Rayen

## Title Create a NeMo-RL dedicate branch and bump Automodel to [the branch](https://github.com/NVIDIA-NeMo/Automodel/tree/ruit/nemor-rl-submodule) ## Background / Motivation - Align with upstream Automodel fixes/features to improve compatibility, performance, and stability. -...

Refactor the SFT and GRPO entry script to adopt the new dataset processor interface introduced in RawDataset and the PROCESSOR_REGISTRY, removing ad‑hoc preprocessing and aligning with the GRPO data path....

**Description** This PR https://github.com/NVIDIA-NeMo/RL/pull/1506 introduces a new executable script: run_grpo.py. The main purpose is to consolidate and generalize functionality that is currently split across run_grpo_math.py and run_grpo_rm.py. After https://github.com/NVIDIA-NeMo/RL/pull/1506 successful...

**Describe the bug** The config field model_name in `examples/configs/recipes/llm/grpo-helpsteer3-llama-3.3-nemotron-super-49b-v1.5-4n8g-fsdp2tp8.yaml ` can not use from Hugging Face model because the model script is not updating from Hugging Face. **How to solve**...

**Describe the bug** When running the nemotron-helpsteer3 GRPO recipe (examples/configs/recipes/llm/grpo-helpsteer3-llama-3.3-nemotron-super-49b-v1.5-4n8g-fsdp2tp8.yaml) with the HelpSteer3 dataset, the log_prob_error is extremely high both before and after PR [#1506](https://github.com/NVIDIA-NeMo/RL/pull/1506).