trl/trainer/cpo_trainer.py [920:1109]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if ignore_keys is None:
            if hasattr(model, "config"):
                ignore_keys = getattr(model.config, "keys_to_ignore_at_inference", [])
            else:
                ignore_keys = []

        prediction_context_manager = (
            autocast(self.accelerator.device.type) if self._peft_has_been_casted_to_bf16 else nullcontext()
        )

        with torch.no_grad(), prediction_context_manager:
            loss, metrics = self.get_batch_loss_metrics(model, inputs, train_eval="eval")

        # force log the metrics
        self.store_metrics(metrics, train_eval="eval")

        if prediction_loss_only:
            return (loss.detach(), None, None)

        # logits for the chosen and rejected samples from model
        logits_dict = {
            "eval_logits/chosen": metrics["eval_logits/chosen"],
            "eval_logits/rejected": metrics["eval_logits/rejected"],
        }
        logits = [v for k, v in logits_dict.items() if k not in ignore_keys]
        logits = torch.tensor(logits, device=self.accelerator.device)
        labels = torch.zeros(logits.shape[0], device=self.accelerator.device)

        return (loss.detach(), logits, labels)

    def store_metrics(self, metrics: dict[str, float], train_eval: Literal["train", "eval"] = "train") -> None:
        for key, value in metrics.items():
            self._stored_metrics[train_eval][key].append(value)

    def evaluation_loop(
        self,
        dataloader: DataLoader,
        description: str,
        prediction_loss_only: Optional[bool] = None,
        ignore_keys: Optional[list[str]] = None,
        metric_key_prefix: str = "eval",
    ) -> EvalLoopOutput:
        """
        Overriding built-in evaluation loop to store metrics for each batch. Prediction/evaluation loop, shared by
        `Trainer.evaluate()` and `Trainer.predict()`.

        Works both with or without labels.
        """

        # Sample and save to game log if requested (for one batch to save time)
        if self.generate_during_eval:
            # Generate random indices within the range of the total number of samples
            num_samples = len(dataloader.dataset)
            random_indices = random.sample(range(num_samples), k=self.args.eval_batch_size)

            # Use dataloader.dataset.select to get the random batch without iterating over the DataLoader
            random_batch_dataset = dataloader.dataset.select(random_indices)
            random_batch = self.data_collator(random_batch_dataset)
            random_batch = self._prepare_inputs(random_batch)

            policy_output_decoded = self.generate_from_model(self.model, random_batch)

            table = pd.DataFrame(
                columns=["Prompt", "Policy"],
                data=[
                    [prompt, pol[len(prompt) :]] for prompt, pol in zip(random_batch["prompt"], policy_output_decoded)
                ],
            )
            if "wandb" in self.args.report_to:
                wandb.log({"game_log": wandb.Table(data=table)})

            if "comet_ml" in self.args.report_to:
                log_table_to_comet_experiment(
                    name="game_log.csv",
                    table=table,
                )

        # Base evaluation
        initial_output = super().evaluation_loop(
            dataloader, description, prediction_loss_only, ignore_keys, metric_key_prefix
        )

        return initial_output

    def log(self, logs: dict[str, float], start_time: Optional[float] = None) -> None:
        """
        Log `logs` on the various objects watching training, including stored metrics.

        Args:
            logs (`dict[str, float]`):
                The values to log.
            start_time (`float` or `None`, *optional*, defaults to `None`):
                Start time of the training.
        """
        # logs either has 'loss' or 'eval_loss'
        train_eval = "train" if "loss" in logs else "eval"
        # Add averaged stored metrics to logs
        for key, metrics in self._stored_metrics[train_eval].items():
            logs[key] = torch.tensor(metrics).mean().item()
        del self._stored_metrics[train_eval]
        return super().log(logs, start_time)

    def _shift_right(self, input_ids):
        if self.decoder_start_token_id is None:
            raise ValueError(
                "model.config.decoder_start_token_id has to be defined. It is usually set to the pad_token_id."
            )

        # shift inputs to the right
        if is_torch_fx_proxy(input_ids):
            # Item assignment is not supported natively for proxies.
            shifted_input_ids = torch.full(input_ids.shape[:-1] + (1,), self.decoder_start_token_id)
            shifted_input_ids = torch.cat([shifted_input_ids, input_ids[..., :-1]], dim=-1)
        else:
            shifted_input_ids = input_ids.new_zeros(input_ids.shape)
            shifted_input_ids[..., 1:] = input_ids[..., :-1].clone()
            shifted_input_ids[..., 0] = self.decoder_start_token_id

        if self.pad_token_id is None:
            raise ValueError("model.config.pad_token_id has to be defined.")
        # replace possible -100 values in labels by `pad_token_id`
        shifted_input_ids.masked_fill_(shifted_input_ids == -100, self.pad_token_id)

        return shifted_input_ids

    # Ensure the model card is saved along with the checkpoint
    def _save_checkpoint(self, model, trial):
        if self.args.hub_model_id is None:
            model_name = Path(self.args.output_dir).name
        else:
            model_name = self.args.hub_model_id.split("/")[-1]
        self.create_model_card(model_name=model_name)
        super()._save_checkpoint(model, trial)

    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{xu2024contrastive,
            title        = {{Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation}},
            author       = {Haoran Xu and Amr Sharaf and Yunmo Chen and Weiting Tan and Lingfeng Shen and Benjamin Van Durme and Kenton Murray and Young Jin Kim},
            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=51iwkioZpn}
        }""")

