open-llm-leaderboard-old/details_lmsys__vicuna-13b-v1.3

该数据集是在评估模型lmsys/vicuna-13b-v1.3在Open LLM Leaderboard上的表现时自动生成的。数据集包含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。此外，还有一个results配置存储了所有运行的聚合结果，并用于计算和显示Open LLM Leaderboard上的聚合指标。

This dataset was automatically generated during the evaluation of the model lmsys/vicuna-13b-v1.3 on the Open LLM Leaderboard. It comprises 3 configurations, each corresponding to a distinct evaluation task. The dataset is generated from a single run, where specific splits are available under each configuration, with split names derived from the timestamp of the run. The train split always points to the most recent results. Additionally, a results configuration is included to store the aggregated results of all runs, and to calculate and display the aggregate metrics on the Open LLM Leaderboard.

原始信息汇总

数据集概述

数据集描述

• 数据集摘要： 该数据集是在模型lmsys/vicuna-13b-v1.3在Open LLM Leaderboard上的评估运行期间自动创建的。

  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"存储所有运行结果的聚合，并用于计算和显示Open LLM Leaderboard上的聚合指标。

  加载运行细节的示例如下： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_lmsys__vicuna-13b-v1.3", "harness_winogrande_5", split="train")

最新结果

以下是2023-10-21T21:13:42.887863运行的最新结果：

python { "all": { "em": 0.016673657718120804, "em_stderr": 0.0013113056398144408, "f1": 0.08239932885906037, "f1_stderr": 0.0019047507167675335, "acc": 0.427940733843833, "acc_stderr": 0.010367986551641579 }, "harness|drop|3": { "em": 0.016673657718120804, "em_stderr": 0.0013113056398144408, "f1": 0.08239932885906037, "f1_stderr": 0.0019047507167675335 }, "harness|gsm8k|5": { "acc": 0.10765731614859743, "acc_stderr": 0.008537484003023366 }, "harness|winogrande|5": { "acc": 0.7482241515390686, "acc_stderr": 0.012198489100259792 } }