open-llm-leaderboard/details_databricks__dolly-v2-12b

该数据集是在模型databricks/dolly-v2-12b在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由64个配置组成，每个配置对应一个评估任务。它由2次运行生成，每次运行在每个配置中表示为特定的拆分，并以运行的时间戳命名。train拆分始终指向最新结果。一个名为results的额外配置存储了运行的所有聚合结果，这些结果用于计算和显示Open LLM Leaderboard上的聚合指标。README还提供了如何使用`datasets`库中的`load_dataset`函数加载运行细节的示例。

This dataset was automatically created during the evaluation run of the model databricks/dolly-v2-12b on the Open LLM Leaderboard. The dataset consists of 64 configurations, each corresponding to one evaluation task. It is generated from two runs, where each run is represented as a specific split in each configuration and named after the timestamp of the run. The train split always points to the most recent results. An additional configuration named `results` stores all aggregated results from the runs, which are used to calculate and display the aggregate metrics on the Open LLM Leaderboard. The README also provides examples of how to use the `load_dataset` function from the `datasets` library to load the run details.

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 databricks/dolly-v2-12b 在 Open LLM Leaderboard 上的自动创建的。

数据集结构

• 配置数量：64个配置，每个配置对应一个评估任务。
• 数据来源：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。
• 最新结果："train" 分割始终指向最新的结果。
• 结果汇总：一个额外的配置 "results" 存储所有运行的汇总结果，用于计算和显示在 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_databricks__dolly-v2-12b", "harness_winogrande_5", split="train")

最新结果

以下是 2023-09-23T05:02:42.236847 运行的最新结果： python { "all": { "em": 0.0016778523489932886, "em_stderr": 0.0004191330178826844, "f1": 0.06285968959731549, "f1_stderr": 0.0014820300080071475, "acc": 0.31032723721601535, "acc_stderr": 0.008366390657090902 }, "harness|drop|3": { "em": 0.0016778523489932886, "em_stderr": 0.0004191330178826844, "f1": 0.06285968959731549, "f1_stderr": 0.0014820300080071475 }, "harness|gsm8k|5": { "acc": 0.012130401819560273, "acc_stderr": 0.0030152942428909495 }, "harness|winogrande|5": { "acc": 0.6085240726124704, "acc_stderr": 0.013717487071290854 } }

配置详情

以下是部分配置的详细信息：

• harness_arc_challenge_25

  • 分割：2023_07_18T13_43_42.069045
  • 路径：**/details_harness|arc:challenge|25_2023-07-18T13:43:42.069045.parquet
  • 分割：latest
  • 路径：**/details_harness|arc:challenge|25_2023-07-18T13:43:42.069045.parquet

• harness_drop_3

  • 分割：2023_09_23T05_02_42.236847
  • 路径：**/details_harness|drop|3_2023-09-23T05-02-42.236847.parquet
  • 分割：latest
  • 路径：**/details_harness|drop|3_2023-09-23T05-02-42.236847.parquet

• harness_gsm8k_5

  • 分割：2023_09_23T05_02_42.236847
  • 路径：**/details_harness|gsm8k|5_2023-09-23T05-02-42.236847.parquet
  • 分割：latest
  • 路径：**/details_harness|gsm8k|5_2023-09-23T05-02-42.236847.parquet

• harness_hellaswag_10

  • 分割：2023_07_18T13_43_42.069045
  • 路径：**/details_harness|hellaswag|10_2023-07-18T13:43:42.069045.parquet
  • 分割：latest
  • 路径：**/details_harness|hellaswag|10_2023-07-18T13:43:42.069045.parquet

• harness_hendrycksTest_5

  • 分割：2023_07_18T13_43_42.069045
  • 路径：**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-18T13:43:42.069045.parquet 等
  • 分割：latest
  • 路径：**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-18T13:43:42.069045.parquet 等