Reproduction

in https://github.com/huggingface/trl/blob/v0.19-release/trl/trainer/grpo_config.py line 547, perhaps it should be
if self.generation_batch_size % (self.per_device_train_batch_size * num_processes) != 0:

System Info

trl env

Checklist

• I have checked that my issue isn't already filed (see open issues)
• I have included my system information
• Any code provided is minimal, complete, and reproducible (more on MREs)
• Any code provided is properly formatted in code blocks, (no screenshot, more on code blocks)
• Any traceback provided is complete