huggingface/pytorch-image-models · error · ValueError

Invalid learning rate: {}

Error message

Invalid learning rate: {}

What it means

Nvnovograd optimizer constructor validation: learning rate must satisfy 0.0 <= lr. Negative lr is rejected when timm.optim.Nvnovograd is instantiated.

Source

Thrown at timm/optim/nvnovograd.py:43

        weight_decay (float, optional): weight decay (L2 penalty) (default: 0)
        grad_averaging: gradient averaging
        amsgrad (boolean, optional): whether to use the AMSGrad variant of this
            algorithm from the paper `On the Convergence of Adam and Beyond`_
            (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):

View on GitHub (pinned to 9a5261e31b)

Solutions

1. Use a positive lr such as 1e-3
2. Validate lr before constructing when it comes from dynamic sources

Example fix

# before
opt = Nvnovograd(model.parameters(), lr=-1e-3)

# after
opt = Nvnovograd(model.parameters(), lr=1e-3)

assert lr >= 0.0

When it happens

Trigger: Calling timm.optim.Nvnovograd(params, lr=-0.01) or with a misparsed negative lr.

Common situations: Config typos, sign errors in lr schedules fed back into optimizer recreation, CLI parsing mistakes.

Related errors

• Invalid learning rate: {}
• Invalid learning rate: {lr}
• Invalid epsilon value: {}
• Invalid beta parameter at index 0: {}
• Invalid beta parameter at index 1: {}

AI-assisted analysis of huggingface/pytorch-image-models@9a5261e31b (2026-08-27). Data as JSON: /api/errors/8f99af112f0b1e4b. Report an issue: GitHub.