OALL/details_RDson__CoderO1-DeepSeekR1-Coder-32B-Preview

该数据集是在对模型 [RDson/CoderO1-DeepSeekR1-Coder-32B-Preview](https://huggingface.co/RDson/CoderO1-DeepSeekR1-Coder-32B-Preview) 进行评估运行过程中自动创建的。数据集由136个配置组成，每个配置对应一个评估任务。数据集被分割成不同的运行，每个运行都使用时间戳命名，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。可以使用提供的 Python 代码片段加载数据集。README 还包括来自特定运行的最新结果，这些结果可以在 JSON 文件中找到。

Dataset automatically created during the evaluation run of model [RDson/CoderO1-DeepSeekR1-Coder-32B-Preview](https://huggingface.co/RDson/CoderO1-DeepSeekR1-Coder-32B-Preview). The dataset is composed of 136 configurations, each corresponding to one of the evaluated tasks. The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run. The "train" split is always pointing to the latest results. An additional configuration "results" store all the aggregated results of the run. To load the details from a run, you can for instance do the following: python
from datasets import load_dataset
data = load_dataset("OALL/details_RDson__CoderO1-DeepSeekR1-Coder-32B-Preview", "lighteval_xstory_cloze_ar_0_2025_02_06T15_40_51_477476_parquet", split="train") The README also includes the latest results from a specific run, which can be found in a JSON file.