five

open-llm-leaderboard-old/details_JosephusCheung__LL7M

收藏
Hugging Face2023-10-24 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_JosephusCheung__LL7M
下载链接
链接失效反馈
官方服务:
资源简介:
数据集是在模型JosephusCheung/LL7M的评估运行期间自动创建的,用于Open LLM Leaderboard的评估。数据集由64个配置组成,每个配置对应一个评估任务。数据集由2次运行生成,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命名。train分割始终指向最新的结果。此外,还有一个名为results的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。

数据集是在模型JosephusCheung/LL7M的评估运行期间自动创建的,用于Open LLM Leaderboard的评估。数据集由64个配置组成,每个配置对应一个评估任务。数据集由2次运行生成,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命名。train分割始终指向最新的结果。此外,还有一个名为results的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

数据集名为 "Evaluation run of JosephusCheung/LL7M",是在评估模型 JosephusCheung/LL7MOpen LLM Leaderboard 上的运行过程中自动创建的。

数据集组成

  • 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 2 次运行中创建。每次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。
  • 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_JosephusCheung__LL7M", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-24T03:13:24.379539 运行的最新结果

python { "all": { "em": 0.019819630872483222, "em_stderr": 0.0014273827117586067, "f1": 0.07556312919463118, "f1_stderr": 0.0018868261588306972, "acc": 0.3234745894051663, "acc_stderr": 0.007810892751790338 }, "harness|drop|3": { "em": 0.019819630872483222, "em_stderr": 0.0014273827117586067, "f1": 0.07556312919463118, "f1_stderr": 0.0018868261588306972 }, "harness|gsm8k|5": { "acc": 0.006065200909780136, "acc_stderr": 0.00213867030146044 }, "harness|winogrande|5": { "acc": 0.6408839779005525, "acc_stderr": 0.013483115202120236 } }

配置详情

  • harness_arc_challenge_25

    • 分割:2023_10_10T15_26_54.562937
      • 路径:**/details_harness|arc:challenge|25_2023-10-10T15-26-54.562937.parquet
    • 分割:latest
      • 路径:**/details_harness|arc:challenge|25_2023-10-10T15-26-54.562937.parquet
  • harness_drop_3

    • 分割:2023_10_24T03_13_24.379539
      • 路径:**/details_harness|drop|3_2023-10-24T03-13-24.379539.parquet
    • 分割:latest
      • 路径:**/details_harness|drop|3_2023-10-24T03-13-24.379539.parquet
  • harness_gsm8k_5

    • 分割:2023_10_24T03_13_24.379539
      • 路径:**/details_harness|gsm8k|5_2023-10-24T03-13-24.379539.parquet
    • 分割:latest
      • 路径:**/details_harness|gsm8k|5_2023-10-24T03-13-24.379539.parquet
  • harness_hellaswag_10

    • 分割:2023_10_10T15_26_54.562937
      • 路径:**/details_harness|hellaswag|10_2023-10-10T15-26-54.562937.parquet
    • 分割:latest
      • 路径:**/details_harness|hellaswag|10_2023-10-10T15-26-54.562937.parquet
  • harness_hendrycksTest_5

    • 分割:2023_10_10T15_26_54.562937
      • 路径:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-international_law|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-management|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-marketing|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-professional_accounting|5_2023-10-10T15-26-54.562937.parquet
        • **/details_harness|hendrycksTest-professional_law|5_2023-10-10T15-26-54.562937.parquet
        • `**/details_harness|hendrycksTest-professional_medicine|5_20
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