jackf857/llama-3-8b-base-scheduled-beta-margin-dpo-hh-helpful-margin-log

该数据集是从margin-DPO训练运行中导出的每步边际摘要统计信息，包含681行训练数据。数据集记录了训练过程中的各种统计指标，如均值、标准差、最小值、百分位数等，以及每个步骤的有效批次的边际信息。数据集基于Anthropic/hh-rlhf数据集混合器配置，比例为1.0。This dataset contains per-step margin summary statistics exported from a margin-DPO training run, with 681 rows of training data. It records various statistical metrics during the training process, such as mean, standard deviation, minimum, percentiles, etc., as well as margin information for the effective batch at each step. The dataset is based on the Anthropic/hh-rlhf dataset mixer configuration with a ratio of 1.0.