maxent\_grpo.training
=====================

.. automodule:: maxent_grpo.training

   
.. rubric:: Modules

.. autosummary::
   :toctree:
   :recursive:

   baseline
   cli
   controller_objective
   controller_optimizer
   data
   eval
   generation
   metrics
   optim
   patches
   pipeline
   rewards
   rollout
   run_helpers
   runtime
   scoring
   scoring_batching
   scoring_common
   scoring_logprob
   scoring_reference
   seed_paper_eval_callback
   state
   telemetry
   trainer_hooks
   trl_trainer
   types
   weighting
   zero_utils