def __post_init__()

in src/transformers/training_args.py [0:0]


    def __post_init__(self):
        # Set default output_dir if not provided
        if self.output_dir is None:
            self.output_dir = "trainer_output"
            logger.info(
                "No output directory specified, defaulting to 'trainer_output'. "
                "To change this behavior, specify --output_dir when creating TrainingArguments."
            )

        # Parse in args that could be `dict` sent in from the CLI as a string
        for field in self._VALID_DICT_FIELDS:
            passed_value = getattr(self, field)
            # We only want to do this if the str starts with a bracket to indicate a `dict`
            # else its likely a filename if supported
            if isinstance(passed_value, str) and passed_value.startswith("{"):
                loaded_dict = json.loads(passed_value)
                # Convert str values to types if applicable
                loaded_dict = _convert_str_dict(loaded_dict)
                setattr(self, field, loaded_dict)

        # expand paths, if not os.makedirs("~/bar") will make directory
        # in the current directory instead of the actual home
        # see https://github.com/huggingface/transformers/issues/10628
        if self.output_dir is not None:
            self.output_dir = os.path.expanduser(self.output_dir)
        if self.logging_dir is None and self.output_dir is not None:
            self.logging_dir = os.path.join(self.output_dir, default_logdir())
        if self.logging_dir is not None:
            self.logging_dir = os.path.expanduser(self.logging_dir)

        if self.disable_tqdm is None:
            self.disable_tqdm = logger.getEffectiveLevel() > logging.WARN

        if isinstance(self.eval_strategy, EvaluationStrategy):
            warnings.warn(
                "using `EvaluationStrategy` for `eval_strategy` is deprecated and will be removed in version 5"
                " of 🤗 Transformers. Use `IntervalStrategy` instead",
                FutureWarning,
            )
            # Go back to the underlying string or we won't be able to instantiate `IntervalStrategy` on it.
            self.eval_strategy = self.eval_strategy.value
        if self.no_cuda:
            warnings.warn(
                "using `no_cuda` is deprecated and will be removed in version 5.0 of 🤗 Transformers. "
                "Use `use_cpu` instead",
                FutureWarning,
            )
            self.use_cpu = self.no_cuda
        if self.use_ipex:
            warnings.warn(
                "using `use_ipex` is deprecated and will be removed in version 4.54 of 🤗 Transformers. "
                "You only need PyTorch for the needed optimizations on Intel CPU and XPU.",
                FutureWarning,
            )

        self.eval_strategy = IntervalStrategy(self.eval_strategy)
        self.logging_strategy = IntervalStrategy(self.logging_strategy)
        self.save_strategy = SaveStrategy(self.save_strategy)
        self.hub_strategy = HubStrategy(self.hub_strategy)

        self.lr_scheduler_type = SchedulerType(self.lr_scheduler_type)
        if self.do_eval is False and self.eval_strategy != IntervalStrategy.NO:
            self.do_eval = True

        if self.torch_empty_cache_steps is not None:
            if not (isinstance(self.torch_empty_cache_steps, int) and self.torch_empty_cache_steps > 0):
                raise ValueError(
                    f"`torch_empty_cache_steps` must be an integer bigger than 0, got {self.torch_empty_cache_steps}."
                )

        # eval_steps has to be defined and non-zero, fallbacks to logging_steps if the latter is non-zero
        if self.eval_strategy == IntervalStrategy.STEPS and (self.eval_steps is None or self.eval_steps == 0):
            if self.logging_steps > 0:
                logger.info(f"using `logging_steps` to initialize `eval_steps` to {self.logging_steps}")
                self.eval_steps = self.logging_steps
            else:
                raise ValueError(
                    f"evaluation strategy {self.eval_strategy} requires either non-zero --eval_steps or"
                    " --logging_steps"
                )

        # logging_steps must be non-zero for logging_strategy that is other than 'no'
        if self.logging_strategy == IntervalStrategy.STEPS and self.logging_steps == 0:
            raise ValueError(f"logging strategy {self.logging_strategy} requires non-zero --logging_steps")

        if self.logging_strategy == IntervalStrategy.STEPS and self.logging_steps > 1:
            if self.logging_steps != int(self.logging_steps):
                raise ValueError(f"--logging_steps must be an integer if bigger than 1: {self.logging_steps}")
            self.logging_steps = int(self.logging_steps)
        if self.eval_strategy == IntervalStrategy.STEPS and self.eval_steps > 1:
            if self.eval_steps != int(self.eval_steps):
                raise ValueError(f"--eval_steps must be an integer if bigger than 1: {self.eval_steps}")
            self.eval_steps = int(self.eval_steps)
        if self.save_strategy == SaveStrategy.STEPS and self.save_steps > 1:
            if self.save_steps != int(self.save_steps):
                raise ValueError(f"--save_steps must be an integer if bigger than 1: {self.save_steps}")
            self.save_steps = int(self.save_steps)

        # Sanity checks for load_best_model_at_end: we require save and eval strategies to be compatible.
        if self.load_best_model_at_end and self.save_strategy != SaveStrategy.BEST:
            if self.eval_strategy != self.save_strategy:
                raise ValueError(
                    "--load_best_model_at_end requires the save and eval strategy to match, but found\n- Evaluation "
                    f"strategy: {self.eval_strategy}\n- Save strategy: {self.save_strategy}"
                )
            if self.eval_strategy == IntervalStrategy.STEPS and self.save_steps % self.eval_steps != 0:
                if self.eval_steps < 1 or self.save_steps < 1:
                    if not (self.eval_steps < 1 and self.save_steps < 1):
                        raise ValueError(
                            "--load_best_model_at_end requires the saving steps to be a multiple of the evaluation "
                            "steps, which cannot get guaranteed when mixing ratio and absolute steps for save_steps "
                            f"{self.save_steps} and eval_steps {self.eval_steps}."
                        )
                    # Work around floating point precision issues
                    LARGE_MULTIPLIER = 1_000_000
                    if (self.save_steps * LARGE_MULTIPLIER) % (self.eval_steps * LARGE_MULTIPLIER) != 0:
                        raise ValueError(
                            "--load_best_model_at_end requires the saving steps to be a multiple of the evaluation "
                            f"steps, but found {self.save_steps}, which is not a multiple of {self.eval_steps}."
                        )
                else:
                    raise ValueError(
                        "--load_best_model_at_end requires the saving steps to be a round multiple of the evaluation "
                        f"steps, but found {self.save_steps}, which is not a round multiple of {self.eval_steps}."
                    )

        safetensors_available = is_safetensors_available()
        if self.save_safetensors and not safetensors_available:
            raise ValueError(f"--save_safetensors={self.save_safetensors} requires safetensors to be installed!")
        if not self.save_safetensors and safetensors_available:
            logger.info(
                f"Found safetensors installation, but --save_safetensors={self.save_safetensors}. "
                f"Safetensors should be a preferred weights saving format due to security and performance reasons. "
                f"If your model cannot be saved by safetensors please feel free to open an issue at "
                f"https://github.com/huggingface/safetensors!"
            )

        if (
            self.load_best_model_at_end or self.lr_scheduler_type == SchedulerType.REDUCE_ON_PLATEAU
        ) and self.metric_for_best_model is None:
            self.metric_for_best_model = "loss"
        if self.greater_is_better is None and self.metric_for_best_model is not None:
            self.greater_is_better = not self.metric_for_best_model.endswith("loss")
        if self.run_name is None:
            self.run_name = self.output_dir
        if self.framework == "pt" and is_torch_available():
            if self.fp16_backend and self.fp16_backend != "auto":
                warnings.warn(
                    "`fp16_backend` is deprecated and will be removed in version 5 of 🤗 Transformers. Use"
                    " `half_precision_backend` instead",
                    FutureWarning,
                )
                self.half_precision_backend = self.fp16_backend

            if self.bf16 or self.bf16_full_eval:
                if self.use_cpu and not is_torch_available() and not is_torch_xla_available():
                    # cpu
                    raise ValueError("Your setup doesn't support bf16/(cpu, tpu, neuroncore). You need torch>=1.10")
                elif not self.use_cpu:
                    if not is_torch_bf16_gpu_available() and not is_torch_xla_available():  # added for tpu support
                        error_message = "Your setup doesn't support bf16/gpu."
                        if is_torch_cuda_available():
                            error_message += " You need Ampere+ GPU with cuda>=11.0"
                        # gpu
                        raise ValueError(error_message)

