relogic/pretrainkit/multitask_trainer.py [63:147]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
if is_wandb_available():
    import wandb


logger = logging.getLogger(__name__)


def set_seed(seed: int):
    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
    torch.cuda.manual_seed_all(seed)
    # ^^ safe to call this function even if cuda is not available


@contextmanager
def torch_distributed_zero_first(local_rank: int):
    """
    Decorator to make all processes in distributed training wait for each local_master to do something.
    """
    if local_rank not in [-1, 0]:
        torch.distributed.barrier()
    yield
    if local_rank == 0:
        torch.distributed.barrier()


class SequentialDistributedSampler(Sampler):
    """
    Distributed Sampler that subsamples indicies sequentially,
    making it easier to collate all results at the end.

    Even though we only use this sampler for eval and predict (no training),
    which means that the model params won't have to be synced (i.e. will not hang
    for synchronization even if varied number of forward passes), we still add extra
    samples to the sampler to make it evenly divisible (like in `DistributedSampler`)
    to make it easy to `gather` or `reduce` resulting tensors at the end of the loop.
    """

    def __init__(self, dataset, num_replicas=None, rank=None):
        if num_replicas is None:
            if not torch.distributed.is_available():
                raise RuntimeError("Requires distributed package to be available")
            num_replicas = torch.distributed.get_world_size()
        if rank is None:
            if not torch.distributed.is_available():
                raise RuntimeError("Requires distributed package to be available")
            rank = torch.distributed.get_rank()
        self.dataset = dataset
        self.num_replicas = num_replicas
        self.rank = rank
        self.num_samples = int(math.ceil(len(self.dataset) * 1.0 / self.num_replicas))
        self.total_size = self.num_samples * self.num_replicas

    def __iter__(self):
        indices = list(range(len(self.dataset)))

        # add extra samples to make it evenly divisible
        indices += indices[: (self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        indices = indices[self.rank * self.num_samples : (self.rank + 1) * self.num_samples]
        assert len(indices) == self.num_samples

        return iter(indices)

    def __len__(self):
        return self.num_samples


def get_tpu_sampler(dataset: Dataset):
    if xm.xrt_world_size() <= 1:
        return RandomSampler(dataset)
    return DistributedSampler(dataset, num_replicas=xm.xrt_world_size(), rank=xm.get_ordinal())


class Trainer:
    """
    Trainer is a simple but feature-complete training and eval loop for PyTorch,
    optimized for Transformers.
    """

    model: PreTrainedModel
    args: TrainingArguments
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



relogic/pretrainkit/trainer.py [59:143]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
if is_wandb_available():
    import wandb


logger = logging.getLogger(__name__)


def set_seed(seed: int):
    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
    torch.cuda.manual_seed_all(seed)
    # ^^ safe to call this function even if cuda is not available


@contextmanager
def torch_distributed_zero_first(local_rank: int):
    """
    Decorator to make all processes in distributed training wait for each local_master to do something.
    """
    if local_rank not in [-1, 0]:
        torch.distributed.barrier()
    yield
    if local_rank == 0:
        torch.distributed.barrier()


class SequentialDistributedSampler(Sampler):
    """
    Distributed Sampler that subsamples indicies sequentially,
    making it easier to collate all results at the end.

    Even though we only use this sampler for eval and predict (no training),
    which means that the model params won't have to be synced (i.e. will not hang
    for synchronization even if varied number of forward passes), we still add extra
    samples to the sampler to make it evenly divisible (like in `DistributedSampler`)
    to make it easy to `gather` or `reduce` resulting tensors at the end of the loop.
    """

    def __init__(self, dataset, num_replicas=None, rank=None):
        if num_replicas is None:
            if not torch.distributed.is_available():
                raise RuntimeError("Requires distributed package to be available")
            num_replicas = torch.distributed.get_world_size()
        if rank is None:
            if not torch.distributed.is_available():
                raise RuntimeError("Requires distributed package to be available")
            rank = torch.distributed.get_rank()
        self.dataset = dataset
        self.num_replicas = num_replicas
        self.rank = rank
        self.num_samples = int(math.ceil(len(self.dataset) * 1.0 / self.num_replicas))
        self.total_size = self.num_samples * self.num_replicas

    def __iter__(self):
        indices = list(range(len(self.dataset)))

        # add extra samples to make it evenly divisible
        indices += indices[: (self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        indices = indices[self.rank * self.num_samples : (self.rank + 1) * self.num_samples]
        assert len(indices) == self.num_samples

        return iter(indices)

    def __len__(self):
        return self.num_samples


def get_tpu_sampler(dataset: Dataset):
    if xm.xrt_world_size() <= 1:
        return RandomSampler(dataset)
    return DistributedSampler(dataset, num_replicas=xm.xrt_world_size(), rank=xm.get_ordinal())


class Trainer:
    """
    Trainer is a simple but feature-complete training and eval loop for PyTorch,
    optimized for Transformers.
    """

    model: PreTrainedModel
    args: TrainingArguments
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -