five

open-llm-leaderboard/details_h2oai__h2ogpt-gm-oasst1-en-1024-20b

收藏
Hugging Face2023-10-17 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_h2oai__h2ogpt-gm-oasst1-en-1024-20b
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h2oai/h2ogpt-gm-oasst1-en-1024-20b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,每个配置对应一个特定的评估任务。它包含了2次运行的数据,每次运行都作为一个特定的分割,分割名称由运行的时间戳命名。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还提供了一个使用Python中的datasets库加载运行细节的示例。

This dataset was automatically generated during the evaluation run of the model h2oai/h2ogpt-gm-oasst1-en-1024-20b on the Open LLM Leaderboard. The dataset consists of 64 configurations, each corresponding to a specific evaluation task. It contains data from two separate runs, where each run acts as a distinct data split, with the split name corresponding to the timestamp of the run. The train split always points to the most up-to-date results. An additional configuration named "results" stores the aggregated results across all runs, which are used to compute and display the aggregated metrics on the Open LLM Leaderboard. The README also provides an example of loading run details using the datasets library in Python.
提供机构:
open-llm-leaderboard
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h2oai/h2ogpt-gm-oasst1-en-1024-20bOpen LLM Leaderboard上的运行过程中自动创建的。

数据集结构

  • 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。
  • 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。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_h2oai__h2ogpt-gm-oasst1-en-1024-20b", "harness_winogrande_5", split="train")

最新结果

以下是最新结果来自2023-10-17T11:30:13.056869: python { "all": { "em": 0.007340604026845637, "em_stderr": 0.0008741896875346127, "f1": 0.059098154362416305, "f1_stderr": 0.001498238863999793, "acc": 0.3440011895836038, "acc_stderr": 0.008793500407979769 }, "harness|drop|3": { "em": 0.007340604026845637, "em_stderr": 0.0008741896875346127, "f1": 0.059098154362416305, "f1_stderr": 0.001498238863999793 }, "harness|gsm8k|5": { "acc": 0.025018953752843062, "acc_stderr": 0.004302045046564285 }, "harness|winogrande|5": { "acc": 0.6629834254143646, "acc_stderr": 0.013284955769395252 } }

配置详情

以下是数据集的配置详情:

配置列表

  • harness_arc_challenge_25

    • 分割: 2023_07_19T21_35_35.780060
      • 路径: **/details_harness|arc:challenge|25_2023-07-19T21:35:35.780060.parquet
    • 分割: latest
      • 路径: **/details_harness|arc:challenge|25_2023-07-19T21:35:35.780060.parquet
  • harness_drop_3

    • 分割: 2023_10_17T11_30_13.056869
      • 路径: **/details_harness|drop|3_2023-10-17T11-30-13.056869.parquet
    • 分割: latest
      • 路径: **/details_harness|drop|3_2023-10-17T11-30-13.056869.parquet
  • harness_gsm8k_5

    • 分割: 2023_10_17T11_30_13.056869
      • 路径: **/details_harness|gsm8k|5_2023-10-17T11-30-13.056869.parquet
    • 分割: latest
      • 路径: **/details_harness|gsm8k|5_2023-10-17T11-30-13.056869.parquet
  • harness_hellaswag_10

    • 分割: 2023_07_19T21_35_35.780060
      • 路径: **/details_harness|hellaswag|10_2023-07-19T21:35:35.780060.parquet
    • 分割: latest
      • 路径: **/details_harness|hellaswag|10_2023-07-19T21:35:35.780060.parquet
  • harness_hendrycksTest_5

    • 分割: 2023_07_19T21_35_35.780060
      • 路径:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-international_law|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-management|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-marketing|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2023-07-19T21:35:35.780060.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2023-07-19T21:35:35.780060.parquet
        • `**/details_harness|hendrycksTest-professional_accounting|5_2023-07-19T21:35:35.780060.par
二维码
社区交流群
二维码
科研交流群
商业服务