open-llm-leaderboard-old/details_maywell__Synatra-7B-v0.3-dpo

该数据集是在模型maywell/Synatra-7B-v0.3-dpo在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由64个配置组成，每个配置对应一个评估任务。数据集包含1次运行的数据，每次运行在每个配置中表示为特定的分割。train分割始终指向最新的结果。此外，名为results的配置存储了所有运行的聚合结果，这些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Hugging Face datasets库加载数据集的示例。

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maywell/Synatra-7B-v0.3-dpo进行评估运行期间自动创建的，用于Open LLM Leaderboard。

数据集组成

• 数据集由64个配置组成，每个配置对应一个评估任务。
• 数据集来自1次运行，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2023-11-20T08:03:37.008028运行的最新结果：

python { "all": { "acc": 0.610854861666512, "acc_stderr": 0.03282789791741049, "acc_norm": 0.6184353715807913, "acc_norm_stderr": 0.03351856767139879, "mc1": 0.39657282741738065, "mc1_stderr": 0.017124930942023518, "mc2": 0.5646058699056372, "mc2_stderr": 0.015306312553856578, "em": 0.006711409395973154, "em_stderr": 0.0008361500895152437, "f1": 0.086758598993289, "f1_stderr": 0.0017937356641132749 }, "harness|arc:challenge|25": { "acc": 0.6006825938566553, "acc_stderr": 0.014312094557946709, "acc_norm": 0.6279863481228669, "acc_norm_stderr": 0.014124597881844461 }, "harness|hellaswag|10": { "acc": 0.6278629755028878, "acc_stderr": 0.004823867761332464, "acc_norm": 0.8258315076677952, "acc_norm_stderr": 0.0037847921724660665 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5925925925925926, "acc_stderr": 0.04244633238353228, "acc_norm": 0.5925925925925926, "acc_norm_stderr": 0.04244633238353228 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6578947368421053, "acc_stderr": 0.03860731599316092, "acc_norm": 0.6578947368421053, "acc_norm_stderr": 0.03860731599316092 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.59, "acc_stderr": 0.049431107042371025, "acc_norm": 0.59, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.660377358490566, "acc_stderr": 0.02914690474779833, "acc_norm": 0.660377358490566, "acc_norm_stderr": 0.02914690474779833 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6875, "acc_stderr": 0.038760854559127644, "acc_norm": 0.6875, "acc_norm_stderr": 0.038760854559127644 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.32, "acc_stderr": 0.04688261722621505, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5953757225433526, "acc_stderr": 0.03742461193887248, "acc_norm": 0.5953757225433526, "acc_norm_stderr": 0.03742461193887248 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.28431372549019607, "acc_stderr": 0.04488482852329017, "acc_norm": 0.28431372549019607, "acc_norm_stderr": 0.04488482852329017 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5404255319148936, "acc_stderr": 0.03257901482099835, "acc_norm": 0.5404255319148936, "acc_norm_stderr": 0.03257901482099835 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4473684210526316, "acc_stderr": 0.04677473004491199, "acc_norm": 0.4473684210526316, "acc_norm_stderr": 0.04677473004491199 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5655172413793104, "acc_stderr": 0.041307408795554966, "acc_norm": 0.5655172413793104, "acc_norm_stderr": 0.041307408795554966 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42328042328042326, "acc_stderr": 0.02544636563440678, "acc_norm": 0.42328042328042326, "acc_norm_stderr": 0.02544636563440678 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3888888888888889, "acc_stderr": 0.04360314860077459, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.04360314860077459 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7451612903225806, "acc_stderr": 0.024790118459332208, "acc_norm": 0.7451612903225806, "acc_norm_stderr": 0.024790118459332208 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4729064039408867, "acc_stderr": 0.03512819077876106, "acc_norm": 0.4729064039408867, "acc_norm_stderr": 0.03512819077876106 }, "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": 0.7818181818181819, "acc_stderr": 0.03225078108306289, "acc_norm": 0.7818181818181819, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7929292929292929, "acc_stderr": 0.02886977846026704, "acc_norm": 0.7929292929292929, "acc_norm_stderr": 0.02886977846026704 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8393782383419689, "acc_stderr": 0.026499057701397443, "acc_norm": 0.8393782383419689, "acc_norm_stderr": 0.026499057701397443 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6076923076923076, "acc_stderr": 0.024756000382130952, "acc_norm": 0.6076923076923076, "acc_norm_stderr": 0.024756000382130952 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2814814814814815, "acc_stderr": 0.02742001935094527, "acc_norm": 0.2814814