---
license: mit
datasets:
- Leo-Dai/dapo-math-17k_dedup
---
# 🧠 Parallel-R1-Unseen_Step_200

> **Mid-Training Checkpoint of Parallel-R1: Towards Parallel Thinking via Reinforcement Learning**  
> Stage: **After 200 RL steps via alternating rewards** — showing the adaptive parallel reasoning ability and serve as structure exploration stage.

This checkpoint aims to help you reproduce experimental results in Section 4.5: Extra Bonus: Parallel Thinking as a Mid-Training Exploration Strategy for RL Training.