Method evaluate

ptuning/trainer_seq2seq.py:31–78

Run evaluation and returns metrics. The calling script will be responsible for providing a method to compute metrics, as they are task-dependent (pass it to the init `compute_metrics` argument). You can also subclass and override this method to inject custom behavi

(
        self,
        eval_dataset: Optional[Dataset] = None,
        ignore_keys: Optional[List[str]] = None,
        metric_key_prefix: str = "eval",
        **gen_kwargs
    )

class Seq2SeqTrainer(PrefixTrainer):
    def evaluate(
        self,
        eval_dataset: Optional[Dataset] = None,
        ignore_keys: Optional[List[str]] = None,
        metric_key_prefix: str = "eval",
        **gen_kwargs
    ) -> Dict[str, float]:
        """
        Run evaluation and returns metrics.

        The calling script will be responsible for providing a method to compute metrics, as they are task-dependent
        (pass it to the init `compute_metrics` argument).

        You can also subclass and override this method to inject custom behavior.

        Args:
            eval_dataset (`Dataset`, *optional*):
                Pass a dataset if you wish to override `self.eval_dataset`. If it is an [`~datasets.Dataset`], columns
                not accepted by the `model.forward()` method are automatically removed. It must implement the `__len__`
                method.
            ignore_keys (`List[str]`, *optional*):
                A list of keys in the output of your model (if it is a dictionary) that should be ignored when
                gathering predictions.
            metric_key_prefix (`str`, *optional*, defaults to `"eval"`):
                An optional prefix to be used as the metrics key prefix. For example the metrics "bleu" will be named
                "eval_bleu" if the prefix is `"eval"` (default)
            max_length (`int`, *optional*):
                The maximum target length to use when predicting with the generate method.
            num_beams (`int`, *optional*):
                Number of beams for beam search that will be used when predicting with the generate method. 1 means no
                beam search.
            gen_kwargs:
                Additional `generate` specific kwargs.

        Returns:
            A dictionary containing the evaluation loss and the potential metrics computed from the predictions. The
            dictionary also contains the epoch number which comes from the training state.
        """

        gen_kwargs = gen_kwargs.copy()
        if gen_kwargs.get("max_length") is None and gen_kwargs.get("max_new_tokens") is None:
            gen_kwargs["max_length"] = self.args.generation_max_length
        gen_kwargs["num_beams"] = (
            gen_kwargs["num_beams"] if gen_kwargs.get("num_beams") is not None else self.args.generation_num_beams
        )
        self._gen_kwargs = gen_kwargs

        return super().evaluate(eval_dataset, ignore_keys=ignore_keys, metric_key_prefix=metric_key_prefix)

    def predict(
        self,