{"record":{"id":"8f99af112f0b1e4b","repo":"huggingface/pytorch-image-models","slug":"invalid-learning-rate-8f99af","errorCode":null,"errorMessage":"Invalid learning rate: {}","messagePattern":"Invalid learning rate: (.+?)","errorType":"validation","errorClass":"ValueError","httpStatus":null,"severity":"error","filePath":"timm/optim/nvnovograd.py","lineNumber":43,"sourceCode":"        weight_decay (float, optional): weight decay (L2 penalty) (default: 0)\n        grad_averaging: gradient averaging\n        amsgrad (boolean, optional): whether to use the AMSGrad variant of this\n            algorithm from the paper `On the Convergence of Adam and Beyond`_\n            (default: False)\n    \"\"\"\n\n    def __init__(\n            self,\n            params,\n            lr=1e-3,\n            betas=(0.95, 0.98),\n            eps=1e-8,\n            weight_decay=0,\n            grad_averaging=False,\n            amsgrad=False,\n    ):\n        if not 0.0 <= lr:\n            raise ValueError(\"Invalid learning rate: {}\".format(lr))\n        if not 0.0 <= eps:\n            raise ValueError(\"Invalid epsilon value: {}\".format(eps))\n        if not 0.0 <= betas[0] < 1.0:\n            raise ValueError(\"Invalid beta parameter at index 0: {}\".format(betas[0]))\n        if not 0.0 <= betas[1] < 1.0:\n            raise ValueError(\"Invalid beta parameter at index 1: {}\".format(betas[1]))\n        defaults = dict(\n            lr=lr,\n            betas=betas,\n            eps=eps,\n            weight_decay=weight_decay,\n            grad_averaging=grad_averaging,\n            amsgrad=amsgrad,\n        )\n\n        super(NvNovoGrad, self).__init__(params, defaults)\n\n    def __setstate__(self, state):","sourceCodeStart":25,"sourceCodeEnd":61,"githubUrl":"https://github.com/huggingface/pytorch-image-models/blob/9a5261e31b3b5128526eb2658333b4c0a54464ae/timm/optim/nvnovograd.py#L25-L61","documentation":"Nvnovograd optimizer constructor validation: learning rate must satisfy 0.0 <= lr. Negative lr is rejected when timm.optim.Nvnovograd is instantiated.","triggerScenarios":"Calling timm.optim.Nvnovograd(params, lr=-0.01) or with a misparsed negative lr.","commonSituations":"Config typos, sign errors in lr schedules fed back into optimizer recreation, CLI parsing mistakes.","solutions":["Use a positive lr such as 1e-3","Validate lr before constructing when it comes from dynamic sources"],"exampleFix":"# before\nopt = Nvnovograd(model.parameters(), lr=-1e-3)\n\n# after\nopt = Nvnovograd(model.parameters(), lr=1e-3)","handlingStrategy":"validation","validationCode":"assert lr >= 0.0","typeGuard":null,"tryCatchPattern":null,"preventionTips":["Validate lr from configs/sweeps before optimizer creation"],"tags":["timm","nvnovograd","learning-rate","valueerror"],"backgroundTag":"invalid-optimizer-hyperparameter","analyzedSha":"9a5261e31b3b5128526eb2658333b4c0a54464ae","analyzedAt":"2026-08-27T02:34:25.417Z","schemaVersion":2},"datasetVersion":"2026-08-27T03:17:27.898Z"}