five

open-llm-leaderboard/details_shareAI__CodeLLaMA-chat-13b-Chinese

收藏
Hugging Face2023-09-17 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_shareAI__CodeLLaMA-chat-13b-Chinese
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shareAI/CodeLLaMA-chat-13b-Chinese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,每个配置对应一个特定的评估任务。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,分割名称使用运行的时间戳。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。README还提供了如何使用`datasets`库中的`load_dataset`函数加载运行中的详细信息的示例。

This dataset was automatically created during the evaluation run of the model shareAI/CodeLLaMA-chat-13b-Chinese on the Open LLM Leaderboard. The dataset consists of 64 configurations, each corresponding to a specific evaluation task. The dataset is generated from two runs, where each run is represented as a specific split for each configuration, with the split name using the timestamp of the run. The `train` split always points to the most recent results. An additional configuration named `results` stores the aggregated results from all runs, which are used to calculate and display the aggregated metrics on the Open LLM Leaderboard. The README also provides examples of how to use the `load_dataset` function from the `datasets` library to load detailed information from the runs.
提供机构:
open-llm-leaderboard
原始信息汇总

数据集概述

该数据集是在评估模型 shareAI/CodeLLaMA-chat-13b-ChineseOpen 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。

额外配置

一个额外的配置 "results" 存储了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。

加载数据示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_shareAI__CodeLLaMA-chat-13b-Chinese", "harness_winogrande_5", split="train")

最新结果

以下是 2023-09-17T09:47:36.542667 运行的最新结果

python { "all": { "em": 0.001363255033557047, "em_stderr": 0.0003778609196460702, "f1": 0.054088716442953266, "f1_stderr": 0.00128126893252217, "acc": 0.3932130306078425, "acc_stderr": 0.010830541663790839 }, "harness|drop|3": { "em": 0.001363255033557047, "em_stderr": 0.0003778609196460702, "f1": 0.054088716442953266, "f1_stderr": 0.00128126893252217 }, "harness|gsm8k|5": { "acc": 0.10765731614859743, "acc_stderr": 0.008537484003023356 }, "harness|winogrande|5": { "acc": 0.6787687450670876, "acc_stderr": 0.013123599324558323 } }

配置详情

以下是数据集的配置详情:

  • config_name: harness_arc_challenge_25

    • split: 2023_08_28T09_33_43.580652
      • path: **/details_harness|arc:challenge|25_2023-08-28T09:33:43.580652.parquet
    • split: latest
      • path: **/details_harness|arc:challenge|25_2023-08-28T09:33:43.580652.parquet
  • config_name: harness_drop_3

    • split: 2023_09_17T09_47_36.542667
      • path: **/details_harness|drop|3_2023-09-17T09-47-36.542667.parquet
    • split: latest
      • path: **/details_harness|drop|3_2023-09-17T09-47-36.542667.parquet
  • config_name: harness_gsm8k_5

    • split: 2023_09_17T09_47_36.542667
      • path: **/details_harness|gsm8k|5_2023-09-17T09-47-36.542667.parquet
    • split: latest
      • path: **/details_harness|gsm8k|5_2023-09-17T09-47-36.542667.parquet
  • config_name: harness_hellaswag_10

    • split: 2023_08_28T09_33_43.580652
      • path: **/details_harness|hellaswag|10_2023-08-28T09:33:43.580652.parquet
    • split: latest
      • path: **/details_harness|hellaswag|10_2023-08-28T09:33:43.580652.parquet
  • config_name: harness_hendrycksTest_5

    • split: 2023_08_28T09_33_43.580652
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-international_law|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-management|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-marketing|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-professional_accounting|5_2023-08-28T09:33:43.580652.parquet
        • **/details_harness|hendrycksTest-professional_law|5_2023-08-28T09:33:43.580652.parquet
二维码
社区交流群
二维码
科研交流群
商业服务