credit.trainers.trainerERA5_Diffusion
=====================================

.. py:module:: credit.trainers.trainerERA5_Diffusion


Attributes
----------

.. autoapisummary::

   credit.trainers.trainerERA5_Diffusion.logger


Classes
-------

.. autoapisummary::

   credit.trainers.trainerERA5_Diffusion.TrainerERA5Diffusion


Module Contents
---------------

.. py:data:: logger

.. py:class:: TrainerERA5Diffusion(model: torch.nn.Module, rank: int, conf: dict)

   Bases: :py:obj:`credit.trainers.base_trainer.BaseTrainer`


   Helper class that provides a standard way to create an ABC using
   inheritance.


   .. py:method:: train_one_epoch(epoch, trainloader, optimizer, criterion, scaler, scheduler, metrics)

      Trains the model for one epoch.

      :param epoch: Current epoch number.
      :type epoch: int
      :param conf: Configuration dictionary containing training settings.
      :type conf: dict
      :param trainloader: DataLoader for the training dataset.
      :type trainloader: DataLoader
      :param optimizer: Optimizer used for training.
      :type optimizer: torch.optim.Optimizer
      :param criterion: Loss function used for training.
      :type criterion: callable
      :param scaler: Gradient scaler for mixed precision training.
      :type scaler: torch.cuda.amp.GradScaler
      :param scheduler: Learning rate scheduler.
      :type scheduler: torch.optim.lr_scheduler._LRScheduler
      :param metrics: Function to compute metrics for evaluation.
      :type metrics: callable

      :returns: Dictionary containing training metrics and loss for the epoch.
      :rtype: dict



   .. py:method:: validate(epoch, valid_loader, criterion, metrics)

      Validates the model on the validation dataset.

      :param epoch: Current epoch number.
      :type epoch: int
      :param conf: Configuration dictionary containing validation settings.
      :type conf: dict
      :param valid_loader: DataLoader for the validation dataset.
      :type valid_loader: DataLoader
      :param criterion: Loss function used for validation.
      :type criterion: callable
      :param metrics: Function to compute metrics for evaluation.
      :type metrics: callable

      :returns: Dictionary containing validation metrics and loss for the epoch.
      :rtype: dict