open-llm-leaderboard-old/details_Muhammad2003__Llama3-8B-OpenHermes-DPO

该数据集是在模型Muhammad2003/Llama3-8B-OpenHermes-DPO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，每个配置对应一个评估任务。数据集是从1次运行中创建的，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。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。

原始信息汇总

数据集概述

数据集摘要

该数据集是在评估模型 Muhammad2003/Llama3-8B-OpenHermes-DPO 在 Open LLM Leaderboard 上的自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。数据集从 1 次运行中创建，每个运行可以在每个配置中找到一个特定的分割，分割名称使用运行的时间戳。"train" 分割始终指向最新的结果。

数据集结构

数据集包含多个配置，每个配置对应不同的评估任务。以下是部分配置的详细信息：

配置示例

• config_name: harness_arc_challenge_25

  • data_files:
    • split: 2024_04_19T03_18_30.812682
      • path: **/details_harness|arc:challenge|25_2024-04-19T03-18-30.812682.parquet
    • split: latest
      • path: **/details_harness|arc:challenge|25_2024-04-19T03-18-30.812682.parquet

• config_name: harness_gsm8k_5

  • data_files:
    • split: 2024_04_19T03_18_30.812682
      • path: **/details_harness|gsm8k|5_2024-04-19T03-18-30.812682.parquet
    • split: latest
      • path: **/details_harness|gsm8k|5_2024-04-19T03-18-30.812682.parquet

• config_name: harness_hellaswag_10

  • data_files:
    • split: 2024_04_19T03_18_30.812682
      • path: **/details_harness|hellaswag|10_2024-04-19T03-18-30.812682.parquet
    • split: latest
      • path: **/details_harness|hellaswag|10_2024-04-19T03-18-30.812682.parquet

• config_name: harness_hendrycksTest_5

  • data_files:
    • split: 2024_04_19T03_18_30.812682
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2024-04-19T03-18-30.812682.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2024-04-19T03-18-30.812682.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2024-04-19T03-18-30.812682.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2024-04-19T03-18-30.812682.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-19T03-18-30.812682.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2024-04-19T03-18-30.812682.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2024-04-19T03-18-30.812682.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2024-04-19T03-18-30.812682.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2024-04-19T03-18-30.812682.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2024-04-19T03-18-30.812682.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2024-04-19T03-18-30.812682.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2024-04-19T03-18-30.812682.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2024-04-19T03-18-30.812682.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2024-04-19T03-18-30.812682.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2024-04-19T03-18-30.812682.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-04-19T03-18-30.812682.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2024-04-19T03-18-30.812682.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2024-04-19T03-18-30.812682.parquet

最新结果

以下是 2024-04-19T03:18:30.812682 运行 的最新结果：

python { "all": { "acc": 0.6608427709889227, "acc_stderr": 0.031660872222455005, "acc_norm": 0.6669326217270022, "acc_norm_stderr": 0.032279919939724726, "mc1": 0.2692778457772338, "mc1_stderr": 0.015528566637087286, "mc2": 0.4402682656896514, "mc2_stderr": 0.013925471634741886 }, "harness|arc:challenge|25": { "acc": 0.5435153583617748, "acc_stderr": 0.014555949760496439, "acc_norm": 0.5972696245733788, "acc_norm_stderr": 0.014332236306790147 }, "harness|hellaswag|10": { "acc": 0.6175064728141805, "acc_stderr": 0.0048500288131899764, "acc_norm": 0.8204540928101972, "acc_norm_stderr": 0.003830243764332978 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6888888888888889, "acc_stderr": 0.039992628766177214, "acc_norm": 0.6888888888888889, "acc_norm_stderr": 0.039992628766177214 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6842105263157895, "acc_stderr": 0.037827289808654685, "acc_norm": 0.6842105263157895, "acc_norm_stderr": 0.037827289808654685 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.62, "acc_stderr": 0.048783173121456316, "acc_norm": 0.62, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7584905660377359, "acc_stderr": 0.026341480371118352, "acc_norm": 0.7584905660377359, "acc_norm_stderr": 0.026341480371118352 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7777777777777778, "acc_stderr": 0.03476590104304134, "acc_norm": 0.7777777777777778, "acc_norm_stderr": 0.03476590104304134 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6358381502890174, "acc_stderr": 0.03669072477416907, "acc_norm": 0.6358381502890174, "acc_norm_stderr": 0.03669072477416907 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.49019607843137253, "acc_stderr": 0.04974229460422817, "acc_norm": 0.49019607843137253, "acc_norm_stderr": 0.04974229460422817 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.81, "acc_stderr": 0.03942772444036624, "acc_norm": 0.81, "acc_norm_stderr": 0.03942772444036624 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5872340425531914, "acc_stderr": 0.03218471141400351, "acc_norm": 0.5872340425531914, "acc_norm_stderr": 0.03218471141400351 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5, "acc_stderr": 0.047036043419179864, "acc_norm": 0.5, "acc_norm_stderr": 0.047036043419179864 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6482758620689655, "acc_stderr": 0.0397923663749741, "acc_norm": 0.6482758620689655, "acc_norm_stderr": 0.0397923663749741 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4