Add README

README.md

@@ -27,6 +27,9 @@ PPO-Lagrangian RL fine-tune of Qwen2.5-Coder-7B-Instruct (LoRA rank 16) on Human
 Each `iter_XXXX/` folder contains LoRA adapter weights and a `log.json`
 with per-iteration training metrics (avg_reward, avg_questions, lambda1).
 
+Training was run in two segments (job preemption on HPC); checkpoints are
+merged from both segments in chronological order.
+
 ## Usage
 ```python
 from peft import PeftModel