EleutherAI/lm-eval-EleutherAI_deep-ignorance-unfiltered

该数据集是在对模型EleutherAI/deep-ignorance-unfiltered进行评估过程中自动创建的。数据集由1个配置组成，每个配置对应一个评估任务。数据集由4次运行创建，每次运行在配置中都有特定的分割，分割名称使用运行的timestamp。还有一个额外的配置“results”存储所有运行的聚合结果。要从一个运行中加载数据，可以执行以下Python代码：from datasets import load_dataset
data = load_dataset(
"EleutherAI/lm-eval-EleutherAI_deep-ignorance-unfiltered",
name="EleutherAI__deep-ignorance-unfiltered__wmdp_bio_cloze_signal_categorized_high_signal",
split="latest"
)

Dataset automatically created during the evaluation run of model [EleutherAI/deep-ignorance-unfiltered](https://huggingface.co/EleutherAI/deep-ignorance-unfiltered). The dataset is composed of 1 configuration(s), each one corresponding to one of the evaluated task. The dataset has been created from 4 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.