S. Roy

Blog Post·2025-06-20·13 min read

LLM Training Stages: Pre-training, Mid-training, SFT, RL, and DPO

What actually happens at each stage of training a large language model — what data, what objective, what the model learns, and why the stages are ordered the way they are.

llm-training pretraining mid-training sft rlhf dpo alignment

Tag: dpo

LLM Training Stages: Pre-training, Mid-training, SFT, RL, and DPO