open-llm-leaderboard-old/details_adamo1139__Yi-34B-200K-AEZAKMI-v2
收藏数据集概述
数据集简介
该数据集是在对模型 adamo1139/Yi-34B-200K-AEZAKMI-v2 进行评估运行期间自动创建的，用于 Open LLM Leaderboard 上的评估。
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。
- 每个配置中的 "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。
最新结果
以下是 2023-12-16T22:00:38.648825 运行的最新结果：
python { "all": { "acc": 0.7472785535366926, "acc_stderr": 0.028772452169713955, "acc_norm": 0.7527023693141784, "acc_norm_stderr": 0.029306663104184946, "mc1": 0.40024479804161567, "mc1_stderr": 0.017151605555749138, "mc2": 0.5674054536094885, "mc2_stderr": 0.015461253424328927 }, "harness|arc:challenge|25": { "acc": 0.6416382252559727, "acc_stderr": 0.014012883334859854, "acc_norm": 0.6791808873720137, "acc_norm_stderr": 0.01364094309194653 }, "harness|hellaswag|10": { "acc": 0.6630153355905198, "acc_stderr": 0.00471713572219417, "acc_norm": 0.8561043616809401, "acc_norm_stderr": 0.003502665674197166 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6888888888888889, "acc_stderr": 0.039992628766177214, "acc_norm": 0.6888888888888889, "acc_norm_stderr": 0.039992628766177214 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8421052631578947, "acc_stderr": 0.029674167520101456, "acc_norm": 0.8421052631578947, "acc_norm_stderr": 0.029674167520101456 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.78, "acc_stderr": 0.04163331998932262, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932262 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8113207547169812, "acc_stderr": 0.024079995130062253, "acc_norm": 0.8113207547169812, "acc_norm_stderr": 0.024079995130062253 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8611111111111112, "acc_stderr": 0.0289198029561349, "acc_norm": 0.8611111111111112, "acc_norm_stderr": 0.0289198029561349 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "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": 0.44, "acc_stderr": 0.0498887651569859, "acc_norm": 0.44, "acc_norm_stderr": 0.0498887651569859 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7341040462427746, "acc_stderr": 0.03368762932259432, "acc_norm": 0.7341040462427746, "acc_norm_stderr": 0.03368762932259432 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5294117647058824, "acc_stderr": 0.049665709039785295, "acc_norm": 0.5294117647058824, "acc_norm_stderr": 0.049665709039785295 }, "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": 0.7702127659574468, "acc_stderr": 0.02750175294441242, "acc_norm": 0.7702127659574468, "acc_norm_stderr": 0.02750175294441242 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6228070175438597, "acc_stderr": 0.04559522141958216, "acc_norm": 0.6228070175438597, "acc_norm_stderr": 0.04559522141958216 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7241379310344828, "acc_stderr": 0.037245636197746325, "acc_norm": 0.7241379310344828, "acc_norm_stderr": 0.037245636197746325 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6798941798941799, "acc_stderr": 0.024026846392873502, "acc_norm": 0.6798941798941799, "acc_norm_stderr": 0.024026846392873502 }, "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": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9, "acc_stderr": 0.017066403719657255, "acc_norm": 0.9, "acc_norm_stderr": 0.017066403719657255 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6699507389162561, "acc_stderr": 0.033085304262282574, "acc_norm": 0.6699507389162561, "acc_norm_stderr": 0.033085304262282574 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.76, "acc_stderr": 0.04292346959909282, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909282 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8424242424242424, "acc_stderr": 0.028450388805284336, "acc_norm": 0.8424242424242424, "acc_norm_stderr": 0.028450388805284336 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9191919191919192, "acc_stderr": 0.019417681889724536, "acc_norm": 0.9191919191919192, "acc_norm_stderr": 0.019417681889724536 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9637305699481865, "acc_stderr": 0.013492659751295153, "acc_norm": 0.9637305699481865, "acc_norm_stderr": 0.013492659751295153 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.782051282051282, "acc_stderr": 0.02093244577446319, "acc_norm": 0.782051282051282, "acc_norm_stderr": 0.02093244577446319 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3888888888888889, "acc_stderr": 0.029723278961476664, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.029723278961476664 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.8235294117647058, "acc_stderr": 0.02476290267805791, "acc_norm": 0.823
