taresco/details_taresco__lugha_llama_8b_wura_math_no_instruction_mask

该数据集是在评估模型 taresco/lugha_llama_8b_wura_math_no_instruction_mask 时自动创建的。数据集包含7个配置，每个配置对应一个评估任务，并从9次运行中收集了结果。每个运行的结果都根据时间戳进行了分割和命名。此外，还有一个 results 配置，用于存储所有运行的综合结果。可以使用 load_dataset 函数从 datasets 库中加载数据集。README 中提供了加载最新结果的示例，并给出了相应的 Python 代码片段。

The dataset is an automatically created collection of results from the evaluation of the model taresco/lugha_llama_8b_wura_math_no_instruction_mask. It consists of 7 configurations, each corresponding to an evaluated task, and includes results from 9 runs. Each runs results are split and named based on the timestamp. There is also a results configuration that aggregates all the results. The dataset can be loaded using the load_dataset function from the datasets library. The README includes examples of how to load the latest results and provides a Python code snippet for reference.