Source code for

# Copyright The PyTorch Lightning team.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# See the License for the specific language governing permissions and
# limitations under the License.
import os
from typing import Any, Dict, Optional

from lightning_utilities.core.apply_func import apply_to_collection
from lightning_utilities.core.imports import RequirementCache

from lightning_fabric.accelerators.tpu import _XLA_AVAILABLE
from import TorchCheckpointIO
from lightning_fabric.utilities.cloud_io import get_filesystem
from lightning_fabric.utilities.types import _PATH

[docs]class XLACheckpointIO(TorchCheckpointIO): """CheckpointIO that utilizes :func:`` to save checkpoints for TPU training strategies.""" def __init__(self, *args: Any, **kwargs: Any) -> None: if not _XLA_AVAILABLE: raise ModuleNotFoundError(str(_XLA_AVAILABLE)) super().__init__(*args, **kwargs)
[docs] def save_checkpoint(self, checkpoint: Dict[str, Any], path: _PATH, storage_options: Optional[Any] = None) -> None: """Save model/training states as a checkpoint file through state-dump and file-write. Args: checkpoint: dict containing model and trainer state path: write-target path storage_options: not used in ``XLACheckpointIO.save_checkpoint`` Raises: TypeError: If ``storage_options`` arg is passed in """ if storage_options is not None: raise TypeError( "`Trainer.save_checkpoint(..., storage_options=...)` with `storage_options` arg" f" is not supported for `{self.__class__.__name__}`. Please implement your custom `CheckpointIO`" " to define how you'd like to use `storage_options`." ) fs = get_filesystem(path) fs.makedirs(os.path.dirname(path), exist_ok=True) if RequirementCache("omegaconf"): # workaround for from omegaconf import DictConfig, ListConfig, OmegaConf checkpoint = apply_to_collection(checkpoint, (DictConfig, ListConfig), OmegaConf.to_container) import torch_xla.core.xla_model as xm{k: v for k, v in checkpoint.items() if k != "callbacks"}, path)

© Copyright Copyright (c) 2018-2023, Lightning AI et al...

Built with Sphinx using a theme provided by Read the Docs.