five

open-llm-leaderboard/details_Corianas__Quokka_590m

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_Corianas__Quokka_590m
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Corianas/Quokka_590m在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,每个配置对应一个被评估的任务。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分割始终指向最新的结果。一个名为results的额外配置存储了运行的所有聚合结果,这些结果用于计算和显示Open LLM Leaderboard上的聚合指标。README还提供了如何使用`datasets`库中的`load_dataset`函数加载数据集的示例。

This dataset was automatically created during the evaluation run of the model Corianas/Quokka_590m on the Open LLM Leaderboard. The dataset comprises 64 configurations, each corresponding to an evaluated task. The dataset is derived from two runs, where each run is represented as a specific split for every configuration. The `train` split always points to the most up-to-date results. An additional configuration named `results` stores all aggregated results from the runs, which are utilized to compute and display the aggregate metrics on the Open LLM Leaderboard. The README also includes examples demonstrating how to load the dataset via 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

数据集简介

该数据集是在评估模型 Corianas/Quokka_590mOpen 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" 分割始终指向最新的结果。

数据加载示例

以下是加载特定运行细节的示例代码: python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Corianas__Quokka_590m", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-14T16:50:32.705897 运行 的最新结果: python { "all": { "em": 0.0036703020134228187, "em_stderr": 0.0006192871806511148, "f1": 0.03957634228187927, "f1_stderr": 0.0012672315965293443, "acc": 0.2509865824782952, "acc_stderr": 0.0070261881296128145 }, "harness|drop|3": { "em": 0.0036703020134228187, "em_stderr": 0.0006192871806511148, "f1": 0.03957634228187927, "f1_stderr": 0.0012672315965293443 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 }, "harness|winogrande|5": { "acc": 0.5019731649565904, "acc_stderr": 0.014052376259225629 } }

配置详情

以下是部分配置的详细信息:

  • config_name: harness_arc_challenge_25

    • data_files:
      • split: 2023_07_24T09_57_25.772408
        • path: **/details_harness|arc:challenge|25_2023-07-24T09:57:25.772408.parquet
      • split: latest
        • path: **/details_harness|arc:challenge|25_2023-07-24T09:57:25.772408.parquet
  • config_name: harness_drop_3

    • data_files:
      • split: 2023_10_14T16_50_32.705897
        • path: **/details_harness|drop|3_2023-10-14T16-50-32.705897.parquet
      • split: latest
        • path: **/details_harness|drop|3_2023-10-14T16-50-32.705897.parquet
  • config_name: harness_gsm8k_5

    • data_files:
      • split: 2023_10_14T16_50_32.705897
        • path: **/details_harness|gsm8k|5_2023-10-14T16-50-32.705897.parquet
      • split: latest
        • path: **/details_harness|gsm8k|5_2023-10-14T16-50-32.705897.parquet
  • config_name: harness_hellaswag_10

    • data_files:
      • split: 2023_07_24T09_57_25.772408
        • path: **/details_harness|hellaswag|10_2023-07-24T09:57:25.772408.parquet
      • split: latest
        • path: **/details_harness|hellaswag|10_2023-07-24T09:57:25.772408.parquet
  • config_name: harness_hendrycksTest_5

    • data_files:
      • split: 2023_07_24T09_57_25.772408
        • path:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-college_biology|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-college_chemistry|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-college_computer_science|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-college_mathematics|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-college_medicine|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-college_physics|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-computer_security|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-conceptual_physics|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-econometrics|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-electrical_engineering|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-formal_logic|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-global_facts|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-high_school_biology|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-high_school_european_history|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-high_school_geography|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-high_school_physics|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-high_school_psychology|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-high_school_statistics|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-high_school_us_history|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-high_school_world_history|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-human_aging|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-human_sexuality|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-international_law|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-jurisprudence|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-logical_fallacies|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-machine_learning|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-management|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-marketing|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-medical_genetics|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-miscellaneous|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-moral_disputes|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-moral_scenarios|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-nutrition|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-philosophy|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-prehistory|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-professional_accounting|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-professional_law|5_2023-07-24T09:57:25.772408.parquet
          • **/details_harness|hendrycksTest-professional_medicine|5_2023-07-24T09:57:2
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