        if self.fp16 and self.bf16:
            raise ValueError("At most one of fp16 and bf16 can be True, but not both")

        if self.fp16_full_eval and self.bf16_full_eval:
            raise ValueError("At most one of fp16 and bf16 can be True for full eval, but not both")

        if self.bf16:
            if self.half_precision_backend == "apex":
                raise ValueError(" `--half_precision_backend apex`: GPU bf16 is not supported by apex.")

        if self.half_precision_backend == "apex":
            if not is_apex_available():
                raise ImportError(
                    "Using FP16 with APEX but APEX is not installed, please refer to"
                    " https://www.github.com/nvidia/apex."
                )
            try:
                from apex import amp  # noqa: F401
            except ImportError as e:
                raise ImportError(
                    f"apex.amp is deprecated in the latest version of apex, causing this error {e}. Either revert to an older version or use pytorch amp by setting half_precision_backend='auto' instead. See https://github.com/NVIDIA/apex/pull/1896 "
                )

        if self.lr_scheduler_type == SchedulerType.REDUCE_ON_PLATEAU:
            if self.eval_strategy == IntervalStrategy.NO:
                raise ValueError("lr_scheduler_type reduce_lr_on_plateau requires an eval strategy")
            if not is_torch_available():
                raise ValueError("lr_scheduler_type reduce_lr_on_plateau requires torch>=0.2.0")

        self.optim = OptimizerNames(self.optim)
        if self.adafactor:
            warnings.warn(
                "`--adafactor` is deprecated and will be removed in version 5 of 🤗 Transformers. Use `--optim"
                " adafactor` instead",
                FutureWarning,
            )
            self.optim = OptimizerNames.ADAFACTOR

        # We need to setup the accelerator config here *before* the first call to `self.device`
        if is_accelerate_available():
            if not isinstance(self.accelerator_config, AcceleratorConfig):
                if self.accelerator_config is None:
                    self.accelerator_config = AcceleratorConfig()
                elif isinstance(self.accelerator_config, dict):
                    self.accelerator_config = AcceleratorConfig(**self.accelerator_config)
                # Check that a user didn't pass in the class instantiator
                # such as `accelerator_config = AcceleratorConfig`
                elif isinstance(self.accelerator_config, type):
                    raise NotImplementedError(
                        "Tried passing in a callable to `accelerator_config`, but this is not supported. "
                        "Please pass in a fully constructed `AcceleratorConfig` object instead."
                    )
                else:
                    self.accelerator_config = AcceleratorConfig.from_json_file(self.accelerator_config)
            if self.accelerator_config.split_batches:
                logger.info(
                    "Using `split_batches=True` in `accelerator_config` will override the `per_device_train_batch_size` "
                    "Batches will be split across all processes equally when using `split_batches=True`."
                )

        # Initialize device before we proceed
        if self.framework == "pt" and is_torch_available():
            self.device

        # Disable average tokens when using single device
        if self.average_tokens_across_devices:
            try:
                if self.world_size == 1:
                    logger.info(
                        "average_tokens_across_devices is True but world size is 1. Setting it to False automatically."
                    )
                    self.average_tokens_across_devices = False
            except ImportError as e:
                logger.warning(f"Can not specify world size due to {e}. Turn average_tokens_across_devices to False.")
                self.average_tokens_across_devices = False

        if self.torchdynamo is not None:
            warnings.warn(
                "`torchdynamo` is deprecated and will be removed in version 5 of 🤗 Transformers. Use"
                " `torch_compile_backend` instead",
                FutureWarning,
            )
            self.torch_compile_backend = self.torchdynamo
        if (self.torch_compile_mode is not None or self.torch_compile_backend is not None) and not self.torch_compile:
            self.torch_compile = True
        if self.torch_compile and self.torch_compile_backend is None:
            if not self.use_cpu and is_torch_hpu_available():
                self.torch_compile_backend = "hpu_backend"
            else:
                self.torch_compile_backend = "inductor"

        # accelerate integration for torch compile
        if self.torch_compile:
            # set env vars for accelerate
            prefix = "ACCELERATE_DYNAMO_"
            os.environ[prefix + "BACKEND"] = self.torch_compile_backend
            if self.torch_compile_mode is not None:
                os.environ[prefix + "MODE"] = self.torch_compile_mode

        if self.framework == "pt" and is_torch_available() and self.torch_compile:
            if is_torch_tf32_available():
                if self.tf32 is None and not self.fp16 or self.bf16:
                    logger.info(
                        "Setting TF32 in CUDA backends to speedup torch compile, you won't see any improvement"
                        " otherwise."
                    )
                    torch.backends.cuda.matmul.allow_tf32 = True
                    torch.backends.cudnn.allow_tf32 = True
            else:
                logger.warning(
                    "The speedups for torchdynamo mostly come with GPU Ampere or higher and which is not detected here."
                )
        if self.framework == "pt" and is_torch_available() and self.tf32 is not None:
            if self.tf32:
                if is_torch_tf32_available():
                    torch.backends.cuda.matmul.allow_tf32 = True
                    torch.backends.cudnn.allow_tf32 = True
                else:
                    raise ValueError("--tf32 requires Ampere or a newer GPU arch, cuda>=11 and torch>=1.7")
            else:
                if is_torch_tf32_available():
                    torch.backends.cuda.matmul.allow_tf32 = False
                    torch.backends.cudnn.allow_tf32 = False
                # no need to assert on else

        # if training args is specified, it will override the one specified in the accelerate config
        if self.half_precision_backend != "apex":
            mixed_precision_dtype = os.environ.get("ACCELERATE_MIXED_PRECISION", "no")
            if self.fp16:
                mixed_precision_dtype = "fp16"
            elif self.bf16:
                mixed_precision_dtype = "bf16"
            os.environ["ACCELERATE_MIXED_PRECISION"] = mixed_precision_dtype

        if self.report_to is None:
            logger.info(
                "The default value for the training argument `--report_to` will change in v5 (from all installed "
                "integrations to none). In v5, you will need to use `--report_to all` to get the same behavior as "
                "now. You should start updating your code and make this info disappear :-)."
            )
            self.report_to = "all"
        if self.report_to == "all" or self.report_to == ["all"]:
            # Import at runtime to avoid a circular import.
            from .integrations import get_available_reporting_integrations

            self.report_to = get_available_reporting_integrations()

            if "codecarbon" in self.report_to and torch.version.hip:
                logger.warning(
                    "When using the Trainer, CodeCarbonCallback requires the `codecarbon` package, which is not compatible with AMD ROCm (https://github.com/mlco2/codecarbon/pull/490). Automatically disabling the codecarbon callback. Reference: https://huggingface.co/docs/transformers/v4.39.3/en/main_classes/trainer#transformers.TrainingArguments.report_to."
                )
                self.report_to.remove("codecarbon")

        elif self.report_to == "none" or self.report_to == ["none"]:
            self.report_to = []
        elif not isinstance(self.report_to, list):
            self.report_to = [self.report_to]

        if self.warmup_ratio < 0 or self.warmup_ratio > 1:
            raise ValueError("warmup_ratio must lie in range [0,1]")
        elif self.warmup_ratio > 0 and self.warmup_steps > 0:
            logger.info(
                "Both warmup_ratio and warmup_steps given, warmup_steps will override any effect of warmup_ratio"
                " during training"
            )

        if not isinstance(self.warmup_steps, int) or self.warmup_steps < 0:
            raise ValueError("warmup_steps must be of type int and must be 0 or a positive integer.")

        if isinstance(self.fsdp, bool):
            self.fsdp = [FSDPOption.FULL_SHARD] if self.fsdp else ""
        if isinstance(self.fsdp, str):
            self.fsdp = [FSDPOption(s) for s in self.fsdp.split()]
        if self.fsdp == [FSDPOption.OFFLOAD]:
            raise ValueError(
                "`--fsdp offload` can't work on its own. It needs to be added to `--fsdp full_shard` or "
                '`--fsdp shard_grad_op`. For example, `--fsdp "full_shard offload"`.'
            )
        elif FSDPOption.FULL_SHARD in self.fsdp and FSDPOption.SHARD_GRAD_OP in self.fsdp:
            raise ValueError("`--fsdp full_shard` is not compatible with `--fsdp shard_grad_op`.")

