five

open-llm-leaderboard/details_ajibawa-2023__WikiHow-Mistral-Instruct-7B

收藏
Hugging Face2024-03-27 更新2024-06-11 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_ajibawa-2023__WikiHow-Mistral-Instruct-7B
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在模型 ajibawa-2023/WikiHow-Mistral-Instruct-7B 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,每个配置对应一个评估任务。它包含来自 1 次运行的数据,每次运行在每个配置中表示为特定的拆分,使用运行的时间戳命名。train 拆分始终指向最新结果。一个名为 results 的额外配置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。README 还提供了如何使用 Python 中的 datasets 库加载运行中的详细信息的示例。

该数据集是在模型 ajibawa-2023/WikiHow-Mistral-Instruct-7B 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,每个配置对应一个评估任务。它包含来自 1 次运行的数据,每次运行在每个配置中表示为特定的拆分,使用运行的时间戳命名。train 拆分始终指向最新结果。一个名为 results 的额外配置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。README 还提供了如何使用 Python 中的 datasets 库加载运行中的详细信息的示例。
提供机构:
open-llm-leaderboard
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 ajibawa-2023/WikiHow-Mistral-Instruct-7BOpen LLM Leaderboard 上的自动创建的。数据集包含 63 个配置,每个配置对应一个评估任务。

数据集结构

数据集由 1 次运行创建,每次运行可以在每个配置中找到特定的分割,分割名称使用运行的时间戳。"train" 分割始终指向最新的结果。

额外配置

一个额外的配置 "results" 存储了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_ajibawa-2023__WikiHow-Mistral-Instruct-7B", "harness_winogrande_5", split="train")

最新结果

以下是 最新结果 的摘要:

python { "all": { "acc": 0.5839934762085257, "acc_stderr": 0.03351842092706338, "acc_norm": 0.5899437387341447, "acc_norm_stderr": 0.03421478494471268, "mc1": 0.4467564259485924, "mc1_stderr": 0.017403977522557144, "mc2": 0.6216363503197562, "mc2_stderr": 0.015598061017739119 }, "harness|arc:challenge|25": { "acc": 0.5776450511945392, "acc_stderr": 0.014434138713379988, "acc_norm": 0.6092150170648464, "acc_norm_stderr": 0.01425856388051378 }, "harness|hellaswag|10": { "acc": 0.6099382593108943, "acc_stderr": 0.004867670042866695, "acc_norm": 0.8098984266082454, "acc_norm_stderr": 0.003915792315457788 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, # 其他任务的结果... }

配置详情

  • config_name: harness_arc_challenge_25

    • split: 2024_03_27T17_47_31.561196
      • path: **/details_harness|arc:challenge|25_2024-03-27T17-47-31.561196.parquet
    • split: latest
      • path: **/details_harness|arc:challenge|25_2024-03-27T17-47-31.561196.parquet
  • config_name: harness_gsm8k_5

    • split: 2024_03_27T17_47_31.561196
      • path: **/details_harness|gsm8k|5_2024-03-27T17-47-31.561196.parquet
    • split: latest
      • path: **/details_harness|gsm8k|5_2024-03-27T17-47-31.561196.parquet
  • config_name: harness_hellaswag_10

    • split: 2024_03_27T17_47_31.561196
      • path: **/details_harness|hellaswag|10_2024-03-27T17-47-31.561196.parquet
    • split: latest
      • path: **/details_harness|hellaswag|10_2024-03-27T17-47-31.561196.parquet
  • config_name: harness_hendrycksTest_5

    • split: 2024_03_27T17_47_31.561196
      • path: **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-anatomy|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-astronomy|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-business_ethics|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-college_biology|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-college_chemistry|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-college_computer_science|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-college_mathematics|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-college_medicine|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-college_physics|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-computer_security|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-econometrics|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-formal_logic|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-global_facts|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-high_school_biology|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-high_school_computer_science|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-high_school_european_history|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-high_school_geography|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-high_school_mathematics|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-high_school_physics|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-high_school_psychology|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-high_school_statistics|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-high_school_us_history|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-high_school_world_history|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-human_aging|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-human_sexuality|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-international_law|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-jurisprudence|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-logical_fallacies|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-machine_learning|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-management|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-marketing|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-medical_genetics|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-miscellaneous|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-moral_disputes|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-moral_scenarios|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-nutrition|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-philosophy|5_2024-03-27T17-47-31.561196.parquet
      • path: **/details_harness|hendrycksTest-prehistory|5_2024-03-27T17-47-31.561196.parquet
      • path: `**/
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作