five

open-llm-leaderboard-old/details_LTC-AI-Labs__L2-7b-Hermes-WVG-Test

收藏
Hugging Face2023-10-23 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_LTC-AI-Labs__L2-7b-Hermes-WVG-Test
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在评估模型LTC-AI-Labs/L2-7b-Hermes-WVG-Test期间自动创建的,用于Open LLM Leaderboard。数据集包含64个配置,每个配置对应一个评估任务。数据集由2次运行创建,每次运行在每个配置中作为一个特定的分割存在,分割名称使用运行的时间戳命名。此外,还有一个名为results的配置,存储了所有运行的聚合结果,用于计算和显示Leaderboard上的聚合指标。

该数据集是在评估模型LTC-AI-Labs/L2-7b-Hermes-WVG-Test期间自动创建的,用于Open LLM Leaderboard。数据集包含64个配置,每个配置对应一个评估任务。数据集由2次运行创建,每次运行在每个配置中作为一个特定的分割存在,分割名称使用运行的时间戳命名。此外,还有一个名为results的配置,存储了所有运行的聚合结果,用于计算和显示Leaderboard上的聚合指标。
提供机构:
open-llm-leaderboard-old
原始信息汇总

数据集概述

数据集是在模型 LTC-AI-Labs/L2-7b-Hermes-WVG-TestOpen LLM Leaderboard 上的评估运行期间自动创建的。

数据集组成

  • 该数据集包含 64 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。

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_LTC-AI-Labs__L2-7b-Hermes-WVG-Test", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-23T11:36:43.083367 运行的最新结果: python { "all": { "em": 0.004614093959731544, "em_stderr": 0.0006940305886353454, "f1": 0.0669966442953021, "f1_stderr": 0.0015535849060621194, "acc": 0.4029062221565332, "acc_stderr": 0.009334616003613282 }, "harness|drop|3": { "em": 0.004614093959731544, "em_stderr": 0.0006940305886353454, "f1": 0.0669966442953021, "f1_stderr": 0.0015535849060621194 }, "harness|gsm8k|5": { "acc": 0.058377558756633814, "acc_stderr": 0.00645808355783246 }, "harness|winogrande|5": { "acc": 0.7474348855564326, "acc_stderr": 0.012211148449394105 } }

配置详情

  • config_name: harness_arc_challenge_25

    • split: 2023_10_04T09_05_10.171975
      • path: **/details_harness|arc:challenge|25_2023-10-04T09-05-10.171975.parquet
    • split: latest
      • path: **/details_harness|arc:challenge|25_2023-10-04T09-05-10.171975.parquet
  • config_name: harness_drop_3

    • split: 2023_10_23T11_36_43.083367
      • path: **/details_harness|drop|3_2023-10-23T11-36-43.083367.parquet
    • split: latest
      • path: **/details_harness|drop|3_2023-10-23T11-36-43.083367.parquet
  • config_name: harness_gsm8k_5

    • split: 2023_10_23T11_36_43.083367
      • path: **/details_harness|gsm8k|5_2023-10-23T11-36-43.083367.parquet
    • split: latest
      • path: **/details_harness|gsm8k|5_2023-10-23T11-36-43.083367.parquet
  • config_name: harness_hellaswag_10

    • split: 2023_10_04T09_05_10.171975
      • path: **/details_harness|hellaswag|10_2023-10-04T09-05-10.171975.parquet
    • split: latest
      • path: **/details_harness|hellaswag|10_2023-10-04T09-05-10.171975.parquet
  • config_name: harness_hendrycksTest_5

    • split: 2023_10_04T09_05_10.171975
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-international_law|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-management|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-marketing|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-professional_accounting|5_2023-10-04T09-05-10.171975.parquet
        • **/details_harness|hendrycksTest-professional_law|5_2023-10-04T0
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