GRPO Reinforcement Learning Training

For each prompt p:
  1. Generate N completions: {c₁, c₂, ..., cₙ}
  2. Compute rewards: {r₁, r₂, ..., rₙ}
  3. Learn to increase probability of high-reward completions
     relative to low-reward ones in the same group

from datasets import load_dataset, Dataset

SYSTEM_PROMPT = """
Respond in the following format:
<reasoning>
[Your step-by-step thinking]
</reasoning>
<answer>
[Final answer]
</answer>
"""

def prepare_dataset(raw_data):
    """
    Transform raw data into GRPO-compatible format.

    Returns: Dataset with columns:
    - 'prompt': List[Dict] with role/content (system + user messages)
    - 'answer': str (ground truth, optional but recommended)
    """
    return raw_data.map(lambda x: {
        'prompt': [
            {'role': 'system', 'content': SYSTEM_PROMPT},
            {'role': 'user', 'content': x['question']}
        ],
        'answer': extract_answer(x['raw_answer'])
    })

def reward_function_name(
    prompts,        # List[List[Dict]]: Original prompts
    completions,    # List[List[Dict]]: Model generations
    answer=None,    # Optional: Ground truth from dataset
    **kwargs        # Additional dataset columns
) -> list[float]:
    """
    Evaluate completions and return rewards.

    Returns: List of floats (one per completion)
    """
    # Extract completion text
    responses = [comp[0]['content'] for comp in completions]

    # Compute rewards
    rewards = []
    for response in responses:
        score = compute_score(response)
        rewards.append(score)

    return rewards

def correctness_reward(prompts, completions, answer, **kwargs):
    """Reward correct answers with high score."""
    responses = [comp[0]['content'] for comp in completions]
    extracted = [extract_final_answer(r) for r in responses]
    return [2.0 if ans == gt else 0.0
            for ans, gt in zip(extracted, answer)]

import re

def format_reward(completions, **kwargs):
    """Reward XML-like structured format."""
    pattern = r'<reasoning>.*?</reasoning>\s*<answer>.*?</answer>'
    responses = [comp[0]['content'] for comp in completions]
    return [1.0 if re.search(pattern, r, re.DOTALL) else 0.0
            for r in responses]

def incremental_format_reward(completions, **kwargs):
    """Award partial credit for format compliance."""
    responses = [comp[0]['content'] for comp in completions]
    rewards = []

    for r in responses:
        score = 0.0
        if '<reasoning>' in r:
            score += 0.25
        if '</reasoning>' in r:
            score += 0.25
        if '<answer>' in r:
            score += 0.25
        if '</answer>' in r:
            score += 0.25
        # Penalize extra text after closing tag
        if r.count('</answer>') == 1:
            extra_text = r.split('</answer>')[-1].strip()
            score -= len(extra_text) * 0.001
        rewards.append(score)

    return rewards

from trl import GRPOConfig

training_args = GRPOConfig(
    output_dir="outputs/grpo-model",

    # Learning rate
    learning_rate=5e-6,          # Lower = more stable
    adam_beta1=0.9,
    adam_beta2=0.99,
    weight_decay=0.1,
    warmup_ratio=0.1,
    lr_scheduler_type='cosine',

    # Batch settings
    per_device_train_batch_size=1,
    gradient_accumulation_steps=4,  # Effective batch = 4

    # GRPO-specific
    num_generations=8,            # Group size: 8-16 recommended
    max_prompt_length=256,
    max_completion_length=512,

    # Training duration
    num_train_epochs=1,
    max_steps=None,               # Or set fixed steps (e.g., 500)

    # Optimization
    bf16=True,                    # Faster on A100/H100
    optim="adamw_8bit",          # Memory-efficient optimizer
    max_grad_norm=0.1,

    # Logging
    logging_steps=1,
    save_steps=100,
    report_to="wandb",            # Or "none" for no logging
)

training_args = GRPOConfig(
    output_dir="outputs/grpo-model",
    learning_rate=1e-5,
    per_device_train_batch_size=4,
    gradient_accumulation_steps=2,
    num_generations=16,           # Larger groups = better signal
    max_prompt_length=512,
    max_completion_length=1024,
    num_train_epochs=1,
    bf16=True,
    use_vllm=True,                # Fast generation with vLLM
    logging_steps=10,
)

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import LoraConfig
from trl import GRPOTrainer

# Load model
model_name = "Qwen/Qwen2.5-1.5B-Instruct"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",  # 2-3x faster
    device_map="auto"
)

tokenizer = AutoTokenizer.from_pretrained(model_name)
tokenizer.pad_token = tokenizer.eos_token

# Optional: LoRA for parameter-efficient training
peft_config = LoraConfig(
    r=16,                         # Rank (higher = more capacity)
    lora_alpha=32,               # Scaling factor (typically 2*r)
    target_modules=[
        "q_proj", "k_proj", "v_proj", "o_proj",
        "gate_proj", "up_proj", "down_proj"
    ],
    task_type="CAUSAL_LM",
    lora_dropout=0.05,
)

# Initialize trainer
trainer = GRPOTrainer(
    model=model,
    processing_class=tokenizer,
    reward_funcs=[
        incremental_format_reward,
        format_reward,
        correctness_reward,
    ],
    args=training_args,
    train_dataset=dataset,
    peft_config=peft_config,      # Remove for full fine-tuning
)

# Train
trainer.train()

# Save
trainer.save_model("final_model")

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="google/gemma-3-1b-it",
    max_seq_length=1024,
    load_in_4bit=True,
    fast_inference=True,
    max_lora_rank=32,
)

model = FastLanguageModel.get_peft_model(
    model,
    r=32,
    target_modules=["q_proj", "k_proj", "v_proj", "o_proj",
                    "gate_proj", "up_proj", "down_proj"],
    lora_alpha=32,
    use_gradient_checkpointing="unsloth",
)

# Rest is identical to standard setup
trainer = GRPOTrainer(model=model, ...)
trainer.train()

Step   Reward    Reward_Std   KL
100    0.5       0.3          0.02
200    0.8       0.25         0.05
300    1.2       0.2          0.08  ← Good progression
400    1.5       0.15         0.12