five

open-llm-leaderboard/details_aisquared__chopt-2_7b

收藏
Hugging Face2023-10-13 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_aisquared__chopt-2_7b
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 aisquared/chopt-2_7b 在 Open LLM Leaderboard 上进行评估时自动生成的。数据集包含 64 个配置,每个配置对应一个被评估的任务。数据集由 2 次运行生成,每次运行在每个配置中表示为特定的分割,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。此外,results 配置存储了所有运行的聚合结果,用于在 Open LLM Leaderboard 上计算和显示聚合指标。README 还提供了如何使用 Python 中的 datasets 库加载数据集的示例,并包含了特定运行的最新结果。

This dataset was automatically generated when the model aisquared/chopt-2_7b was evaluated on the Open LLM Leaderboard. It contains 64 configurations, each corresponding to one evaluated task. The dataset is derived from two runs, where each run is represented as a dedicated split under each configuration, with split names named after the run's timestamp. The 'train' split always points to the most recent results. Furthermore, the 'results' configuration stores aggregated results across all runs, which are used to compute and display aggregate metrics on the Open LLM Leaderboard. The README also provides examples of loading the dataset using the `datasets` library in Python, and includes the latest results from specific runs.
提供机构:
open-llm-leaderboard
原始信息汇总

数据集概述

数据集来源

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_aisquared__chopt-2_7b", "harness_winogrande_5", split="train")

最新结果

  • 这些是最新的结果,来自 2023-10-13T00:33:45.271884 的运行: python { "all": { "em": 0.001363255033557047, "em_stderr": 0.0003778609196461222, "f1": 0.04857906879194641, "f1_stderr": 0.0012385170365466402, "acc": 0.2888713496448303, "acc_stderr": 0.006940791015329276 }, "harness|drop|3": { "em": 0.001363255033557047, "em_stderr": 0.0003778609196461222, "f1": 0.04857906879194641, "f1_stderr": 0.0012385170365466402 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 }, "harness|winogrande|5": { "acc": 0.5777426992896606, "acc_stderr": 0.013881582030658552 } }

配置详情

  • harness_arc_challenge_25

    • 分割:2023_07_19T16_07_47.560826, latest
    • 路径:**/details_harness|arc:challenge|25_2023-07-19T16:07:47.560826.parquet
  • harness_drop_3

    • 分割:2023_10_13T00_33_45.271884, latest
    • 路径:**/details_harness|drop|3_2023-10-13T00-33-45.271884.parquet
  • harness_gsm8k_5

    • 分割:2023_10_13T00_33_45.271884, latest
    • 路径:**/details_harness|gsm8k|5_2023-10-13T00-33-45.271884.parquet
  • harness_hellaswag_10

    • 分割:2023_07_19T16_07_47.560826, latest
    • 路径:**/details_harness|hellaswag|10_2023-07-19T16:07:47.560826.parquet
  • harness_hendrycksTest_5

    • 分割:2023_07_19T16_07_47.560826, latest
    • 路径:多个路径,例如 **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T16:07:47.560826.parquet
  • harness_hendrycksTest_abstract_algebra_5

    • 分割:2023_07_19T16_07_47.560826, latest
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T16:07:47.560826.parquet
  • harness_hendrycksTest_anatomy_5

    • 分割:2023_07_19T16_07_47.560826, latest
    • 路径:**/details_harness|hendrycksTest-anatomy|5_2023-07-19T16:07:47.560826.parquet
  • harness_hendrycksTest_astronomy_5

    • 分割:2023_07_19T16_07_47.560826, latest
    • 路径:**/details_harness|hendrycksTest-astronomy|5_2023-07-19T16:07:47.560826.parquet
  • harness_hendrycksTest_business_ethics_5

    • 分割:2023_07_19T16_07_47.560826, latest
    • 路径:**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T16:07:47.560826.parquet
  • harness_hendrycksTest_clinical_knowledge_5

    • 分割:2023_07_19T16_07_47.560826, latest
    • 路径:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T16:07:47.560826.parquet
  • harness_hendrycksTest_college_biology_5

    • 分割:2023_07_19T16_07_47.560826, latest
    • 路径:**/details_harness|hendrycksTest-college_biology|5_2023-07-19T16:07:47.560826.parquet
  • harness_hendrycksTest_college_chemistry_5

    • 分割:2023_07_19T16_07_47.560826, latest
    • 路径:**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T16:07:47.560826.parquet
  • harness_hendrycksTest_college_computer_science_5

    • 分割:2023_07_19T16_07_47.560826, latest
    • 路径:**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T16:07:47.560826.parquet
  • harness_hendrycksTest_college_mathematics_5

    • 分割:2023_07_19T16_07_47.560826, latest
    • 路径:**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T16:07:47.560826.parquet
  • harness_hendrycksTest_college_medicine_5

    • 分割:2023_07_19T16_07_47.560826, latest
    • 路径:**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T16:07:47.560826.parquet
  • harness_hendrycksTest_college_physics_5

    • 分割:2023_07_19T16_07_47.560826, latest
    • 路径:**/details_harness|hendrycksTest-college_physics|5_2023-07-19T16:07:47.560826.parquet
  • harness_hendrycksTest_computer_security_5

    • 分割:2023_07_19T16_07_47.560826, latest
    • 路径:**/details_harness|hendrycksTest-computer_security|5_2023-07-19T16:07:47.560826.parquet
  • harness_hendrycksTest_conceptual_physics_5

    • 分割:2023_07_19T16_07_47.560826, latest
    • 路径:**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T16:07:47.560826.parquet
  • harness_hendrycksTest_econometrics_5

    • 分割:2023_07_19T16_07_47.560826, latest
    • 路径:**/details_harness|hendrycksTest-econometrics|5_2023-07-19T16:07:47.560826.parquet
  • harness_hendrycksTest_electrical_engineering_5

    • 分割:2023_07_19T16_07_47.560826, latest
    • 路径:**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T16:07:47.560826.parquet
  • harness_hendrycksTest_elementary_mathematics_5

    • 分割:2023_07_19T16_07_47.560826, latest
    • 路径:**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T16:07:47.560826.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