five

open-llm-leaderboard/details_CobraMamba__mamba-gpt-3b

收藏
Hugging Face2023-10-14 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_CobraMamba__mamba-gpt-3b
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在Open LLM Leaderboard上对模型CobraMamba/mamba-gpt-3b进行评估时自动生成的。数据集包含64个配置,每个配置对应一个评估任务。数据集由2次运行的数据组成,每次运行在每个配置中表示为特定的split。train split始终指向最新的结果。此外,还有一个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上的指标。README还提供了如何使用Hugging Face datasets库加载数据集的示例。

This dataset was automatically generated during the evaluation of the model CobraMamba/mamba-gpt-3b on the Open LLM Leaderboard. It consists of 64 configurations, each corresponding to an evaluation task. The dataset comprises data from 2 runs, where each run is represented as a specific split under each configuration. The train split always points to the most recent results. In addition, there is a results configuration that stores the aggregated results of all runs, which are used to calculate and display the metrics on the Open LLM Leaderboard. The README also provides examples of how to load the dataset using the Hugging Face datasets library.
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 CobraMamba/mamba-gpt-3bOpen LLM Leaderboard 上的自动创建的。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" 分割总是指向最新的结果。

额外配置

有一个额外的配置 "results",存储所有运行的聚合结果,用于计算和显示聚合指标在 Open LLM Leaderboard 上。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_CobraMamba__mamba-gpt-3b", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-14T18:11:22.900658 运行的最新结果: python { "all": { "em": 0.030935402684563757, "em_stderr": 0.001773143572150097, "f1": 0.08682676174496619, "f1_stderr": 0.002178422368740777, "acc": 0.32631481001667695, "acc_stderr": 0.007357115747858964 }, "harness|drop|3": { "em": 0.030935402684563757, "em_stderr": 0.001773143572150097, "f1": 0.08682676174496619, "f1_stderr": 0.002178422368740777 }, "harness|gsm8k|5": { "acc": 0.002274450341167551, "acc_stderr": 0.001312157814867419 }, "harness|winogrande|5": { "acc": 0.6503551696921863, "acc_stderr": 0.013402073680850508 } }

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_19T15_20_46.724343
      • 路径: **/details_harness|arc:challenge|25_2023-07-19T15:20:46.724343.parquet
    • 分割: latest
      • 路径: **/details_harness|arc:challenge|25_2023-07-19T15:20:46.724343.parquet
  • harness_drop_3

    • 分割: 2023_10_14T18_11_22.900658
      • 路径: **/details_harness|drop|3_2023-10-14T18-11-22.900658.parquet
    • 分割: latest
      • 路径: **/details_harness|drop|3_2023-10-14T18-11-22.900658.parquet
  • harness_gsm8k_5

    • 分割: 2023_10_14T18_11_22.900658
      • 路径: **/details_harness|gsm8k|5_2023-10-14T18-11-22.900658.parquet
    • 分割: latest
      • 路径: **/details_harness|gsm8k|5_2023-10-14T18-11-22.900658.parquet
  • harness_hellaswag_10

    • 分割: 2023_07_19T15_20_46.724343
      • 路径: **/details_harness|hellaswag|10_2023-07-19T15:20:46.724343.parquet
    • 分割: latest
      • 路径: **/details_harness|hellaswag|10_2023-07-19T15:20:46.724343.parquet
  • harness_hendrycksTest_5

    • 分割: 2023_07_19T15_20_46.724343
      • 路径:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-international_law|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-management|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-marketing|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-professional_accounting|5_2023-07-19T15:20:46.724343.parquet
        • **/details_harness|hendrycksTest-professional_law|5_2023-07-19T15:20:46.724343.parquet
        • `**/details
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