open-llm-leaderboard-old/details_meta-math__MetaMath-Llemma-7B
收藏数据集概述
数据集名称
Evaluation run of meta-math/MetaMath-Llemma-7B
数据集摘要
该数据集是在模型meta-math/MetaMath-Llemma-7B在Open LLM Leaderboard上的评估运行期间自动创建的。
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分割，分割名称使用运行的时间戳。
- "train"分割始终指向最新的结果。
- 额外的"results"配置存储所有运行结果的聚合（用于计算和显示在Open LLM Leaderboard上的聚合指标）。
最新结果
以下是2023-12-10T10:48:07.737490运行的最新结果：
python { "all": { "acc": 0.4805727831472479, "acc_stderr": 0.03501873176922748, "acc_norm": 0.47876803306000837, "acc_norm_stderr": 0.03574673517078834, "mc1": 0.2594859241126071, "mc1_stderr": 0.015345409485557994, "mc2": 0.39610018025256144, "mc2_stderr": 0.015159247351087708 }, "harness|arc:challenge|25": { "acc": 0.439419795221843, "acc_stderr": 0.014503747823580125, "acc_norm": 0.46501706484641636, "acc_norm_stderr": 0.01457558392201967 }, "harness|hellaswag|10": { "acc": 0.4731129257120096, "acc_stderr": 0.004982561815214125, "acc_norm": 0.6169089822744473, "acc_norm_stderr": 0.004851466623601442 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4074074074074074, "acc_stderr": 0.04244633238353228, "acc_norm": 0.4074074074074074, "acc_norm_stderr": 0.04244633238353228 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5263157894736842, "acc_stderr": 0.04063302731486671, "acc_norm": 0.5263157894736842, "acc_norm_stderr": 0.04063302731486671 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.47924528301886793, "acc_stderr": 0.030746349975723463, "acc_norm": 0.47924528301886793, "acc_norm_stderr": 0.030746349975723463 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4930555555555556, "acc_stderr": 0.04180806750294938, "acc_norm": 0.4930555555555556, "acc_norm_stderr": 0.04180806750294938 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4682080924855491, "acc_stderr": 0.03804749744364763, "acc_norm": 0.4682080924855491, "acc_norm_stderr": 0.03804749744364763 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.39215686274509803, "acc_stderr": 0.048580835742663434, "acc_norm": 0.39215686274509803, "acc_norm_stderr": 0.048580835742663434 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.65, "acc_stderr": 0.047937248544110196, "acc_norm": 0.65, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4808510638297872, "acc_stderr": 0.032662042990646796, "acc_norm": 0.4808510638297872, "acc_norm_stderr": 0.032662042990646796 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.32456140350877194, "acc_stderr": 0.044045561573747664, "acc_norm": 0.32456140350877194, "acc_norm_stderr": 0.044045561573747664 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5241379310344828, "acc_stderr": 0.0416180850350153, "acc_norm": 0.5241379310344828, "acc_norm_stderr": 0.0416180850350153 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.41005291005291006, "acc_stderr": 0.025331202438944423, "acc_norm": 0.41005291005291006, "acc_norm_stderr": 0.025331202438944423 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3968253968253968, "acc_stderr": 0.04375888492727061, "acc_norm": 0.3968253968253968, "acc_norm_stderr": 0.04375888492727061 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5193548387096775, "acc_stderr": 0.028422687404312107, "acc_norm": 0.5193548387096775, "acc_norm_stderr": 0.028422687404312107 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.41379310344827586, "acc_stderr": 0.03465304488406795, "acc_norm": 0.41379310344827586, "acc_norm_stderr": 0.03465304488406795 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.59, "acc_stderr": 0.049431107042371025, "acc_norm": 0.59, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5636363636363636, "acc_stderr": 0.03872592983524754, "acc_norm": 0.5636363636363636, "acc_norm_stderr": 0.03872592983524754 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5757575757575758, "acc_stderr": 0.035212249088415845, "acc_norm": 0.5757575757575758, "acc_norm_stderr": 0.035212249088415845 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.5492227979274611, "acc_stderr": 0.03590910952235524, "acc_norm": 0.5492227979274611, "acc_norm_stderr": 0.03590910952235524 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5, "acc_stderr": 0.02535100632816969, "acc_norm": 0.5, "acc_norm_stderr": 0.02535100632816969 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.27037037037037037, "acc_stderr": 0.027080372815145665, "acc_norm": 0.27037037037037037, "acc_norm_stderr": 0.027080372815145665 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.4831932773109244, "
