five

open-llm-leaderboard-old/details_Weyaxi__Einstein-v6-7B

收藏
Hugging Face2024-04-07 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_Weyaxi__Einstein-v6-7B
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 Weyaxi/Einstein-v6-7B 在 Open LLM Leaderboard 上的评估运行期间自动创建的。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。此外,results 配置存储了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。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。

该数据集是在模型 Weyaxi/Einstein-v6-7B 在 Open LLM Leaderboard 上的评估运行期间自动创建的。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。此外,results 配置存储了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。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。
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 Weyaxi/Einstein-v6-7B 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 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。
  • 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_Weyaxi__Einstein-v6-7B", "harness_winogrande_5", split="train")

最新结果

以下是 2024-04-07T23:08:14.135508 运行的最新结果

python { "all": { "acc": 0.6249346822625347, "acc_stderr": 0.03265093006175728, "acc_norm": 0.6260138397047245, "acc_norm_stderr": 0.033315262754761814, "mc1": 0.3537331701346389, "mc1_stderr": 0.016737814358846147, "mc2": 0.5202006447699588, "mc2_stderr": 0.015081682299858599 }, "harness|arc:challenge|25": { "acc": 0.5947098976109215, "acc_stderr": 0.014346869060229318, "acc_norm": 0.6356655290102389, "acc_norm_stderr": 0.01406326027988242 }, "harness|hellaswag|10": { "acc": 0.6333399721171081, "acc_stderr": 0.004809077205343493, "acc_norm": 0.8276239792869946, "acc_norm_stderr": 0.0037693500791958954 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.047609522856952365, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952365 }, # 其他任务的结果省略... }

配置详情

  • harness_arc_challenge_25

    • 分割:2024_04_05T23_24_27.950456
      • 路径:**/details_harness|arc:challenge|25_2024-04-05T23-24-27.950456.parquet
    • 分割:2024_04_07T23_08_14.135508
      • 路径:**/details_harness|arc:challenge|25_2024-04-07T23-08-14.135508.parquet
    • 分割:latest
      • 路径:**/details_harness|arc:challenge|25_2024-04-07T23-08-14.135508.parquet
  • harness_gsm8k_5

    • 分割:2024_04_05T23_24_27.950456
      • 路径:**/details_harness|gsm8k|5_2024-04-05T23-24-27.950456.parquet
    • 分割:2024_04_07T23_08_14.135508
      • 路径:**/details_harness|gsm8k|5_2024-04-07T23-08-14.135508.parquet
    • 分割:latest
      • 路径:**/details_harness|gsm8k|5_2024-04-07T23-08-14.135508.parquet
  • harness_hellaswag_10

    • 分割:2024_04_05T23_24_27.950456
      • 路径:**/details_harness|hellaswag|10_2024-04-05T23-24-27.950456.parquet
    • 分割:2024_04_07T23_08_14.135508
      • 路径:**/details_harness|hellaswag|10_2024-04-07T23-08-14.135508.parquet
    • 分割:latest
      • 路径:**/details_harness|hellaswag|10_2024-04-07T23-08-14.135508.parquet
  • harness_hendrycksTest_5

    • 分割:2024_04_05T23_24_27.950456
      • 路径:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-international_law|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-management|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-marketing|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2024-04-05T23-24-27.950456.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2024-04-05T23-24-27.950456.parquet
        • `**/details_harness|hendrycksTest-nutrition
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