open-llm-leaderboard-old/details_HIT-SCIR__huozi3
收藏数据集概述
数据集简介
该数据集是在模型 HIT-SCIR/huozi3 在 Open LLM Leaderboard 上的评估运行期间自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
数据集由 1 次运行创建，每个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。
结果配置
一个额外的配置 "results" 存储了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。
最新结果
以下是 2024-03-07T20:44:41.862473 运行的最新结果：
python { "all": { "acc": 0.7031073624622961, "acc_stderr": 0.03049104652532932, "acc_norm": 0.7077570494310711, "acc_norm_stderr": 0.031083441064630134, "mc1": 0.35006119951040393, "mc1_stderr": 0.01669794942015103, "mc2": 0.4945311053451425, "mc2_stderr": 0.014719497916036287 }, "harness|arc:challenge|25": { "acc": 0.6126279863481229, "acc_stderr": 0.014235872487909865, "acc_norm": 0.6501706484641638, "acc_norm_stderr": 0.013936809212158294 }, "harness|hellaswag|10": { "acc": 0.6619199362676758, "acc_stderr": 0.004720891597174731, "acc_norm": 0.8599880501892053, "acc_norm_stderr": 0.00346290260113618 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252606, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252606 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6962962962962963, "acc_stderr": 0.03972552884785136, "acc_norm": 0.6962962962962963, "acc_norm_stderr": 0.03972552884785136 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7894736842105263, "acc_stderr": 0.03317672787533157, "acc_norm": 0.7894736842105263, "acc_norm_stderr": 0.03317672787533157 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.72, "acc_stderr": 0.04512608598542126, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542126 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7584905660377359, "acc_stderr": 0.02634148037111836, "acc_norm": 0.7584905660377359, "acc_norm_stderr": 0.02634148037111836 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8125, "acc_stderr": 0.032639560491693344, "acc_norm": 0.8125, "acc_norm_stderr": 0.032639560491693344 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6994219653179191, "acc_stderr": 0.03496101481191179, "acc_norm": 0.6994219653179191, "acc_norm_stderr": 0.03496101481191179 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4411764705882353, "acc_stderr": 0.049406356306056595, "acc_norm": 0.4411764705882353, "acc_norm_stderr": 0.049406356306056595 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.81, "acc_stderr": 0.039427724440366234, "acc_norm": 0.81, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6808510638297872, "acc_stderr": 0.030472973363380045, "acc_norm": 0.6808510638297872, "acc_norm_stderr": 0.030472973363380045 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6052631578947368, "acc_stderr": 0.04598188057816542, "acc_norm": 0.6052631578947368, "acc_norm_stderr": 0.04598188057816542 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6620689655172414, "acc_stderr": 0.039417076320648906, "acc_norm": 0.6620689655172414, "acc_norm_stderr": 0.039417076320648906 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.47354497354497355, "acc_stderr": 0.025715239811346758, "acc_norm": 0.47354497354497355, "acc_norm_stderr": 0.025715239811346758 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5, "acc_stderr": 0.04472135954999579, "acc_norm": 0.5, "acc_norm_stderr": 0.04472135954999579 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8290322580645161, "acc_stderr": 0.02141724293632158, "acc_norm": 0.8290322580645161, "acc_norm_stderr": 0.02141724293632158 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5960591133004927, "acc_stderr": 0.03452453903822032, "acc_norm": 0.5960591133004927, "acc_norm_stderr": 0.03452453903822032 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.74, "acc_stderr": 0.0440844002276808, "acc_norm": 0.74, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.806060606060606, "acc_stderr": 0.03087414513656208, "acc_norm": 0.806060606060606, "acc_norm_stderr": 0.03087414513656208 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8434343434343434, "acc_stderr": 0.025890520358141454, "acc_norm": 0.8434343434343434, "acc_norm_stderr": 0.025890520358141454 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9222797927461139, "acc_stderr": 0.019321805557223164, "acc_norm": 0.9222797927461139, "acc_norm_stderr": 0.019321805557223164 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6923076923076923, "acc_stderr": 0.023400928918310495, "acc_norm": 0.6923076923076923, "acc_norm_stderr": 0.023400928918310495 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.37407407407407406, "acc_stderr": 0.02950286112895529, "acc_norm": 0.37407407407407406, "acc_norm_stderr": 0.02950286112895529 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.7899159663865546, "acc_stderr": 0.026461398717471874, "acc_norm": 0.7899159663865546, "acc_norm_stderr": 0.026461398717471874 }, "harness|hend
