open-llm-leaderboard-old/details_JCX-kcuf__Llama-2-7b-chat-hf-gpt-4-80k

该数据集是在Open LLM Leaderboard上对模型[JCX-kcuf/Llama-2-7b-chat-hf-gpt-4-80k]进行评估时自动创建的。数据集由63个配置组成，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命名。train分割始终指向最新的结果。此外，一个名为results的配置存储了所有运行的聚合结果，并用于计算和显示在Open LLM Leaderboard上的聚合指标。

原始信息汇总

数据集概述

数据集摘要

该数据集是在模型 JCX-kcuf/Llama-2-7b-chat-hf-gpt-4-80k 在 Open LLM Leaderboard 上的评估运行期间自动创建的。

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。
• 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

这些是最新的结果，来自 2024-03-24T16:38:02.853843 的运行。详细结果如下： python { "all": { "acc": 0.48794065821108334, "acc_stderr": 0.034336121936290494, "acc_norm": 0.4930534896524456, "acc_norm_stderr": 0.035095955994255836, "mc1": 0.32802937576499386, "mc1_stderr": 0.016435632932815032, "mc2": 0.48450117635749573, "mc2_stderr": 0.015286188446075932 }, "harness|arc:challenge|25": { "acc": 0.4991467576791809, "acc_stderr": 0.014611369529813272, "acc_norm": 0.5477815699658704, "acc_norm_stderr": 0.014544519880633825 }, "harness|hellaswag|10": { "acc": 0.5571599283011353, "acc_stderr": 0.004957068377516512, "acc_norm": 0.746265684126668, "acc_norm_stderr": 0.0043425802776627265 }, "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": 0.43703703703703706, "acc_stderr": 0.04284958639753399, "acc_norm": 0.43703703703703706, "acc_norm_stderr": 0.04284958639753399 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5, "acc_stderr": 0.04068942293855797, "acc_norm": 0.5, "acc_norm_stderr": 0.04068942293855797 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5245283018867924, "acc_stderr": 0.030735822206205608, "acc_norm": 0.5245283018867924, "acc_norm_stderr": 0.030735822206205608 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5138888888888888, "acc_stderr": 0.041795966175810016, "acc_norm": 0.5138888888888888, "acc_norm_stderr": 0.041795966175810016 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4161849710982659, "acc_stderr": 0.03758517775404947, "acc_norm": 0.4161849710982659, "acc_norm_stderr": 0.03758517775404947 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2549019607843137, "acc_stderr": 0.043364327079931785, "acc_norm": 0.2549019607843137, "acc_norm_stderr": 0.043364327079931785 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.59, "acc_stderr": 0.049431107042371025, "acc_norm": 0.59, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.40425531914893614, "acc_stderr": 0.03208115750788684, "acc_norm": 0.40425531914893614, "acc_norm_stderr": 0.03208115750788684 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3508771929824561, "acc_stderr": 0.04489539350270701, "acc_norm": 0.3508771929824561, "acc_norm_stderr": 0.04489539350270701 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5103448275862069, "acc_stderr": 0.04165774775728763, "acc_norm": 0.5103448275862069, "acc_norm_stderr": 0.04165774775728763 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.30423280423280424, "acc_stderr": 0.023695415009463087, "acc_norm": 0.30423280423280424, "acc_norm_stderr": 0.023695415009463087 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.23809523809523808, "acc_stderr": 0.03809523809523811, "acc_norm": 0.23809523809523808, "acc_norm_stderr": 0.03809523809523811 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5645161290322581, "acc_stderr": 0.02820622559150274, "acc_norm": 0.5645161290322581, "acc_norm_stderr": 0.02820622559150274 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3694581280788177, "acc_stderr": 0.03395970381998574, "acc_norm": 0.3694581280788177, "acc_norm_stderr": 0.03395970381998574 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.593939393939394, "acc_stderr": 0.03834816355401181, "acc_norm": 0.593939393939394, "acc_norm_stderr": 0.03834816355401181 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6414141414141414, "acc_stderr": 0.034169036403915214, "acc_norm": 0.6414141414141414, "acc_norm_stderr": 0.034169036403915214 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7253886010362695, "acc_stderr": 0.03221024508041153, "acc_norm": 0.7253886010362695, "acc_norm_stderr": 0.03221024508041153 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.45897435897435895, "acc_stderr": 0.025265525491284295, "acc_norm": 0.45897435897435895, "acc_norm_stderr": 0.025265525491284295 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2777777777777778, "acc_stderr": 0.027309140588230193, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.027309140588230193 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.4495798319327731, "acc_stderr": 0.03231293497137707, "acc_norm": 0.4495798319327731, "