huggingface/pytorch-image-models · error · ValueError

Invalid beta parameter at index 0: {}

Error message

Invalid beta parameter at index 0: {}

What it means

Nvnovograd constructor validation: betas[0] must satisfy 0.0 <= beta1 < 1.0. Out-of-range momentum decay breaks the running gradient-norm average.

Source

Thrown at timm/optim/nvnovograd.py:47

            (default: False)
    """

    def __init__(
            self,
            params,
            lr=1e-3,
            betas=(0.95, 0.98),
            eps=1e-8,
            weight_decay=0,
            grad_averaging=False,
            amsgrad=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,
            grad_averaging=grad_averaging,
            amsgrad=amsgrad,
        )

        super(NvNovoGrad, self).__init__(params, defaults)

    def __setstate__(self, state):
        super(NvNovoGrad, self).__setstate__(state)
        for group in self.param_groups:
            group.setdefault('amsgrad', False)

View on GitHub (pinned to 9a5261e31b)

Solutions

1. Use betas like (0.9, 0.999)
2. Bound beta1 to [0,1) in sweep configs

Example fix

# before
opt = Nvnovograd(model.parameters(), betas=(1.0, 0.999))

# after
opt = Nvnovograd(model.parameters(), betas=(0.9, 0.999))

assert 0.0 <= betas[0] < 1.0

When it happens

Trigger: Calling timm.optim.Nvnovograd(params, betas=(1.0, 0.999)) or negative beta1.

Common situations: Hyperparameter sweeps crossing the boundary, betas copied from incompatible optimizers.

Related errors

• Invalid beta parameter at index 1: {}
• Invalid beta parameter at index 0: {betas[0]}
• Invalid beta parameter at index 1: {betas[1]}
• Invalid learning rate: {}
• Invalid epsilon value: {}

AI-assisted analysis of huggingface/pytorch-image-models@9a5261e31b (2026-08-27). Data as JSON: /api/errors/dc88a300e2ecc030. Report an issue: GitHub.