open-llm-leaderboard-old/details_Intel__neural-chat-7b-v3-3

该数据集是在评估模型Intel/neural-chat-7b-v3-3时自动创建的，主要用于在Open LLM Leaderboard上进行评估。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次运行生成，每次运行的结果作为特定的分割存储在配置中，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，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

该数据集是在评估模型 Intel/neural-chat-7b-v3-3 在 Open LLM Leaderboard 上的运行过程中自动创建的。

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，每次运行可以在每个配置中找到特定的分片，分片名称使用运行的时间戳。
• "train" 分片始终指向最新的结果。
• 额外的 "results" 配置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_Intel__neural-chat-7b-v3-3", "harness_winogrande_5", split="train")

最新结果

以下是 2023-12-09T20:33:34.862293 运行 的最新结果：

python { "all": { "acc": 0.633718840288445, "acc_stderr": 0.03262856399270551, "acc_norm": 0.6351165946232198, "acc_norm_stderr": 0.03329008839330021, "mc1": 0.4700122399020808, "mc1_stderr": 0.017471992091697534, "mc2": 0.6301479198844473, "mc2_stderr": 0.015176409746133967 }, "harness|arc:challenge|25": { "acc": 0.6373720136518771, "acc_stderr": 0.014049106564955007, "acc_norm": 0.6689419795221843, "acc_norm_stderr": 0.013752062419817837 }, "harness|hellaswag|10": { "acc": 0.6617207727544314, "acc_stderr": 0.004721571443354415, "acc_norm": 0.8526190001991635, "acc_norm_stderr": 0.0035376085010691773 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6148148148148148, "acc_stderr": 0.0420392104015628, "acc_norm": 0.6148148148148148, "acc_norm_stderr": 0.0420392104015628 }, "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": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6679245283018868, "acc_stderr": 0.02898545565233439, "acc_norm": 0.6679245283018868, "acc_norm_stderr": 0.02898545565233439 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7291666666666666, "acc_stderr": 0.03716177437566017, "acc_norm": 0.7291666666666666, "acc_norm_stderr": 0.03716177437566017 }, "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": 0.54, "acc_stderr": 0.05009082659620333, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6473988439306358, "acc_stderr": 0.03643037168958546, "acc_norm": 0.6473988439306358, "acc_norm_stderr": 0.03643037168958546 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.46078431372549017, "acc_stderr": 0.04959859966384181, "acc_norm": 0.46078431372549017, "acc_norm_stderr": 0.04959859966384181 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.74, "acc_stderr": 0.044084400227680794, "acc_norm": 0.74, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5531914893617021, "acc_stderr": 0.032500536843658404, "acc_norm": 0.5531914893617021, "acc_norm_stderr": 0.032500536843658404 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4298245614035088, "acc_stderr": 0.04657047260594963, "acc_norm": 0.4298245614035088, "acc_norm_stderr": 0.04657047260594963 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5655172413793104, "acc_stderr": 0.04130740879555498, "acc_norm": 0.5655172413793104, "acc_norm_stderr": 0.04130740879555498 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3835978835978836, "acc_stderr": 0.025043757318520193, "acc_norm": 0.3835978835978836, "acc_norm_stderr": 0.025043757318520193 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4523809523809524, "acc_stderr": 0.044518079590553275, "acc_norm": 0.4523809523809524, "acc_norm_stderr": 0.044518079590553275 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7483870967741936, "acc_stderr": 0.02468597928623996, "acc_norm": 0.7483870967741936, "acc_norm_stderr": 0.02468597928623996 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.458128078817734, "acc_stderr": 0.03505630140785741, "acc_norm": 0.458128078817734, "acc_norm_stderr": 0.03505630140785741 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.68, "acc_stderr": 0.046882617226215034, "acc_norm": 0.68, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7636363636363637, "acc_stderr": 0.033175059300091826, "acc_norm": 0.7636363636363637, "acc_norm_stderr": 0.033175059300091826 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7878787878787878, "acc_stderr": 0.02912652283458682, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.02912652283458682 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8704663212435233, "acc_stderr": 0.02423353229775873, "acc_norm": 0.8704663212435233, "acc_norm_stderr": 0.02423353229775873 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6333333333333333, "acc_stderr": 0.02443301646605246, "acc_norm": 0.6333333333333333, "acc_norm_stderr": 0.02443301646605246 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3592592592592593, "acc_stderr": 0.029252905927251972, "acc_norm": 0.3592592592592593, "acc_norm_stderr": 0.