model/lamb.py [20:49]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    r"""Implements Lamb algorithm.
    It has been proposed in `Large Batch Optimization for Deep Learning: Training BERT in 76 minutes`_.
    Arguments:
        params (iterable): iterable of parameters to optimize or dicts defining
            parameter groups
        lr (float, optional): learning rate (default: 1e-3)
        betas (Tuple[float, float], optional): coefficients used for computing
            running averages of gradient and its square (default: (0.9, 0.999))
        eps (float, optional): term added to the denominator to improve
            numerical stability (default: 1e-8)
        weight_decay (float, optional): weight decay (L2 penalty) (default: 0)
        adam (bool, optional): always use trust ratio = 1, which turns this into
            Adam. Useful for comparison purposes.
    .. _Large Batch Optimization for Deep Learning: Training BERT in 76 minutes:
        https://arxiv.org/abs/1904.00962
    """

    def __init__(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-6,
                 weight_decay=0, adam=False):
        if not 0.0 <= lr:
            raise ValueError("Invalid learning rate: {}".format(lr))
        if not 0.0 <= eps:
            raise ValueError("Invalid epsilon value: {}".format(eps))
        if not 0.0 <= betas[0] < 1.0:
            raise ValueError("Invalid beta parameter at index 0: {}".format(betas[0]))
        if not 0.0 <= betas[1] < 1.0:
            raise ValueError("Invalid beta parameter at index 1: {}".format(betas[1]))
        defaults = dict(lr=lr, betas=betas, eps=eps,
                        weight_decay=weight_decay)
        self.adam = adam
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



model/lamb.py [143:172]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    r"""Implements Lamb algorithm.
    It has been proposed in `Large Batch Optimization for Deep Learning: Training BERT in 76 minutes`_.
    Arguments:
        params (iterable): iterable of parameters to optimize or dicts defining
            parameter groups
        lr (float, optional): learning rate (default: 1e-3)
        betas (Tuple[float, float], optional): coefficients used for computing
            running averages of gradient and its square (default: (0.9, 0.999))
        eps (float, optional): term added to the denominator to improve
            numerical stability (default: 1e-8)
        weight_decay (float, optional): weight decay (L2 penalty) (default: 0)
        adam (bool, optional): always use trust ratio = 1, which turns this into
            Adam. Useful for comparison purposes.
    .. _Large Batch Optimization for Deep Learning: Training BERT in 76 minutes:
        https://arxiv.org/abs/1904.00962
    """

    def __init__(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-6,
                 weight_decay=0, adam=False):
        if not 0.0 <= lr:
            raise ValueError("Invalid learning rate: {}".format(lr))
        if not 0.0 <= eps:
            raise ValueError("Invalid epsilon value: {}".format(eps))
        if not 0.0 <= betas[0] < 1.0:
            raise ValueError("Invalid beta parameter at index 0: {}".format(betas[0]))
        if not 0.0 <= betas[1] < 1.0:
            raise ValueError("Invalid beta parameter at index 1: {}".format(betas[1]))
        defaults = dict(lr=lr, betas=betas, eps=eps,
                        weight_decay=weight_decay)
        self.adam = adam
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -