five

open-llm-leaderboard-old/details_seyf1elislam__WestKunai-X-7b

收藏
Hugging Face2024-03-07 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_seyf1elislam__WestKunai-X-7b
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 seyf1elislam/WestKunai-X-7b 在 Open LLM Leaderboard 上的评估运行期间自动创建的。数据集由 63 个配置组成,每个配置对应一个被评估的任务。数据集是从一次或多次运行中生成的,每次运行都作为每个配置中的一个特定分割存储。train 分割始终指向最新的结果。一个名为 results 的额外配置存储了所有运行的聚合结果,这些结果用于计算和显示 Open LLM Leaderboard 上的聚合指标。README 还提供了如何使用 datasets 库加载数据集的示例,并包含了特定运行的最新结果。

该数据集是在模型 seyf1elislam/WestKunai-X-7b 在 Open LLM Leaderboard 上的评估运行期间自动创建的。数据集由 63 个配置组成,每个配置对应一个被评估的任务。数据集是从一次或多次运行中生成的,每次运行都作为每个配置中的一个特定分割存储。train 分割始终指向最新的结果。一个名为 results 的额外配置存储了所有运行的聚合结果,这些结果用于计算和显示 Open LLM Leaderboard 上的聚合指标。README 还提供了如何使用 datasets 库加载数据集的示例,并包含了特定运行的最新结果。
提供机构:
open-llm-leaderboard-old
原始信息汇总

数据集概述

数据集来源

该数据集是在评估模型 seyf1elislam/WestKunai-X-7bOpen LLM Leaderboard 上的自动创建的。

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。数据集从 1 次运行中创建,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_seyf1elislam__WestKunai-X-7b", "harness_winogrande_5", split="train")

最新结果

以下是 最新结果 的摘要:

python { "all": { "acc": 0.6590899971602918, "acc_stderr": 0.03182934425098771, "acc_norm": 0.658926884007924, "acc_norm_stderr": 0.03248697366155038, "mc1": 0.5275397796817626, "mc1_stderr": 0.01747693019071219, "mc2": 0.680060645857469, "mc2_stderr": 0.014977490893069068 }, "harness|arc:challenge|25": { "acc": 0.6834470989761092, "acc_stderr": 0.013592431519068074, "acc_norm": 0.7107508532423208, "acc_norm_stderr": 0.013250012579393441 }, "harness|hellaswag|10": { "acc": 0.7067317267476598, "acc_stderr": 0.004543299338935427, "acc_norm": 0.8786098386775543, "acc_norm_stderr": 0.0032591270576681724 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, # 其他任务的结果... }

配置详情

  • config_name: harness_arc_challenge_25

    • split: 2024_03_07T17_17_30.755145
      • path: **/details_harness|arc:challenge|25_2024-03-07T17-17-30.755145.parquet
    • split: latest
      • path: **/details_harness|arc:challenge|25_2024-03-07T17-17-30.755145.parquet
  • config_name: harness_gsm8k_5

    • split: 2024_03_07T17_17_30.755145
      • path: **/details_harness|gsm8k|5_2024-03-07T17-17-30.755145.parquet
    • split: latest
      • path: **/details_harness|gsm8k|5_2024-03-07T17-17-30.755145.parquet
  • config_name: harness_hellaswag_10

    • split: 2024_03_07T17_17_30.755145
      • path: **/details_harness|hellaswag|10_2024-03-07T17-17-30.755145.parquet
    • split: latest
      • path: **/details_harness|hellaswag|10_2024-03-07T17-17-30.755145.parquet
  • config_name: harness_hendrycksTest_5

    • split: 2024_03_07T17_17_30.755145
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-international_law|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-management|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-marketing|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-professional_accounting|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-professional_law|5_2024-03-07T17-17-30.755145.parquet
        • **/details_harness|hendrycksTest-professional_medicine|5_2024-03
二维码
社区交流群
二维码
科研交流群
商业服务