five

open-llm-leaderboard/details_TheTravellingEngineer__bloom-1b1-RLHF

收藏
Hugging Face2023-12-02 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_TheTravellingEngineer__bloom-1b1-RLHF
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 TheTravellingEngineer/bloom-1b1-RLHF 在 Open LLM Leaderboard 上的评估运行期间自动创建的。它由 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 次运行中生成的,每次运行在每个配置中表示为特定的分割,使用运行的时间戳命名。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。可以使用 datasets 库中的 load_dataset 函数加载该数据集。

This dataset was automatically created during the evaluation run of the model TheTravellingEngineer/bloom-1b1-RLHF on the Open LLM Leaderboard. It comprises 64 configurations, each corresponding to one evaluated task. The dataset is generated from three runs, where each run is represented as a specific split under each configuration and named with the timestamp of the corresponding run. The "train" split always points to the most recent results. An additional configuration named "results" stores the aggregated results across all runs, which are used to calculate and display the aggregate metrics on the Open LLM Leaderboard. This dataset can be loaded using the load_dataset function from the datasets library.
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 TheTravellingEngineer/bloom-1b1-RLHFOpen LLM Leaderboard 上的运行过程中自动创建的。

数据集结构

  • 配置数量:64个配置,每个配置对应一个评估任务。
  • 创建来源:数据集从3次运行中创建,每次运行在每个配置中都有一个特定的分割,分割名称使用运行的时间戳。
  • 最新结果:"train" 分割总是指向最新的结果。
  • 聚合结果: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_TheTravellingEngineer__bloom-1b1-RLHF", "harness_gsm8k_5", split="train")

最新结果

以下是 2023-12-02T13:14:43.588399 运行 的最新结果: python { "all": { "acc": 0.0, "acc_stderr": 0.0 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 } }

配置详情

  • harness_arc_challenge_25

    • 分割:2023_08_09T08_38_39.084452, latest
    • 路径:**/details_harness|arc:challenge|25_2023-08-09T08:38:39.084452.parquet
  • harness_drop_3

    • 分割:2023_10_16T19_51_27.983287, latest
    • 路径:**/details_harness|drop|3_2023-10-16T19-51-27.983287.parquet
  • harness_gsm8k_5

    • 分割:2023_10_16T19_51_27.983287, 2023_12_02T13_14_43.588399, latest
    • 路径:**/details_harness|gsm8k|5_2023-10-16T19-51-27.983287.parquet, **/details_harness|gsm8k|5_2023-12-02T13-14-43.588399.parquet
  • harness_hellaswag_10

    • 分割:2023_08_09T08_38_39.084452, latest
    • 路径:**/details_harness|hellaswag|10_2023-08-09T08:38:39.084452.parquet
  • harness_hendrycksTest_5

    • 分割:2023_08_09T08_38_39.084452, latest
    • 路径:多个路径,详见原文档
  • harness_hendrycksTest_abstract_algebra_5

    • 分割:2023_08_09T08_38_39.084452, latest
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-09T08:38:39.084452.parquet
  • harness_hendrycksTest_anatomy_5

    • 分割:2023_08_09T08_38_39.084452, latest
    • 路径:**/details_harness|hendrycksTest-anatomy|5_2023-08-09T08:38:39.084452.parquet
  • harness_hendrycksTest_astronomy_5

    • 分割:2023_08_09T08_38_39.084452, latest
    • 路径:**/details_harness|hendrycksTest-astronomy|5_2023-08-09T08:38:39.084452.parquet
  • harness_hendrycksTest_business_ethics_5

    • 分割:2023_08_09T08_38_39.084452, latest
    • 路径:**/details_harness|hendrycksTest-business_ethics|5_2023-08-09T08:38:39.084452.parquet
  • harness_hendrycksTest_clinical_knowledge_5

    • 分割:2023_08_09T08_38_39.084452, latest
    • 路径:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-09T08:38:39.084452.parquet
  • harness_hendrycksTest_college_biology_5

    • 分割:2023_08_09T08_38_39.084452, latest
    • 路径:**/details_harness|hendrycksTest-college_biology|5_2023-08-09T08:38:39.084452.parquet
  • harness_hendrycksTest_college_chemistry_5

    • 分割:2023_08_09T08_38_39.084452, latest
    • 路径:**/details_harness|hendrycksTest-college_chemistry|5_2023-08-09T08:38:39.084452.parquet
  • harness_hendrycksTest_college_computer_science_5

    • 分割:2023_08_09T08_38_39.084452, latest
    • 路径:**/details_harness|hendrycksTest-college_computer_science|5_2023-08-09T08:38:39.084452.parquet
  • harness_hendrycksTest_college_mathematics_5

    • 分割:2023_08_09T08_38_39.084452, latest
    • 路径:**/details_harness|hendrycksTest-college_mathematics|5_2023-08-09T08:38:39.084452.parquet
  • harness_hendrycksTest_college_medicine_5

    • 分割:2023_08_09T08_38_39.084452, latest
    • 路径:**/details_harness|hendrycksTest-college_medicine|5_2023-08-09T08:38:39.084452.parquet
  • harness_hendrycksTest_college_physics_5

    • 分割:2023_08_09T08_38_39.084452, latest
    • 路径:**/details_harness|hendrycksTest-college_physics|5_2023-08-09T08:38:39.084452.parquet
  • harness_hendrycksTest_computer_security_5

    • 分割:2023_08_09T08_38_39.084452, latest
    • 路径:**/details_harness|hendrycksTest-computer_security|5_2023-08-09T08:38:39.084452.parquet
  • harness_hendrycksTest_conceptual_physics_5

    • 分割:2023_08_09T08_38_39.084452, latest
    • 路径:**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-09T08:38:39.084452.parquet
  • harness_hendrycksTest_econometrics_5

    • 分割:2023_08_09T08_38_39.084452, latest
    • 路径:**/details_harness|hendrycksTest-econometrics|5_2023-08-09T08:38:39.084452.parquet
  • harness_hendrycksTest_electrical_engineering_5

    • 分割:2023_08_09T08_38_39.084452, latest
    • 路径:**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-09T08:38:39.084452.parquet
  • harness_hendrycksTest_elementary_mathematics_5

    • 分割:2023_08_09T08_38_39.084452, latest
    • 路径:**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-09T08:38:39.084452.parquet
  • harness_hendrycksTest_formal_logic_5

    • 分割:2023_08_09T08_38_39.084452, latest
    • 路径:**/details_harness|hendrycksTest-formal_logic|5_2023-08-09T08:38:39.084452.parquet
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