torchforge-rl-training

# torchforge: PyTorch-Native Agentic RL Library

torchforge is Meta's PyTorch-native RL library that separates infrastructure concerns from algorithm concerns. It enables rapid RL research by letting you focus on algorithms while handling distributed training, inference, and weight sync automatically.

## When to Use torchforge

**Choose torchforge when you need:**
- Clean separation between RL algorithms and infrastructure
- PyTorch-native abstractions (no Ray dependency)
- Easy algorithm experimentation (GRPO, DAPO, SAPO in ~100 lines)
- Scalable training with Monarch actor system
- Integration with TorchTitan for model parallelism

**Consider alternatives when:**
- You need production-ready stability → use **miles** or **verl**
- You want Megatron-native training → use **slime**
- torchforge is experimental and APIs may change

## Key Features

- **Algorithm isolation**: Implement RL algorithms without touching infrastructure
- **Scalability**: From single GPU to thousands via Monarch
- **Modern stack**: TorchTitan (training), vLLM (inference), TorchStore (sync)
- **Loss functions**: GRPO, DAPO, CISPO, GSPO, SAPO built-in

## Architecture Overview

```
┌─────────────────────────────────────────────────────────┐
│ Application Layer (Your Code)                           │
│ - Define reward models, loss functions, sampling        │
└─────────────────────┬───────────────────────────────────┘
                      │
┌─────────────────────▼───────────────────────────────────┐
│ Forge API Layer                                         │
│ - Episode, Group dataclasses                           │
│ - Service interfaces (async/await)                      │
└─────────────────────┬───────────────────────────────────┘
                      │
┌─────────────────────▼───────────────────────────────────┐
│ Distributed Services (Monarch)                          │
│ ├── Trainer (TorchTitan FSDP)                          │
│ ├── Generator (vLLM inference)                          │
│ ├── Reference Model (frozen KL baseline)               │
│ └── Reward Actors (compute rewards)                    │
└─────────────────────────────────────────────────────────┘
```

## Installation

```bash
# Create environment
conda create -n forge python=3.12
conda activate forge

# Install (handles PyTorch nightly + dependencies)
./scripts/install.sh

# Verify
python -c "import torch, forge, vllm; print('OK')"
```

### ROCm Installation

```bash
./scripts/install_rocm.sh
```

## Quick Start

### SFT Training (2+ GPUs)

```bash
python -m apps.sft.main --config apps/sft/llama3_8b.yaml
```

### GRPO Training (3+ GPUs)

```bash
python -m apps.grpo.main --config apps/grpo/qwen3_1_7b.yaml
```

---

## Workflow 1: GRPO Training for Math Reasoning

Use this workflow for training reasoning models with group-relative advantages.

### Prerequisites Checklist
- [ ] 3+ GPUs (GPU0: trainer, GPU1: ref_model, GPU2: generator)
- [ ] Model from HuggingFace Hub
- [ ] Training dataset (GSM8K, MATH, etc.)

### Step 1: Create Configuration

```yaml
# config/grpo_math.yaml
model: "Qwen/Qwen2.5-7B-Instruct"

dataset:
  path: "openai/gsm8k"
  split: "train"
  streaming: true

training:
  batch_size: 4
  learning_rate: 1e-6
  seq_len: 4096
  dtype: bfloat16
  gradient_accumulation_steps: 4

grpo:
  n_samples: 8           # Responses per prompt
  clip_low: 0.2
  clip_high: 0.28
  beta: 0.1              # KL penalty coefficient
  temperature: 0.7

services:
  generator:
    procs: 1
    num_replicas: 1
    with_gpus: true
  trainer:
    procs: 1
    num_replicas: 1
    with_gpus: true
  ref_model:
    procs: 1
    num_replicas: 1
    with_gpus: true
```

### Step 2: Define Reward Function

```python
# rewards.py
# Reward functions are in forge.data.rewards
from forge.data.rewards import MathReward, ThinkingReward
import re

# Or define your own reward function
class CustomMathReward:
    def __call__(self, prompt: str, response: str, target: str) -> float:
        # Extract answer from response
        match = re.search(r'\\boxed{([^}]+)}', response)
        if not match:
            return 0.0

        answer = match.group(1).strip()
        return 1.0 if answer == target else 0.0
```

### Step 3: Launch Training

```bash
python -m apps.grpo.main --config config/grpo_math.yaml
```

### Step 4: Monitor Progress
- [ ] Check W&B dashboard for loss curves
- [ ] Verify entropy is decreasing (policy becoming more deterministic)
- [ ] Monitor KL divergence (should stay bounded)

---

## Workflow 2: Custom Loss Function

Use this workflow to implement new RL algorithms.

### Step 1: Create Loss Class

```python
# src/forge/losses/custom_loss.py
import torch
import torch.nn as nn

class CustomLoss(nn.Module):
    def __init__(self, clip_range: float = 0.2, beta: float = 0.1):
        super().__init__()
        self.clip_range = clip_range
        self.beta = beta

    def forward(
        self,
        logprobs: torch.Tensor,
        ref_logprobs: torch.Tensor,
        advantages: torch.Tensor,
        padding_mask: torch.Tensor,
    ) -> torch.Tensor:
        # Compute importance ratio
        ratio = torch.exp(logprobs - ref_logprobs)

        # Clipped policy gradient
        clipped_ratio = torch.clamp(
            ratio,
            1 - self.clip_range,
            1 + self.clip_range
        )
        pg_loss = -torch.min(ratio * advantages, clipped_ratio * advantages)

        # KL penalty
        kl = ref_logprobs - logprobs

        # Apply mask and aggregate
        masked_loss = (pg_loss + self.beta * kl) * padding_mask
        loss = masked_loss.sum() / padding_mask.sum()

        return loss
```

### Step 2: Integrate into Application

```python
# apps/custom/main.py
from forge.losses.custom_loss import CustomLoss

loss_fn = CustomLoss(clip_range=0.2, beta=0.1)

# In training loop
loss = loss_fn(
    logprobs=logprobs,
    ref_logprobs=ref_logprobs,
    advantages=advantages,
    padding_mask=padding_mask,
)
```

---

## Workflow 3: Multi-GPU D