W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.5-margin-log

该数据集是从New-DPO训练运行中导出的每一步边缘摘要统计信息。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。数据集的来源是基于模型repo id为`W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.5`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等。数据集混合器使用了`Anthropic/hh-rlhf`。Per-step margin summary statistics exported from a New-DPO training run. The dataset includes various statistical features during training, such as epoch, step, batch_size, mean, std, min, p10, median, p90, max, pos_frac, sample, and npy. The source of the dataset is based on the training run with model repo id `W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.5`, with training parameters including beta, f_divergence_type, f_alpha_divergence_coef, s_star, eta, and q_t. The dataset mixer uses `Anthropic/hh-rlhf`.