taresco/details__store2_scratch_oogundep_post-training_runs_llama3base_no_instruction_mask_30k
收藏Hugging Face2025-05-18 更新2025-07-05 收录
下载链接：
https://hf-mirror.com/datasets/taresco/details__store2_scratch_oogundep_post-training_runs_llama3base_no_instruction_mask_30k
下载链接
链接失效反馈官方服务：
资源简介：
这个数据集是在对模型[_store2_scratch_oogundep_post-training_runs_llama3base_no_instruction_mask_30k](https://huggingface.co/_store2_scratch_oogundep_post-training_runs_llama3base_no_instruction_mask_30k)进行评估运行时自动创建的。数据集由7个配置组成，每个配置对应一个评估任务。数据集是从7次运行中创建的。每个运行都可以在配置的特定分割中找到，分割的名称使用运行的时间戳。"train"分割始终指向最新的结果。还有一个名为"results"的额外配置，用于存储所有运行的汇总结果。
Dataset automatically created during the evaluation run of model [_store2_scratch_oogundep_post-training_runs_llama3base_no_instruction_mask_30k](https://huggingface.co/_store2_scratch_oogundep_post-training_runs_llama3base_no_instruction_mask_30k).
The dataset is composed of 7 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 7 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.
提供机构：
taresco
