OALL/details_meta-llama__Llama-3.1-70B

这是一个自动创建的评估运行数据集，用于评估模型 [meta-llama/Llama-3.1-70B](https://huggingface.co/meta-llama/Llama-3.1-70B)。数据集由 136 个配置组成，每个配置对应一个评估任务。数据集已从 1 次运行中创建。每个运行都可以在每个配置中找到作为特定的分割，分割使用运行的 timestamp 命名。train 分割始终指向最新的结果。还有一个额外的配置 results 存储运行的所有聚合结果。要加载运行的详细信息，可以使用以下 Python 代码示例：
python
from datasets import load_dataset
data = load_dataset("OALL/details_meta-llama__Llama-3.1-70B", "lighteval_xstory_cloze_ar_0_2025_01_11T23_22_16_340994_parquet", split="train")

Dataset automatically created during the evaluation run of model [meta-llama/Llama-3.1-70B](https://huggingface.co/meta-llama/Llama-3.1-70B). The dataset is composed of 136 configuration, each one coresponding 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. To load the details from a run, you can for instance do the following:
python
from datasets import load_dataset
data = load_dataset("OALL/details_meta-llama__Llama-3.1-70B", "lighteval_xstory_cloze_ar_0_2025_01_11T23_22_16_340994_parquet", split="train")