jweston/details_jweston__smollm3-dpo-aligned_private

数据集是在评估模型[jweston/smollm3-dpo-aligned](https://huggingface.co/jweston/smollm3-dpo-aligned)时自动创建的。数据集由3个配置组成，每个配置对应一个评估任务。数据集由1次运行创建，每次运行在各个配置中都可以作为一个特定的分割找到，分割的名称使用运行的时戳。train分割始终指向最新的结果。还有一个额外的配置results存储所有运行的综合结果。可以使用Hugging Face数据集库加载数据集。

Dataset automatically created during the evaluation run of model [jweston/smollm3-dpo-aligned](https://huggingface.co/jweston/smollm3-dpo-aligned). The dataset is composed of 3 configuration, each one corresponding to one of the evaluated task. 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.