five

open-llm-leaderboard-old/details_222gate__Blurdus-7b-v0.1

收藏
Hugging Face2024-01-21 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_222gate__Blurdus-7b-v0.1
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[222gate/Blurdus-7b-v0.1](https://huggingface.co/222gate/Blurdus-7b-v0.1)在[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)上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。数据集从1次运行中创建,每次运行的结果作为特定分割存储在配置中,分割名称使用运行的时间戳。train分割始终指向最新结果。此外,results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。

该数据集是在模型[222gate/Blurdus-7b-v0.1](https://huggingface.co/222gate/Blurdus-7b-v0.1)在[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)上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。数据集从1次运行中创建,每次运行的结果作为特定分割存储在配置中,分割名称使用运行的时间戳。train分割始终指向最新结果。此外,results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。
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 222gate/Blurdus-7b-v0.1Open 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,每个运行在每个配置中作为一个特定的拆分存在,拆分名称使用运行的时间戳。"train" 拆分始终指向最新的结果。

结果配置

一个额外的配置 "results" 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_222gate__Blurdus-7b-v0.1", "harness_winogrande_5", split="train")

最新结果

以下是 最新结果 的摘要:

python { "all": { "acc": 0.6537793068429774, "acc_stderr": 0.03204806721727468, "acc_norm": 0.6535097790386686, "acc_norm_stderr": 0.03271036283162906, "mc1": 0.5740514075887393, "mc1_stderr": 0.01731047190407654, "mc2": 0.6971802454568737, "mc2_stderr": 0.015138148073785463 }, "harness|arc:challenge|25": { "acc": 0.7005119453924915, "acc_stderr": 0.01338502163731357, "acc_norm": 0.7226962457337884, "acc_norm_stderr": 0.013082095839059376 }, "harness|hellaswag|10": { "acc": 0.7225652260505875, "acc_stderr": 0.004468178273665677, "acc_norm": 0.8849830711013742, "acc_norm_stderr": 0.0031839033919416975 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, # 其他任务的结果... }

配置详情

  • config_name: harness_arc_challenge_25

    • 数据文件:
      • 拆分: 2024_01_21T04_02_50.944739
        • 路径: **/details_harness|arc:challenge|25_2024-01-21T04-02-50.944739.parquet
      • 拆分: latest
        • 路径: **/details_harness|arc:challenge|25_2024-01-21T04-02-50.944739.parquet
  • config_name: harness_gsm8k_5

    • 数据文件:
      • 拆分: 2024_01_21T04_02_50.944739
        • 路径: **/details_harness|gsm8k|5_2024-01-21T04-02-50.944739.parquet
      • 拆分: latest
        • 路径: **/details_harness|gsm8k|5_2024-01-21T04-02-50.944739.parquet
  • config_name: harness_hellaswag_10

    • 数据文件:
      • 拆分: 2024_01_21T04_02_50.944739
        • 路径: **/details_harness|hellaswag|10_2024-01-21T04-02-50.944739.parquet
      • 拆分: latest
        • 路径: **/details_harness|hellaswag|10_2024-01-21T04-02-50.944739.parquet
  • config_name: harness_hendrycksTest_5

    • 数据文件:
      • 拆分: 2024_01_21T04_02_50.944739
        • 路径:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-college_biology|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-college_chemistry|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-college_computer_science|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-college_mathematics|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-college_medicine|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-college_physics|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-computer_security|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-econometrics|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-formal_logic|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-global_facts|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-high_school_biology|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-high_school_european_history|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-high_school_geography|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-high_school_physics|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-high_school_psychology|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-high_school_statistics|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-high_school_us_history|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-high_school_world_history|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-human_aging|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-human_sexuality|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-international_law|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-jurisprudence|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-logical_fallacies|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-machine_learning|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-management|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-marketing|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-medical_genetics|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-miscellaneous|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-moral_disputes|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-moral_scenarios|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-nutrition|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-philosophy|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-prehistory|5_2024-01-21T04-02-50.944739.parquet
          • **/details_harness|hendrycksTest-professional_accounting|5_2024-01-21T04-02-50.944739.parquet
          • `**/details_harness|hendrycksTest-professional_law|5_2
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