open-llm-leaderboard-old/details_jisukim8873__falcon-7B-case-0

该数据集是在模型 jisukim8873/falcon-7B-case-0 在 Open LLM Leaderboard 上的评估运行期间自动创建的。数据集由 63 个配置组成，每个配置对应一个被评估的任务。它包含 1 次运行的结果，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。一个名为 results 的额外配置存储了运行的所有聚合结果，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 Python 中的 datasets 库加载运行细节的示例。

原始信息汇总

数据集概述

数据集简介

该数据集是在评估模型 jisukim8873/falcon-7B-case-0 在 Open LLM Leaderboard 上的自动创建的。

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，每个运行在每个配置中作为一个特定的分割存在，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_jisukim8873__falcon-7B-case-0", "harness_winogrande_5", split="train")

最新结果

这些是最新的结果，来自运行 2024-02-29T15:48:27.299750： python { "all": { "acc": 0.30022094167540725, "acc_stderr": 0.032067143737355745, "acc_norm": 0.3007172075179623, "acc_norm_stderr": 0.03280148602944142, "mc1": 0.24724602203182375, "mc1_stderr": 0.01510240479735965, "mc2": 0.3617782578587819, "mc2_stderr": 0.014303952786254175 }, "harness|arc:challenge|25": { "acc": 0.45051194539249145, "acc_stderr": 0.014539646098471627, "acc_norm": 0.49146757679180886, "acc_norm_stderr": 0.014609263165632186 }, "harness|hellaswag|10": { "acc": 0.5967934674367655, "acc_stderr": 0.004895390341445623, "acc_norm": 0.782513443537144, "acc_norm_stderr": 0.004116931383157345 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.04688261722621504, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.3851851851851852, "acc_stderr": 0.042039210401562783, "acc_norm": 0.3851851851851852, "acc_norm_stderr": 0.042039210401562783 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.23026315789473684, "acc_stderr": 0.03426059424403165, "acc_norm": 0.23026315789473684, "acc_norm_stderr": 0.03426059424403165 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2943396226415094, "acc_stderr": 0.028049186315695245, "acc_norm": 0.2943396226415094, "acc_norm_stderr": 0.028049186315695245 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2777777777777778, "acc_stderr": 0.037455547914624576, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.037455547914624576 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.17, "acc_stderr": 0.0377525168068637, "acc_norm": 0.17, "acc_norm_stderr": 0.0377525168068637 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.23121387283236994, "acc_stderr": 0.0321473730202947, "acc_norm": 0.23121387283236994, "acc_norm_stderr": 0.0321473730202947 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.17647058823529413, "acc_stderr": 0.03793281185307809, "acc_norm": 0.17647058823529413, "acc_norm_stderr": 0.03793281185307809 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3446808510638298, "acc_stderr": 0.03106898596312215, "acc_norm": 0.3446808510638298, "acc_norm_stderr": 0.03106898596312215 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3508771929824561, "acc_stderr": 0.044895393502706986, "acc_norm": 0.3508771929824561, "acc_norm_stderr": 0.044895393502706986 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2689655172413793, "acc_stderr": 0.036951833116502325, "acc_norm": 0.2689655172413793, "acc_norm_stderr": 0.036951833116502325 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25925925925925924, "acc_stderr": 0.02256989707491842, "acc_norm": 0.25925925925925924, "acc_norm_stderr": 0.02256989707491842 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.16666666666666666, "acc_stderr": 0.033333333333333375, "acc_norm": 0.16666666666666666, "acc_norm_stderr": 0.033333333333333375 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.27, "acc_stderr": 0.0446196043338474, "acc_norm": 0.27, "acc_norm_stderr": 0.0446196043338474 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3258064516129032, "acc_stderr": 0.0266620105785671, "acc_norm": 0.3258064516129032, "acc_norm_stderr": 0.0266620105785671 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.28078817733990147, "acc_stderr": 0.03161856335358609, "acc_norm": 0.28078817733990147, "acc_norm_stderr": 0.03161856335358609 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.28, "acc_stderr": 0.045126085985421276, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421276 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.3515151515151515, "acc_stderr": 0.037282069986826503, "acc_norm": 0.3515151515151515, "acc_norm_stderr": 0.037282069986826503 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.2727272727272727, "acc_stderr": 0.03173071239071724, "acc_norm": 0.2727272727272727, "acc_norm_stderr": 0.03173071239071724 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.25906735751295334, "acc_stderr": 0.03161877917935411, "acc_norm": 0.25906735751295334, "acc_norm_stderr": 0.03161877917935411 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2282051282051282, "acc_stderr": 0.02127839386358628, "acc_norm": 0.2282051282051282, "acc_norm_stderr": 0.02127839386358628 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24444444444444444, "acc_stderr": 0.02620276653465215, "acc_norm": 0.24444444444444444, "acc_norm_stderr": 0.02620276653465215 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc":