W-61/llama-multi-beta-testing-margin_dpo-hh-helpful-beta-0p1-20260429-085449-margin
收藏Hugging Face2026-04-29 更新2026-05-03 收录
下载链接:
https://hf-mirror.com/datasets/W-61/llama-multi-beta-testing-margin_dpo-hh-helpful-beta-0p1-20260429-085449-margin
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是一个来自Margin-DPO训练运行的每一步边缘摘要统计。它包含了训练过程中的多个统计特征,如epoch、step、batch_size、mean、std、min、p10、median、p90、max、pos_frac、sample和npy等。数据集来源于一个特定的训练运行,使用了特定的模型和参数配置,并且数据集混合了Anthropic/hh-rlhf的数据。
Per-step margin summary statistics exported from a Margin-DPO training run. It includes various statistical features during the training process, such as epoch, step, batch_size, mean, std, min, p10, median, p90, max, pos_frac, sample, and npy. The dataset comes from a specific training run with particular model and parameter configurations, and it mixes data from Anthropic/hh-rlhf.
提供机构:
W-61



