open-llm-leaderboard-old/details_mvpmaster__pmmpk-EinstainMorcoro14KrishnaHercules-7b-slerp

该数据集是在评估模型mvpmaster/pmmpk-EinstainMorcoro14KrishnaHercules-7b-slerp时自动生成的，包含63个配置，每个配置对应一个评估任务。数据集由1次运行生成，每次运行的结果存储为特定的分割，分割名称使用运行的时间戳。train分割始终指向最新的结果。此外，results配置存储了所有运行的聚合结果，用于计算和展示在Open LLM Leaderboard上的聚合指标。

原始信息汇总

数据集概述

该数据集是在对模型 mvpmaster/pmmpk-EinstainMorcoro14KrishnaHercules-7b-slerp 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。

数据集组成

• 该数据集包含 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，每次运行的详细结果可以在每个配置中找到，以运行的时间戳命名的特定分割形式存储。
• 每个配置中的 "train" 分割始终指向最新的结果。
• 一个额外的配置 "results" 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 2024-03-21T21:07:02.623911 运行的最新结果：

python { "all": { "acc": 0.6555154124082347, "acc_stderr": 0.031953975895505166, "acc_norm": 0.6556857924606263, "acc_norm_stderr": 0.0326111399873225, "mc1": 0.4565483476132191, "mc1_stderr": 0.01743728095318369, "mc2": 0.6269217532109524, "mc2_stderr": 0.015229668754636253 }, "harness|arc:challenge|25": { "acc": 0.6578498293515358, "acc_stderr": 0.013864152159177275, "acc_norm": 0.6928327645051194, "acc_norm_stderr": 0.013481034054980941 }, "harness|hellaswag|10": { "acc": 0.6786496713802032, "acc_stderr": 0.004660405565338758, "acc_norm": 0.8658633738299144, "acc_norm_stderr": 0.00340102551787373 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6074074074074074, "acc_stderr": 0.04218506215368881, "acc_norm": 0.6074074074074074, "acc_norm_stderr": 0.04218506215368881 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7368421052631579, "acc_stderr": 0.03583496176361073, "acc_norm": 0.7368421052631579, "acc_norm_stderr": 0.03583496176361073 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.63, "acc_stderr": 0.04852365870939099, "acc_norm": 0.63, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7132075471698113, "acc_stderr": 0.027834912527544067, "acc_norm": 0.7132075471698113, "acc_norm_stderr": 0.027834912527544067 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7361111111111112, "acc_stderr": 0.03685651095897532, "acc_norm": 0.7361111111111112, "acc_norm_stderr": 0.03685651095897532 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.54, "acc_stderr": 0.05009082659620333, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6705202312138728, "acc_stderr": 0.03583901754736412, "acc_norm": 0.6705202312138728, "acc_norm_stderr": 0.03583901754736412 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.45098039215686275, "acc_stderr": 0.04951218252396262, "acc_norm": 0.45098039215686275, "acc_norm_stderr": 0.04951218252396262 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.79, "acc_stderr": 0.04093601807403326, "acc_norm": 0.79, "acc_norm_stderr": 0.04093601807403326 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6042553191489362, "acc_stderr": 0.031967586978353627, "acc_norm": 0.6042553191489362, "acc_norm_stderr": 0.031967586978353627 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.49122807017543857, "acc_stderr": 0.04702880432049615, "acc_norm": 0.49122807017543857, "acc_norm_stderr": 0.04702880432049615 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5724137931034483, "acc_stderr": 0.04122737111370332, "acc_norm": 0.5724137931034483, "acc_norm_stderr": 0.04122737111370332 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.41005291005291006, "acc_stderr": 0.02533120243894444, "acc_norm": 0.41005291005291006, "acc_norm_stderr": 0.02533120243894444 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4523809523809524, "acc_stderr": 0.044518079590553275, "acc_norm": 0.4523809523809524, "acc_norm_stderr": 0.044518079590553275 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.38, "acc_stderr": 0.04878317312145633, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7870967741935484, "acc_stderr": 0.023287665127268545, "acc_norm": 0.7870967741935484, "acc_norm_stderr": 0.023287665127268545 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.47783251231527096, "acc_stderr": 0.035145285621750094, "acc_norm": 0.47783251231527096, "acc_norm_stderr": 0.035145285621750094 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8, "acc_stderr": 0.031234752377721175, "acc_norm": 0.8, "acc_norm_stderr": 0.031234752377721175 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.797979797979798, "acc_stderr": 0.028606204289229872, "acc_norm": 0.797979797979798, "acc_norm_stderr": 0.028606204289229872 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8860103626943006, "acc_stderr": 0.022935144053919436, "acc_norm": 0.8860103626943006, "acc_norm_stderr": 0.022935144053919436 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6666666666666666, "acc_stderr": 0.023901157979402534, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.023901157979402534 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.337037037037037, "acc_stderr": 0.02882088466625326, "acc_norm": 0.337037037037037, "acc_norm_stderr": 0.02882088466625326 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.680672268907563, "acc_stderr": 0.0302839955258