{"record":{"id":"ecccc2171a9aea60","repo":"huggingface/pytorch-image-models","slug":"invalid-weight-decay-value-weight-decay-ecccc2","errorCode":null,"errorMessage":"Invalid weight_decay value: {weight_decay}","messagePattern":"Invalid weight_decay value: (.+?)","errorType":"validation","errorClass":"ValueError","httpStatus":null,"severity":"error","filePath":"timm/optim/nadamw.py","lineNumber":64,"sourceCode":"            betas: Tuple[float, float] = (0.9, 0.999),\n            eps: float = 1e-8,\n            weight_decay: float = 1e-2,\n            caution: bool = False,\n            corrected_weight_decay: bool = False,\n            maximize: bool = False,\n            foreach: Optional[bool] = None,\n            capturable: bool = False,\n    ):\n        if not 0.0 <= lr:\n            raise ValueError(f'Invalid learning rate: {lr}')\n        if not 0.0 <= eps:\n            raise ValueError(f'Invalid epsilon value: {eps}')\n        if not 0.0 <= betas[0] < 1.0:\n            raise ValueError(f'Invalid beta parameter at index 0: {betas[0]}')\n        if not 0.0 <= betas[1] < 1.0:\n            raise ValueError(f'Invalid beta parameter at index 1: {betas[1]}')\n        if not 0.0 <= weight_decay:\n            raise ValueError(f'Invalid weight_decay value: {weight_decay}')\n        defaults = dict(\n            lr=lr,\n            betas=betas,\n            eps=eps,\n            weight_decay=weight_decay,\n            caution=caution,\n            corrected_weight_decay=corrected_weight_decay,\n            foreach=foreach,\n            maximize=maximize,\n            capturable=capturable,\n        )\n        super().__init__(params, defaults)\n\n    def __setstate__(self, state):\n        super().__setstate__(state)\n        for group in self.param_groups:\n            group.setdefault('caution', False)\n            group.setdefault('corrected_weight_decay', False)","sourceCodeStart":46,"sourceCodeEnd":82,"githubUrl":"https://github.com/huggingface/pytorch-image-models/blob/9a5261e31b3b5128526eb2658333b4c0a54464ae/timm/optim/nadamw.py#L46-L82","documentation":"NAdamW constructor validation: weight_decay must satisfy 0.0 <= weight_decay. Negative decoupled weight decay is rejected at construction.","triggerScenarios":"Calling timm.optim.NAdamW(params, weight_decay=-0.05).","commonSituations":"Sign confusion when implementing weight growth experiments, or a config value typo.","solutions":["Use a non-negative weight_decay such as 0.05","If you intended weight growth, that is not supported; use 0 or positive decay"],"exampleFix":"# before\nopt = NAdamW(model.parameters(), weight_decay=-0.05)\n\n# after\nopt = NAdamW(model.parameters(), weight_decay=0.05)","handlingStrategy":"validation","validationCode":"assert weight_decay >= 0.0","typeGuard":null,"tryCatchPattern":null,"preventionTips":["Remember decoupled decay only supports non-negative values","Check config sign conventions"],"tags":["timm","nadamw","weight-decay","valueerror"],"backgroundTag":"invalid-optimizer-hyperparameter","analyzedSha":"9a5261e31b3b5128526eb2658333b4c0a54464ae","analyzedAt":"2026-08-27T02:34:25.417Z","schemaVersion":2},"datasetVersion":"2026-08-27T03:17:27.898Z"}