{"record":{"id":"1050598b4e5f564b","repo":"huggingface/pytorch-image-models","slug":"invalid-weight-decay-value-weight-decay","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/adopt.py","lineNumber":97,"sourceCode":"            differentiable: bool = False,\n    ):\n        if isinstance(lr, Tensor):\n            if foreach and not capturable:\n                raise ValueError(\n                    \"lr as a Tensor is not supported for capturable=False and foreach=True\"\n                )\n            if lr.numel() != 1:\n                raise ValueError(\"Tensor lr must be 1-element\")\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\n        defaults = dict(\n            lr=lr,\n            betas=betas,\n            eps=eps,\n            weight_decay=weight_decay,\n            clip_exp=clip_exp,\n            decoupled=decoupled,\n            corrected_weight_decay=corrected_weight_decay,\n            caution=caution,\n            maximize=maximize,\n            foreach=foreach,\n            capturable=capturable,\n            differentiable=differentiable,\n        )\n        super().__init__(params, defaults)\n\n    def __setstate__(self, state):","sourceCodeStart":79,"sourceCodeEnd":115,"githubUrl":"https://github.com/huggingface/pytorch-image-models/blob/9a5261e31b3b5128526eb2658333b4c0a54464ae/timm/optim/adopt.py#L79-L115","documentation":"Raised by ADOPT's constructor when weight_decay is negative. ADOPT decouples weight decay as an added non-negative penalty; negative decay would grow weights and is rejected.","triggerScenarios":"Constructing timm.optim.Adopt(params, weight_decay=-1e-4).","commonSituations":"Sign typo in config, or confusing weight decay with a norm-growth regularizer; sweeps exploring negative decay values.","solutions":["Use a non-negative weight_decay, typically 0.0 to 0.1 (e.g. 0.02)","If you wanted no decay, pass weight_decay=0.0 explicitly"],"exampleFix":"# before\nopt = timm.optim.Adopt(model.parameters(), lr=1e-3, weight_decay=-0.02)\n# after\nopt = timm.optim.Adopt(model.parameters(), lr=1e-3, weight_decay=0.02)","handlingStrategy":"validation","validationCode":"assert weight_decay >= 0.0, f'weight_decay must be >= 0, got {weight_decay}'","typeGuard":"def valid_weight_decay(wd) -> bool:\n    return isinstance(wd, (int, float)) and wd >= 0.0","tryCatchPattern":null,"preventionTips":["Use 0.0 to disable decay, never a negative value","Bound weight-decay sweeps to [0, 1]"],"tags":["optimizer","adopt","weight-decay","validation"],"backgroundTag":"optimizer-hyperparameter-out-of-range","analyzedSha":"9a5261e31b3b5128526eb2658333b4c0a54464ae","analyzedAt":"2026-08-27T02:34:25.417Z","schemaVersion":2},"datasetVersion":"2026-08-27T03:17:27.898Z"}