taresco/details__store3_scratch_oogundep_openmath_instruct_merged_linear_llama_instruct

该数据集是在对模型 _store3_scratch_oogundep_openmath_instruct_merged_linear_llama_instruct 进行评估时自动创建的。数据集包含与评估任务相对应的一个配置。该数据集由一次运行的结果创建而成，每个配置中的特定分割以运行的时戳命名。train 分割始终指向最新的结果。还有一个名为 results 的附加配置，用于存储所有聚合的结果。数据集文件为 Parquet 格式，可以使用 Python 的 datasets 库加载。最新结果包括 GPT-4o 的评分及其标准误差。

The dataset was automatically created during the evaluation run of the model _store3_scratch_oogundep_openmath_instruct_merged_linear_llama_instruct. It consists of one configuration per evaluated task. The dataset has been created from the results of one run, with each configuration containing a specific split named after the timestamp of the run. The train split always points to the latest results. There is also an additional configuration named results that stores all aggregated results. The dataset files are in Parquet format and can be loaded using the datasets library in Python. The latest results include judge scores for GPT-4o and their standard errors.