Correct GRPO to Group Relative Policy Optimization (#427)

Author: joecummings

docs/source/getting_started.md

@@ -5,5 +5,5 @@ Welcome to TorchForge! This guide will help you get up and running with TorchFor
 TorchForge specializes in post-training techniques for large language models, including:
 
 - **Supervised Fine-Tuning (SFT)**: Adapt pre-trained models to specific tasks using labeled data
-- **Generalized Reward Policy Optimization (GRPO)**: Advanced reinforcement learning for model alignment
+- **Group Relative Policy Optimization (GRPO)**: Advanced reinforcement learning for model alignment
 - **Multi-GPU Distributed Training**: Efficient scaling across multiple GPUs and nodes

docs/source/index.md

@@ -7,7 +7,7 @@ Key Features
 ------------
 
 * **Post-Training Focus**: Specializes in techniques
-  like Supervised Fine-Tuning (SFT) and Generalized Reward Policy Optimization (GRPO)
+  like Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO)
 * **PyTorch Integration**: Built natively on PyTorch with
   dependencies on [PyTorch nightly](https://pytorch.org/get-started/locally/),
   [Monarch](https://meta-pytorch.org/monarch), [vLLM](https://docs.vllm.ai/en/latest/),