five

open-llm-leaderboard-old/details_nbeerbower__flammen2

收藏
Hugging Face2024-03-07 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_nbeerbower__flammen2
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nbeerbower/flammen2的评估运行中自动创建的,用于Open LLM Leaderboard。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,并且运行的时间戳用于命名分割。train分割始终指向最新的结果。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。

该数据集是在模型nbeerbower/flammen2的评估运行中自动创建的,用于Open LLM Leaderboard。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,并且运行的时间戳用于命名分割。train分割始终指向最新的结果。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

该数据集是在对模型 nbeerbower/flammen2 进行评估运行期间自动创建的,用于 Open LLM Leaderboard

数据集组成

  • 数据集包含 63 个配置,每个配置对应一个评估任务。
  • 数据集从 1 次运行中创建,每个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。
  • 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_nbeerbower__flammen2", "harness_winogrande_5", split="train")

最新结果

这些是最新结果(来自 2024-03-07T14:56:03.347153 运行)的示例: python { "all": { "acc": 0.6516597303553882, "acc_stderr": 0.032191341755437426, "acc_norm": 0.652284214333548, "acc_norm_stderr": 0.0328480902926615, "mc1": 0.4589963280293758, "mc1_stderr": 0.017444544447661192, "mc2": 0.6311863762763213, "mc2_stderr": 0.015342834368109374 }, "harness|arc:challenge|25": { "acc": 0.6732081911262798, "acc_stderr": 0.013706665975587331, "acc_norm": 0.689419795221843, "acc_norm_stderr": 0.013522292098053064 }, "harness|hellaswag|10": { "acc": 0.6941844254132643, "acc_stderr": 0.004598103566842479, "acc_norm": 0.8686516630153356, "acc_norm_stderr": 0.0033709059327855623 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, # 其他任务的结果... }

配置详情

  • config_name: harness_arc_challenge_25

    • 数据文件:
      • 分割: 2024_03_07T14_56_03.347153
        • 路径: **/details_harness|arc:challenge|25_2024-03-07T14-56-03.347153.parquet
      • 分割: latest
        • 路径: **/details_harness|arc:challenge|25_2024-03-07T14-56-03.347153.parquet
  • config_name: harness_gsm8k_5

    • 数据文件:
      • 分割: 2024_03_07T14_56_03.347153
        • 路径: **/details_harness|gsm8k|5_2024-03-07T14-56-03.347153.parquet
      • 分割: latest
        • 路径: **/details_harness|gsm8k|5_2024-03-07T14-56-03.347153.parquet
  • config_name: harness_hellaswag_10

    • 数据文件:
      • 分割: 2024_03_07T14_56_03.347153
        • 路径: **/details_harness|hellaswag|10_2024-03-07T14-56-03.347153.parquet
      • 分割: latest
        • 路径: **/details_harness|hellaswag|10_2024-03-07T14-56-03.347153.parquet
  • config_name: harness_hendrycksTest_5

    • 数据文件:
      • 分割: 2024_03_07T14_56_03.347153
        • 路径:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-college_biology|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-college_chemistry|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-college_computer_science|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-college_mathematics|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-college_medicine|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-college_physics|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-computer_security|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-econometrics|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-formal_logic|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-global_facts|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-high_school_biology|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-high_school_computer_science|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-high_school_european_history|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-high_school_geography|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-high_school_mathematics|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-high_school_physics|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-high_school_psychology|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-high_school_statistics|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-high_school_us_history|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-high_school_world_history|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-human_aging|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-human_sexuality|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-international_law|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-jurisprudence|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-logical_fallacies|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-machine_learning|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-management|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-marketing|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-medical_genetics|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-miscellaneous|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-moral_disputes|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-moral_scenarios|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-nutrition|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-philosophy|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-prehistory|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-professional_accounting|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-professional_law|5_2024-03-07T14-56-03.347153.parquet
          • **/details_harness|hendrycksTest-professional_medicine|5_2024-03-07T14-56-03.347153
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