open-llm-leaderboard/details_chargoddard__ypotryll-22b-epoch2-qlora

该数据集是在Open LLM Leaderboard上对模型chargoddard/ypotryll-22b-epoch2-qlora进行评估时自动创建的。数据集由64个配置组成，每个配置对应一个评估任务。数据集由3次运行创建，每次运行的结果作为特定分割存储在配置中，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 when evaluating the model chargoddard/ypotryll-22b-epoch2-qlora on the Open LLM Leaderboard. It comprises 64 configurations, each corresponding to one evaluation task. The dataset is generated via three runs, where the results of each run are stored as a specific split within the corresponding configuration, with split names adopting the timestamp of the run. The train split always points to the most recent results. Furthermore, 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

数据集摘要

该数据集是在模型chargoddard/ypotryll-22b-epoch2-qlora在Open LLM Leaderboard上的评估运行期间自动创建的。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3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。

数据集结构

数据集包含以下配置：

• harness_arc_challenge_25
• harness_drop_3
• harness_gsm8k_5
• harness_hellaswag_10
• harness_hendrycksTest_5

每个配置包含多个分割，每个分割对应不同的运行时间戳，最新的结果存储在名为"latest"的分割中。

数据加载示例

以下是加载数据集的示例代码： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_chargoddard__ypotryll-22b-epoch2-qlora", "harness_winogrande_5", split="train")

最新结果

以下是2023-09-26T17:07:11.654928运行的最新结果： python { "all": { "em": 0.39198825503355705, "em_stderr": 0.004999564353850857, "f1": 0.452352139261747, "f1_stderr": 0.004826380442768646, "acc": 0.4085244316417271, "acc_stderr": 0.00908196050272276 }, "harness|drop|3": { "em": 0.39198825503355705, "em_stderr": 0.004999564353850857, "f1": 0.452352139261747, "f1_stderr": 0.004826380442768646 }, "harness|gsm8k|5": { "acc": 0.053828658074298714, "acc_stderr": 0.006216328640238116 }, "harness|winogrande|5": { "acc": 0.7632202052091555, "acc_stderr": 0.0119475923652074 } }