Method __init__

bitsandbytes/optim/lars.py:12–63

Base LARS optimizer. Arguments: params (`torch.tensor`): The input parameters to optimize. lr (`float`): The learning rate. momentum (`float`, defaults to 0): The momentum value speeds up the optimi

(
        self,
        params,
        lr,
        momentum=0,
        dampening=0,
        weight_decay=0,
        nesterov=False,
        optim_bits=32,
        args=None,
        min_8bit_size=4096,
        max_unorm=0.02,
    )

class LARS(Optimizer1State):
    def __init__(
        self,
        params,
        lr,
        momentum=0,
        dampening=0,
        weight_decay=0,
        nesterov=False,
        optim_bits=32,
        args=None,
        min_8bit_size=4096,
        max_unorm=0.02,
    ):
        """
        Base LARS optimizer.

        Arguments:
            params (`torch.tensor`):
                The input parameters to optimize.
            lr (`float`):
                The learning rate.
            momentum (`float`, defaults to 0):
                The momentum value speeds up the optimizer by taking bigger steps.
            dampening (`float`, defaults to 0):
                The dampening value reduces the momentum of the optimizer.
            weight_decay (`float`, defaults to 1e-2):
                The weight decay value for the optimizer.
            nesterov (`bool`, defaults to `False`):
                Whether to use Nesterov momentum.
            optim_bits (`int`, defaults to 32):
                The number of bits of the optimizer state.
            args (`object`, defaults to `None`):
                An object with additional arguments.
            min_8bit_size (`int`, defaults to 4096):
                The minimum number of elements of the parameter tensors for 8-bit optimization.
            max_unorm (`float`, defaults to 0.02):
                The maximum gradient norm.
        """
        if momentum == 0:
            raise NotImplementedError("LARS without momentum is not supported!")
        super().__init__(
            "lars",
            params,
            lr,
            (momentum, dampening),
            0.0,
            weight_decay,
            optim_bits,
            args,
            min_8bit_size,
            max_unorm=max_unorm,
        )


class LARS8bit(Optimizer1State):