open-llm-leaderboard/details_psmathur__model_009

该数据集是在评估模型psmathur/model_009时自动生成的，包含3个配置，每个配置对应一个评估任务。数据集由1次运行生成，每次运行的结果以时间戳命名的分割形式存储，train分割始终指向最新结果。此外，还有一个results配置存储所有运行的聚合结果，用于在Open LLM Leaderboard上计算和显示聚合指标。

This dataset was automatically generated during the evaluation of the model psmathur/model_009. It contains 3 configurations, each corresponding to one evaluation task. The dataset is generated from a single run, and the results of each run are stored as splits named by timestamps, with the "train" split always pointing to the latest result. Additionally, there is a "results" configuration that stores the aggregated results of all runs, which is used to calculate and display aggregate metrics on the Open LLM Leaderboard.

原始信息汇总

数据集卡片 for Evaluation run of psmathur/model_009

数据集描述

数据集概述

数据集是在对模型 psmathur/model_009 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。

该数据集由3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。

额外的配置 "results" 存储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）。

最新结果

以下是从运行 2023-11-09T07:41:27.734814 获得的最新结果：

python { "all": { "em": 0.3341023489932886, "em_stderr": 0.004830400685277283, "f1": 0.440147860738256, "f1_stderr": 0.0045184970708564655, "acc": 0.6087212395126058, "acc_stderr": 0.0120913878225072 }, "harness|drop|3": { "em": 0.3341023489932886, "em_stderr": 0.004830400685277283, "f1": 0.440147860738256, "f1_stderr": 0.0045184970708564655 }, "harness|gsm8k|5": { "acc": 0.39423805913570886, "acc_stderr": 0.01346085235709565 }, "harness|winogrande|5": { "acc": 0.8232044198895028, "acc_stderr": 0.010721923287918747 } }

数据集结构

配置

• harness_drop_3

  • 分割: 2023_11_09T07_41_27.734814
    • 路径: **/details_harness|drop|3_2023-11-09T07-41-27.734814.parquet
  • 分割: latest
    • 路径: **/details_harness|drop|3_2023-11-09T07-41-27.734814.parquet

• harness_gsm8k_5

  • 分割: 2023_11_09T07_41_27.734814
    • 路径: **/details_harness|gsm8k|5_2023-11-09T07-41-27.734814.parquet
  • 分割: latest
    • 路径: **/details_harness|gsm8k|5_2023-11-09T07-41-27.734814.parquet

• harness_winogrande_5

  • 分割: 2023_11_09T07_41_27.734814
    • 路径: **/details_harness|winogrande|5_2023-11-09T07-41-27.734814.parquet
  • 分割: latest
    • 路径: **/details_harness|winogrande|5_2023-11-09T07-41-27.734814.parquet

• results

  • 分割: 2023_11_09T07_41_27.734814
    • 路径: results_2023-11-09T07-41-27.734814.parquet
  • 分割: latest
    • 路径: results_2023-11-09T07-41-27.734814.parquet