five

open-llm-leaderboard-old/details_h2oai__h2ogpt-oig-oasst1-256-6_9b

收藏
Hugging Face2023-09-23 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_h2oai__h2ogpt-oig-oasst1-256-6_9b
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-oig-oasst1-256-6_9b](https://huggingface.co/h2oai/h2ogpt-oig-oasst1-256-6_9b)在[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/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,每个配置对应一个评估任务。数据集由2次运行创建,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。此外,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](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)上的聚合指标。

该数据集是在模型[h2oai/h2ogpt-oig-oasst1-256-6_9b](https://huggingface.co/h2oai/h2ogpt-oig-oasst1-256-6_9b)在[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/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,每个配置对应一个评估任务。数据集由2次运行创建,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。此外,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](https://huggingface.co/spaces/HuggingFaceH4/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

数据集来源

该数据集是在对模型 h2oai/h2ogpt-oig-oasst1-256-6_9b 进行评估运行时自动创建的,用于 Open LLM Leaderboard

数据集结构

  • 该数据集包含 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,每次运行在每个配置中作为一个特定的分片存在,分片名称使用运行的时间戳。
  • "train" 分片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_h2oai__h2ogpt-oig-oasst1-256-6_9b", "harness_winogrande_5", split="train")

最新结果

以下是 2023-09-23T02:25:51.324956 运行的最新结果: python { "all": { "em": 0.0006291946308724832, "em_stderr": 0.0002568002749723939, "f1": 0.04599517617449677, "f1_stderr": 0.0011593544147047532, "acc": 0.3248508682225, "acc_stderr": 0.008493981824488952 }, "harness|drop|3": { "em": 0.0006291946308724832, "em_stderr": 0.0002568002749723939, "f1": 0.04599517617449677, "f1_stderr": 0.0011593544147047532 }, "harness|gsm8k|5": { "acc": 0.01592115238817286, "acc_stderr": 0.0034478192723890037 }, "harness|winogrande|5": { "acc": 0.6337805840568271, "acc_stderr": 0.013540144376588901 } }

配置详情

以下是数据集的部分配置详情:

  • harness_arc_challenge_25

    • 分片:2023_07_19T17_44_24.016368
    • 路径:**/details_harness|arc:challenge|25_2023-07-19T17:44:24.016368.parquet
    • 分片:latest
    • 路径:**/details_harness|arc:challenge|25_2023-07-19T17:44:24.016368.parquet
  • harness_drop_3

    • 分片:2023_09_23T02_25_51.324956
    • 路径:**/details_harness|drop|3_2023-09-23T02-25-51.324956.parquet
    • 分片:latest
    • 路径:**/details_harness|drop|3_2023-09-23T02-25-51.324956.parquet
  • harness_gsm8k_5

    • 分片:2023_09_23T02_25_51.324956
    • 路径:**/details_harness|gsm8k|5_2023-09-23T02-25-51.324956.parquet
    • 分片:latest
    • 路径:**/details_harness|gsm8k|5_2023-09-23T02-25-51.324956.parquet
  • harness_hellaswag_10

    • 分片:2023_07_19T17_44_24.016368
    • 路径:**/details_harness|hellaswag|10_2023-07-19T17:44:24.016368.parquet
    • 分片:latest
    • 路径:**/details_harness|hellaswag|10_2023-07-19T17:44:24.016368.parquet
  • harness_hendrycksTest_5

    • 分片:2023_07_19T17_44_24.016368
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T17:44:24.016368.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T17:44:24.016368.parquet
  • harness_hendrycksTest_abstract_algebra_5

    • 分片:2023_07_19T17_44_24.016368
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T17:44:24.016368.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T17:44:24.016368.parquet
  • harness_hendrycksTest_anatomy_5

    • 分片:2023_07_19T17_44_24.016368
    • 路径:**/details_harness|hendrycksTest-anatomy|5_2023-07-19T17:44:24.016368.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-anatomy|5_2023-07-19T17:44:24.016368.parquet
  • harness_hendrycksTest_astronomy_5

    • 分片:2023_07_19T17_44_24.016368
    • 路径:**/details_harness|hendrycksTest-astronomy|5_2023-07-19T17:44:24.016368.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-astronomy|5_2023-07-19T17:44:24.016368.parquet
  • harness_hendrycksTest_business_ethics_5

    • 分片:2023_07_19T17_44_24.016368
    • 路径:**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T17:44:24.016368.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T17:44:24.016368.parquet
  • harness_hendrycksTest_clinical_knowledge_5

    • 分片:2023_07_19T17_44_24.016368
    • 路径:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T17:44:24.016368.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T17:44:24.016368.parquet
  • harness_hendrycksTest_college_biology_5

    • 分片:2023_07_19T17_44_24.016368
    • 路径:**/details_harness|hendrycksTest-college_biology|5_2023-07-19T17:44:24.016368.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-college_biology|5_2023-07-19T17:44:24.016368.parquet
  • harness_hendrycksTest_college_chemistry_5

    • 分片:2023_07_19T17_44_24.016368
    • 路径:**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T17:44:24.016368.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T17:44:24.016368.parquet
  • harness_hendrycksTest_college_computer_science_5

    • 分片:2023_07_19T17_44_24.016368
    • 路径:**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T17:44:24.016368.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T17:44:24.016368.parquet
  • harness_hendrycksTest_college_mathematics_5

    • 分片:2023_07_19T17_44_24.016368
    • 路径:**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T17:44:24.016368.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T17:44:24.016368.parquet
  • harness_hendrycksTest_college_medicine_5

    • 分片:2023_07_19T17_44_24.016368
    • 路径:**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T17:44:24.016368.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T17:44:24.016368.parquet
  • harness_hendrycksTest_college_physics_5

    • 分片:2023_07_19T17_44_24.016368
    • 路径:**/details_harness|hendrycksTest-college_physics|5_2023-07-19T17:44:24.016368.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-college_physics|5_2023-07-19T17:44:24.016368.parquet
  • harness_hendrycksTest_computer_security_5

    • 分片:2023_07_19T17_44_24.016368
    • 路径:**/details_harness|hendrycksTest-computer_security|5_2023-07-19T17:44:24.016368.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-computer_security|5_2023-07-19T17:44:24.016368.parquet
  • harness_hendrycksTest_conceptual_physics_5

    • 分片:2023_07_19T17_44_24.016368
    • 路径:**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T17:44:24.016368.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T17:44:24.016368.parquet
  • harness_hendrycksTest_econometrics_5

    • 分片:2023_07_19T17_44_24.016368
    • 路径:**/details_harness|hendrycksTest-econometrics|5_2023-07-19T17:44:24.016368.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-econometrics|5_2023-07-19T17:44:24.016368.parquet
  • harness_hendrycksTest_electrical_engineering_5

    • 分片:2023
二维码
社区交流群
二维码
科研交流群
商业服务