Method get_optimizer_cls_and_kwargs

src/transformers/trainer.py:1259–1287

Returns the optimizer class and optimizer parameters based on the training arguments. Args: args (`transformers.training_args.TrainingArguments`): The training arguments for the training session. model (`PreTrainedModel`, *optional*):

(args: TrainingArguments, model: PreTrainedModel | None = None)

    @staticmethod
    def get_optimizer_cls_and_kwargs(args: TrainingArguments, model: PreTrainedModel | None = None) -> tuple[Any, Any]:
        """
        Returns the optimizer class and optimizer parameters based on the training arguments.

        Args:
            args (`transformers.training_args.TrainingArguments`):
                The training arguments for the training session.
            model (`PreTrainedModel`, *optional*):
                The model being trained. Required for some optimizers (GaLore, Apollo, LOMO).

        Returns:
            A tuple containing the optimizer class and a dictionary of optimizer keyword arguments.
        """
        ctx = OptimizerContext(
            args=args,
            model=model,
            optimizer_kwargs={"lr": args.learning_rate},
            adam_kwargs={
                "betas": (args.adam_beta1, args.adam_beta2),
                "eps": args.adam_epsilon,
            },
            optim_args=_parse_optim_args(args.optim_args),
        )

        handler = _OPTIMIZER_HANDLERS.get(args.optim)
        if handler is None:
            raise ValueError(f"Trainer cannot instantiate unsupported optimizer: {args.optim}")

        return handler(ctx)

    def get_decay_parameter_names(self, model: nn.Module) -> list[str]:
        """