open-llm-leaderboard-old/details_pansophic__rocket-3B
收藏数据集概述
数据集简介
该数据集是在对模型 pansophic/rocket-3B 进行评估运行时自动创建的,用于 Open LLM Leaderboard。
数据集组成
- 数据集包含 63 个配置,每个配置对应一个评估任务。
- 数据集从 1 次运行中创建,每次运行可以在每个配置中找到特定的拆分,拆分名称使用运行的时间戳。
- "train" 拆分始终指向最新的结果。
- 额外的 "results" 配置存储所有运行的聚合结果,用于计算和显示 Open LLM Leaderboard 上的聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_pansophic__rocket-3B", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-29T18:54:49.996831 运行的最新结果: python { "all": { "acc": 0.47477902512156295, "acc_stderr": 0.03464180645885471, "acc_norm": 0.476642281206908, "acc_norm_stderr": 0.03535757378171989, "mc1": 0.3843329253365973, "mc1_stderr": 0.017028707301245206, "mc2": 0.5581803060616521, "mc2_stderr": 0.01597966786555303 }, "harness|arc:challenge|25": { "acc": 0.47952218430034127, "acc_stderr": 0.014599131353035009, "acc_norm": 0.5059726962457338, "acc_norm_stderr": 0.014610348300255793 }, "harness|hellaswag|10": { "acc": 0.5887273451503684, "acc_stderr": 0.004910588449330022, "acc_norm": 0.7668791077474607, "acc_norm_stderr": 0.004219544466789609 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4148148148148148, "acc_stderr": 0.042561937679014075, "acc_norm": 0.4148148148148148, "acc_norm_stderr": 0.042561937679014075 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.46710526315789475, "acc_stderr": 0.040601270352363966, "acc_norm": 0.46710526315789475, "acc_norm_stderr": 0.040601270352363966 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5207547169811321, "acc_stderr": 0.03074634997572347, "acc_norm": 0.5207547169811321, "acc_norm_stderr": 0.03074634997572347 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4861111111111111, "acc_stderr": 0.04179596617581, "acc_norm": 0.4861111111111111, "acc_norm_stderr": 0.04179596617581 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4393063583815029, "acc_stderr": 0.03784271932887467, "acc_norm": 0.4393063583815029, "acc_norm_stderr": 0.03784271932887467 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3137254901960784, "acc_stderr": 0.04617034827006717, "acc_norm": 0.3137254901960784, "acc_norm_stderr": 0.04617034827006717 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.61, "acc_stderr": 0.04902071300001974, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.39148936170212767, "acc_stderr": 0.03190701242326812, "acc_norm": 0.39148936170212767, "acc_norm_stderr": 0.03190701242326812 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2807017543859649, "acc_stderr": 0.042270544512322, "acc_norm": 0.2807017543859649, "acc_norm_stderr": 0.042270544512322 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4413793103448276, "acc_stderr": 0.04137931034482758, "acc_norm": 0.4413793103448276, "acc_norm_stderr": 0.04137931034482758 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3148148148148148, "acc_stderr": 0.023919984164047732, "acc_norm": 0.3148148148148148, "acc_norm_stderr": 0.023919984164047732 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.36507936507936506, "acc_stderr": 0.04306241259127154, "acc_norm": 0.36507936507936506, "acc_norm_stderr": 0.04306241259127154 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5161290322580645, "acc_stderr": 0.028429203176724555, "acc_norm": 0.5161290322580645, "acc_norm_stderr": 0.028429203176724555 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.33497536945812806, "acc_stderr": 0.033208527423483104, "acc_norm": 0.33497536945812806, "acc_norm_stderr": 0.033208527423483104 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5757575757575758, "acc_stderr": 0.03859268142070264, "acc_norm": 0.5757575757575758, "acc_norm_stderr": 0.03859268142070264 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5202020202020202, "acc_stderr": 0.035594435655639176, "acc_norm": 0.5202020202020202, "acc_norm_stderr": 0.035594435655639176 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.6476683937823834, "acc_stderr": 0.03447478286414357, "acc_norm": 0.6476683937823834, "acc_norm_stderr": 0.03447478286414357 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.41025641025641024, "acc_stderr": 0.02493931390694077, "acc_norm": 0.41025641025641024, "acc_norm_stderr": 0.02493931390694077 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.23703703703703705, "acc_stderr": 0.025928876132766104, "acc_norm": 0.23703703703703705, "acc_norm_stderr": 0.025928876132766104 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.40336134453781514, "acc_stderr": 0.031866081214088314, "acc_norm": 0.40336134453781514, "acc_norm_stderr": 0.031866081214088314 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.33774834437086093, "acc_stderr": 0.03861557546255169, "acc_norm": 0.33774834437086093, "acc_norm_stderr": 