ViperEkura 4e508afa2d fix : SFT pipeline position_ids default & doc boundary preservation ... - change position_ids_mode default from "none" to "doc_reset" so SFT preprocessing always generates position_ids (was causing dataset load KeyError) - generate per-doc position_ids before packing (doc_reset mode), preserving document boundaries for BFD packing (cross-doc attention leak fix) - change _align_bucket padding from [1] to [0] to avoid accidentally training on loss_mask padding		2026-07-04 15:59:11 +08:00
..
__init__.py	refactor : 基于声明式 JSON 配置的预处理管线重构	2026-05-30 20:45:09 +08:00
base.py	refactor : 清理工厂和配置系统中的死代码与冗余抽象	2026-06-07 11:39:50 +08:00
model_config.py	refactor : neftune_alpha 在 Embedding 构造时传入，由模型配置链路负责	2026-06-19 14:23:27 +08:00
preprocess_config.py	fix : SFT pipeline position_ids default & doc boundary preservation	2026-07-04 15:59:11 +08:00
train_config.py	refactor: merge validation into MetricCallback, simplify progress bar to optimizer steps	2026-07-03 21:43:08 +08:00