W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.01-margin-log
收藏Hugging Face2026-04-28 更新2026-05-03 收录
下载链接：
https://hf-mirror.com/datasets/W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.01-margin-log
下载链接
链接失效反馈官方服务：
资源简介：
该数据集是从New-DPO训练运行中导出的每一步边缘统计摘要。包含训练过程中的各种统计指标，如epoch、step、batch_size、mean、std、min、p10、median、p90、max、pos_frac等。数据来源的训练运行基于模型W-61/llama-3-8b-base-sft-hh-helpful-4xh200，使用了特定的训练参数和数据集混合器（Anthropic/hh-rlhf）。
Per-step margin summary statistics exported from a New-DPO training run. Includes various statistical metrics during training such as epoch, step, batch_size, mean, std, min, p10, median, p90, max, pos_frac, etc. The data comes from a training run based on the model W-61/llama-3-8b-base-sft-hh-helpful-4xh200, using specific training parameters and a dataset mixer (Anthropic/hh-rlhf).
提供机构：
W-61
