Trainer

class FlagEmbedding.finetune.reranker.decoder_only.layerwise.DecoderOnlyRerankerTrainer(model: PreTrainedModel | Module | None = None, args: TrainingArguments = None, data_collator: DataCollator | None = None, train_dataset: Dataset | IterableDataset | Dataset | None = None, eval_dataset: Dataset | dict[str, Dataset] | Dataset | None = None, processing_class: PreTrainedTokenizerBase | BaseImageProcessor | FeatureExtractionMixin | ProcessorMixin | None = None, model_init: Callable[[], PreTrainedModel] | None = None, compute_loss_func: Callable | None = None, compute_metrics: Callable[[EvalPrediction], dict] | None = None, callbacks: list[TrainerCallback] | None = None, optimizers: tuple[Optimizer | None, LambdaLR | None] = (None, None), optimizer_cls_and_kwargs: tuple[type[Optimizer], dict[str, Any]] | None = None, preprocess_logits_for_metrics: Callable[[Tensor, Tensor], Tensor] | None = None)

Trainer class for encoder only base reranker models.