benchmarks/fp8/ms_amp/fp8_utils.py [80:109]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    if accelerator is None:
        accelerator = Accelerator()
    model = AutoModelForSequenceClassification.from_pretrained(model_name)
    train_dataloader, eval_dataloader = get_dataloaders(model_name, batch_size)
    optimizer = AdamW(model.parameters(), lr=0.0001)
    lr_scheduler = get_linear_schedule_with_warmup(
        optimizer=optimizer,
        num_warmup_steps=100,
        num_training_steps=len(train_dataloader) * 2,
    )
    train_dataloader, eval_dataloader = accelerator.prepare(train_dataloader, eval_dataloader)
    return model, optimizer, train_dataloader, eval_dataloader, lr_scheduler


def get_named_parameters(model):
    """
    Same thing as `Accelerator.get_named_parameters` Returns a list of the named parameters of the model (extracted
    from parallel)
    """
    from accelerate.utils import extract_model_from_parallel

    model = extract_model_from_parallel(model)
    return {n: p for n, p in model.named_parameters()}


def evaluate_model(model, dataloader, metric, accelerator=None):
    "Turns model to .eval(), runs dataloader, calculates metric, then turns eval back on"
    model.eval()
    for step, batch in enumerate(dataloader):
        with torch.no_grad():
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



benchmarks/fp8/torchao/fp8_utils.py [80:109]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    if accelerator is None:
        accelerator = Accelerator()
    model = AutoModelForSequenceClassification.from_pretrained(model_name)
    train_dataloader, eval_dataloader = get_dataloaders(model_name, batch_size)
    optimizer = AdamW(model.parameters(), lr=0.0001)
    lr_scheduler = get_linear_schedule_with_warmup(
        optimizer=optimizer,
        num_warmup_steps=100,
        num_training_steps=len(train_dataloader) * 2,
    )
    train_dataloader, eval_dataloader = accelerator.prepare(train_dataloader, eval_dataloader)
    return model, optimizer, train_dataloader, eval_dataloader, lr_scheduler


def get_named_parameters(model):
    """
    Same thing as `Accelerator.get_named_parameters` Returns a list of the named parameters of the model (extracted
    from parallel)
    """
    from accelerate.utils import extract_model_from_parallel

    model = extract_model_from_parallel(model)
    return {n: p for n, p in model.named_parameters()}


def evaluate_model(model, dataloader, metric, accelerator=None):
    "Turns model to .eval(), runs dataloader, calculates metric, then turns eval back on"
    model.eval()
    for step, batch in enumerate(dataloader):
        with torch.no_grad():
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -