open-llm-leaderboard/details_jondurbin__airoboros-l2-7b-gpt4-2.0

该数据集是在评估模型jondurbin/airoboros-l2-7b-gpt4-2.0时自动创建的，评估在Open LLM Leaderboard上进行。数据集由3个配置组成，每个配置对应一个评估任务。数据集是从1次运行中创建的，每次运行可以在每个配置中找到特定的分割，分割使用运行的时间戳命名。train分割始终指向最新的结果。此外，还有一个results配置存储了所有运行的聚合结果，用于计算和显示在Open LLM Leaderboard上的聚合指标。

This dataset was automatically created during the evaluation of the model jondurbin/airoboros-l2-7b-gpt4-2.0, which was conducted on the Open LLM Leaderboard. The dataset consists of three configurations, each corresponding to one evaluation task. Generated from a single run, the dataset contains specific splits for every configuration, and the splits are named using the timestamp of the run. The train split always points to the most recent results. In addition, there is a results configuration that stores the aggregated results across all runs, which are used to calculate and display the aggregate metrics shown on the Open LLM Leaderboard.

原始信息汇总

数据集卡片 for Evaluation run of jondurbin/airoboros-l2-7b-gpt4-2.0

数据集描述

数据集概述

该数据集是在模型 jondurbin/airoboros-l2-7b-gpt4-2.0 的评估运行期间自动创建的，用于 Open LLM Leaderboard。

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。

还有一个额外的配置 "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 2023-10-22T19:06:34.610591 运行的最新结果：

python { "all": { "em": 0.2790478187919463, "em_stderr": 0.004593378120842089, "f1": 0.3568791946308748, "f1_stderr": 0.004541856353836489, "acc": 0.3714854775657577, "acc_stderr": 0.008787294914639698 }, "harness|drop|3": { "em": 0.2790478187919463, "em_stderr": 0.004593378120842089, "f1": 0.3568791946308748, "f1_stderr": 0.004541856353836489 }, "harness|gsm8k|5": { "acc": 0.03184230477634572, "acc_stderr": 0.004836348558260957 }, "harness|winogrande|5": { "acc": 0.7111286503551697, "acc_stderr": 0.01273824127101844 } }

配置

• harness_drop_3

  • 分割: 2023_10_22T19_06_34.610591
    • 路径: **/details_harness|drop|3_2023-10-22T19-06-34.610591.parquet
  • 分割: latest
    • 路径: **/details_harness|drop|3_2023-10-22T19-06-34.610591.parquet

• harness_gsm8k_5

  • 分割: 2023_10_22T19_06_34.610591
    • 路径: **/details_harness|gsm8k|5_2023-10-22T19-06-34.610591.parquet
  • 分割: latest
    • 路径: **/details_harness|gsm8k|5_2023-10-22T19-06-34.610591.parquet

• harness_winogrande_5

  • 分割: 2023_10_22T19_06_34.610591
    • 路径: **/details_harness|winogrande|5_2023-10-22T19-06-34.610591.parquet
  • 分割: latest
    • 路径: **/details_harness|winogrande|5_2023-10-22T19-06-34.610591.parquet

• results

  • 分割: 2023_10_22T19_06_34.610591
    • 路径: results_2023-10-22T19-06-34.610591.parquet
  • 分割: latest
    • 路径: results_2023-10-22T19-06-34.610591.parquet