open-llm-leaderboard/details_Weyaxi__Luban-Marcoroni-13B

该数据集是在评估模型Weyaxi/Luban-Marcoroni-13B时自动创建的，评估在Open LLM Leaderboard上进行。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，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 created during the evaluation of the model Weyaxi/Luban-Marcoroni-13B, with the evaluation conducted on the Open LLM Leaderboard. It comprises 64 configurations, each corresponding to one evaluation task. The dataset is generated from two runs, and each run has a specific split for every configuration, with the split name using the timestamp of the corresponding run. The train split always points to the most recent results. Additionally, the results configuration stores the aggregated results of all runs, and is used to calculate and display the aggregated metrics on the Open LLM Leaderboard.

原始信息汇总

数据集概述

数据集简介

该数据集是在评估模型 Weyaxi/Luban-Marcoroni-13B 在 Open LLM Leaderboard 上的运行过程中自动创建的。

数据集结构

• 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，用于计算和显示 Open LLM Leaderboard 上的聚合指标。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Weyaxi__Luban-Marcoroni-13B", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-28T10:04:59.815183 运行的最新结果： python { "all": { "em": 0.00776006711409396, "em_stderr": 0.0008986296432392762, "f1": 0.10247063758389327, "f1_stderr": 0.001983240759454083, "acc": 0.4351997070321265, "acc_stderr": 0.010043960065261932 }, "harness|drop|3": { "em": 0.00776006711409396, "em_stderr": 0.0008986296432392762, "f1": 0.10247063758389327, "f1_stderr": 0.001983240759454083 }, "harness|gsm8k|5": { "acc": 0.10007581501137225, "acc_stderr": 0.008266274528685636 }, "harness|winogrande|5": { "acc": 0.7703235990528808, "acc_stderr": 0.011821645601838227 } }

配置详情

以下是部分配置的详细信息：

• harness_arc_challenge_25

  • 分割：2023_09_13T17_02_11.381984
  • 路径：**/details_harness|arc:challenge|25_2023-09-13T17-02-11.381984.parquet
  • 分割：latest
  • 路径：**/details_harness|arc:challenge|25_2023-09-13T17-02-11.381984.parquet

• harness_drop_3

  • 分割：2023_10_28T10_04_59.815183
  • 路径：**/details_harness|drop|3_2023-10-28T10-04-59.815183.parquet
  • 分割：latest
  • 路径：**/details_harness|drop|3_2023-10-28T10-04-59.815183.parquet

• harness_gsm8k_5

  • 分割：2023_10_28T10_04_59.815183
  • 路径：**/details_harness|gsm8k|5_2023-10-28T10-04-59.815183.parquet
  • 分割：latest
  • 路径：**/details_harness|gsm8k|5_2023-10-28T10-04-59.815183.parquet

• harness_hellaswag_10

  • 分割：2023_09_13T17_02_11.381984
  • 路径：**/details_harness|hellaswag|10_2023-09-13T17-02-11.381984.parquet
  • 分割：latest
  • 路径：**/details_harness|hellaswag|10_2023-09-13T17-02-11.381984.parquet

• harness_hendrycksTest_5

  • 分割：2023_09_13T17_02_11.381984
  • 路径：**/details_harness|hendrycksTest-abstract_algebra|5_2023-09-13T17-02-11.381984.parquet 等 50 个文件
  • 分割：latest
  • 路径：**/details_harness|hendrycksTest-abstract_algebra|5_2023-09-13T17-02-11.381984.parquet 等 50 个文件