open-llm-leaderboard-old/details_OpenBuddy__openbuddy-deepseek-67b-v15.3-4k

该数据集是在Open LLM Leaderboard上对模型OpenBuddy/openbuddy-deepseek-67b-v15.3-4k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。数据集从1次运行中生成，每次运行可以在每个配置中找到，分割以运行的时间戳命名。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，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

数据集简介

该数据集是在模型OpenBuddy/openbuddy-deepseek-67b-v15.3-4k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。
• 数据集由1次运行创建，每次运行的详细结果可以在每个配置中找到，以运行的时间戳命名的特定分割形式存储。
• "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，用于计算和显示在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-v15.3-4k", "harness_winogrande_5", split="train")

最新结果

以下是2024-02-09T22:49:01.759420运行的最新结果：

python { "all": { "acc": 0.7037037887005099, "acc_stderr": 0.030360436222896765, "acc_norm": 0.705791859309744, "acc_norm_stderr": 0.03096775478949484, "mc1": 0.39167686658506734, "mc1_stderr": 0.01708779588176963, "mc2": 0.5487991903265673, "mc2_stderr": 0.0154115507137422 }, "harness|arc:challenge|25": { "acc": 0.64419795221843, "acc_stderr": 0.01399057113791876, "acc_norm": 0.6757679180887372, "acc_norm_stderr": 0.013678810399518822 }, "harness|hellaswag|10": { "acc": 0.6621190997809201, "acc_stderr": 0.004720210816162063, "acc_norm": 0.8515236008763195, "acc_norm_stderr": 0.0035484490542860114 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "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": 0.75, "acc_stderr": 0.03523807393012047, "acc_norm": 0.75, "acc_norm_stderr": 0.03523807393012047 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.8, "acc_stderr": 0.040201512610368445, "acc_norm": 0.8, "acc_norm_stderr": 0.040201512610368445 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7735849056603774, "acc_stderr": 0.025757559893106748, "acc_norm": 0.7735849056603774, "acc_norm_stderr": 0.025757559893106748 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8402777777777778, "acc_stderr": 0.030635578972093278, "acc_norm": 0.8402777777777778, "acc_norm_stderr": 0.030635578972093278 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6705202312138728, "acc_stderr": 0.03583901754736412, "acc_norm": 0.6705202312138728, "acc_norm_stderr": 0.03583901754736412 }, "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": 0.77, "acc_stderr": 0.04229525846816506, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6595744680851063, "acc_stderr": 0.030976692998534422, "acc_norm": 0.6595744680851063, "acc_norm_stderr": 0.030976692998534422 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5175438596491229, "acc_stderr": 0.04700708033551038, "acc_norm": 0.5175438596491229, "acc_norm_stderr": 0.04700708033551038 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6689655172413793, "acc_stderr": 0.03921545312467122, "acc_norm": 0.6689655172413793, "acc_norm_stderr": 0.03921545312467122 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.5476190476190477, "acc_stderr": 0.025634258115554955, "acc_norm": 0.5476190476190477, "acc_norm_stderr": 0.025634258115554955 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5, "acc_stderr": 0.04472135954999579, "acc_norm": 0.5, "acc_norm_stderr": 0.04472135954999579 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8258064516129032, "acc_stderr": 0.021576248184514573, "acc_norm": 0.8258064516129032, "acc_norm_stderr": 0.021576248184514573 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5862068965517241, "acc_stderr": 0.03465304488406795, "acc_norm": 0.5862068965517241, "acc_norm_stderr": 0.03465304488406795 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.78, "acc_stderr": 0.04163331998932261, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932261 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8303030303030303, "acc_stderr": 0.029311188674983134, "acc_norm": 0.8303030303030303, "acc_norm_stderr": 0.029311188674983134 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8939393939393939, "acc_stderr": 0.021938047738853106, "acc_norm": 0.8939393939393939, "acc_norm_stderr": 0.021938047738853106 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9430051813471503, "acc_stderr": 0.01673108529360756, "acc_norm": 0.9430051813471503, "acc_norm_stderr": 0.01673108529360756 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6948717948717948, "acc_stderr": 0.023346335293325884, "acc_norm": 0.6948717948717948, "acc_norm_stderr": 0.023346335293325884 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3592592592592593, "acc_stderr": 0.029252905927251976, "acc_norm": 0.3592592592592593, "acc_norm_stderr": 0.029252905927251976 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.827731