W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-8-margin-log

该数据集是从New-DPO训练运行中导出的每一步的边缘摘要统计。数据集包含多个统计特征，如epoch、step、batch_size、mean、std、min、p10、median、p90、max、pos_frac、sample（每个示例的边缘）和npy（保存完整边缘数组的可选路径）。数据来源于特定的训练运行，训练参数包括beta、f_divergence_type、f_alpha_divergence_coef、s_star、eta和q_t。数据集混合器使用了Anthropic/hh-rlhf数据集。

Per-step margin summary statistics exported from a New-DPO training run. The dataset includes various statistical features such as epoch, step, batch_size, mean, std, min, p10, median, p90, max, pos_frac, sample (per-example margins), and npy (optional path to the saved full margin array). The data comes from a specific training run with parameters including beta, f_divergence_type, f_alpha_divergence_coef, s_star, eta, and q_t. The dataset mixer uses Anthropic/hh-rlhf.