{"record":{"id":"3235cf9c830b0dae","repo":"huggingface/pytorch-image-models","slug":"invalid-beta-parameter-at-index-0-3235cf","errorCode":null,"errorMessage":"Invalid beta parameter at index 0: {}","messagePattern":"Invalid beta parameter at index 0: (.+?)","errorType":"validation","errorClass":"ValueError","httpStatus":null,"severity":"error","filePath":"timm/optim/adamw.py","lineNumber":68,"sourceCode":"            self,\n            params: ParamsT,\n            lr: float = 1e-3,\n            betas: Tuple[float, float] = (0.9, 0.999),\n            eps: float = 1e-8,\n            weight_decay: float = 1e-2,\n            amsgrad: bool = False,\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(\"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            amsgrad=amsgrad,\n            caution=caution,\n            corrected_weight_decay=corrected_weight_decay,\n            foreach=foreach,\n            maximize=maximize,\n            capturable=capturable,\n        )\n        super(AdamWLegacy, self).__init__(params, defaults)\n\n    def __setstate__(self, state):\n        super(AdamWLegacy, self).__setstate__(state)","sourceCodeStart":50,"sourceCodeEnd":86,"githubUrl":"https://github.com/huggingface/pytorch-image-models/blob/9a5261e31b3b5128526eb2658333b4c0a54464ae/timm/optim/adamw.py#L50-L86","documentation":"Raised by timm's AdamW optimizer constructor when the first beta (beta1, the momentum decay coefficient) is outside the valid range [0.0, 1.0). Beta1 controls exponential decay of the first-moment estimate; values <0 or >=1 are mathematically invalid for the running-average update.","triggerScenarios":"Calling timm.optim.AdamW(params, betas=(beta1, beta2)) with beta1 < 0.0 or beta1 >= 1.0, e.g. betas=(1.0, 0.999) or betas=(-0.1, 0.999).","commonSituations":"Typo in a training config (e.g. 0.5 vs 5.0), swapping lr and beta values in argparse/YAML, or copying hyperparameters from a paper that used a different parameterization.","solutions":["Set beta1 to a value in [0.0, 1.0), typically 0.9","Check your config/YAML for a typo in betas or the value bound to beta1","If beta1 came from CLI args, verify the argparse type=float and default"],"exampleFix":"# before\nopt = timm.optim.AdamW(model.parameters(), lr=1e-3, betas=(9.0, 0.999))\n# after\nopt = timm.optim.AdamW(model.parameters(), lr=1e-3, betas=(0.9, 0.999))","handlingStrategy":"validation","validationCode":"assert len(betas) == 2 and all(0.0 <= b < 1.0 for b in betas), f'betas out of range: {betas}'","typeGuard":"def valid_adamw_betas(betas: tuple) -> bool:\n    return len(betas) == 2 and all(isinstance(b, (int, float)) and 0.0 <= b < 1.0 for b in betas)","tryCatchPattern":null,"preventionTips":["Validate hyperparameter ranges in one place before building the optimizer","Use argparse type=float and range checks for betas","Keep a single config schema for optimizer hyperparameters"],"tags":["optimizer","adamw","hyperparameters","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"}