        if self.gradient_checkpointing and (
            FSDPOption.FULL_SHARD in self.fsdp or FSDPOption.HYBRID_SHARD in self.fsdp
        ):
            logger.warning(
                "When using FSDP full shard, instead of using `gradient_checkpointing` in TrainingArguments, please"
                " use `activation_checkpointing` in `fsdp_config`. The former introduces a redundant AllGather"
                " operation in backward pass. Reference: https://github.com/huggingface/transformers/issues/30404"
            )

        if self.fsdp_config is None:
            self.fsdp_config = {}

        if isinstance(self.fsdp_config, str):
            if len(self.fsdp) == 0:
                warnings.warn("`--fsdp_config` is useful only when `--fsdp` is specified.")
            with open(self.fsdp_config, encoding="utf-8") as f:
                self.fsdp_config = json.load(f)

        if self.fsdp_config is not None and isinstance(self.fsdp_config, dict):
            for k in list(self.fsdp_config.keys()):
                if k.startswith("fsdp_"):
                    v = self.fsdp_config.pop(k)
                    self.fsdp_config[k[5:]] = v

        if self.fsdp_min_num_params > 0:
            warnings.warn("using `--fsdp_min_num_params` is deprecated. Use fsdp_config instead ", FutureWarning)

        self.fsdp_config["min_num_params"] = max(self.fsdp_config.get("min_num_params", 0), self.fsdp_min_num_params)

        # if fsdp_config["transformer_layer_cls_to_wrap"] is specified as a string, convert it to a list with a single object
        if isinstance(self.fsdp_config.get("transformer_layer_cls_to_wrap", None), str):
            self.fsdp_config["transformer_layer_cls_to_wrap"] = [self.fsdp_config["transformer_layer_cls_to_wrap"]]

        if self.fsdp_transformer_layer_cls_to_wrap is not None:
            warnings.warn(
                "using `--fsdp_transformer_layer_cls_to_wrap` is deprecated. Use fsdp_config instead ", FutureWarning
            )
            self.fsdp_config["transformer_layer_cls_to_wrap"] = self.fsdp_config.get(
                "transformer_layer_cls_to_wrap", []
            ) + [self.fsdp_transformer_layer_cls_to_wrap]

        if len(self.fsdp) == 0 and self.fsdp_config["min_num_params"] > 0:
            warnings.warn("`min_num_params` is useful only when `--fsdp` is specified.")

        if len(self.fsdp) == 0 and self.fsdp_config.get("transformer_layer_cls_to_wrap", None) is not None:
            warnings.warn("`transformer_layer_cls_to_wrap` is useful only when `--fsdp` is specified.")

        if (
            len(self.fsdp) > 0
            and self.fsdp_config["min_num_params"] > 0
            and self.fsdp_config.get("transformer_layer_cls_to_wrap", None) is not None
        ):
            raise ValueError("`min_num_params` and `transformer_layer_cls_to_wrap` are mutually exclusive.")
        self.fsdp_config["xla"] = self.fsdp_config.get("xla", False)
        self.fsdp_config["xla_fsdp_v2"] = self.fsdp_config.get("xla_fsdp_v2", False)
        self.fsdp_config["xla_fsdp_grad_ckpt"] = self.fsdp_config.get("xla_fsdp_grad_ckpt", False)
        if self.fsdp_config["xla"]:
            if len(self.fsdp) > 0:
                # store XLA fsdp configuration parameters into a dictionary
                # Copy the config to avoid modifying the original config (which may be used for JSON serialization)
                self.xla_fsdp_config = self.fsdp_config.get("xla_fsdp_settings", {}).copy()
                # apply appropriate string to torch.dtype conversions for parameters
                if "compute_dtype" in self.xla_fsdp_config:
                    self.xla_fsdp_config["compute_dtype"] = getattr(torch, self.xla_fsdp_config["compute_dtype"])
                if "buffer_dtype" in self.xla_fsdp_config:
                    self.xla_fsdp_config["buffer_dtype"] = getattr(torch, self.xla_fsdp_config["buffer_dtype"])
            else:
                warnings.warn("XLA FSDP can be used only when `--fsdp` is specified.")
        else:
            if self.fsdp_config["xla_fsdp_grad_ckpt"]:
                warnings.warn("`--xla_fsdp_grad_ckpt` is useful only when `--xla` is set to true.")

