five

open-llm-leaderboard-old/details_SC44__Mistral-7B-private-spef

收藏
Hugging Face2024-01-28 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_SC44__Mistral-7B-private-spef
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SC44/Mistral-7B-private-spef进行评估时自动生成的。数据集由63个配置组成,每个配置对应一个被评估的任务。数据集是从3次运行中创建的,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还提供了一个示例,展示了如何使用`datasets`库中的`load_dataset`函数加载运行中的详细信息。

该数据集是在Open LLM Leaderboard上对模型SC44/Mistral-7B-private-spef进行评估时自动生成的。数据集由63个配置组成,每个配置对应一个被评估的任务。数据集是从3次运行中创建的,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还提供了一个示例,展示了如何使用`datasets`库中的`load_dataset`函数加载运行中的详细信息。
提供机构:
open-llm-leaderboard-old
原始信息汇总

数据集概述

该数据集是在对模型 SC44/Mistral-7B-private-spef 进行评估运行期间自动创建的,用于 Open LLM Leaderboard

数据集组成

  • 数据集包含 63 个配置,每个配置对应一个评估任务。
  • 数据集从 3 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。
  • 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_SC44__Mistral-7B-private-spef", "harness_winogrande_5", split="train")

最新结果

以下是 2024-01-28T19:27:06.867214 运行的最新结果

python { "all": { "acc": 0.6382392684300928, "acc_stderr": 0.032384718544664244, "acc_norm": 0.6378658562238155, "acc_norm_stderr": 0.03306133547434673, "mc1": 0.5287637698898409, "mc1_stderr": 0.017474513848525518, "mc2": 0.6900902744814158, "mc2_stderr": 0.014893271831165143 }, "harness|arc:challenge|25": { "acc": 0.6663822525597269, "acc_stderr": 0.01377868705417654, "acc_norm": 0.6988054607508533, "acc_norm_stderr": 0.01340674176784764 }, "harness|hellaswag|10": { "acc": 0.6845249950209121, "acc_stderr": 0.0046375504780073636, "acc_norm": 0.8734315873332006, "acc_norm_stderr": 0.0033180935797029183 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, ... }

配置详情

  • config_name: harness_arc_challenge_25

    • split: 2024_01_28T06_31_36.611463
      • path: **/details_harness|arc:challenge|25_2024-01-28T06-31-36.611463.parquet
    • split: 2024_01_28T06_45_28.511432
      • path: **/details_harness|arc:challenge|25_2024-01-28T06-45-28.511432.parquet
    • split: 2024_01_28T19_27_06.867214
      • path: **/details_harness|arc:challenge|25_2024-01-28T19-27-06.867214.parquet
    • split: latest
      • path: **/details_harness|arc:challenge|25_2024-01-28T19-27-06.867214.parquet
  • config_name: harness_gsm8k_5

    • split: 2024_01_28T06_31_36.611463
      • path: **/details_harness|gsm8k|5_2024-01-28T06-31-36.611463.parquet
    • split: 2024_01_28T06_45_28.511432
      • path: **/details_harness|gsm8k|5_2024-01-28T06-45-28.511432.parquet
    • split: 2024_01_28T19_27_06.867214
      • path: **/details_harness|gsm8k|5_2024-01-28T19-27-06.867214.parquet
    • split: latest
      • path: **/details_harness|gsm8k|5_2024-01-28T19-27-06.867214.parquet
  • config_name: harness_hellaswag_10

    • split: 2024_01_28T06_31_36.611463
      • path: **/details_harness|hellaswag|10_2024-01-28T06-31-36.611463.parquet
    • split: 2024_01_28T06_45_28.511432
      • path: **/details_harness|hellaswag|10_2024-01-28T06-45-28.511432.parquet
    • split: 2024_01_28T19_27_06.867214
      • path: **/details_harness|hellaswag|10_2024-01-28T19-27-06.867214.parquet
    • split: latest
      • path: **/details_harness|hellaswag|10_2024-01-28T19-27-06.867214.parquet
  • config_name: harness_hendrycksTest_5

    • split: 2024_01_28T06_31_36.611463
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-28T06-31-36.611463.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2024-01-28T06-31-36.611463.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2024-01-28T06-31-36.611463.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2024-01-28T06-31-36.611463.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-28T06-31-36.611463.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2024-01-28T06-31-36.611463.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2024-01-28T06-31-36.611463.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2024-01-28T06-31-36.611463.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2024-01-28T06-31-36.611463.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2024-01-28T06-31-36.611463.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2024-01-28T06-31-36.611463.parquet
    • split: 2024_01_28T06_45_28.511432
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-28T06-45-28.511432.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2024-01-28T06-45-28.511432.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2024-01-28T06-45-28.511432.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2024-01-28T06-45-28.511432.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-28T06-45-28.511432.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2024-01-28T06-45-28.511432.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2024-01-28T06-45-28.511432.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2024-01-28T06-45-28.511432.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2024-01-28T06-45-28.511432.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2024-01-28T06-45-28.511432.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2024-01-28T06-45-28.511432.parquet
    • split: 2024_01_28T19_27_06.867214
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-28T19-27-06.867214.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2024-01-28T19-27-06.867214.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2024-01-28T19-27-06.867214.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2024-01-28T19-27-06.867214.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-28T19-27-06.867214.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2024-01-28T19-27-06.867214.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2024-01-28T19-27-06.867214.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2024-01-28T19-27-06.867214.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2024-01-28T19-27-06.867214.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2024-01-28T19-27-06.867214.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2024-01-28T19-27-06.867214.parquet
    • split: latest
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-28T19-27-06.867214.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2024-01-28T19-27-06.867214.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2024-01-28T19-27-06.867214.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2024-01-28T19-27-06.867214.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-28T19-27-06.867214.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2024-01-28T19-27-06
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