five

open-llm-leaderboard/details_golaxy__goims

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_golaxy__goims
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golaxy/goims的评估运行期间自动创建的,用于Open LLM Leaderboard的评估。数据集包含64个配置,每个配置对应一个评估任务。数据集由2次运行生成,每次运行的结果作为特定配置中的一个分割,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,results配置存储了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。

This dataset was automatically created during the evaluation runs of the model golaxy/goims for the Open LLM Leaderboard evaluation. It contains 64 configurations, each corresponding to one evaluation task. The dataset is generated from 2 runs, where the results of each run serve as a split under its respective configuration, with the split name being the timestamp of the run. The train split always points to the most recent results. Additionally, the "results" configuration stores the aggregated results of all runs, which are used to calculate and display the aggregated metrics on the Open LLM Leaderboard.
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 golaxy/goimsOpen LLM Leaderboard 上的表现时自动创建的。数据集包含64个配置,每个配置对应一个评估任务。

数据集结构

数据集由2次运行结果组成,每次运行的结果可以在每个配置中作为特定的分片找到,分片名称使用运行的时间戳。"train" 分片始终指向最新的结果。

额外配置

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

以下是加载特定运行详细信息的示例代码: python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_golaxy__goims", "harness_winogrande_5", split="train")

最新结果

以下是 最新结果 的示例: python { "all": { "em": 0.001572986577181208, "em_stderr": 0.00040584511324177333, "f1": 0.061753355704698, "f1_stderr": 0.0014402452492549395, "acc": 0.379924161053344, "acc_stderr": 0.009802745022083587 }, "harness|drop|3": { "em": 0.001572986577181208, "em_stderr": 0.00040584511324177333, "f1": 0.061753355704698, "f1_stderr": 0.0014402452492549395 }, "harness|gsm8k|5": { "acc": 0.06292645943896892, "acc_stderr": 0.006688762581532711 }, "harness|winogrande|5": { "acc": 0.696921862667719, "acc_stderr": 0.012916727462634463 } }

配置详情

以下是数据集的配置详情:

  • harness_arc_challenge_25

    • 分片: 2023_08_09T10_57_12.922580
      • 路径: **/details_harness|arc:challenge|25_2023-08-09T10:57:12.922580.parquet
    • 分片: latest
      • 路径: **/details_harness|arc:challenge|25_2023-08-09T10:57:12.922580.parquet
  • harness_drop_3

    • 分片: 2023_10_17T02_18_23.733040
      • 路径: **/details_harness|drop|3_2023-10-17T02-18-23.733040.parquet
    • 分片: latest
      • 路径: **/details_harness|drop|3_2023-10-17T02-18-23.733040.parquet
  • harness_gsm8k_5

    • 分片: 2023_10_17T02_18_23.733040
      • 路径: **/details_harness|gsm8k|5_2023-10-17T02-18-23.733040.parquet
    • 分片: latest
      • 路径: **/details_harness|gsm8k|5_2023-10-17T02-18-23.733040.parquet
  • harness_hellaswag_10

    • 分片: 2023_08_09T10_57_12.922580
      • 路径: **/details_harness|hellaswag|10_2023-08-09T10:57:12.922580.parquet
    • 分片: latest
      • 路径: **/details_harness|hellaswag|10_2023-08-09T10:57:12.922580.parquet
  • harness_hendrycksTest_5

    • 分片: 2023_08_09T10_57_12.922580
      • 路径:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-international_law|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-management|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-marketing|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-professional_accounting|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-professional_law|5_2023-08-09T10:57:12.922580.parquet
        • **/details_harness|hendrycksTest-professional_medicine|5_2023-08-09T10:57:12
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