        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/orpo_trainer.py [899:1086]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if ignore_keys is None:
            if hasattr(model, "config"):
                ignore_keys = getattr(model.config, "keys_to_ignore_at_inference", [])
            else:
                ignore_keys = []

        prediction_context_manager = (
            autocast(self.accelerator.device.type) if self._peft_has_been_casted_to_bf16 else nullcontext()
        )

        with torch.no_grad(), prediction_context_manager:
            loss, metrics = self.get_batch_loss_metrics(model, inputs, train_eval="eval")

        # force log the metrics
        self.store_metrics(metrics, train_eval="eval")

        if prediction_loss_only:
            return (loss.detach(), None, None)

        # logits for the chosen and rejected samples from model
        logits_dict = {
            "eval_logits/chosen": metrics["eval_logits/chosen"],
            "eval_logits/rejected": metrics["eval_logits/rejected"],
        }
        logits = [v for k, v in logits_dict.items() if k not in ignore_keys]
        logits = torch.tensor(logits, device=self.accelerator.device)
        labels = torch.zeros(logits.shape[0], device=self.accelerator.device)

        return (loss.detach(), logits, labels)

    def store_metrics(self, metrics: dict[str, float], train_eval: Literal["train", "eval"] = "train") -> None:
        for key, value in metrics.items():
            self._stored_metrics[train_eval][key].append(value)

    def evaluation_loop(
        self,
        dataloader: DataLoader,
        description: str,
        prediction_loss_only: Optional[bool] = None,
        ignore_keys: Optional[list[str]] = None,
        metric_key_prefix: str = "eval",
    ) -> EvalLoopOutput:
        """
        Overriding built-in evaluation loop to store metrics for each batch. Prediction/evaluation loop, shared by
        `Trainer.evaluate()` and `Trainer.predict()`.

        Works both with or without labels.
        """

        # Sample and save to game log if requested (for one batch to save time)
        if self.generate_during_eval:
            # Generate random indices within the range of the total number of samples
            num_samples = len(dataloader.dataset)
            random_indices = random.sample(range(num_samples), k=self.args.eval_batch_size)

            # Use dataloader.dataset.select to get the random batch without iterating over the DataLoader
            random_batch_dataset = dataloader.dataset.select(random_indices)
            random_batch = self.data_collator(random_batch_dataset)
            random_batch = self._prepare_inputs(random_batch)

            policy_output_decoded = self.generate_from_model(self.model, random_batch)

            table = pd.DataFrame(
                columns=["Prompt", "Policy"],
                data=[
                    [prompt, pol[len(prompt) :]] for prompt, pol in zip(random_batch["prompt"], policy_output_decoded)
                ],
            )
            if "wandb" in self.args.report_to:
                wandb.log({"game_log": wandb.Table(data=table)})

            if "comet_ml" in self.args.report_to:
                log_table_to_comet_experiment(
                    name="game_log.csv",
                    table=table,
                )

        # Base evaluation
        initial_output = super().evaluation_loop(
            dataloader, description, prediction_loss_only, ignore_keys, metric_key_prefix
        )

        return initial_output

    def log(self, logs: dict[str, float], start_time: Optional[float] = None) -> None:
        """
        Log `logs` on the various objects watching training, including stored metrics.

        Args:
            logs (`dict[str, float]`):
                The values to log.
            start_time (`float` or `None`, *optional*, defaults to `None`):
                Start time of the training.
        """
        # logs either has 'loss' or 'eval_loss'
        train_eval = "train" if "loss" in logs else "eval"
        # Add averaged stored metrics to logs
        for key, metrics in self._stored_metrics[train_eval].items():
            logs[key] = torch.tensor(metrics).mean().item()
        del self._stored_metrics[train_eval]
        return super().log(logs, start_time)

    def _shift_right(self, input_ids):
        if self.decoder_start_token_id is None:
            raise ValueError(
                "model.config.decoder_start_token_id has to be defined. It is usually set to the pad_token_id."
            )

        # shift inputs to the right
        if is_torch_fx_proxy(input_ids):
            # Item assignment is not supported natively for proxies.
            shifted_input_ids = torch.full(input_ids.shape[:-1] + (1,), self.decoder_start_token_id)
            shifted_input_ids = torch.cat([shifted_input_ids, input_ids[..., :-1]], dim=-1)
        else:
            shifted_input_ids = input_ids.new_zeros(input_ids.shape)
            shifted_input_ids[..., 1:] = input_ids[..., :-1].clone()
            shifted_input_ids[..., 0] = self.decoder_start_token_id

        if self.pad_token_id is None:
            raise ValueError("model.config.pad_token_id has to be defined.")
        # replace possible -100 values in labels by `pad_token_id`
        shifted_input_ids.masked_fill_(shifted_input_ids == -100, self.pad_token_id)

        return shifted_input_ids

    # Ensure the model card is saved along with the checkpoint
    def _save_checkpoint(self, model, trial):
        if self.args.hub_model_id is None:
            model_name = Path(self.args.output_dir).name
        else:
            model_name = self.args.hub_model_id.split("/")[-1]
        self.create_model_card(model_name=model_name)
        super()._save_checkpoint(model, trial)

    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{hong2024orpo,
            title        = {{ORPO: Monolithic Preference Optimization without Reference Model}},
            author       = {Jiwoo Hong and Noah Lee and James Thorne},
            year         = 2024,
            eprint       = {arXiv:2403.07691}
        }""")

        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(),
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -