 1235198 dataset_size: 1246451 - 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: 506429 num_examples: 201 download_size: 493751 dataset_size: 506429 - 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: 233373 num_examples: 100 download_size: 234971 dataset_size: 233373 - 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: 337751 num_examples: 166 download_size: 331544 dataset_size: 337751 - 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: 280154 num_examples: 171 download_size: 270377 dataset_size: 280154 - config_name: piqa features: - name: doc_id dtype: int64 - name: doc struct: - name: goal dtype: string - name: label dtype: int64 - name: sol1 dtype: string - name: sol2 dtype: string - name: target dtype: string - name: arguments struct: - name: gen_args_0 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: gen_args_1 struct: - name: arg_0 dtype: string - name: arg_1 dtype: string - name: resps list: list: list: string - name: filtered_resps list: list: string - name: filter dtype: string - name: metrics list: 'null' - name: doc_hash dtype: string - name: prompt_hash dtype: string - name: target_hash dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 1782450 num_examples: 1838 download_size: 1554928 dataset_size: 1782450 - 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: 27564793 num_examples: 17944 download_size: 20842324 dataset_size: 27564793 - 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: 981729 num_examples: 1267 download_size: 884648 dataset_size: 981729 configs: - config_name: arc_challenge data_files: - split: train path: arc_challenge/train-* - config_name: arc_easy data_files: - split: train path: arc_easy/train-* - config_name: bbh_cot_fewshot_boolean_expressions data_files: - split: train path: bbh_cot_fewshot_boolean_expressions/train-* - config_name: bbh_cot_fewshot_causal_judgement data_files: - split: train path: bbh_cot_fewshot_causal_judgement/train-* - config_name: bbh_cot_fewshot_date_understanding data_files: - split: train path: bbh_cot_fewshot_date_understanding/train-* - config_name: bbh_cot_fewshot_disambiguation_qa data_files: - split: train path: bbh_cot_fewshot_disambiguation_qa/train-* - config_name: bbh_cot_fewshot_dyck_languages data_files: - split: train path: bbh_cot_fewshot_dyck_languages/train-* - config_name: bbh_cot_fewshot_formal_fallacies data_files: - split: train path: bbh_cot_fewshot_formal_fallacies/train-* - config_name: bbh_cot_fewshot_geometric_shapes data_files: - split: train path: bbh_cot_fewshot_geometric_shapes/train-* - config_name: bbh_cot_fewshot_hyperbaton data_files: - split: train path: bbh_cot_fewshot_hyperbaton/train-* - config_name: bbh_cot_fewshot_logical_deduction_five_objects data_files: - split: train path: bbh_cot_fewshot_logical_deduction_five_objects/train-* - config_name: bbh_cot_fewshot_logical_deduction_seven_objects data_files: - split: train path: bbh_cot_fewshot_logical_deduction_seven_objects/train-* - config_name: bbh_cot_fewshot_logical_deduction_three_objects data_files: - split: train path: bbh_cot_fewshot_logical_deduction_three_objects/train-* - config_name: bbh_cot_fewshot_movie_recommendation data_files: - split: train path: bbh_cot_fewshot_movie_recommendation/train-* - config_name: bbh_cot_fewshot_multistep_arithmetic_two data_files: - split: train path: bbh_cot_fewshot_multistep_arithmetic_two/train-* - config_name: bbh_cot_fewshot_navigate data_files: - split: train path: bbh_cot_fewshot_navigate/train-* - config_name: bbh_cot_fewshot_object_counting data_files: - split: train path: bbh_cot_fewshot_object_counting/train-* - config_name: bbh_cot_fewshot_penguins_in_a_table data_files: - split: train path: bbh_cot_fewshot_penguins_in_a_table/train-* - config_name: bbh_cot_fewshot_reasoning_about_colored_objects data_files: - split: train path: bbh_cot_fewshot_reasoning_about_colored_objects/train-* - config_name: bbh_cot_fewshot_ruin_names data_files: - split: train path: bbh_cot_fewshot_ruin_names/train-* - config_name: bbh_cot_fewshot_salient_translation_error_detection data_files: - split: train path: bbh_cot_fewshot_salient_translation_error_detection/train-* - config_name: bbh_cot_fewshot_snarks data_files: - split: train path: bbh_cot_fewshot_snarks/train-* - config_name: bbh_cot_fewshot_sports_understanding data_files: - split: train path: bbh_cot_fewshot_sports_understanding/train-* - config_name: bbh_cot_fewshot_temporal_sequences data_files: - split: train path: bbh_cot_fewshot_temporal_sequences/train-* - config_name: bbh_cot_fewshot_tracking_shuffled_objects_five_objects data_files: - split: train path: bbh_cot_fewshot_tracking_shuffled_objects_five_objects/train-* - config_name: bbh_cot_fewshot_tracking_shuffled_objects_seven_objects data_files: - split: train path: bbh_cot_fewshot_tracking_shuffled_objects_seven_objects/train-* - config_name: bbh_cot_fewshot_tracking_shuffled_objects_three_objects data_files: - split: train path: bbh_cot_fewshot_tracking_shuffled_objects_three_objects/train-* - config_name: bbh_cot_fewshot_web_of_lies data_files: - split: train path: bbh_cot_fewshot_web_of_lies/train-* - config_name: bbh_cot_fewshot_word_sorting data_files: - split: train path: bbh_cot_fewshot_word_sorting/train-* - config_name: cleanslate_qa data_files: - split: train path: cleanslate_qa/train-* - config_name: coqa data_files: - split: train path: coqa/train-* - config_name: drop data_files: - split: train path: drop/train-* - config_name: gsm8k data_files: - split: train path: gsm8k/train-* - config_name: hellaswag data_files: - split: train path: hellaswag/train-* - config_name: humaneval_plus data_files: - split: train path: humaneval_plus/train-* - config_name: lambada_openai data_files: - split: train path: lambada_openai/train-* - config_name: mmlu_abstract_algebra data_files: - split: train path: mmlu_abstract_algebra/train-* - config_name: mmlu_anatomy data_files: - split: train path: mmlu_anatomy/train-* - config_name: mmlu_astronomy data_files: - split: train path: mmlu_astronomy/train-* - config_name: mmlu_business_ethics data_files: - split: train path: mmlu_business_ethics/train-* - config_name: mmlu_clinical_knowledge data_files: - split: train path: mmlu_clinical_knowledge/train-* - config_name: mmlu_college_biology data_files: - split: train path: mmlu_college_biology/train-* - config_name: mmlu_college_chemistry data_files: - split: train path: mmlu_college_chemistry/train-* - config_name: mmlu_college_computer_science data_files: - split: train path: mmlu_college_computer_science/train-* - config_name: mmlu_college_mathematics data_files: - split: train path: mmlu_college_mathematics/train-* - config_name: mmlu_college_medicine data_files: - split: train path: mmlu_college_medicine/train-* - config_name: mmlu_college_physics data_files: - split: train path: mmlu_college_physics/train-* - config_name: mmlu_computer_security data_files: - split: train path: mmlu_computer_security/train-* - config_name: mmlu_conceptual_physics data_files: - split: train path: mmlu_conceptual_physics/train-* - config_name: mmlu_econometrics data_files: - split: train path: mmlu_econometrics/train-* - config_name: mmlu_electrical_engineering data_files: - split: train path: mmlu_electrical_engineering/train-* - config_name: mmlu_elementary_mathematics data_files: - split: train path: mmlu_elementary_mathematics/train-* - config_name: mmlu_formal_logic data_files: - split: train path: mmlu_formal_logic/train-* - config_name: mmlu_global_facts data_files: - split: train path: mmlu_global_facts/train-* - config_name: mmlu_high_school_biology data_files: - split: train path: mmlu_high_school_biology/train-* - config_name: mmlu_high_school_chemistry data_files: - split: train path: mmlu_high_school_chemistry/train-* - config_name: mmlu_high_school_computer_science data_files: - split: train path: mmlu_high_school_computer_science/train-* - config_name: mmlu_high_school_european_history data_files: - split: train path: mmlu_high_school_european_history/train-* - config_name: mmlu_high_school_geography data_files: - split: train path: mmlu_high_school_geography/train-* - config_name: mmlu_high_school_government_and_politics data_files: - split: train path: mmlu_high_school_government_and_politics/train-* - config_name: mmlu_high_school_macroeconomics data_files: - split: train path: mmlu_high_school_macroeconomics/train-* - config_name: mmlu_high_school_mathematics data_files: - split: train path: mmlu_high_school_mathematics/train-* - config_name: mmlu_high_school_microeconomics data_files: - split: train path: mmlu_high_school_microeconomics/train-* - config_name: mmlu_high_school_physics data_files: - split: train path: mmlu_high_school_physics/train-* - config_name: mmlu_high_school_psychology data_files: - split: train path: mmlu_high_school_psychology/train-* - config_name: mmlu_high_school_statistics data_files: - split: train path: mmlu_high_school_statistics/train-* - config_name: mmlu_high_school_us_history data_files: - split: train path: mmlu_high_school_us_history/train-* - config_name: mmlu_high_school_world_history data_files: - split: train path: mmlu_high_school_world_history/train-* - config_name: mmlu_human_aging data_files: - split: train path: mmlu_human_aging/train-* - config_name: mmlu_human_sexuality data_files: - split: train path: mmlu_human_sexuality/train-* - config_name: mmlu_international_law data_files: - split: train path: mmlu_international_law/train-* - config_name: mmlu_jurisprudence data_files: - split: train path: mmlu_jurisprudence/train-* - config_name: mmlu_logical_fallacies data_files: - split: train path: mmlu_logical_fallacies/train-* - config_name: mmlu_machine_learning data_files: - split: train path: mmlu_machine_learning/train-* - config_name: mmlu_management data_files: - split: train path: mmlu_management/train-* - config_name: mmlu_marketing data_files: - split: train path: mmlu_marketing/train-* - config_name: mmlu_medical_genetics data_files: - split: train path: mmlu_medical_genetics/train-* - config_name: mmlu_miscellaneous data_files: - split: train path: mmlu_miscellaneous/train-* - config_name: mmlu_moral_disputes data_files: - split: train path: mmlu_moral_disputes/train-* - config_name: mmlu_moral_scenarios data_files: - split: train path: mmlu_moral_scenarios/train-* - config_name: mmlu_nutrition data_files: - split: train path: mmlu_nutrition/train-* - config_name: mmlu_philosophy data_files: - split: train path: mmlu_philosophy/train-* - config_name: mmlu_prehistory data_files: - split: train path: mmlu_prehistory/train-* - config_name: mmlu_professional_accounting data_files: - split: train path: mmlu_professional_accounting/train-* - config_name: mmlu_professional_law data_files: - split: train path: mmlu_professional_law/train-* - config_name: mmlu_professional_medicine data_files: - split: train path: mmlu_professional_medicine/train-* - config_name: mmlu_professional_psychology data_files: - split: train path: mmlu_professional_psychology/train-* - config_name: mmlu_public_relations data_files: - split: train path: mmlu_public_relations/train-* - config_name: mmlu_security_studies data_files: - split: train path: mmlu_security_studies/train-* - config_name: mmlu_sociology data_files: - split: train path: mmlu_sociology/train-* - config_name: mmlu_us_foreign_policy data_files: - split: train path: mmlu_us_foreign_policy/train-* - config_name: mmlu_virology data_files: - split: train path: mmlu_virology/train-* - config_name: mmlu_world_religions data_files: - split: train path: mmlu_world_religions/train-* - config_name: piqa data_files: - split: train path: piqa/train-* - config_name: triviaqa data_files: - split: train path: triviaqa/train-* - config_name: winogrande data_files: - split: train path: winogrande/train-* ---

应用场景：