lvogel123/testoutput

这是一个包含模型评估结果、样本信息和运行统计的数据集。具体包含字段如：日志路径、评估ID、运行ID、创建时间、任务类型、任务ID、模型类型、样本数量、完成样本数量、平均值、不同评分标准下的均值、拒绝率、说服力原始均值、特异性原始均值等。样本信息中还包括样本ID、训练纪元、目标、消息、元提示、元目标、元ID、元类别、元注释等。统计信息包括开始时间、完成时间、模型使用情况、输入输出标记数量等。

This is a dataset containing model evaluation results, sample information, and run statistics. It includes fields such as log path, evaluation ID, run ID, creation time, task type, task ID, model type, number of samples, number of completed samples, mean values, mean values under different scoring criteria, refusal rate, convincing raw mean, specificity raw mean, etc. Sample information also includes sample ID, training epoch, target, messages, meta prompt, meta objective, meta ID, meta category, meta annotations, etc. Statistics include start time, completion time, model usage, number of input and output tokens, etc.