open-llm-leaderboard-old/details_OpenBuddy__openbuddy-deepseek-67b-v15-base

该数据集是在Open LLM Leaderboard上对模型OpenBuddy/openbuddy-deepseek-67b-v15-base进行评估时自动创建的。数据集包含63个配置，每个配置对应一个评估任务。数据集由1次运行创建，每次运行的结果存储为特定配置中的一个分割，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 OpenBuddy/openbuddy-deepseek-67b-v15-base 的评估运行期间自动创建的，用于 Open LLM Leaderboard。

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。
• 数据集来自 1 次运行，每次运行在每个配置中都有一个特定的分割，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。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_OpenBuddy__openbuddy-deepseek-67b-v15-base", "harness_winogrande_5", split="train")

最新结果

以下是 2023-12-10T00:18:57.450795 运行的最新结果：

python { "all": { "acc": 0.7077078977933982, "acc_stderr": 0.030015760444243065, "acc_norm": 0.7114942838020437, "acc_norm_stderr": 0.030600759357365358, "mc1": 0.3671970624235006, "mc1_stderr": 0.016874805001453178, "mc2": 0.5230963516759597, "mc2_stderr": 0.014845955802002899 }, "harness|arc:challenge|25": { "acc": 0.6356655290102389, "acc_stderr": 0.014063260279882419, "acc_norm": 0.6629692832764505, "acc_norm_stderr": 0.013813476652902276 }, "harness|hellaswag|10": { "acc": 0.6751643098984266, "acc_stderr": 0.004673563250946104, "acc_norm": 0.8602867954590719, "acc_norm_stderr": 0.003459806991389836 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.04605661864718381, "acc_norm": 0.3, "acc_norm_stderr": 0.04605661864718381 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.674074074074074, "acc_stderr": 0.040491220417025055, "acc_norm": 0.674074074074074, "acc_norm_stderr": 0.040491220417025055 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8157894736842105, "acc_stderr": 0.0315469804508223, "acc_norm": 0.8157894736842105, "acc_norm_stderr": 0.0315469804508223 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.78, "acc_stderr": 0.04163331998932261, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932261 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7962264150943397, "acc_stderr": 0.024790784501775406, "acc_norm": 0.7962264150943397, "acc_norm_stderr": 0.024790784501775406 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8541666666666666, "acc_stderr": 0.029514245964291762, "acc_norm": 0.8541666666666666, "acc_norm_stderr": 0.029514245964291762 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6936416184971098, "acc_stderr": 0.035149425512674394, "acc_norm": 0.6936416184971098, "acc_norm_stderr": 0.035149425512674394 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.39215686274509803, "acc_stderr": 0.04858083574266345, "acc_norm": 0.39215686274509803, "acc_norm_stderr": 0.04858083574266345 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.76, "acc_stderr": 0.04292346959909283, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7021276595744681, "acc_stderr": 0.02989614568209546, "acc_norm": 0.7021276595744681, "acc_norm_stderr": 0.02989614568209546 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5350877192982456, "acc_stderr": 0.046920083813689104, "acc_norm": 0.5350877192982456, "acc_norm_stderr": 0.046920083813689104 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6896551724137931, "acc_stderr": 0.03855289616378949, "acc_norm": 0.6896551724137931, "acc_norm_stderr": 0.03855289616378949 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.5317460317460317, "acc_stderr": 0.025699352832131792, "acc_norm": 0.5317460317460317, "acc_norm_stderr": 0.025699352832131792 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5079365079365079, "acc_stderr": 0.044715725362943486, "acc_norm": 0.5079365079365079, "acc_norm_stderr": 0.044715725362943486 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8290322580645161, "acc_stderr": 0.02141724293632159, "acc_norm": 0.8290322580645161, "acc_norm_stderr": 0.02141724293632159 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5665024630541872, "acc_stderr": 0.034867317274198714, "acc_norm": 0.5665024630541872, "acc_norm_stderr": 0.034867317274198714 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8242424242424242, "acc_stderr": 0.02972094300622445, "acc_norm": 0.8242424242424242, "acc_norm_stderr": 0.02972094300622445 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9090909090909091, "acc_stderr": 0.020482086775424208, "acc_norm": 0.9090909090909091, "acc_norm_stderr": 0.020482086775424208 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9481865284974094, "acc_stderr": 0.01599622932024412, "acc_norm": 0.9481865284974094, "acc_norm_stderr": 0.01599622932024412 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7076923076923077, "acc_stderr": 0.02306043838085774, "acc_norm": 0.7076923076923077, "acc_norm_stderr": 0.02306043838085774 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4, "acc_stderr": 0.029869605095316908, "acc_norm": 0.4, "acc_norm_stderr": 0.029869605095316908 }, "harness|hend