Adam与AdamW

1. Adam optimizer

adam优化器是经常使用到的模型训练时的优化器，但是在bert的训练中不起作用，具体表现是，模型的f1上不来。

2. AdamW

transformers 库实现了基于权重衰减的优化器，AdamW，这个优化器初始化时有6个参数，第一个是params，可以是torch的Parameter，也可以是一个grouped参数。betas是Adam的beta参数，b1和b2。eps也是Adam为了数值稳定的参数。correct_bias，如果应用到tf的模型上时需要设置为False

class AdamW(Optimizer):
    """
    Implements Adam algorithm with weight decay fix as introduced in
    `Decoupled Weight Decay Regularization <https://arxiv.org/abs/1711.05101>`__.

    Parameters:
        params (:obj:`Iterable[torch.nn.parameter.Parameter]`):
            Iterable of parameters to optimize or dictionaries defining parameter groups.
        lr (:obj:`float`, `optional`, defaults to 1e-3):
            The learning rate to use.
        betas (:obj:`Tuple[float,float]`, `optional`, defaults to (0.9, 0.999)):
            Adam's betas parameters (b1, b2).
        eps (:obj:`float`, `optional`, defaults to 1e-6):
            Adam's epsilon for numerical stability.
        weight_decay (:obj:`float`, `optional`, defaults to 0):
            Decoupled weight decay to apply.
        correct_bias (:obj:`bool`, `optional`, defaults to `True`):
            Whether ot not to correct bias in Adam (for instance, in Bert TF repository they use :obj:`False`).
    """

    def __init__(
        self,
        params: Iterable[torch.nn.parameter.Parameter],
        lr: float = 1e-3,
        betas: Tuple[float, float] = (0.9, 0.999),
        eps: float = 1e-6,
        weight_decay: float = 0.0,
        correct_bias: bool = True,
    ):

3. BertAdam与AdamW的使用区别

# Parameters:
lr = 1e-3
max_grad_norm = 1.0
num_training_steps = 1000
num_warmup_steps = 100
warmup_proportion = float(num_warmup_steps) / float(num_training_steps)  # 0.1

### Previously BertAdam optimizer was instantiated like this:
optimizer = BertAdam(model.parameters(), lr=lr, schedule='warmup_linear', warmup=warmup_proportion, t_total=num_training_steps)
### and used like this:
for batch in train_data:
    loss = model(batch)
    loss.backward()
    optimizer.step()

### In Transformers, optimizer and schedules are splitted and instantiated like this:
optimizer = AdamW(model.parameters(), lr=lr, correct_bias=False)  # To reproduce BertAdam specific behavior set correct_bias=False
scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps=num_warmup_steps, num_training_steps=num_training_steps)  # PyTorch scheduler
### and used like this:
for batch in train_data:
    model.train()
    loss = model(batch)
    loss.backward()
    torch.nn.utils.clip_grad_norm_(model.parameters(), max_grad_norm)  # Gradient clipping is not in AdamW anymore (so you can use amp without issue)
    optimizer.step()
    scheduler.step()
    optimizer.zero_grad()

https://github.com/huggingface/transformers