five

open-llm-leaderboard-old/details_juhwanlee__llmdo-Mistral-7B-case-c

收藏
Hugging Face2024-03-03 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_juhwanlee__llmdo-Mistral-7B-case-c
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juhwanlee/llmdo-Mistral-7B-case-c的评估运行中自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集从1次运行中创建,每次运行可以在每个配置的特定分割中找到,分割以运行的时间戳命名。train分割始终指向最新的结果。此外,一个名为results的配置存储了所有运行的聚合结果,用于计算和显示在Open LLM Leaderboard上的聚合指标。README还提供了如何加载运行细节的示例代码,并展示了最新的评估结果。

该数据集是在模型juhwanlee/llmdo-Mistral-7B-case-c的评估运行中自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集从1次运行中创建,每次运行可以在每个配置的特定分割中找到,分割以运行的时间戳命名。train分割始终指向最新的结果。此外,一个名为results的配置存储了所有运行的聚合结果,用于计算和显示在Open LLM Leaderboard上的聚合指标。README还提供了如何加载运行细节的示例代码,并展示了最新的评估结果。
提供机构:
open-llm-leaderboard-old
原始信息汇总

数据集概述

该数据集是在对模型 juhwanlee/llmdo-Mistral-7B-case-c 进行评估运行期间自动创建的,用于 Open LLM Leaderboard。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

数据集由多个配置组成,每个配置包含不同的评估任务。每个配置中包含多个分割(split),分割名称使用运行的时间戳。"train" 分割始终指向最新的结果。

配置示例

  • 配置名称: harness_arc_challenge_25

    • 数据文件:
      • 分割: 2024_03_03T01_21_26.841475
        • 路径: **/details_harness|arc:challenge|25_2024-03-03T01-21-26.841475.parquet
      • 分割: latest
        • 路径: **/details_harness|arc:challenge|25_2024-03-03T01-21-26.841475.parquet
  • 配置名称: harness_gsm8k_5

    • 数据文件:
      • 分割: 2024_03_03T01_21_26.841475
        • 路径: **/details_harness|gsm8k|5_2024-03-03T01-21-26.841475.parquet
      • 分割: latest
        • 路径: **/details_harness|gsm8k|5_2024-03-03T01-21-26.841475.parquet
  • 配置名称: harness_hellaswag_10

    • 数据文件:
      • 分割: 2024_03_03T01_21_26.841475
        • 路径: **/details_harness|hellaswag|10_2024-03-03T01-21-26.841475.parquet
      • 分割: latest
        • 路径: **/details_harness|hellaswag|10_2024-03-03T01-21-26.841475.parquet
  • 配置名称: harness_hendrycksTest_5

    • 数据文件:
      • 分割: 2024_03_03T01_21_26.841475
        • 路径:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-03T01-21-26.841475.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2024-03-03T01-21-26.841475.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2024-03-03T01-21-26.841475.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2024-03-03T01-21-26.841475.parquet
          • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-03T01-21-26.841475.parquet
          • **/details_harness|hendrycksTest-college_biology|5_2024-03-03T01-21-26.841475.parquet
          • **/details_harness|hendrycksTest-college_chemistry|5_2024-03-03T01-21-26.841475.parquet
          • **/details_harness|hendrycksTest-college_computer_science|5_2024-03-03T01-21-26.841475.parquet
          • **/details_harness|hendrycksTest-college_mathematics|5_2024-03-03T01-21-26.841475.parquet
          • **/details_harness|hendrycksTest-college_medicine|5_2024-03-03T01-21-26.841475.parquet
          • **/details_harness|hendrycksTest-college_physics|5_2024-03-03T01-21-26.841475.parquet
          • **/details_harness|hendrycksTest-computer_security|5_2024-03-03T01-21-26.841475.parquet
          • **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-03T01-21-26.841475.parquet
          • **/details_harness|hendrycksTest-econometrics|5_2024-03-03T01-21-26.841475.parquet
          • **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-03T01-21-26.841475.parquet
          • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-03T01-21-26.841475.parquet
          • **/details_harness|hendrycksTest-formal_logic|5_2024-03-03T01-21-26.841475.parquet
          • **/details_harness|hendrycksTest-global_facts|5_2024-03-03T01-21-26.841475.parquet
          • ...

最新结果

以下是 2024-03-03T01:21:26.841475 运行 的最新结果:

python { "all": { "acc": 0.6159264992632708, "acc_stderr": 0.03280344263610405, "acc_norm": 0.6214576349320463, "acc_norm_stderr": 0.03347483296351587, "mc1": 0.29008567931456547, "mc1_stderr": 0.01588623687420952, "mc2": 0.44688799937298396, "mc2_stderr": 0.014500935780738989 }, "harness|arc:challenge|25": { "acc": 0.5776450511945392, "acc_stderr": 0.014434138713379983, "acc_norm": 0.6092150170648464, "acc_norm_stderr": 0.014258563880513782 }, "harness|hellaswag|10": { "acc": 0.6215893248356901, "acc_stderr": 0.0048399957456023174, "acc_norm": 0.8292172873929496, "acc_norm_stderr": 0.0037554989417818516 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6148148148148148, "acc_stderr": 0.04203921040156279, "acc_norm": 0.6148148148148148, "acc_norm_stderr": 0.04203921040156279 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6381578947368421, "acc_stderr": 0.039105257528497236, "acc_norm": 0.6381578947368421, "acc_norm_stderr": 0.039105257528497236 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.59, "acc_stderr": 0.049431107042371025, "acc_norm": 0.59, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6792452830188679, "acc_stderr": 0.028727502957880274, "acc_norm": 0.6792452830188679, "acc_norm_stderr": 0.028727502957880274 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7222222222222222, "acc_stderr": 0.037455547914624555, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.037455547914624555 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6242774566473989, "acc_stderr": 0.036928207672648664, "acc_norm": 0.6242774566473989, "acc_norm_stderr": 0.036928207672648664 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3627450980392157, "acc_stderr": 0.04784060704105653, "acc_norm": 0.3627450980392157, "acc_norm_stderr": 0.04784060704105653 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.74, "acc_stderr": 0.0440844002276808, "acc_norm": 0.74, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.48936170212765956, "acc_stderr": 0.03267862331014063, "acc_norm": 0.48936170212765956, "acc_norm_stderr": 0.03267862331014063 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4824561403508772, "acc_stderr": 0.04700708033551038, "acc_norm": 0.4824561403508772, "acc_norm_stderr": 0.04700708033551038 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5724137931034483, "acc_stderr": 0.04122737111370332, "acc_norm": 0.5724137931034483, "acc_norm_stderr": 0.04122737111370332 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4047619047

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