        # accelerate integration for FSDP
        if len(self.fsdp) > 0 and not self.fsdp_config["xla"]:
            os.environ["ACCELERATE_USE_FSDP"] = "true"
            from accelerate.utils.constants import (
                FSDP_AUTO_WRAP_POLICY,
                FSDP_SHARDING_STRATEGY,
            )

            prefix = "FSDP_"
            for fsdp_option in self.fsdp:
                if fsdp_option.upper() in FSDP_SHARDING_STRATEGY:
                    # set environment variable for FSDP sharding strategy
                    os.environ[f"{prefix}SHARDING_STRATEGY"] = str(
                        FSDP_SHARDING_STRATEGY.index(fsdp_option.upper()) + 1
                    )
                elif fsdp_option == FSDPOption.OFFLOAD:
                    os.environ[f"{prefix}OFFLOAD_PARAMS"] = "true"
                elif fsdp_option == FSDPOption.AUTO_WRAP:
                    os.environ[f"{prefix}AUTO_WRAP_POLICY"] = FSDP_AUTO_WRAP_POLICY[0]
                    if self.fsdp_config["min_num_params"] > 0:
                        os.environ[f"{prefix}MIN_NUM_PARAMS"] = str(self.fsdp_config["min_num_params"])
                        os.environ[f"{prefix}AUTO_WRAP_POLICY"] = FSDP_AUTO_WRAP_POLICY[1]
                    elif self.fsdp_config.get("transformer_layer_cls_to_wrap", None) is not None:
                        os.environ[f"{prefix}TRANSFORMER_CLS_TO_WRAP"] = ",".join(
                            self.fsdp_config["transformer_layer_cls_to_wrap"]
                        )
            prefetch_policy = self.fsdp_config.get("backward_prefetch", "NO_PREFETCH")
            os.environ[f"{prefix}BACKWARD_PREFETCH"] = prefetch_policy.upper()
            os.environ[f"{prefix}FORWARD_PREFETCH"] = str(self.fsdp_config.get("forward_prefetch", "false")).lower()

            sync_module_states = str(self.fsdp_config.get("sync_module_states", "true")).lower()
            cpu_ram_efficient_loading = str(self.fsdp_config.get("cpu_ram_efficient_loading", "false")).lower()

            if sync_module_states == "false" and cpu_ram_efficient_loading == "true":
                # In this case, all the processes except the main process would have random weights leading
                # to unexpected behaviour during training, thus throwing error here to prevent it.
                raise ValueError('`sync_module_states` must be `"True"` if `cpu_ram_efficient_loading` is `"True"`')

            os.environ[f"{prefix}SYNC_MODULE_STATES"] = sync_module_states
            os.environ[f"{prefix}CPU_RAM_EFFICIENT_LOADING"] = cpu_ram_efficient_loading

            os.environ[f"{prefix}USE_ORIG_PARAMS"] = str(self.fsdp_config.get("use_orig_params", "true")).lower()

        if self.tpu_metrics_debug:
            warnings.warn(
                "using `--tpu_metrics_debug` is deprecated and will be removed in version 5 of 🤗 Transformers. Use"
                " `--debug tpu_metrics_debug` instead",
                FutureWarning,
            )
            if self.debug is None:
                self.debug = " tpu_metrics_debug"
            else:
                self.debug += " tpu_metrics_debug"
            self.tpu_metrics_debug = False

        if isinstance(self.debug, str):
            self.debug = [DebugOption(s) for s in self.debug.split()]
        elif self.debug is None:
            self.debug = []

        self.deepspeed_plugin = None
        if self.deepspeed:
            # - must be run very last in arg parsing, since it will use a lot of these settings.
            # - must be run before the model is created.
            if not is_accelerate_available():
                raise ValueError(
                    f"--deepspeed requires Accelerate to be installed: `pip install 'accelerate>={ACCELERATE_MIN_VERSION}'`."
                )
            from transformers.integrations.deepspeed import HfTrainerDeepSpeedConfig

            # will be used later by the Trainer
            # note: leave self.deepspeed unmodified in case a user relies on it not to be modified)
            self.hf_deepspeed_config = HfTrainerDeepSpeedConfig(self.deepspeed)
            self.hf_deepspeed_config.trainer_config_process(self)

            # Accelerate DeepSpeed Plugin
            from accelerate.utils import DeepSpeedPlugin

            os.environ["ACCELERATE_USE_DEEPSPEED"] = "true"
            self.deepspeed_plugin = DeepSpeedPlugin(hf_ds_config=self.hf_deepspeed_config)
        elif strtobool(os.environ.get("ACCELERATE_USE_DEEPSPEED", "false")):
            # Accelerate DeepSpeed Plugin
            from accelerate.utils import DeepSpeedPlugin

            self.deepspeed_plugin = DeepSpeedPlugin()
            mixed_precision = os.environ.get("ACCELERATE_MIXED_PRECISION", "no")
            self.deepspeed_plugin.set_mixed_precision(mixed_precision)
            self.deepspeed_plugin.set_deepspeed_weakref()

        if self.use_cpu:
            self.dataloader_pin_memory = False

        if self.dataloader_num_workers == 0 and self.dataloader_prefetch_factor is not None:
            raise ValueError(
                "--dataloader_prefetch_factor can only be set when data is loaded in a different process, i.e."
                " when --dataloader_num_workers > 1."
            )

        if self.push_to_hub_token is not None:
            warnings.warn(
                "`--push_to_hub_token` is deprecated and will be removed in version 5 of 🤗 Transformers. Use "
                "`--hub_token` instead.",
                FutureWarning,
            )
            self.hub_token = self.push_to_hub_token

        if self.push_to_hub_model_id is not None:
            self.hub_model_id = get_full_repo_name(
                self.push_to_hub_model_id, organization=self.push_to_hub_organization, token=self.hub_token
            )
            if self.push_to_hub_organization is not None:
                warnings.warn(
                    "`--push_to_hub_model_id` and `--push_to_hub_organization` are deprecated and will be removed in "
                    "version 5 of 🤗 Transformers. Use `--hub_model_id` instead and pass the full repo name to this "
                    f"argument (in this case {self.hub_model_id}).",
                    FutureWarning,
                )
            else:
                warnings.warn(
                    "`--push_to_hub_model_id` is deprecated and will be removed in version 5 of 🤗 Transformers. Use "
                    "`--hub_model_id` instead and pass the full repo name to this argument (in this case "
                    f"{self.hub_model_id}).",
                    FutureWarning,
                )
        elif self.push_to_hub_organization is not None:
            self.hub_model_id = f"{self.push_to_hub_organization}/{Path(self.output_dir).name}"
            warnings.warn(
                "`--push_to_hub_organization` is deprecated and will be removed in version 5 of 🤗 Transformers. Use "
                "`--hub_model_id` instead and pass the full repo name to this argument (in this case "
                f"{self.hub_model_id}).",
                FutureWarning,
            )

        if self.eval_use_gather_object and not is_accelerate_available("0.30.0"):
            raise ValueError(
                "--eval_use_gather_object requires Accelerate to be version of `accelerate` > 0.30.0."
                "This is not supported and we recommend you to update your version."
            )

        if self.data_seed is not None:
            if not is_accelerate_available("1.1.0"):
                raise NotImplementedError(
                    "data_seed requires Accelerate version `accelerate` >= 1.1.0. "
                    "This is not supported and we recommend you to update your version."
                )

        if self.include_inputs_for_metrics:
            logger.warning(
                "Using `include_inputs_for_metrics` is deprecated and will be removed in version 5 of 🤗 Transformers. Please use `include_for_metrics` list argument instead."
            )
            self.include_for_metrics.append("inputs")