ryzax/lm-eval-results
收藏Hugging Face2025-10-05 更新2025-11-01 收录
下载链接：
https://hf-mirror.com/datasets/ryzax/lm-eval-results
下载链接
链接失效反馈官方服务：
资源简介：
该数据集是在对模型Qwen3-1.7B进行评估运行时自动创建的。数据集包含1个配置，每个配置对应一个评估任务。数据集由6次运行创建，每次运行作为特定分割存储，分割名称使用运行的时戳。train分割始终指向最新结果。此外，还有一个名为results的附加配置，存储所有运行的汇总结果。README还提供了使用Python加载运行详情的示例。
Dataset automatically created during the evaluation run of model Qwen3-1.7B. The dataset consists of 1 configuration, each corresponding to an evaluated task. The dataset was created from 6 runs, each represented as a specific split named with the timestamp of the run. The train split always points to the latest results. There is an additional configuration results that stores all aggregated results of the runs. The README also provides an example of how to load the details from a run using Python.
提供机构：
ryzax
