five

open-llm-leaderboard-old/details_ontocord__Felix-8B

收藏
Hugging Face2024-03-24 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_ontocord__Felix-8B
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ontocord/Felix-8B进行评估时自动创建的。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,每次运行可以在每个配置的特定分割中找到,分割以运行的时间戳命名。train分割始终指向最新结果。此外,results配置存储了所有运行的聚合结果,并用于计算和显示Open LLM Leaderboard上的聚合指标。

该数据集是在Open LLM Leaderboard上对模型ontocord/Felix-8B进行评估时自动创建的。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,每次运行可以在每个配置的特定分割中找到,分割以运行的时间戳命名。train分割始终指向最新结果。此外,results配置存储了所有运行的聚合结果,并用于计算和显示Open LLM 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

数据集简介

该数据集是在对模型ontocord/Felix-8B进行评估运行期间自动创建的,评估结果展示在Open LLM Leaderboard上。

数据集结构

  • 数据集包含63个配置,每个配置对应一个评估任务。
  • 数据集来自1次运行,每次运行在每个配置中都有特定的分割,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"results"配置存储所有运行的聚合结果,用于计算和显示聚合指标。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_ontocord__Felix-8B", "harness_winogrande_5", split="train")

最新结果

以下是2024-03-24T15:20:31.705809运行的最新结果:

python { "all": { "acc": 0.612649700691218, "acc_stderr": 0.03305040966646445, "acc_norm": 0.6151543718243965, "acc_norm_stderr": 0.03371183008869724, "mc1": 0.4810281517747858, "mc1_stderr": 0.01749089640576235, "mc2": 0.6423168880426268, "mc2_stderr": 0.015674777578177736 }, "harness|arc:challenge|25": { "acc": 0.6245733788395904, "acc_stderr": 0.014150631435111728, "acc_norm": 0.6501706484641638, "acc_norm_stderr": 0.013936809212158292 }, "harness|hellaswag|10": { "acc": 0.6721768571997611, "acc_stderr": 0.00468460631064233, "acc_norm": 0.8461461860187214, "acc_norm_stderr": 0.00360071170449341 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, # 其他任务的结果... }

配置详情

  • harness_arc_challenge_25

    • 分割: 2024_03_24T15_20_31.705809, latest
    • 路径: **/details_harness|arc:challenge|25_2024-03-24T15-20-31.705809.parquet
  • harness_gsm8k_5

    • 分割: 2024_03_24T15_20_31.705809, latest
    • 路径: **/details_harness|gsm8k|5_2024-03-24T15-20-31.705809.parquet
  • harness_hellaswag_10

    • 分割: 2024_03_24T15_20_31.705809, latest
    • 路径: **/details_harness|hellaswag|10_2024-03-24T15-20-31.705809.parquet
  • harness_hendrycksTest_5

    • 分割: 2024_03_24T15_20_31.705809
    • 路径:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-astronomy|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-business_ethics|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-college_biology|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-college_chemistry|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-college_computer_science|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-college_mathematics|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-college_medicine|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-college_physics|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-computer_security|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-econometrics|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-formal_logic|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-global_facts|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-high_school_biology|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-high_school_computer_science|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-high_school_european_history|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-high_school_geography|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-high_school_mathematics|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-high_school_physics|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-high_school_psychology|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-high_school_statistics|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-high_school_us_history|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-high_school_world_history|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-human_aging|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-human_sexuality|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-international_law|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-jurisprudence|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-logical_fallacies|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-machine_learning|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-management|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-marketing|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-medical_genetics|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-miscellaneous|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-moral_disputes|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-moral_scenarios|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-nutrition|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-philosophy|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-prehistory|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-professional_accounting|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-professional_law|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-professional_medicine|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-professional_psychology|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-public_relations|5_2024-03-24T15-20-31.705809.parquet
      • **/details_harness|hendrycksTest-security_studies|5_2024-03-24T15-20-31.705809.parquet
      • `**/details_harness|hendrycksTest-sociology|5_2024
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