five

open-llm-leaderboard-old/details_Locutusque__Mistral-7B-SFT

收藏
Hugging Face2024-01-06 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_Locutusque__Mistral-7B-SFT
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在Open LLM Leaderboard上对Locutusque/Mistral-7B-SFT模型进行评估时自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行都可以在特定配置中找到,分割名称使用运行的时间戳。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,并用于计算和显示Open LLM Leaderboard上的聚合指标。

该数据集是在Open LLM Leaderboard上对Locutusque/Mistral-7B-SFT模型进行评估时自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行都可以在特定配置中找到,分割名称使用运行的时间戳。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,并用于计算和显示Open LLM Leaderboard上的聚合指标。
提供机构:
open-llm-leaderboard-old
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 Locutusque/Mistral-7B-SFTOpen 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

  • 配置数量:63 个配置
  • 数据来源:从 1 次运行中创建,每个运行可以在每个配置中找到一个特定的分割,分割名称使用运行的时间戳。
  • 最新结果:"train" 分割总是指向最新的结果。
  • 结果汇总:一个额外的配置 "results" 存储所有运行的汇总结果,用于计算和显示在 Open LLM Leaderboard 上的汇总指标。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Locutusque__Mistral-7B-SFT", "harness_winogrande_5", split="train")

最新结果

以下是 2024-01-06T00:40:05.281264 运行的最新结果

python { "all": { "acc": 0.5077681827057031, "acc_stderr": 0.0344008200063349, "acc_norm": 0.5137878006927419, "acc_norm_stderr": 0.035168382989525696, "mc1": 0.33659730722154224, "mc1_stderr": 0.016542412809494884, "mc2": 0.5202273247093547, "mc2_stderr": 0.015217658009446144 }, "harness|arc:challenge|25": { "acc": 0.4257679180887372, "acc_stderr": 0.014449464278868809, "acc_norm": 0.46501706484641636, "acc_norm_stderr": 0.014575583922019669 }, "harness|hellaswag|10": { "acc": 0.5544712208723361, "acc_stderr": 0.004960082528852433, "acc_norm": 0.756920932085242, "acc_norm_stderr": 0.004280658234718768 }, # 其他任务的结果... }

配置详情

  • config_name: harness_arc_challenge_25

    • data_files:
      • split: 2024_01_06T00_40_05.281264
        • path: **/details_harness|arc:challenge|25_2024-01-06T00-40-05.281264.parquet
      • split: latest
        • path: **/details_harness|arc:challenge|25_2024-01-06T00-40-05.281264.parquet
  • config_name: harness_gsm8k_5

    • data_files:
      • split: 2024_01_06T00_40_05.281264
        • path: **/details_harness|gsm8k|5_2024-01-06T00-40-05.281264.parquet
      • split: latest
        • path: **/details_harness|gsm8k|5_2024-01-06T00-40-05.281264.parquet
  • config_name: harness_hellaswag_10

    • data_files:
      • split: 2024_01_06T00_40_05.281264
        • path: **/details_harness|hellaswag|10_2024-01-06T00-40-05.281264.parquet
      • split: latest
        • path: **/details_harness|hellaswag|10_2024-01-06T00-40-05.281264.parquet
  • config_name: harness_hendrycksTest_5

    • data_files:
      • split: 2024_01_06T00_40_05.281264
        • path:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-college_biology|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-college_chemistry|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-college_computer_science|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-college_mathematics|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-college_medicine|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-college_physics|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-computer_security|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-econometrics|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-formal_logic|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-global_facts|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-high_school_biology|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-high_school_european_history|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-high_school_geography|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-high_school_physics|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-high_school_psychology|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-high_school_statistics|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-high_school_us_history|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-high_school_world_history|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-human_aging|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-human_sexuality|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-international_law|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-jurisprudence|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-logical_fallacies|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-machine_learning|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-management|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-marketing|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-medical_genetics|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-miscellaneous|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-moral_disputes|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-moral_scenarios|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-nutrition|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-philosophy|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-prehistory|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-professional_accounting|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-professional_law|5_2024-01-06T00-40-05.281264.parquet
          • **/details_harness|hendrycksTest-professional_medicine|5_2024-01-06T00-40-05.281264.par
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