open-llm-leaderboard-old/details_migtissera__Tess-M-v1.3

该数据集是在Open LLM Leaderboard上对模型migtissera/Tess-M-v1.3进行评估时自动创建的。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

该数据集是在评估模型 migtissera/Tess-M-v1.3 在 Open LLM Leaderboard 上的运行过程中自动创建的。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，每次运行的详细结果可以在每个配置的特定分割中找到，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，每个配置对应一个评估任务。以下是部分配置的详细信息：

配置示例

• 配置名称: harness_arc_challenge_25

  • 数据文件:
    • 分割: 2023_12_04T23_32_51.712332
      • 路径: **/details_harness|arc:challenge|25_2023-12-04T23-32-51.712332.parquet
    • 分割: latest
      • 路径: **/details_harness|arc:challenge|25_2023-12-04T23-32-51.712332.parquet

• 配置名称: harness_gsm8k_5

  • 数据文件:
    • 分割: 2023_12_04T23_32_51.712332
      • 路径: **/details_harness|gsm8k|5_2023-12-04T23-32-51.712332.parquet
    • 分割: latest
      • 路径: **/details_harness|gsm8k|5_2023-12-04T23-32-51.712332.parquet

• 配置名称: harness_hellaswag_10

  • 数据文件:
    • 分割: 2023_12_04T23_32_51.712332
      • 路径: **/details_harness|hellaswag|10_2023-12-04T23-32-51.712332.parquet
    • 分割: latest
      • 路径: **/details_harness|hellaswag|10_2023-12-04T23-32-51.712332.parquet

• 配置名称: harness_hendrycksTest_5

  • 数据文件:
    • 分割: 2023_12_04T23_32_51.712332
      • 路径:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-12-04T23-32-51.712332.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-12-04T23-32-51.712332.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2023-12-04T23-32-51.712332.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2023-12-04T23-32-51.712332.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-04T23-32-51.712332.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2023-12-04T23-32-51.712332.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2023-12-04T23-32-51.712332.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2023-12-04T23-32-51.712332.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2023-12-04T23-32-51.712332.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2023-12-04T23-32-51.712332.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2023-12-04T23-32-51.712332.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2023-12-04T23-32-51.712332.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2023-12-04T23-32-51.712332.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2023-12-04T23-32-51.712332.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2023-12-04T23-32-51.712332.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-04T23-32-51.712332.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2023-12-04T23-32-51.712332.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2023-12-04T23-32-51.712332.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2023-12-04T23-32-51.712332.parquet
        • ...

最新结果

以下是来自 2023-12-04T23:32:51.712332 运行的最新结果：

python { "all": { "acc": 0.747566002523043, "acc_stderr": 0.028749261755203245, "acc_norm": 0.7529037953743296, "acc_norm_stderr": 0.029285728391357593, "mc1": 0.397796817625459, "mc1_stderr": 0.017133934248559638, "mc2": 0.5603469779031626, "mc2_stderr": 0.015661408014010857 }, "harness|arc:challenge|25": { "acc": 0.5921501706484642, "acc_stderr": 0.014361097288449705, "acc_norm": 0.6254266211604096, "acc_norm_stderr": 0.014144193471893456 }, "harness|hellaswag|10": { "acc": 0.6494722166899024, "acc_stderr": 0.004761601303258892, "acc_norm": 0.8394742083250348, "acc_norm_stderr": 0.0036634275361781586 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7111111111111111, "acc_stderr": 0.03915450630414251, "acc_norm": 0.7111111111111111, "acc_norm_stderr": 0.03915450630414251 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8618421052631579, "acc_stderr": 0.028081042939576552, "acc_norm": 0.8618421052631579, "acc_norm_stderr": 0.028081042939576552 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.76, "acc_stderr": 0.04292346959909283, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8377358490566038, "acc_stderr": 0.022691482872035353, "acc_norm": 0.8377358490566038, "acc_norm_stderr": 0.022691482872035353 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8888888888888888, "acc_stderr": 0.026280550932848062, "acc_norm": 0.8888888888888888, "acc_norm_stderr": 0.026280550932848062 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.54, "acc_stderr": 0.05009082659620333, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.48, "acc_stderr": 0.05021167315686779, "acc_norm": 0.48, "acc_norm_stderr": 0.05021167315686779 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7109826589595376, "acc_stderr": 0.03456425745086999, "acc_norm": 0.7109826589595376, "acc_norm_stderr": 0.03456425745086999 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.43137254901960786, "acc_stderr": 0.04928099597287534, "acc_norm": 0.43137254901960786, "acc_norm_stderr": 0.04928099597287534 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.82, "acc_stderr": 0.03861229196653695, "acc_norm": 0.82, "acc_norm_stderr": 0.03861229196653695 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7829787234042553, "acc_stderr": 0.026947483121496228, "acc_norm": 0.7829787234042553, "acc_norm_stderr": 0.026947483121496228 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5789473684210527, "acc_stderr": 0.046446020912223177, "acc_norm": 0.5789473684210527, "acc_norm_stderr": 0.046446020912223177 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7448275862068966, "acc_stderr": 0.03632984052707842, "acc_norm": 0.7448275862068966, "acc_norm_stderr": 0.03632984052707842 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6640211640211641, "acc_stderr": 0.024326310