microsoft/qlib · error · NotImplementedError

optimizer {} is not supported!

Error message

optimizer {} is not supported!

What it means

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.

Source

Thrown at qlib/contrib/model/pytorch_gru_ts.py:132

        if self.seed is not None:
            np.random.seed(self.seed)
            torch.manual_seed(self.seed)

        self.GRU_model = GRUModel(
            d_feat=self.d_feat,
            hidden_size=self.hidden_size,
            num_layers=self.num_layers,
            dropout=self.dropout,
        )
        self.logger.info("model:\n{:}".format(self.GRU_model))
        self.logger.info("model size: {:.4f} MB".format(count_parameters(self.GRU_model)))

        if optimizer.lower() == "adam":
            self.train_optimizer = optim.Adam(self.GRU_model.parameters(), lr=self.lr)
        elif optimizer.lower() == "gd":
            self.train_optimizer = optim.SGD(self.GRU_model.parameters(), lr=self.lr)
        else:
            raise NotImplementedError("optimizer {} is not supported!".format(optimizer))

        self.fitted = False
        self.GRU_model.to(self.device)

    @property
    def use_gpu(self):
        return self.device != torch.device("cpu")

    def mse(self, pred, label, weight):
        loss = weight * (pred - label) ** 2
        return torch.mean(loss)

    def loss_fn(self, pred, label, weight=None):
        mask = ~torch.isnan(label)

        if weight is None:
            weight = torch.ones_like(label)

View on GitHub (pinned to 79633dd950)

Solutions

  1. Use optimizer="adam" or optimizer="gd".
  2. Subclass GRUModelTS and assign a custom torch optimizer after super().__init__ if you need another algorithm.

Example fix

# before
GRUModelTS(optimizer="adamw", lr=1e-3)

# after
GRUModelTS(optimizer="adam", lr=1e-3)
Defensive patterns

Strategy: validation

Validate before calling

assert params["optimizer"].lower() in {"adam", "gd"}, "GRUModelTS supports only 'adam' and 'gd'"

Type guard

def is_supported_optimizer(name: str) -> bool:
    return isinstance(name, str) and name.lower() in {"adam", "gd"}

Try / catch

try:
    model = GRUModelTS(**params)
except NotImplementedError as e:
    if "optimizer" in str(e):
        params["optimizer"] = "adam"
        model = GRUModelTS(**params)
    else:
        raise

Prevention

When it happens

Trigger: GRUModelTS(optimizer="sgd"/"adamw"/"rmsprop", ...). Constructing the model in a workflow's model init immediately raises NotImplementedError.

Common situations: Reusing a config written for LightGBM/XGBoost handlers where optimizer names differ; using "sgd" instead of qlib's "gd" alias.

Related errors

AI-assisted analysis of microsoft/qlib@79633dd950 (2026-08-15). Data as JSON: /api/errors/3a0cbf143fcbc06d. Report an issue: GitHub.