TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_AT_OURS-SFT-countdown_6arg__v1
收藏Hugging Face2025-11-10 更新2025-11-15 收录
下载链接:
https://hf-mirror.com/datasets/TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_AT_OURS-SFT-countdown_6arg__v1
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是用于评估任务countdown_6arg的实验数据集,包含实验的元数据、训练数据、超参数配置、日志以及评估结果。数据集中的特征包括问题、答案、任务配置、任务来源、提示信息、模型响应及其评估信息等。数据集分为测试集和训练集,其中测试集包含1000个样本。
This dataset is for evaluating the countdown_6arg task, containing experiment metadata, training data, hyperparameter configurations, logs, and evaluation results. The features in the dataset include questions, answers, task configurations, task sources, prompt information, model responses, and their evaluation information. The dataset is split into a test set and a training set, with the test set containing 1000 samples.
提供机构:
TAUR-dev



