open-llm-leaderboard-old/details_S-miguel__The-Trinity-Coder-7B

该数据集是在Open LLM Leaderboard上对模型S-miguel/The-Trinity-Coder-7B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。train分割始终指向最新的结果。此外，还有一个名为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 S-miguel/The-Trinity-Coder-7B 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 "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 2024-03-23T10:17:41.109127 运行的最新结果：

python { "all": { "acc": 0.6534282218245622, "acc_stderr": 0.032087196236594055, "acc_norm": 0.6533558565004056, "acc_norm_stderr": 0.03275467258129072, "mc1": 0.42962056303549573, "mc1_stderr": 0.0173292345804091, "mc2": 0.6125265483406871, "mc2_stderr": 0.01534471270068822 }, "harness|arc:challenge|25": { "acc": 0.643344709897611, "acc_stderr": 0.013998056902620196, "acc_norm": 0.6936860068259386, "acc_norm_stderr": 0.013470584417276513 }, "harness|hellaswag|10": { "acc": 0.6715793666600279, "acc_stderr": 0.004686789042445371, "acc_norm": 0.8616809400517825, "acc_norm_stderr": 0.003445289925011736 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.38, "acc_stderr": 0.04878317312145632, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145632 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6666666666666666, "acc_stderr": 0.04072314811876837, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.04072314811876837 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7039473684210527, "acc_stderr": 0.03715062154998904, "acc_norm": 0.7039473684210527, "acc_norm_stderr": 0.03715062154998904 }, "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": 0.7283018867924528, "acc_stderr": 0.027377706624670713, "acc_norm": 0.7283018867924528, "acc_norm_stderr": 0.027377706624670713 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7708333333333334, "acc_stderr": 0.03514697467862388, "acc_norm": 0.7708333333333334, "acc_norm_stderr": 0.03514697467862388 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.630057803468208, "acc_stderr": 0.0368122963339432, "acc_norm": 0.630057803468208, "acc_norm_stderr": 0.0368122963339432 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4215686274509804, "acc_stderr": 0.04913595201274498, "acc_norm": 0.4215686274509804, "acc_norm_stderr": 0.04913595201274498 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.74, "acc_stderr": 0.04408440022768079, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768079 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5659574468085107, "acc_stderr": 0.03240038086792747, "acc_norm": 0.5659574468085107, "acc_norm_stderr": 0.03240038086792747 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.543859649122807, "acc_stderr": 0.046854730419077895, "acc_norm": 0.543859649122807, "acc_norm_stderr": 0.046854730419077895 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5862068965517241, "acc_stderr": 0.04104269211806232, "acc_norm": 0.5862068965517241, "acc_norm_stderr": 0.04104269211806232 }, "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": 0.46825396825396826, "acc_stderr": 0.04463112720677171, "acc_norm": 0.46825396825396826, "acc_norm_stderr": 0.04463112720677171 }, "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": 0.8064516129032258, "acc_stderr": 0.022475258525536057, "acc_norm": 0.8064516129032258, "acc_norm_stderr": 0.022475258525536057 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4827586206896552, "acc_stderr": 0.035158955511656986, "acc_norm": 0.4827586206896552, "acc_norm_stderr": 0.035158955511656986 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.66, "acc_stderr": 0.04760952285695237, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695237 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7636363636363637, "acc_stderr": 0.033175059300091805, "acc_norm": 0.7636363636363637, "acc_norm_stderr": 0.033175059300091805 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7878787878787878, "acc_stderr": 0.0291265228345868, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.0291265228345868 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8756476683937824, "acc_stderr": 0.023814477086593556, "acc_norm": 0.8756476683937824, "acc_norm_stderr": 0.023814477086593556 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6487179487179487, "acc_stderr": 0.024203665177902803, "acc_norm": 0.6487179487179487, "acc_norm_stderr": 0.024203665177902803 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.34444444444444444, "acc_stderr": 0.028972648884844267, "acc_norm": 0.34444444444444444, "acc_norm_stderr": 0.028972648884844267 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6932773109243697,