five

open-llm-leaderboard/details_lmsys__vicuna-7b-v1.5

收藏
Hugging Face2023-10-21 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_lmsys__vicuna-7b-v1.5
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 lmsys/vicuna-7b-v1.5 在 Open LLM Leaderboard 上的评估运行期间自动创建的。数据集由 64 个配置组成,每个配置对应一个被评估的任务。数据集是从 3 次运行中创建的,每次运行在每个配置中表示为特定的分割。train 分割始终指向最新的结果。一个名为 results 的额外配置存储了所有运行的聚合结果,这些结果用于计算和显示 Open LLM Leaderboard 上的聚合指标。README 还包含了一个如何使用 Hugging Face 数据集库加载运行细节的示例。
提供机构:
open-llm-leaderboard
原始信息汇总

数据集概述

数据集摘要

该数据集是在评估模型 lmsys/vicuna-7b-v1.5Open LLM Leaderboard 上的自动创建的。数据集包含 64 个配置,每个配置对应一个评估任务。数据集从 3 次运行中创建,每次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。"train" 分割总是指向最新的结果。一个额外的配置 "results" 存储所有运行的聚合结果,用于计算和显示在 Open LLM Leaderboard 上的聚合指标。

最新结果

以下是 2023-10-21T21:05:37.153515 运行的最新结果

python { "all": { "em": 0.017932046979865772, "em_stderr": 0.0013590184569504276, "f1": 0.08961094798657747, "f1_stderr": 0.002014243406072028, "acc": 0.4016346602057357, "acc_stderr": 0.010076117588605417 }, "harness|drop|3": { "em": 0.017932046979865772, "em_stderr": 0.0013590184569504276, "f1": 0.08961094798657747, "f1_stderr": 0.002014243406072028 }, "harness|gsm8k|5": { "acc": 0.08188021228203184, "acc_stderr": 0.007552338527716956 }, "harness|winogrande|5": { "acc": 0.7213891081294396, "acc_stderr": 0.012599896649493878 } }

配置详情

以下是数据集的配置详情:

  • config_name: harness_arc_challenge_25

    • split: 2023_08_17T12_09_52.202468
      • path: **/details_harness|arc:challenge|25_2023-08-17T12:09:52.202468.parquet
    • split: latest
      • path: **/details_harness|arc:challenge|25_2023-08-17T12:09:52.202468.parquet
  • config_name: harness_drop_3

    • split: 2023_10_19T12_56_49.814418
      • path: **/details_harness|drop|3_2023-10-19T12-56-49.814418.parquet
    • split: 2023_10_21T21_05_37.153515
      • path: **/details_harness|drop|3_2023-10-21T21-05-37.153515.parquet
    • split: latest
      • path: **/details_harness|drop|3_2023-10-21T21-05-37.153515.parquet
  • config_name: harness_gsm8k_5

    • split: 2023_10_19T12_56_49.814418
      • path: **/details_harness|gsm8k|5_2023-10-19T12-56-49.814418.parquet
    • split: 2023_10_21T21_05_37.153515
      • path: **/details_harness|gsm8k|5_2023-10-21T21-05-37.153515.parquet
    • split: latest
      • path: **/details_harness|gsm8k|5_2023-10-21T21-05-37.153515.parquet
  • config_name: harness_hellaswag_10

    • split: 2023_08_17T12_09_52.202468
      • path: **/details_harness|hellaswag|10_2023-08-17T12:09:52.202468.parquet
    • split: latest
      • path: **/details_harness|hellaswag|10_2023-08-17T12:09:52.202468.parquet
  • config_name: harness_hendrycksTest_5

    • split: 2023_08_17T12_09_52.202468
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-international_law|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-management|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-marketing|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2023-08-17T12:09:52.202468.parquet
        • **/details_harness|hendrycksTest-professional_accounting|5_2023-08-17
搜集汇总
数据集介绍
main_image_url
以上内容由遇见数据集搜集并总结生成
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