trl/trainer/nash_md_trainer.py [465:544]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )

        if (
            self.args.torch_empty_cache_steps is not None
            and self.state.global_step % self.args.torch_empty_cache_steps == 0
        ):
            empty_cache()

        kwargs = {}
        # For LOMO optimizers you need to explicitly use the learning rate
        if self.args.optim in [OptimizerNames.LOMO, OptimizerNames.ADALOMO]:
            kwargs["learning_rate"] = self._get_learning_rate()

        if self.args.n_gpu > 1:
            loss = loss.mean()  # mean() to average on multi-gpu parallel training

        if self.use_apex:
            with amp.scale_loss(loss, self.optimizer) as scaled_loss:
                scaled_loss.backward()
        else:
            self.accelerator.backward(loss, **kwargs)

        return loss.detach() / self.args.gradient_accumulation_steps

    def create_model_card(
        self,
        model_name: Optional[str] = None,
        dataset_name: Optional[str] = None,
        tags: Union[str, list[str], None] = None,
    ):
        """
        Creates a draft of a model card using the information available to the `Trainer`.

        Args:
            model_name (`str` or `None`, *optional*, defaults to `None`):
                Name of the model.
            dataset_name (`str` or `None`, *optional*, defaults to `None`):
                Name of the dataset used for training.
            tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
                Tags to be associated with the model card.
        """
        if not self.is_world_process_zero():
            return

        if hasattr(self.model.config, "_name_or_path") and not os.path.isdir(self.model.config._name_or_path):
            base_model = self.model.config._name_or_path
        else:
            base_model = None

        # normalize `tags` to a mutable set
        if tags is None:
            tags = set()
        elif isinstance(tags, str):
            tags = {tags}
        else:
            tags = set(tags)

        if hasattr(self.model.config, "unsloth_version"):
            tags.add("unsloth")

        tags.update(self._tag_names)

        citation = textwrap.dedent("""\
        @inproceedings{munos2024nash,
            title        = {{Nash Learning from Human Feedback}},
            author       = {R{\'{e}}mi Munos and Michal Valko and Daniele Calandriello and Mohammad Gheshlaghi Azar and Mark Rowland and Zhaohan Daniel Guo and Yunhao Tang and Matthieu Geist and Thomas Mesnard and C{\\^{o}}me Fiegel and Andrea Michi and Marco Selvi and Sertan Girgin and Nikola Momchev and Olivier Bachem and Daniel J. Mankowitz and Doina Precup and Bilal Piot},
            year         = 2024,
            booktitle    = {Forty-first International Conference on Machine Learning, {ICML} 2024, Vienna, Austria, July 21-27, 2024},
            publisher    = {OpenReview.net},
            url          = {https://openreview.net/forum?id=Y5AmNYiyCQ}
        }""")

        model_card = generate_model_card(
            base_model=base_model,
            model_name=model_name,
            hub_model_id=self.hub_model_id,
            dataset_name=dataset_name,
            tags=tags,
            wandb_url=wandb.run.get_url() if is_wandb_available() and wandb.run is not None else None,
            comet_url=get_comet_experiment_url(),
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



trl/trainer/xpo_trainer.py [511:588]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )

        if (
            self.args.torch_empty_cache_steps is not None
            and self.state.global_step % self.args.torch_empty_cache_steps == 0
        ):
            empty_cache()

        kwargs = {}
        # For LOMO optimizers you need to explicitly use the learning rate
        if self.args.optim in [OptimizerNames.LOMO, OptimizerNames.ADALOMO]:
            kwargs["learning_rate"] = self._get_learning_rate()

        if self.args.n_gpu > 1:
            loss = loss.mean()  # mean() to average on multi-gpu parallel training

        if self.use_apex:
            with amp.scale_loss(loss, self.optimizer) as scaled_loss:
                scaled_loss.backward()
        else:
            self.accelerator.backward(loss, **kwargs)

        return loss.detach() / self.args.gradient_accumulation_steps

    def create_model_card(
        self,
        model_name: Optional[str] = None,
        dataset_name: Optional[str] = None,
        tags: Union[str, list[str], None] = None,
    ):
        """
        Creates a draft of a model card using the information available to the `Trainer`.

        Args:
            model_name (`str` or `None`, *optional*, defaults to `None`):
                Name of the model.
            dataset_name (`str` or `None`, *optional*, defaults to `None`):
                Name of the dataset used for training.
            tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
                Tags to be associated with the model card.
        """
        if not self.is_world_process_zero():
            return

        if hasattr(self.model.config, "_name_or_path") and not os.path.isdir(self.model.config._name_or_path):
            base_model = self.model.config._name_or_path
        else:
            base_model = None

        # normalize `tags` to a mutable set
        if tags is None:
            tags = set()
        elif isinstance(tags, str):
            tags = {tags}
        else:
            tags = set(tags)

        if hasattr(self.model.config, "unsloth_version"):
            tags.add("unsloth")

        tags.update(self._tag_names)

        citation = textwrap.dedent("""\
        @article{jung2024binary,
            title        = {{Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF}},
            author       = {Tengyang Xie and Dylan J. Foster and Akshay Krishnamurthy and Corby Rosset and Ahmed Awadallah and Alexander Rakhlin},
            year         = 2024,
            eprint       = {arXiv:2405.21046}
        }""")

        model_card = generate_model_card(
            base_model=base_model,
            model_name=model_name,
            hub_model_id=self.hub_model_id,
            dataset_name=dataset_name,
            tags=tags,
            wandb_url=wandb.run.get_url() if is_wandb_available() and wandb.run is not None else None,
            comet_url=get_comet_experiment_url(),
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -