{"record":{"id":"3a0cbf143fcbc06d","repo":"microsoft/qlib","slug":"optimizer-is-not-supported-3a0cbf","errorCode":null,"errorMessage":"optimizer {} is not supported!","messagePattern":"optimizer (.+?) is not supported!","errorType":"exception","errorClass":"NotImplementedError","httpStatus":null,"severity":"error","filePath":"qlib/contrib/model/pytorch_gru_ts.py","lineNumber":132,"sourceCode":"        if self.seed is not None:\n            np.random.seed(self.seed)\n            torch.manual_seed(self.seed)\n\n        self.GRU_model = GRUModel(\n            d_feat=self.d_feat,\n            hidden_size=self.hidden_size,\n            num_layers=self.num_layers,\n            dropout=self.dropout,\n        )\n        self.logger.info(\"model:\\n{:}\".format(self.GRU_model))\n        self.logger.info(\"model size: {:.4f} MB\".format(count_parameters(self.GRU_model)))\n\n        if optimizer.lower() == \"adam\":\n            self.train_optimizer = optim.Adam(self.GRU_model.parameters(), lr=self.lr)\n        elif optimizer.lower() == \"gd\":\n            self.train_optimizer = optim.SGD(self.GRU_model.parameters(), lr=self.lr)\n        else:\n            raise NotImplementedError(\"optimizer {} is not supported!\".format(optimizer))\n\n        self.fitted = False\n        self.GRU_model.to(self.device)\n\n    @property\n    def use_gpu(self):\n        return self.device != torch.device(\"cpu\")\n\n    def mse(self, pred, label, weight):\n        loss = weight * (pred - label) ** 2\n        return torch.mean(loss)\n\n    def loss_fn(self, pred, label, weight=None):\n        mask = ~torch.isnan(label)\n\n        if weight is None:\n            weight = torch.ones_like(label)\n","sourceCodeStart":114,"sourceCodeEnd":150,"githubUrl":"https://github.com/microsoft/qlib/blob/79633dd9506ea689e5400dea0197717b5b3d74b7/qlib/contrib/model/pytorch_gru_ts.py#L114-L150","documentation":"Raised in GRUModelTS.__init__ (the time-series GRU variant) when `optimizer` is not \"adam\" or \"gd\". Same two-optimizer whitelist as the non-TS GRU; the check is case-insensitive and fires at model construction.","triggerScenarios":"GRUModelTS(optimizer=\"sgd\"/\"adamw\"/\"rmsprop\", ...). Constructing the model in a workflow's model init immediately raises NotImplementedError.","commonSituations":"Reusing a config written for LightGBM/XGBoost handlers where optimizer names differ; using \"sgd\" instead of qlib's \"gd\" alias.","solutions":["Use optimizer=\"adam\" or optimizer=\"gd\".","Subclass GRUModelTS and assign a custom torch optimizer after super().__init__ if you need another algorithm."],"exampleFix":"# before\nGRUModelTS(optimizer=\"adamw\", lr=1e-3)\n\n# after\nGRUModelTS(optimizer=\"adam\", lr=1e-3)","handlingStrategy":"validation","validationCode":"assert params[\"optimizer\"].lower() in {\"adam\", \"gd\"}, \"GRUModelTS supports only 'adam' and 'gd'\"","typeGuard":"def is_supported_optimizer(name: str) -> bool:\n    return isinstance(name, str) and name.lower() in {\"adam\", \"gd\"}","tryCatchPattern":"try:\n    model = GRUModelTS(**params)\nexcept NotImplementedError as e:\n    if \"optimizer\" in str(e):\n        params[\"optimizer\"] = \"adam\"\n        model = GRUModelTS(**params)\n    else:\n        raise","preventionTips":["Use 'gd' for SGD-family optimizers in qlib pytorch models.","Validate constructor hyper-parameters before launching runs."],"tags":["pytorch","qlib","optimizer","configuration"],"backgroundTag":null,"analyzedSha":"79633dd9506ea689e5400dea0197717b5b3d74b7","analyzedAt":"2026-08-15T07:01:27.511Z","schemaVersion":2},"datasetVersion":"2026-08-15T22:17:37.221Z"}