TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_Random-RL-countdown_4arg__v1
收藏Hugging Face2025-11-09 更新2025-11-15 收录
下载链接:
https://hf-mirror.com/datasets/TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_Random-RL-countdown_4arg__v1
下载链接
链接失效反馈官方服务:
资源简介:
这是一个用于评估任务countdown_4arg的实验数据集,包含了问题、答案、任务配置等相关信息,以及实验的日志和元数据信息。数据集分为三个主要配置:evals_eval_rl、logs__evaluation_eval_rl和metadata,每个配置下有具体的字段和split信息。
This is an experiment dataset for evaluating the countdown_4arg task, containing information such as questions, answers, task configurations, as well as logs and metadata of the experiment. The dataset is divided into three main configurations: evals_eval_rl, logs__evaluation_eval_rl, and metadata, each with specific fields and split information.
提供机构:
TAUR-dev



