five

open-llm-leaderboard/details_alibidaran__medical_transcription_generator

收藏
Hugging Face2023-10-24 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_alibidaran__medical_transcription_generator
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 alibidaran/medical_transcription_generator 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,每个配置对应一个评估任务。数据集是从 2 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。train 分割始终指向最新结果。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 alibidaran/medical_transcription_generator on the Open LLM Leaderboard. It consists of 64 configurations, each corresponding to one evaluation task. The dataset was generated from 2 runs, with each run represented as a specific split within each configuration. 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

数据集来源

  • 数据集是在评估模型 alibidaran/medical_transcription_generator 的过程中自动创建的。

数据集组成

  • 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。
  • 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。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_alibidaran__medical_transcription_generator", "harness_winogrande_5", split="train")

最新结果

  • 最新结果来自 2023-10-24T21:21:57.279571 运行,包含以下指标: python { "all": { "em": 0.0019924496644295304, "em_stderr": 0.00045666764626670043, "f1": 0.014220847315436273, "f1_stderr": 0.0008227845342657542, "acc": 0.2521704814522494, "acc_stderr": 0.00702597803203845 }, "harness|drop|3": { "em": 0.0019924496644295304, "em_stderr": 0.00045666764626670043, "f1": 0.014220847315436273, "f1_stderr": 0.0008227845342657542 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 }, "harness|winogrande|5": { "acc": 0.5043409629044988, "acc_stderr": 0.0140519560640769 } }

配置详情

  • 以下是部分配置及其数据文件路径:
    • harness_arc_challenge_25
      • 分割:2023_07_19T19_11_07.660746
        • 路径:**/details_harness|arc:challenge|25_2023-07-19T19:11:07.660746.parquet
      • 分割:latest
        • 路径:**/details_harness|arc:challenge|25_2023-07-19T19:11:07.660746.parquet
    • harness_drop_3
      • 分割:2023_10_24T21_21_57.279571
        • 路径:**/details_harness|drop|3_2023-10-24T21-21-57.279571.parquet
      • 分割:latest
        • 路径:**/details_harness|drop|3_2023-10-24T21-21-57.279571.parquet
    • harness_gsm8k_5
      • 分割:2023_10_24T21_21_57.279571
        • 路径:**/details_harness|gsm8k|5_2023-10-24T21-21-57.279571.parquet
      • 分割:latest
        • 路径:**/details_harness|gsm8k|5_2023-10-24T21-21-57.279571.parquet
    • harness_hellaswag_10
      • 分割:2023_07_19T19_11_07.660746
        • 路径:**/details_harness|hellaswag|10_2023-07-19T19:11:07.660746.parquet
      • 分割:latest
        • 路径:**/details_harness|hellaswag|10_2023-07-19T19:11:07.660746.parquet
    • harness_hendrycksTest_5
      • 分割:2023_07_19T19_11_07.660746
        • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-anatomy|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-astronomy|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-college_biology|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-college_physics|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-computer_security|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-econometrics|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-formal_logic|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-global_facts|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-high_school_biology|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-high_school_european_history|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-high_school_geography|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-high_school_physics|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-high_school_psychology|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-high_school_statistics|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-high_school_us_history|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-high_school_world_history|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-human_aging|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-human_sexuality|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-international_law|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-jurisprudence|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-logical_fallacies|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-machine_learning|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-management|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-marketing|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-medical_genetics|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-miscellaneous|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-moral_disputes|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-moral_scenarios|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-nutrition|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-philosophy|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-prehistory|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-professional_accounting|5_2023-07-19T19:11:07.660746.parquet
        • 路径:**/details_harness|hendrycksTest-professional_law|5_2023-07-19T19:11:07.660746.parquet
        • 路径:`**/details_harness|hendrycksTest-professional_medicine|5_2023-07-19T19:11:07.660
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