five

open-llm-leaderboard-old/details_OEvortex__vortex-3b-v2

收藏
Hugging Face2024-03-22 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_OEvortex__vortex-3b-v2
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OEvortex/vortex-3b-v2进行评估时自动创建的。它由63个配置组成,每个配置对应一个评估任务。数据集是从1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,使用运行的时间戳命名。train分割始终指向最新的结果。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Open LLM Leaderboard上的聚合指标。可以使用`datasets`库中的`load_dataset`函数加载该数据集。

该数据集是在Open LLM Leaderboard上对模型OEvortex/vortex-3b-v2进行评估时自动创建的。它由63个配置组成,每个配置对应一个评估任务。数据集是从1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,使用运行的时间戳命名。train分割始终指向最新的结果。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Open LLM Leaderboard上的聚合指标。可以使用`datasets`库中的`load_dataset`函数加载该数据集。
提供机构:
open-llm-leaderboard-old
原始信息汇总

数据集概述

数据集描述

该数据集是在对模型 OEvortex/vortex-3b-v2 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。
  • 数据集由 1 次运行创建,每个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_OEvortex__vortex-3b-v2", "harness_winogrande_5", split="train")

最新结果

以下是 2024-03-22T01:39:03.287931 运行的最新结果

python { "all": { "acc": 0.2583531088279041, "acc_stderr": 0.030793547311393207, "acc_norm": 0.2601888180617266, "acc_norm_stderr": 0.03153852072302, "mc1": 0.22399020807833536, "mc1_stderr": 0.014594964329474203, "mc2": 0.3380010409129166, "mc2_stderr": 0.014377199793086676 }, "harness|arc:challenge|25": { "acc": 0.35494880546075086, "acc_stderr": 0.013983036904094094, "acc_norm": 0.3967576791808874, "acc_norm_stderr": 0.014296513020180628 }, "harness|hellaswag|10": { "acc": 0.48894642501493724, "acc_stderr": 0.00498856194427739, "acc_norm": 0.650368452499502, "acc_norm_stderr": 0.004758790172436687 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, # 其他任务的结果省略... }

配置详情

  • harness_arc_challenge_25

    • 分割:2024_03_22T01_39_03.287931
    • 路径:**/details_harness|arc:challenge|25_2024-03-22T01-39-03.287931.parquet
    • 分割:latest
    • 路径:**/details_harness|arc:challenge|25_2024-03-22T01-39-03.287931.parquet
  • harness_gsm8k_5

    • 分割:2024_03_22T01_39_03.287931
    • 路径:**/details_harness|gsm8k|5_2024-03-22T01-39-03.287931.parquet
    • 分割:latest
    • 路径:**/details_harness|gsm8k|5_2024-03-22T01-39-03.287931.parquet
  • harness_hellaswag_10

    • 分割:2024_03_22T01_39_03.287931
    • 路径:**/details_harness|hellaswag|10_2024-03-22T01-39-03.287931.parquet
    • 分割:latest
    • 路径:**/details_harness|hellaswag|10_2024-03-22T01-39-03.287931.parquet
  • harness_hendrycksTest_5

    • 分割:2024_03_22T01_39_03.287931
    • 路径:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-astronomy|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-business_ethics|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-college_biology|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-college_chemistry|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-college_computer_science|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-college_mathematics|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-college_medicine|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-college_physics|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-computer_security|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-econometrics|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-formal_logic|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-global_facts|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-high_school_biology|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-high_school_computer_science|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-high_school_european_history|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-high_school_geography|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-high_school_mathematics|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-high_school_physics|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-high_school_psychology|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-high_school_statistics|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-high_school_us_history|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-high_school_world_history|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-human_aging|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-human_sexuality|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-international_law|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-jurisprudence|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-logical_fallacies|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-machine_learning|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-management|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-marketing|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-medical_genetics|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-miscellaneous|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-moral_disputes|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-moral_scenarios|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-nutrition|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-philosophy|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-prehistory|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-professional_accounting|5_2024-03-22T01-39-03.287931.parquet
      • **/details_harness|hendrycksTest-professional_law|5_2024-03-22T01-39-03.287931.parquet
      • `**/details_harness
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