open-llm-leaderboard/details_pankajmathur__orca_mini_v3_70b

该数据集是在模型 pankajmathur/orca_mini_v3_70b 在 Open LLM Leaderboard 上的评估运行期间自动创建的。数据集由 61 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，每次运行在每个配置中作为一个特定的分割存在，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，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 库加载运行细节的示例。This dataset was automatically generated during the evaluation run of the model pankajmathur/orca_mini_v3_70b on the Open LLM Leaderboard. It consists of 61 configurations, each corresponding to one evaluation task. The dataset was constructed from a single run, where each run acts as a specific split under each configuration, and the split names use the timestamp of the run. The 'train' split always points to the most recent results. Additionally, there is a configuration named 'results' that stores the aggregated results of all runs, which are used to calculate and display the aggregate metrics on the Open LLM Leaderboard. The README also provides examples of how to load run details using the `datasets` library in Python.

原始信息汇总

数据集概述

该数据集是在对模型 pankajmathur/orca_mini_v3_70b 进行评估运行期间自动创建的。数据集包含 61 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。

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：

• 配置名称: harness_arc_challenge_25

  • 数据文件:
    • 分割: 2023_10_09T02_12_05.216705
      • 路径: **/details_harness|arc:challenge|25_2023-10-09T02-12-05.216705.parquet
    • 分割: latest
      • 路径: **/details_harness|arc:challenge|25_2023-10-09T02-12-05.216705.parquet

• 配置名称: harness_hellaswag_10

  • 数据文件:
    • 分割: 2023_10_09T02_12_05.216705
      • 路径: **/details_harness|hellaswag|10_2023-10-09T02-12-05.216705.parquet
    • 分割: latest
      • 路径: **/details_harness|hellaswag|10_2023-10-09T02-12-05.216705.parquet

• 配置名称: harness_hendrycksTest_5

  • 数据文件:
    • 分割: 2023_10_09T02_12_05.216705
      • 路径:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2023-10-09T02-12-05.216705.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-09T02-12-05.216705.parquet

最新结果

以下是 2023-10-09T02:12:05.216705 运行 的最新结果：

python { "all": { "acc": 0.7010508529623596, "acc_stderr": 0.0309286120388273, "acc_norm": 0.7049679984523141, "acc_norm_stderr": 0.030896356315399304, "mc1": 0.42962056303549573, "mc1_stderr": 0.017329234580409098, "mc2": 0.6126968953087459, "mc2_stderr": 0.015087648780065216 }, "harness|arc:challenge|25": { "acc": 0.6646757679180887, "acc_stderr": 0.013796182947785562, "acc_norm": 0.712457337883959, "acc_norm_stderr": 0.013226719056266129 }, "harness|hellaswag|10": { "acc": 0.6951802429794861, "acc_stderr": 0.00459390260197934, "acc_norm": 0.8785102569209321, "acc_norm_stderr": 0.0032602788112468337 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6296296296296297, "acc_stderr": 0.04171654161354543, "acc_norm": 0.6296296296296297, "acc_norm_stderr": 0.04171654161354543 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8157894736842105, "acc_stderr": 0.0315469804508223, "acc_norm": 0.8157894736842105, "acc_norm_stderr": 0.0315469804508223 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.77, "acc_stderr": 0.042295258468165044, "acc_norm": 0.77, "acc_norm_stderr": 0.042295258468165044 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7396226415094339, "acc_stderr": 0.027008766090708052, "acc_norm": 0.7396226415094339, "acc_norm_stderr": 0.027008766090708052 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8125, "acc_stderr": 0.032639560491693344, "acc_norm": 0.8125, "acc_norm_stderr": 0.032639560491693344 }, "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": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001974, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6589595375722543, "acc_stderr": 0.036146654241808254, "acc_norm": 0.6589595375722543, "acc_norm_stderr": 0.036146654241808254 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.38235294117647056, "acc_stderr": 0.04835503696107223, "acc_norm": 0.38235294117647056, "acc_norm_stderr": 0.04835503696107223 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.76, "acc_stderr": 0.042923469599092816, "acc_norm": 0.76, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6936170212765957, "acc_stderr": 0.03013590647851756, "acc_norm": 0.6936170212765957, "acc_norm_stderr": 0.03013590647851756 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4473684210526316, "acc_stderr": 0.04677473004491199, "acc_norm": 0.4473684210526316, "acc_norm_stderr": 0.04677473004491199 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.63448275