five

open-llm-leaderboard/details_TheBloke__robin-33B-v2-fp16

收藏
Hugging Face2023-08-27 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_TheBloke__robin-33B-v2-fp16
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TheBloke/robin-33B-v2-fp16的评估运行期间自动创建的,用于Open LLM Leaderboard的评估。数据集由61个配置组成,每个配置对应一个评估任务。数据集从1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,分割以运行的时间戳命名。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,并用于计算和显示Open LLM Leaderboard上的聚合指标。

This dataset was automatically created during the evaluation run of the model TheBloke/robin-33B-v2-fp16, and is intended for evaluations on the Open LLM Leaderboard. The dataset comprises 61 configurations, each corresponding to one evaluation task. It is generated from a single run, where each configuration includes a specific split named after the timestamp of the run. The "train" split always points to the most recent results. Additionally, the "results" configuration stores the aggregated results across all runs, and is used to calculate and display the aggregate metrics on the Open LLM Leaderboard.
提供机构:
open-llm-leaderboard
原始信息汇总

数据集概述

数据集简介

该数据集是在评估模型 TheBloke/robin-33B-v2-fp16Open LLM Leaderboard 上的自动创建的。

数据集组成

  • 数据集包含 61 个配置,每个配置对应一个评估任务。
  • 数据集来自 1 次运行,每个运行可以在每个配置中作为一个特定的分片找到,分片名称使用运行的时间戳。
  • "train" 分片总是指向最新的结果。
  • 一个额外的配置 "results" 存储所有运行的聚合结果,用于计算和显示在 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_TheBloke__robin-33B-v2-fp16", "harness_truthfulqa_mc_0", split="train")

最新结果

这些是最新的结果,来自 2023-07-31T16:41:32.452325 的运行: python { "all": { "acc": 0.5493694357469432, "acc_stderr": 0.03462857618448208, "acc_norm": 0.5533043005336739, "acc_norm_stderr": 0.03460642548466365, "mc1": 0.3574051407588739, "mc1_stderr": 0.016776599676729398, "mc2": 0.5388029530988832, "mc2_stderr": 0.014742138833066059 }, "harness|arc:challenge|25": { "acc": 0.5947098976109215, "acc_stderr": 0.014346869060229321, "acc_norm": 0.6237201365187713, "acc_norm_stderr": 0.014157022555407156 }, "harness|hellaswag|10": { "acc": 0.6331408086038638, "acc_stderr": 0.004809626723626824, "acc_norm": 0.8362875921131249, "acc_norm_stderr": 0.0036925819391622834 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, # 其他任务的结果... }

配置详情

  • harness_arc_challenge_25

    • 分片:2023_07_31T16_41_32.452325
    • 路径:**/details_harness|arc:challenge|25_2023-07-31T16:41:32.452325.parquet
    • 分片:latest
    • 路径:**/details_harness|arc:challenge|25_2023-07-31T16:41:32.452325.parquet
  • harness_hellaswag_10

    • 分片:2023_07_31T16_41_32.452325
    • 路径:**/details_harness|hellaswag|10_2023-07-31T16:41:32.452325.parquet
    • 分片:latest
    • 路径:**/details_harness|hellaswag|10_2023-07-31T16:41:32.452325.parquet
  • harness_hendrycksTest_5

    • 分片:2023_07_31T16_41_32.452325
    • 路径:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-astronomy|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-business_ethics|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-college_biology|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-college_chemistry|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-college_computer_science|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-college_mathematics|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-college_medicine|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-college_physics|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-computer_security|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-conceptual_physics|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-econometrics|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-electrical_engineering|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-formal_logic|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-global_facts|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-high_school_biology|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-high_school_european_history|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-high_school_geography|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-high_school_physics|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-high_school_psychology|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-high_school_statistics|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-high_school_us_history|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-high_school_world_history|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-human_aging|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-human_sexuality|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-international_law|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-jurisprudence|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-logical_fallacies|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-machine_learning|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-management|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-marketing|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-medical_genetics|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-miscellaneous|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-moral_disputes|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-moral_scenarios|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-nutrition|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-philosophy|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-prehistory|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-professional_accounting|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-professional_law|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-professional_medicine|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-professional_psychology|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-public_relations|5_2023-07-31T16:41:32.452325.parquet
      • **/details_harness|hendrycksTest-security_studies|5_2023-07-31T16:41:32.452325.parquet
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