open-llm-leaderboard-old/details_automerger__Experiment27Neuralsirkrishna-7B

该数据集是在模型 automerger/Experiment27Neuralsirkrishna-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，每个配置对应一个评估任务。数据集包含 1 次运行的数据，每次运行在每个配置中表示为特定的分割，train 分割始终指向最新结果。名为 results 的额外配置存储了运行的所有聚合结果，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 Python 中的 datasets 库加载运行中的详细信息的示例。

原始信息汇总

数据集概述

数据集简介

该数据集是在对模型 automerger/Experiment27Neuralsirkrishna-7B 进行评估运行期间自动创建的。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，每次运行的详细信息可以在每个配置中找到，使用运行的时间戳作为分割名称。"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，每个配置对应一个特定的评估任务。每个配置包含多个分割，其中 "train" 分割指向最新的结果。

配置示例

• config_name: harness_arc_challenge_25

  • data_files:
    • split: 2024_03_11T19_51_50.411484
      • path: **/details_harness|arc:challenge|25_2024-03-11T19-51-50.411484.parquet
    • split: latest
      • path: **/details_harness|arc:challenge|25_2024-03-11T19-51-50.411484.parquet

• config_name: harness_gsm8k_5

  • data_files:
    • split: 2024_03_11T19_51_50.411484
      • path: **/details_harness|gsm8k|5_2024-03-11T19-51-50.411484.parquet
    • split: latest
      • path: **/details_harness|gsm8k|5_2024-03-11T19-51-50.411484.parquet

• config_name: harness_hellaswag_10

  • data_files:
    • split: 2024_03_11T19_51_50.411484
      • path: **/details_harness|hellaswag|10_2024-03-11T19-51-50.411484.parquet
    • split: latest
      • path: **/details_harness|hellaswag|10_2024-03-11T19-51-50.411484.parquet

• config_name: harness_hendrycksTest_5

  • data_files:
    • split: 2024_03_11T19_51_50.411484
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-11T19-51-50.411484.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2024-03-11T19-51-50.411484.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2024-03-11T19-51-50.411484.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2024-03-11T19-51-50.411484.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-11T19-51-50.411484.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2024-03-11T19-51-50.411484.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2024-03-11T19-51-50.411484.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2024-03-11T19-51-50.411484.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2024-03-11T19-51-50.411484.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2024-03-11T19-51-50.411484.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2024-03-11T19-51-50.411484.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2024-03-11T19-51-50.411484.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-11T19-51-50.411484.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2024-03-11T19-51-50.411484.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-11T19-51-50.411484.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-11T19-51-50.411484.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2024-03-11T19-51-50.411484.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2024-03-11T19-51-50.411484.parquet

最新结果

以下是来自 2024-03-11T19:51:50.411484 运行的最新结果：

python { "all": { "acc": 0.6525135225054541, "acc_stderr": 0.03207449149012873, "acc_norm": 0.6518414876767434, "acc_norm_stderr": 0.03274696054605214, "mc1": 0.616891064871481, "mc1_stderr": 0.017018461679389855, "mc2": 0.7739528869601758, "mc2_stderr": 0.013774958307913162 }, "harness|arc:challenge|25": { "acc": 0.7107508532423208, "acc_stderr": 0.013250012579393441, "acc_norm": 0.7320819112627986, "acc_norm_stderr": 0.012942030195136438 }, "harness|hellaswag|10": { "acc": 0.7142003584943238, "acc_stderr": 0.004508710891053863, "acc_norm": 0.8903604859589723, "acc_norm_stderr": 0.003118013608669293 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6518518518518519, "acc_stderr": 0.041153246103369526, "acc_norm": 0.6518518518518519, "acc_norm_stderr": 0.041153246103369526 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7039473684210527, "acc_stderr": 0.03715062154998904, "acc_norm": 0.7039473684210527, "acc_norm_stderr": 0.03715062154998904 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.64, "acc_stderr": 0.04824181513244218, "acc_norm": 0.64, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7094339622641509, "acc_stderr": 0.02794321998933714, "acc_norm": 0.7094339622641509, "acc_norm_stderr": 0.02794321998933714 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7708333333333334, "acc_stderr": 0.03514697467862388, "acc_norm": 0.7708333333333334, "acc_norm_stderr": 0.03514697467862388 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6473988439306358, "acc_stderr": 0.036430371689585475, "acc_norm": 0.6473988439306358, "acc_norm_stderr": 0.036430371689585475 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.39215686274509803, "acc_stderr": 0.04858083574266345, "acc_norm": 0.39215686274509803, "acc_norm_stderr": 0.04858083574266345 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5531914893617021, "acc_stderr": 0.0325005368436584, "acc_norm": 0.5531914893617021, "acc_norm_stderr": 0.0325005368436584 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.47368421052631576, "acc_stderr": 0.046970851366478626, "acc_norm": 0.47368421052631576, "acc_norm_stderr": 0.046970851366478626 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5448275862068965, "acc_stderr": 0.04149886942192117, "acc_norm": 0.5448275862068965, "acc_norm_stderr": 0.04149886942192117 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.41798941798941797, "acc_stderr": 0.025402555503260912, "acc_norm": 0.41798941798941797, "acc_norm_stderr": 0.025402555503260912 }, "harness|hendrycks