open-llm-leaderboard/details_chavinlo__alpaca-native

该数据集是在Open LLM Leaderboard上对模型chavinlo/alpaca-native进行评估时自动生成的。数据集由64个配置组成，每个配置对应一个评估任务。数据集由2次运行生成，每次运行在每个配置中表示为特定的分割，分割名称使用运行的时间戳。train分割始终指向最新结果。一个名为results的额外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。文件还提供了一个Python代码片段来加载运行中的详细信息，并列出了特定运行的最新结果。

This dataset was automatically generated when evaluating the model chavinlo/alpaca-native on the Open LLM Leaderboard. It consists of 64 configurations, each corresponding to one evaluation task. The dataset is generated from two experimental runs, where each run is represented as a specific split under each configuration, with the split name using the run's timestamp as its identifier. The 'train' split always points to the most recent evaluation results. An additional configuration named 'results' stores the aggregated results across all runs, which are used to calculate and display the aggregate metrics on the Open LLM Leaderboard. The accompanying file also provides a Python code snippet to load detailed run information, and lists the latest results for a specific run.

原始信息汇总

数据集概述

该数据集是在对模型 chavinlo/alpaca-native 进行评估时自动创建的，用于 Open LLM Leaderboard。数据集包含 64 个配置，每个配置对应一个评估任务。数据集从 2 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

数据集包含以下配置：

• harness_arc_challenge_25

  • 分割：2023_09_21T20_23_20.255556
  • 路径：**/details_harness|arc:challenge|25_2023-09-21T20-23-20.255556.parquet
  • 分割：latest
  • 路径：**/details_harness|arc:challenge|25_2023-09-21T20-23-20.255556.parquet

• harness_drop_3

  • 分割：2023_09_17T15_14_48.848140
  • 路径：**/details_harness|drop|3_2023-09-17T15-14-48.848140.parquet
  • 分割：latest
  • 路径：**/details_harness|drop|3_2023-09-17T15-14-48.848140.parquet

• harness_gsm8k_5

  • 分割：2023_09_17T15_14_48.848140
  • 路径：**/details_harness|gsm8k|5_2023-09-17T15-14-48.848140.parquet
  • 分割：latest
  • 路径：**/details_harness|gsm8k|5_2023-09-17T15-14-48.848140.parquet

• harness_hellaswag_10

  • 分割：2023_09_21T20_23_20.255556
  • 路径：**/details_harness|hellaswag|10_2023-09-21T20-23-20.255556.parquet
  • 分割：latest
  • 路径：**/details_harness|hellaswag|10_2023-09-21T20-23-20.255556.parquet

• harness_hendrycksTest_5

  • 分割：2023_09_21T20_23_20.255556
  • 路径：
    • **/details_harness|hendrycksTest-abstract_algebra|5_2023-09-21T20-23-20.255556.parquet
    • **/details_harness|hendrycksTest-anatomy|5_2023-09-21T20-23-20.255556.parquet
    • **/details_harness|hendrycksTest-astronomy|5_2023-09-21T20-23-20.255556.parquet
    • **/details_harness|hendrycksTest-business_ethics|5_2023-09-21T20-23-20.255556.parquet
    • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-21T20-23-20.255556.parquet
    • **/details_harness|hendrycksTest-college_biology|5_2023-09-21T20-23-20.255556.parquet
    • **/details_harness|hendrycksTest-college_chemistry|5_2023-09-21T20-23-20.255556.parquet
    • **/details_harness|hendrycksTest-college_computer_science|5_2023-09-21T20-23-20.255556.parquet
    • **/details_harness|hendrycksTest-college_mathematics|5_2023-09-21T20-23-20.255556.parquet
    • **/details_harness|hendrycksTest-college_medicine|5_2023-09-21T20-23-20.255556.parquet
    • **/details_harness|hendrycksTest-college_physics|5_2023-09-21T20-23-20.255556.parquet
    • **/details_harness|hendrycksTest-computer_security|5_2023-09-21T20-23-20.255556.parquet
    • **/details_harness|hendrycksTest-conceptual_physics|5_2023-09-21T20-23-20.255556.parquet
    • **/details_harness|hendrycksTest-econometrics|5_2023-09-21T20-23-20.255556.parquet
    • **/details_harness|hendrycksTest-electrical_engineering|5_2023-09-21T20-23-20.255556.parquet
    • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-09-21T20-23-20.255556.parquet
    • **/details_harness|hendrycksTest-formal_logic|5_2023-09-21T20-23-20.255556.parquet
    • **/details_harness|hendrycksTest-global_facts|5_2023-09-21T20-23-20.255556.parquet
    • **/details_harness|hendrycksTest-high_school_biology|5_2023-09-21T20-23-20.255556.parquet

最新结果

以下是 2023-09-21T20:23:20.255556 运行 的最新结果：

python { "all": { "acc": 0.41927597389078103, "acc_stderr": 0.035302205782678654, "acc_norm": 0.42235476219088836, "acc_norm_stderr": 0.035290265393035695, "mc1": 0.2484700122399021, "mc1_stderr": 0.015127427096520674, "mc2": 0.3759916250814691, "mc2_stderr": 0.015396201572279763 }, "harness|arc:challenge|25": { "acc": 0.5127986348122867, "acc_stderr": 0.014606603181012538, "acc_norm": 0.5204778156996587, "acc_norm_stderr": 0.01459913135303501 }, "harness|hellaswag|10": { "acc": 0.5959968133837881, "acc_stderr": 0.004896952378506926, "acc_norm": 0.7699661422027485, "acc_norm_stderr": 0.004199941217549452 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.04512608598542129, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542129 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.45925925925925926, "acc_stderr": 0.04304979692464242, "acc_norm": 0.45925925925925926, "acc_norm_stderr": 0.04304979692464242 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.3618421052631579, "acc_stderr": 0.03910525752849724, "acc_norm": 0.3618421052631579, "acc_norm_stderr": 0.03910525752849724 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.44150943396226416, "acc_stderr": 0.030561590426731837, "acc_norm": 0.44150943396226416, "acc_norm_stderr": 0.030561590426731837 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3819444444444444, "acc_stderr": 0.040629907841466674, "acc_norm": 0.3819444444444444, "acc_norm_stderr": 0.040629907841466674 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3815028901734104, "acc_stderr": 0.03703851193099521, "acc_norm": 0.3815028901734104, "acc_norm_stderr": 0.03703851193099521 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237656, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237656 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.37446808510638296, "acc_stderr": 0.03163910665367291, "acc_norm": 0.37446808510638296, "acc_norm_stderr": 0.03163910665367291 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2543859649122807, "acc_stderr": 0.040969851398436716, "acc_norm": 0.2543859649122807, "acc_norm_stderr": 0.040969851398436716 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.3655