Method __init__

src/transformers/trainer.py:364–618

(
        self,
        model: PreTrainedModel | nn.Module | None = None,
        args: TrainingArguments | None = None,
        data_collator: DataCollator | None = None,
        train_dataset: "Dataset | IterableDataset | datasets.Dataset | None" = None,
        eval_dataset: "Dataset | dict[str, Dataset] | datasets.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[torch.optim.Optimizer | None, torch.optim.lr_scheduler.LambdaLR | None] = (None, None),
        optimizer_cls_and_kwargs: tuple[type[torch.optim.Optimizer], dict[str, Any]] | None = None,
        preprocess_logits_for_metrics: Callable[[torch.Tensor, torch.Tensor], torch.Tensor] | None = None,
    )

    # ---- Initialization & Validation ----

    def __init__(
        self,
        model: PreTrainedModel | nn.Module | None = None,
        args: TrainingArguments | None = None,
        data_collator: DataCollator | None = None,
        train_dataset: "Dataset | IterableDataset | datasets.Dataset | None" = None,
        eval_dataset: "Dataset | dict[str, Dataset] | datasets.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[torch.optim.Optimizer | None, torch.optim.lr_scheduler.LambdaLR | None] = (None, None),
        optimizer_cls_and_kwargs: tuple[type[torch.optim.Optimizer], dict[str, Any]] | None = None,
        preprocess_logits_for_metrics: Callable[[torch.Tensor, torch.Tensor], torch.Tensor] | None = None,
    ):
        # Init flow:
        #   1. Args & seed               – defaults, determinism
        #   2. Accelerator & logging     – accelerator, memory tracker, log level, device setup
        #   3. Model resolution          – model / model_init, Liger Kernel, quantization checks
        #   4. Distributed strategy      – model-parallel, FSDP, SageMaker MP flags
        #   5. Device placement          – move model to device, model wrapping
        #   6. Model introspection       – loss kwargs, label names, label smoother
        #   7. Store init arguments      – data, callables, optimizer, scheduler, validation
        #   8. Callbacks                 – reporting integrations, JIT checkpoint, progress bar
        #   9. Hub & output              – repo init, output directory
        #  10. Training state            – TrainerState, TrainerControl, internal bookkeeping
        #  11. Finalize                  – use_cache, XLA FSDPv2 mesh, memory tracker stop

        # ---- 1. Args & seed --------------------------------------------------------
        if args is None:
            output_dir = "tmp_trainer"
            logger.info(f"No `TrainingArguments` passed, using `output_dir={output_dir}`.")
            args = TrainingArguments(output_dir=output_dir)
        self.args = args
        # Seed must be set before instantiating the model when using model_init
        enable_full_determinism(self.args.seed) if self.args.full_determinism else set_seed(self.args.seed)

        # ---- 2. Accelerator & logging ----------------------------------------------
        # `create_accelerator_and_postprocess` reads self.model and self.args,
        # and may set self.deepspeed — store temporary refs before calling it.
        self.deepspeed = None
        self.model = model
        self.create_accelerator_and_postprocess()

        self._memory_tracker = TrainerMemoryTracker(self.args.skip_memory_metrics)
        self._memory_tracker.start()

        log_level = args.get_process_log_level()
        logging.set_verbosity(log_level)

        args._setup_devices  # force device and distributed setup init explicitly

        # ---- 3. Model resolution ----------------------------------------------------