def main()

in fairseq_cli/train.py [0:0]

• 48 lines of code
• 24 McCabe index (conditional complexity)

def main(args, init_distributed=False):
    utils.import_user_module(args)

    assert args.max_tokens is not None or args.max_sentences is not None, \
        'Must specify batch size either with --max-tokens or --max-sentences'

    # Initialize CUDA and distributed training
    if torch.cuda.is_available() and not args.cpu:
        torch.cuda.set_device(args.device_id)
    torch.manual_seed(args.seed)
    if init_distributed:
        args.distributed_rank = distributed_utils.distributed_init(args)

    # Print args
    print(args)

    # Setup task, e.g., translation, language modeling, etc.
    task = tasks.setup_task(args)

    # Load valid dataset (we load training data below, based on the latest checkpoint)
    for valid_sub_split in args.valid_subset.split(','):
        task.load_dataset(valid_sub_split, combine=False, epoch=0)

    # Build model and criterion
    model = task.build_model(args)
    criterion = task.build_criterion(args)
    print(model)
    print('| model {}, criterion {}'.format(args.arch, criterion.__class__.__name__))
    print('| num. model params: {} (num. trained: {})'.format(
        sum(p.numel() for p in model.parameters()),
        sum(p.numel() for p in model.parameters() if p.requires_grad),
    ))

    # Build trainer
    trainer = Trainer(args, task, model, criterion)
    print('| training on {} GPUs'.format(args.distributed_world_size))
    print('| max tokens per GPU = {} and max sentences per GPU = {}'.format(
        args.max_tokens,
        args.max_sentences,
    ))

    # Load the latest checkpoint if one is available and restore the
    # corresponding train iterator
    extra_state, epoch_itr = checkpoint_utils.load_checkpoint(args, trainer)

    # Train until the learning rate gets too small
    max_epoch = args.max_epoch or math.inf
    max_update = args.max_update or math.inf
    lr = trainer.get_lr()
    train_meter = StopwatchMeter()
    train_meter.start()
    valid_losses = [None]
    valid_subsets = args.valid_subset.split(',')
    while lr > args.min_lr and epoch_itr.epoch < max_epoch and trainer.get_num_updates() < max_update:
        # train for one epoch
        train(args, trainer, task, epoch_itr)

        if not args.disable_validation and epoch_itr.epoch % args.validate_interval == 0:
            valid_losses = validate(args, trainer, task, epoch_itr, valid_subsets)
        else:
            valid_losses = [None]

        # only use first validation loss to update the learning rate
        lr = trainer.lr_step(epoch_itr.epoch, valid_losses[0])

        # save checkpoint
        if epoch_itr.epoch % args.save_interval == 0:
            checkpoint_utils.save_checkpoint(args, trainer, epoch_itr, valid_losses[0])

        if ':' in getattr(args, 'data', ''):
            # sharded data: get train iterator for next epoch
            epoch_itr = trainer.get_train_iterator(epoch_itr.epoch)
    train_meter.stop()
    print('| done training in {:.1f} seconds'.format(train_meter.sum))