W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.4-margin-log

该数据集包含了一个名为W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.4-margin-log的训练运行的每一步边缘摘要统计信息。数据集包含多个特征，如epoch、step、batch_size、mean、std等，以及一个名为sample的序列和一个名为npy的字符串。数据集来源于一个特定的训练运行，使用了特定的训练参数和数据集混合器。

This dataset contains per-step margin summary statistics exported from a training run named W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.4-margin-log. The dataset includes multiple features such as epoch, step, batch_size, mean, std, etc., as well as a sequence named sample and a string named npy. The dataset originates from a specific training run with particular training arguments and a dataset mixer.