five

open-llm-leaderboard/details_Sao10K__Mythical-Destroyer-L2-13B

收藏
Hugging Face2023-09-22 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_Sao10K__Mythical-Destroyer-L2-13B
下载链接
链接失效反馈
官方服务:
资源简介:
数据集Sao10K/Mythical-Destroyer-L2-13B是在模型Sao10K/Mythical-Destroyer-L2-13B在Open LLM Leaderboard上的评估运行中自动生成的。数据集由64个配置组成,每个配置对应一个评估任务。数据集由2次运行生成,每次运行的结果作为一个特定的分割存储,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,还有一个名为results的配置,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
原始信息汇总

数据集概述

该数据集是在评估模型 Sao10K/Mythical-Destroyer-L2-13BOpen LLM Leaderboard 上的自动创建的。数据集包含 64 个配置,每个配置对应一个评估任务。

数据集结构

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。

结果配置

一个额外的配置 "results" 存储所有运行的聚合结果,用于计算和显示在 Open LLM Leaderboard 上的聚合指标。

加载数据示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Sao10K__Mythical-Destroyer-L2-13B", "harness_winogrande_5", split="train")

最新结果

以下是 2023-09-22T17:08:07.137217 运行的最新结果

python { "all": { "em": 0.016254194630872482, "em_stderr": 0.0012949822806761588, "f1": 0.12557990771812008, "f1_stderr": 0.0022451692243357826, "acc": 0.4180536664965267, "acc_stderr": 0.010042668742086671 }, "harness|drop|3": { "em": 0.016254194630872482, "em_stderr": 0.0012949822806761588, "f1": 0.12557990771812008, "f1_stderr": 0.0022451692243357826 }, "harness|gsm8k|5": { "acc": 0.08946171341925702, "acc_stderr": 0.007861583049939723 }, "harness|winogrande|5": { "acc": 0.7466456195737964, "acc_stderr": 0.012223754434233618 } }

配置详情

  • config_name: harness_arc_challenge_25

    • data_files:
      • split: 2023_08_29T20_22_32.646135
        • path: **/details_harness|arc:challenge|25_2023-08-29T20:22:32.646135.parquet
      • split: latest
        • path: **/details_harness|arc:challenge|25_2023-08-29T20:22:32.646135.parquet
  • config_name: harness_drop_3

    • data_files:
      • split: 2023_09_22T17_08_07.137217
        • path: **/details_harness|drop|3_2023-09-22T17-08-07.137217.parquet
      • split: latest
        • path: **/details_harness|drop|3_2023-09-22T17-08-07.137217.parquet
  • config_name: harness_gsm8k_5

    • data_files:
      • split: 2023_09_22T17_08_07.137217
        • path: **/details_harness|gsm8k|5_2023-09-22T17-08-07.137217.parquet
      • split: latest
        • path: **/details_harness|gsm8k|5_2023-09-22T17-08-07.137217.parquet
  • config_name: harness_hellaswag_10

    • data_files:
      • split: 2023_08_29T20_22_32.646135
        • path: **/details_harness|hellaswag|10_2023-08-29T20:22:32.646135.parquet
      • split: latest
        • path: **/details_harness|hellaswag|10_2023-08-29T20:22:32.646135.parquet
  • config_name: harness_hendrycksTest_5

    • data_files:
      • split: 2023_08_29T20_22_32.646135
        • path:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-college_biology|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-college_chemistry|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-college_computer_science|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-college_mathematics|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-college_medicine|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-college_physics|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-computer_security|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-conceptual_physics|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-econometrics|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-electrical_engineering|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-formal_logic|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-global_facts|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-high_school_biology|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-high_school_european_history|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-high_school_geography|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-high_school_physics|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-high_school_psychology|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-high_school_statistics|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-high_school_us_history|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-high_school_world_history|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-human_aging|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-human_sexuality|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-international_law|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-jurisprudence|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-logical_fallacies|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-machine_learning|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-management|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-marketing|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-medical_genetics|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-miscellaneous|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-moral_disputes|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-moral_scenarios|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-nutrition|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-philosophy|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-prehistory|5_2023-08-29T20:22:32.646135.parquet
          • **/details_harness|hendrycksTest-professional_accounting|5_2023-08-29T20:22:32.
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