open-llm-leaderboard-old/details_Weyaxi__Stellaris-internlm2-20b-r128

该数据集是在评估模型Weyaxi/Stellaris-internlm2-20b-r128时自动生成的，评估是在Open LLM Leaderboard上进行的。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，每次运行都可以在特定配置中找到，分割名称使用运行的时间戳。train分割始终指向最新结果。此外，results配置存储了所有运行的聚合结果，并用于计算和显示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 Weyaxi/Stellaris-internlm2-20b-r128 在 Open LLM Leaderboard 上的评估运行期间自动创建的。

数据集组成

• 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。
• 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 2024-01-22T02:02:49.417178 运行的最新结果：

python { "all": { "acc": 0.6473729518927601, "acc_stderr": 0.03165407821154855, "acc_norm": 0.6587026634697054, "acc_norm_stderr": 0.032520024648863555, "mc1": 0.3427172582619339, "mc1_stderr": 0.016614949385347032, "mc2": 0.5250446633100931, "mc2_stderr": 0.015325921720538403 }, "harness|arc:challenge|25": { "acc": 0.5767918088737202, "acc_stderr": 0.014438036220848029, "acc_norm": 0.6126279863481229, "acc_norm_stderr": 0.014235872487909869 }, "harness|hellaswag|10": { "acc": 0.6256721768571998, "acc_stderr": 0.004829598101635788, "acc_norm": 0.8174666401115316, "acc_norm_stderr": 0.0038549403270910537 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5777777777777777, "acc_stderr": 0.04266763404099582, "acc_norm": 0.5777777777777777, "acc_norm_stderr": 0.04266763404099582 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7697368421052632, "acc_stderr": 0.03426059424403165, "acc_norm": 0.7697368421052632, "acc_norm_stderr": 0.03426059424403165 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7283018867924528, "acc_stderr": 0.027377706624670713, "acc_norm": 0.7283018867924528, "acc_norm_stderr": 0.027377706624670713 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7986111111111112, "acc_stderr": 0.03353647469713839, "acc_norm": 0.7986111111111112, "acc_norm_stderr": 0.03353647469713839 }, "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": 0.56, "acc_stderr": 0.049888765156985884, "acc_norm": 0.56, "acc_norm_stderr": 0.049888765156985884 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6820809248554913, "acc_stderr": 0.0355068398916558, "acc_norm": 0.6820809248554913, "acc_norm_stderr": 0.0355068398916558 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.37254901960784315, "acc_stderr": 0.04810840148082635, "acc_norm": 0.37254901960784315, "acc_norm_stderr": 0.04810840148082635 }, "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": 0.6468085106382979, "acc_stderr": 0.031245325202761926, "acc_norm": 0.6468085106382979, "acc_norm_stderr": 0.031245325202761926 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.47368421052631576, "acc_stderr": 0.046970851366478626, "acc_norm": 0.47368421052631576, "acc_norm_stderr": 0.046970851366478626 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6, "acc_stderr": 0.040824829046386284, "acc_norm": 0.6, "acc_norm_stderr": 0.040824829046386284 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4497354497354497, "acc_stderr": 0.02562085704293665, "acc_norm": 0.4497354497354497, "acc_norm_stderr": 0.02562085704293665 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.46825396825396826, "acc_stderr": 0.04463112720677173, "acc_norm": 0.46825396825396826, "acc_norm_stderr": 0.04463112720677173 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8161290322580645, "acc_stderr": 0.022037217340267822, "acc_norm": 0.8161290322580645, "acc_norm_stderr": 0.022037217340267822 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5812807881773399, "acc_stderr": 0.034711928605184676, "acc_norm": 0.5812807881773399, "acc_norm_stderr": 0.034711928605184676 }, "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": 0.7878787878787878, "acc_stderr": 0.03192271569548302, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.03192271569548302 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8131313131313131, "acc_stderr": 0.02777253333421896, "acc_norm": 0.8131313131313131, "acc_norm_stderr": 0.02777253333421896 }, "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": 0.6692307692307692, "acc_stderr": 0.023854795680971114, "acc_norm": 0.6692307692307692, "acc_norm_stderr": 0.023854795680971114 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3, "acc_stderr": 0.02794045713622842, "acc_norm": 0.3, "acc_norm_stderr": 0.02794045713622842 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.7226890756302521, "acc_stderr": 0.029079374539480007, "acc_