five

open-llm-leaderboard/details_bigcode__tiny_starcoder_py

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_bigcode__tiny_starcoder_py
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 bigcode/tiny_starcoder_py 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 Python 中的 datasets 库加载数据集的示例,并包含了特定运行的最新结果。

This dataset was automatically created during the evaluation run of the model bigcode/tiny_starcoder_py on the Open LLM Leaderboard. The dataset comprises 64 configurations, each corresponding to one evaluated task. The dataset was generated from two evaluation 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 aggregated metrics on the Open LLM Leaderboard. The accompanying README also provides examples of how to load the dataset using the datasets library in Python, and includes the most recent results from individual runs.
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 bigcode/tiny_starcoder_pyOpen 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

数据集从 2 次运行中创建,每个运行可以在每个配置中作为一个特定的分割找到,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。

数据加载示例

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

最新结果

以下是 2023-09-17T18:41:27.030233 运行的最新结果: python { "all": { "em": 0.0007340604026845638, "em_stderr": 0.0002773614457335755, "f1": 0.015742449664429566, "f1_stderr": 0.0006568370194517889, "acc": 0.2610447871046265, "acc_stderr": 0.00838467769872364 }, "harness|drop|3": { "em": 0.0007340604026845638, "em_stderr": 0.0002773614457335755, "f1": 0.015742449664429566, "f1_stderr": 0.0006568370194517889 }, "harness|gsm8k|5": { "acc": 0.009855951478392721, "acc_stderr": 0.00272107657704166 }, "harness|winogrande|5": { "acc": 0.5122336227308603, "acc_stderr": 0.01404827882040562 } }

配置详情

  • config_name: harness_arc_challenge_25

    • data_files:
      • split: 2023_07_19T18_53_24.895112
        • path: **/details_harness|arc:challenge|25_2023-07-19T18:53:24.895112.parquet
      • split: latest
        • path: **/details_harness|arc:challenge|25_2023-07-19T18:53:24.895112.parquet
  • config_name: harness_drop_3

    • data_files:
      • split: 2023_09_17T18_41_27.030233
        • path: **/details_harness|drop|3_2023-09-17T18-41-27.030233.parquet
      • split: latest
        • path: **/details_harness|drop|3_2023-09-17T18-41-27.030233.parquet
  • config_name: harness_gsm8k_5

    • data_files:
      • split: 2023_09_17T18_41_27.030233
        • path: **/details_harness|gsm8k|5_2023-09-17T18-41-27.030233.parquet
      • split: latest
        • path: **/details_harness|gsm8k|5_2023-09-17T18-41-27.030233.parquet
  • config_name: harness_hellaswag_10

    • data_files:
      • split: 2023_07_19T18_53_24.895112
        • path: **/details_harness|hellaswag|10_2023-07-19T18:53:24.895112.parquet
      • split: latest
        • path: **/details_harness|hellaswag|10_2023-07-19T18:53:24.895112.parquet
  • config_name: harness_hendrycksTest_5

    • data_files:
      • split: 2023_07_19T18_53_24.895112
        • path:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-college_biology|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-college_medicine|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-college_physics|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-computer_security|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-econometrics|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-formal_logic|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-global_facts|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-high_school_biology|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-high_school_european_history|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-high_school_geography|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-high_school_physics|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-high_school_psychology|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-high_school_statistics|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-high_school_us_history|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-high_school_world_history|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-human_aging|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-human_sexuality|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-international_law|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-jurisprudence|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-logical_fallacies|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-machine_learning|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-management|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-marketing|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-medical_genetics|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-miscellaneous|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-moral_disputes|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-moral_scenarios|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-nutrition|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-philosophy|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-prehistory|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-professional_accounting|5_2023-07-19T18:53:24.895112.parquet
          • **/details_harness|hendrycksTest-professional_law|5_202
搜集汇总
数据集介绍
main_image_url
以上内容由遇见数据集搜集并总结生成
二维码
社区交流群
二维码
科研交流群
商业服务