Class LAMB

bitsandbytes/optim/lamb.py:8–64

class LAMB(Optimizer2State):
    def __init__(
        self,
        params,
        lr=1e-3,
        bias_correction=True,
        betas=(0.9, 0.999),
        eps=1e-8,
        weight_decay=0,
        amsgrad=False,
        adam_w_mode=True,
        optim_bits=32,
        args=None,
        min_8bit_size=4096,
        max_unorm=1.0,
    ):
        """
        Base LAMB optimizer.

        Arguments:
            params (`torch.tensor`):
                The input parameters to optimize.
            lr (`float`, defaults to 1e-3):
                The learning rate.
            bias_correction (`bool`, defaults to `True`):
                Whether to apply bias correction to the first and second-order moments.
            betas (`tuple(float, float)`, defaults to (0.9, 0.999)):
                The beta values are the decay rates of the first and second-order moment of the optimizer.
            eps (`float`, defaults to 1e-8):
                The epsilon value prevents division by zero in the optimizer.
            weight_decay (`float`, defaults to 1e-2):
                The weight decay value for the optimizer.
            amsgrad (`bool`, defaults to `False`):
                Whether to use the [AMSGrad](https://hf.co/papers/1904.09237) variant of Adam that uses the maximum of past squared gradients instead.
            adam_w_mode (`bool`, defaults to `True`):
                Whether to use the AdamW variant.
            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 1.0):
                The maximum gradient norm.
        """
        super().__init__(
            "lamb",
            params,
            lr,
            betas,
            eps,
            weight_decay,
            optim_bits,
            args,
            min_8bit_size,
            max_unorm=max_unorm,
        )