five

open-llm-leaderboard-old/details_0-hero__Matter-0.1-Slim-7B-A

收藏
Hugging Face2024-03-14 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_0-hero__Matter-0.1-Slim-7B-A
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0-hero/Matter-0.1-Slim-7B-A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。它由1次运行创建,每次运行作为每个配置中的一个特定拆分,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。README还提供了如何使用Python中的datasets库加载运行细节的示例。

该数据集是在模型0-hero/Matter-0.1-Slim-7B-A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。它由1次运行创建,每次运行作为每个配置中的一个特定拆分,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。README还提供了如何使用Python中的datasets库加载运行细节的示例。
提供机构:
open-llm-leaderboard-old
原始信息汇总

数据集概述

数据集信息

  • 名称: Evaluation run of 0-hero/Matter-0.1-Slim-7B-A
  • 来源: 自动创建于模型 0-hero/Matter-0.1-Slim-7B-AOpen LLM Leaderboard 的评估运行中。
  • 组成: 包含 63 个配置,每个配置对应一个评估任务。
  • 创建: 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,分割名称使用运行的时间戳。"train" 分割始终指向最新结果。
  • 额外配置: "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_0-hero__Matter-0.1-Slim-7B-A", "harness_winogrande_5", split="train")

最新结果

  • 时间戳: 2024-03-14T10:52:28.159269
  • 详细结果: python { "all": { "acc": 0.605490033884534, "acc_stderr": 0.03326571312658935, "acc_norm": 0.6102815752899539, "acc_norm_stderr": 0.0339481142869132, "mc1": 0.2778457772337821, "mc1_stderr": 0.015680929364024647, "mc2": 0.4178982620141241, "mc2_stderr": 0.014144240439100468 }, "harness|arc:challenge|25": { "acc": 0.5733788395904437, "acc_stderr": 0.014453185592920293, "acc_norm": 0.6049488054607508, "acc_norm_stderr": 0.014285898292938169 }, "harness|hellaswag|10": { "acc": 0.6183031268671579, "acc_stderr": 0.004848099661619697, "acc_norm": 0.8132842063333997, "acc_norm_stderr": 0.003888868099629071 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, # 其他任务的结果... }

配置信息

  • 配置名称: harness_arc_challenge_25

    • 分割: 2024_03_14T10_52_28.159269
      • 路径: **/details_harness|arc:challenge|25_2024-03-14T10-52-28.159269.parquet
    • 分割: latest
      • 路径: **/details_harness|arc:challenge|25_2024-03-14T10-52-28.159269.parquet
  • 配置名称: harness_gsm8k_5

    • 分割: 2024_03_14T10_52_28.159269
      • 路径: **/details_harness|gsm8k|5_2024-03-14T10-52-28.159269.parquet
    • 分割: latest
      • 路径: **/details_harness|gsm8k|5_2024-03-14T10-52-28.159269.parquet
  • 配置名称: harness_hellaswag_10

    • 分割: 2024_03_14T10_52_28.159269
      • 路径: **/details_harness|hellaswag|10_2024-03-14T10-52-28.159269.parquet
    • 分割: latest
      • 路径: **/details_harness|hellaswag|10_2024-03-14T10-52-28.159269.parquet
  • 配置名称: harness_hendrycksTest_5

    • 分割: 2024_03_14T10_52_28.159269
      • 路径:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-international_law|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-management|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-marketing|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-professional_accounting|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-professional_law|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-professional_medicine|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-professional_psychology|5_2024-03-14T10-52-28.159269.parquet
        • **/details_harness|hendrycksTest-public_relations|5_2024-03-14T10-52-
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