open-llm-leaderboard-old/details_vikash06__llama-2-7b-small-model-new

该数据集是在模型vikash06/llama-2-7b-small-model-new在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成，每个配置对应一个评估任务。数据集是从1次运行中创建的，每次运行在每个配置中作为一个特定的分割，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存储了运行的所有聚合结果，用于计算和显示Open LLM Leaderboard上的聚合指标。README还提供了如何使用Python代码加载运行中的详细信息的示例，并列出了特定运行的最新结果。

原始信息汇总

数据集概述

数据集摘要

该数据集是在对模型 vikash06/llama-2-7b-small-model-new 进行评估运行期间自动创建的。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，每次运行的详细信息可以在每个配置中找到，以运行的时间戳命名的特定分片形式存储。"train" 分片始终指向最新的结果。此外，一个额外的配置 "results" 存储了所有运行的聚合结果，用于计算和显示在 Open LLM Leaderboard 上的聚合指标。

最新结果

以下是来自 2023-12-23T17:13:47.425538 运行的最新结果：

python { "all": { "acc": 0.45995921713524485, "acc_stderr": 0.034705933213305985, "acc_norm": 0.46657860357627995, "acc_norm_stderr": 0.035509017738943494, "mc1": 0.2717258261933905, "mc1_stderr": 0.015572840452875833, "mc2": 0.42463864717462163, "mc2_stderr": 0.016089627327060634 }, "harness|arc:challenge|25": { "acc": 0.4308873720136519, "acc_stderr": 0.014471133392642459, "acc_norm": 0.4522184300341297, "acc_norm_stderr": 0.014544519880633823 }, "harness|hellaswag|10": { "acc": 0.5393347938657638, "acc_stderr": 0.004974316807920403, "acc_norm": 0.7234614618601872, "acc_norm_stderr": 0.004463721071319091 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.04688261722621503, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621503 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.45925925925925926, "acc_stderr": 0.04304979692464243, "acc_norm": 0.45925925925925926, "acc_norm_stderr": 0.04304979692464243 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.3684210526315789, "acc_stderr": 0.03925523381052932, "acc_norm": 0.3684210526315789, "acc_norm_stderr": 0.03925523381052932 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.49056603773584906, "acc_stderr": 0.030767394707808093, "acc_norm": 0.49056603773584906, "acc_norm_stderr": 0.030767394707808093 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4513888888888889, "acc_stderr": 0.04161402398403279, "acc_norm": 0.4513888888888889, "acc_norm_stderr": 0.04161402398403279 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "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": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.42196531791907516, "acc_stderr": 0.0376574669386515, "acc_norm": 0.42196531791907516, "acc_norm_stderr": 0.0376574669386515 }, "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": 0.51, "acc_stderr": 0.05024183937956913, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956913 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.42127659574468085, "acc_stderr": 0.03227834510146267, "acc_norm": 0.42127659574468085, "acc_norm_stderr": 0.03227834510146267 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.32456140350877194, "acc_stderr": 0.04404556157374768, "acc_norm": 0.32456140350877194, "acc_norm_stderr": 0.04404556157374768 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4827586206896552, "acc_stderr": 0.04164188720169377, "acc_norm": 0.4827586206896552, "acc_norm_stderr": 0.04164188720169377 }, "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": 0.30158730158730157, "acc_stderr": 0.04104947269903394, "acc_norm": 0.30158730158730157, "acc_norm_stderr": 0.04104947269903394 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5064516129032258, "acc_stderr": 0.02844163823354051, "acc_norm": 0.5064516129032258, "acc_norm_stderr": 0.02844163823354051 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3497536945812808, "acc_stderr": 0.03355400904969565, "acc_norm": 0.3497536945812808, "acc_norm_stderr": 0.03355400904969565 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5696969696969697, "acc_stderr": 0.03866225962879077, "acc_norm": 0.5696969696969697, "acc_norm_stderr": 0.03866225962879077 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5404040404040404, "acc_stderr": 0.035507024651313425, "acc_norm": 0.5404040404040404, "acc_norm_stderr": 0.035507024651313425 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.6787564766839378, "acc_stderr": 0.033699508685490674, "acc_norm": 0.6787564766839378, "acc_norm_stderr": 0.033699508685490674 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.43846153846153846, "acc_stderr": 0.02515826601686856, "acc_norm": 0.43846153846153846, "acc_norm_stderr": 0.02515826601686856 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2777777777777778, "acc_stderr": 0.027309140588230186, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.027309140588230186 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.4579831932773109, "acc_stderr": 0.03236361111951941, "acc_norm": 0.4579831932773109, "acc_norm_stderr": 0.03236361111951941 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.2847682119205298, "acc_stderr