0.03861557546255169 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.6477064220183486, "acc_stderr": 0.020480568843998986, "acc_norm": 0.6477064220183486, "acc_norm_stderr": 0.020480568843998986 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.35185185185185186, "acc_stderr": 0.032568505702936484, "acc_norm": 0.35185185185185186, "acc_norm_stderr": 0.032568505702936484 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.5980392156862745, "acc_stderr": 0.034411900234824655, "acc_norm": 0.5980392156862745, "acc_norm_stderr": 0.034411900234824655 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.679324894514768, "acc_stderr": 0.03038193194999041, "acc_norm": 0.679324894514768, "acc_norm_stderr": 0.03038193194999041 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.5515695067264574, "acc_stderr": 0.03337883736255098, "acc_norm": 0.5515695067264574, "acc_norm_stderr": 0.03337883736255098 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.5114503816793893, "acc_stderr": 0.04384140024078016, "acc_norm": 0.5114503816793893, "acc_norm_stderr": 0.04384140024078016 }, "harness|hendrycksTest-international_law|5": { "acc": 0.6198347107438017, "acc_stderr": 0.04431324501968432, "acc_norm": 0.6198347107438017, "acc_norm_stderr": 0.04431324501968432 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.5648148148148148, "acc_stderr": 0.04792898170907061, "acc_norm": 0.5648148148148148, "acc_norm_stderr": 0.04792898170907061 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.5214723926380368, "acc_stderr": 0.03924746876751129, "acc_norm": 0.5214723926380368, "acc_norm_stderr": 0.03924746876751129 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.35714285714285715, "acc_stderr": 0.04547960999764376, "acc_norm": 0.35714285714285715, "acc_norm_stderr": 0.04547960999764376 }, "harness|hendrycksTest-management|5": { "acc": 0.6310679611650486, "acc_stderr": 0.0477761518115674, "acc_norm": 0.6310679611650486, "acc_norm_stderr": 0.0477761518115674 }, "harness|hendrycksTest-marketing|5": { "acc": 0.6965811965811965, "acc_stderr": 0.030118210106942652, "acc_norm": 0.6965811965811965, "acc_norm_stderr": 0.030118210106942652 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.51, "acc_stderr": 0.05024183937956913, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956913 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.5964240102171137, "acc_stderr": 0.01754433223792642, "acc_norm": 0.5964240102171137, "acc_norm_stderr": 0.01754433223792642 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.4682080924855491, "acc_stderr": 0.026864624366756656, "acc_norm": 0.4682080924855491, "acc_norm_stderr": 0.026864624366756656 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.264804469273743, "acc_stderr": 0.014756906483260657, "acc_norm": 0.264804469273743, "acc_norm_stderr": 0.014756906483260657 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.47058823529411764, "acc_stderr": 0.028580341065138296, "acc_norm": 0.47058823529411764, "acc_norm_stderr": 0.028580341065138296 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.48231511254019294, "acc_stderr": 0.02838032284907713, "acc_norm": 0.48231511254019294, "acc_norm_stderr": 0.02838032284907713 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.5154320987654321, "acc_stderr": 0.027807490044276184, "acc_norm": 0.5154320987654321, "acc_norm_stderr": 0.027807490044276184 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.3475177304964539, "acc_stderr": 0.028406627809590954, "acc_norm": 0.3475177304964539, "acc_norm_stderr": 0.028406627809590954 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.36114732724902215, "acc_stderr": 0.012267935477519034, "acc_norm": 0.36114732724902215, "acc_norm_stderr": 0.012267935477519034 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.38235294117647056, "acc_stderr": 0.029520095697687765, "acc_norm": 0.38235294117647056, "acc_norm_stderr": 0.029520095697687765 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.4444444444444444, "acc_stderr": 0.020102583895887184, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.020102583895887184 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.6454545454545455, "acc_stderr": 0.04582004841505417, "acc_norm": 0.6454545454545455, "acc_norm_stderr": 0.04582004841505417 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.5061224489795918, "acc_stderr": 0.03200682020163907, "acc_norm": 0.5061224489795918, "acc_norm_stderr": 0.03200682020163907 }, "harness|hendrycksTest-sociology|5": { "acc": 0.6616915422885572, "acc_stderr": 0.033455630703391914, "acc_norm": 0.6616915422885572, "acc_norm_stderr": 0.033455630703391914 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-virology|5": { "acc": 0.42168674698795183, "acc_stderr": 0.03844453181770917, "acc_norm": 0.42168674698795183, "acc_norm_stderr": 0.03844453181770917 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.631578947368421, "acc_stderr": 0.036996580176568775, "acc_norm": 0.631578947368421, "acc_norm_stderr": 0.036996580176568775 }, "harness|truthfulqa:mc|0": { "mc1": 0.3843329253365973, "mc1_stderr": 0.017028707301245206, "mc2": 0.5581803060616521, "mc2_stderr": 0.01597966786555303 }, "harness|winogrande|5": { "acc": 0.6795580110497238, "acc_stderr": 0.01311508545768171 }, "harness|gsm8k|5": { "acc": 0.3646702047005307, "acc_stderr": 0.013258428375662245 } }
数据集配置
-
harness_arc_challenge_25
- 拆分:2024_02_29T18_54_49.996831, latest
- 路径:
**/details_harness|arc:challenge|25_2024-02-29T18-54-49.996831.parquet
-
harness_gsm8k_5
- 拆分:2024_02_29T18_54_49.996831, latest
- 路径:
**/details_harness|gsm8k|5_2024-02-29T18-54-49.996831.parquet
-
harness_hellaswag_10
- 拆分:2024_02_29T18_54_49.996831, latest
- 路径:
**/details_harness|hellaswag|10_2024-02-29T18-54-49.996831.parquet
-
harness_hendrycksTest_5
- 拆分:2024_02_29T18_54_49.996831
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-anatomy|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-astronomy|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-business_ethics|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-college_biology|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-college_chemistry|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-college_computer_science|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-college_mathematics|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-college_medicine|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-college_physics|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-computer_security|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-econometrics|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-formal_logic|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-global_facts|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-high_school_biology|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-high_school_chemistry|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-high_school_computer_science|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-high_school_european_history|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-high_school_geography|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-high_school_mathematics|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-high_school_physics|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-high_school_psychology|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-high_school_statistics|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-high_school_us_history|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-high_school_world_history|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-human_aging|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-human_sexuality|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-international_law|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-jurisprudence|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-logical_fallacies|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-machine_learning|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-management|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-marketing|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-medical_genetics|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-miscellaneous|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-moral_disputes|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-moral_scenarios|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-nutrition|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-philosophy|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-prehistory|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-professional_accounting|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-professional_law|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-professional_medicine|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-professional_psychology|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-public_relations|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-security_studies|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-sociology|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-us_foreign_policy|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-virology|5_2024-02-29T18-54-49.996831.parquet**/details_harness|hendrycksTest-world_religions|5_2024-02-29T18-54-49.996831.parquet



