--- license: mit library_name: transformers datasets: - BytedTsinghua-SIA/DAPO-Math-17k language: - en base_model: - deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B pipeline_tag: text-generation ---
JustRL: Simplicity at Scale
πŸš€ Competitive RL Performance Without Complex Techniques 🌟

Code Hugging Face Notion
## Overview **JustRL** demonstrates that competitive reinforcement learning performance for small language models doesn't require complex multi-stage pipelines or dynamic schedules. Using a minimal recipe with single-stage training and fixed hyperparameters, we achieve state-of-the-art results on mathematical reasoning tasks. We release two models: - [**JustRL-DeepSeek-1.5B**](https://huggingface.co/hbx/JustRL-DeepSeek-1.5B): Trained from DeepSeek-R1-Distill-Qwen-1.5B - [**JustRL-Nemotron-1.5B**](https://huggingface.co/hbx/JustRL-Nemotron-1.5B): Trained from OpenMath-Nemotron-1.5B Both models use identical hyperparameters without per-model tuning, demonstrating the robustness of our approach. ![The AIME24 performance curve for scaling from a weak base DeekSeek-R1-Distill-Qwen-1.5B and a strong base OpenMath-Nemotron-1.5B over thousands of steps.](./assets/fig1_aime24_curves_added.png) ## Key Highlights ✨ **Simplicity**: Single-stage training with fixed hyperparameters, without multi-stage pipelines or dynamic schedules πŸ“ˆ **Stability**: Smooth, monotonic improvement over 4,000+ training steps without collapses or oscillations 🎯 **Performance**: State-of-the-art results at 1.5B scale, matching or exceeding more complex approaches πŸ’° **Efficiency**: Comparable or better performance with 2Γ— less compute than multi-stage methods πŸ”“ **Open**: Complete evaluation scripts, and model weights released ## Performance ### JustRL-DeepSeek-1.5B (Based on DeepSeek-R1-Distill-Qwen-1.5B) | Model | AIME24 (@32) | AIME25 (@32) | AMC23 (@32) | MATH-500 (@4) | Minerva (@4) | OlympiadBench (@4) | HMMT25 (@32) | BRUMO25 (@32) | CMIMC25 (@32) | Avg | | ------------------------ | ------------ | ------------ | ----------- | ------------- | ------------ | ------------------ | ------------ | ------------- | ------------- | --------- | | DeepSeek-R1-Distill-1.5B | 29.90 | 22.40 | 63.82 | 84.90 | 34.65 | 45.95 | 13.44 | 30.94 | 12.89 | 37.65 | | DeepScaleR-1.5B-Preview | 40.21 | 28.65 | 73.83 | 89.30 | 39.34 | 52.79 | 18.96 | 40.00 | 21.00 | 44.88 | | ProRL-V2 | 51.87 | 35.73 | 88.75 | 92.00 | 49.03 | 67.84 | 19.38 | 47.29 | **25.86** | 53.08 | | BroRL | **57.50** | 36.88 | / | **92.14** | 49.08 | 61.54 | / | / | / | / | | JustRL-DeepSeek-1.5B | 52.60 | **38.75** | **91.02** | 91.65 | **51.47** | **67.99** | **21.98** | **52.71** | 25.63 | **54.87** | Besides, the real question is whether our simplicity comes at a computational cost. It doesn't. We match half of ProRL-V2's compute budget while using a single-stage recipe with fixed hyperparameters. BroRL requires 4.9Γ— more compute by increasing rollouts to 512 per example, essentially exhaustively exploring the solution space. Our approach achieves competitive performance without this computational overhead. ### JustRL-Nemotron-1.5B (Based on OpenMath-Nemotron-1.5B) | Model | AIME24 (@32) | AIME25 (@32) | AMC23 (@32) | MATH-500 (@4) | Minerva (@4) | OlympiadBench (@4) | HMMT25 (@32) | BRUMO25 (@32) | CMIMC25 (@32) | Avg | | ---------------------- | ------------ | ------------ | ----------- | ------------- | ------------ | ------------------ | ------------ | ------------- | ------------- | --------- | | OpenMath-Nemotron-1.5B | 58.75 | 48.44 | 90.55 | 92.40 | 26.93 | 71.70 | 30.10 | 61.67 | 30.08 | 56.74 | | QUESTA-Nemotron-1.5B | **71.56** | 62.08 | 93.44 | 92.95 | **32.08** | 72.28 | **40.94** | **67.50** | 41.48 | 63.81 | | JustRL-Nemotron-1.5B | 69.69 | **62.92** | **96.02** | **94.15** | 30.24 | **76.59** | 40.63 | 66.88 | **41.72** | **64.32** | We achieve 64.32% average, slightly outperforming QuestA's 63.81% and leading on five of nine benchmarks. The gap is narrow, which makes senseβ€”both approaches are pushing the boundaries of what's achievable at 1.5B scale. The key difference is in how we get there. We use 2Γ— less compute while achieving slightly better average performance without designing a complex curriculum as used in QuestA. ## Training Recipe Our approach is deliberately minimal: **Core Algorithm**: Standard GRPO with binary outcome rewards - **Reward**: Simple DAPO verifier (string-matching, no SymPy) - **Training**: Single-stage, no curriculum or stage transitions - **Hyperparameters**: Fixed throughout (no adaptive schedules) - **Data**: DAPO-Math-17k without filtering or dynamic sampling - **Length Control**: 16K context cap (no explicit penalties) - **Stabilization**: Only "clip higher" for gradient stability Detail hyperparameters and comparisons on training techniques with other methods can refer to our [blog](https://relieved-cafe-fe1.notion.site/JustRL-Scaling-a-1-5B-LLM-with-a-Simple-RL-Recipe-24f6198b0b6b80e48e74f519bfdaf0a8). ## Training Data We train on [DAPO-Math-17k](https://huggingface.co/datasets/BytedTsinghua-SIA/DAPO-Math-17k), a curated dataset of mathematical problems. **No offline difficulty filtering or online dynamic sampling is used.** ## Usage ### Basic Inference ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "hbx/JustRL-Nemotron-1.5B" # or JustRL-DeepSeek-1.5B model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto" ) tokenizer = AutoTokenizer.from_pretrained(model_name) prompt = """ Please reason step by step, and put your final answer within \\boxed{}.""" messages = [{"role": "user", "content": prompt}] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) inputs = tokenizer([text], return_tensors="pt").to(model.device) outputs = model.generate( **inputs, max_new_tokens=16384, temperature=0.7, top_p=0.9, do_sample=True ) response = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True) print(response) ``` ### Batch Inference with vLLM ```python from vllm import LLM, SamplingParams llm = LLM( model="hbx/JustRL-Nemotron-1.5B", tensor_parallel_size=1, max_model_len=32768 ) sampling_params = SamplingParams( temperature=0.7, top_p=0.9, max_tokens=16384, ) problems = [...] # Your list of problems responses = llm.generate(problems, sampling_params) ``` ## Reproduction We provide evaluation scripts based on [POLARIS](https://github.com/ChenxinAn-fdu/POLARIS), the evaluation script is [here](https://github.com/thunlp/JustRL) ```bibtex @misc{he2025justrl, title = {JustRL: Scaling a 1.5B LLM with a Simple RL Recipe}, author = {Bingxiang He and Zekai Qu and Zeyuan Liu and Yinghao Chen and Yuxin Zuo and Cheng Qian and Kaiyan Zhang and Weize Chen and Chaojun Xiao and Ganqu Cui and Ning Ding and Zhiyuan Liu}, howpublished = {\url{https://relieved-cafe-fe1.notion.site/JustRL-Scaling-a-1-5B-LLM-with-a-Simple-RL-Recipe-24f6198b0b6b80e48e74f519bfdaf0a8}}, note = {Notion Blog}, year = {2025}, month = {Nov}, day = {4} }