open-llm-leaderboard-old/details_Aratako__c4ai-command-r-v01-japanese-instruct

该数据集是在Open LLM Leaderboard上对模型Aratako/c4ai-command-r-v01-japanese-instruct进行评估时自动创建的。它由63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，每次运行在每个配置中表示为特定的分割，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。可以使用Python中的datasets库加载该数据集，如提供的代码片段所示。

原始信息汇总

数据集概述

数据集简介

该数据集是在模型Aratako/c4ai-command-r-v01-japanese-instruct的评估运行期间自动创建的，用于Open LLM Leaderboard。

数据集结构

• 配置数量：63个配置，每个配置对应一个评估任务。
• 运行次数：数据集来自1次运行。每个运行结果作为一个特定的分割存储在每个配置中，分割名称使用运行的时间戳。
• 训练分割："train"分割始终指向最新的结果。
• 结果配置：一个额外的"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。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Aratako__c4ai-command-r-v01-japanese-instruct", "harness_winogrande_5", split="train")

最新结果

以下是2024-04-06T15:26:41.930065运行的最新结果：

python { "all": { "acc": 0.6762099088456663, "acc_stderr": 0.031218722032505204, "acc_norm": 0.6788659428254314, "acc_norm_stderr": 0.031843003332528694, "mc1": 0.3463892288861689, "mc1_stderr": 0.01665699710912514, "mc2": 0.5100708052144302, "mc2_stderr": 0.014817034256109527 }, "harness|arc:challenge|25": { "acc": 0.6220136518771331, "acc_stderr": 0.014169664520303098, "acc_norm": 0.658703071672355, "acc_norm_stderr": 0.013855831287497724 }, "harness|hellaswag|10": { "acc": 0.6586337382991436, "acc_stderr": 0.004731989816563666, "acc_norm": 0.8562039434375622, "acc_norm_stderr": 0.003501657107386699 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6, "acc_stderr": 0.04232073695151589, "acc_norm": 0.6, "acc_norm_stderr": 0.04232073695151589 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7368421052631579, "acc_stderr": 0.03583496176361073, "acc_norm": 0.7368421052631579, "acc_norm_stderr": 0.03583496176361073 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.72, "acc_stderr": 0.04512608598542127, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7245283018867924, "acc_stderr": 0.027495663683724057, "acc_norm": 0.7245283018867924, "acc_norm_stderr": 0.027495663683724057 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7847222222222222, "acc_stderr": 0.03437079344106135, "acc_norm": 0.7847222222222222, "acc_norm_stderr": 0.03437079344106135 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.49, "acc_stderr": 0.05024183937956911, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6647398843930635, "acc_stderr": 0.03599586301247078, "acc_norm": 0.6647398843930635, "acc_norm_stderr": 0.03599586301247078 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4411764705882353, "acc_stderr": 0.049406356306056595, "acc_norm": 0.4411764705882353, "acc_norm_stderr": 0.049406356306056595 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.78, "acc_stderr": 0.04163331998932262, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932262 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5787234042553191, "acc_stderr": 0.03227834510146268, "acc_norm": 0.5787234042553191, "acc_norm_stderr": 0.03227834510146268 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5, "acc_stderr": 0.047036043419179864, "acc_norm": 0.5, "acc_norm_stderr": 0.047036043419179864 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5793103448275863, "acc_stderr": 0.0411391498118926, "acc_norm": 0.5793103448275863, "acc_norm_stderr": 0.0411391498118926 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.47619047619047616, "acc_stderr": 0.025722097064388518, "acc_norm": 0.47619047619047616, "acc_norm_stderr": 0.025722097064388518 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4444444444444444, "acc_stderr": 0.04444444444444449, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.04444444444444449 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7741935483870968, "acc_stderr": 0.023785577884181012, "acc_norm": 0.7741935483870968, "acc_norm_stderr": 0.023785577884181012 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5172413793103449, "acc_stderr": 0.035158955511656986, "acc_norm": 0.5172413793103449, "acc_norm_stderr": 0.035158955511656986 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.76, "acc_stderr": 0.04292346959909282, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909282 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.806060606060606, "acc_stderr": 0.030874145136562076, "acc_norm": 0.806060606060606, "acc_norm_stderr": 0.030874145136562076 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8383838383838383, "acc_stderr": 0.026225919863629293, "acc_norm": 0.8383838383838383, "acc_norm_stderr": 0.026225919863629293 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9119170984455959, "acc_stderr": 0.02045374660160103, "acc_norm": 0.9119170984455959, "acc_norm_stderr": 0.02045374660160103 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6564102564102564, "acc_stderr": 0.02407869658063547, "acc_norm": 0.6564102564102564, "acc_norm_stderr": 0.02407869658063547 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.35555555555555557, "acc_stderr": 0.02918571494985739, "acc_norm": 0.35555555555555557, "acc_norm_stderr": 0.02918571494985739 }, "harness|

搜集汇总

背景与挑战

背景概述

该数据集是Open LLM Leaderboard上对模型Aratako/c4ai-command-r-v01-japanese-instruct进行评估时自动生成的，包含63个评估任务配置和1次运行结果，用于计算和显示聚合指标。