microsoft/qlib · error · ValueError

unknown metric `%s`

Error message

unknown metric `%s`

What it means

Raised by GRUModel.metric_fn when self.metric is not "" or "loss". GRU's validation metric is restricted to the (negated) training loss; unlike GRUTS/pytorch_hist, "ic" is not implemented here. The raise occurs during the first validation pass of fit().

Source

Thrown at qlib/contrib/model/pytorch_gru.py:154

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

    def loss_fn(self, pred, label):
        mask = ~torch.isnan(label)

        if self.loss == "mse":
            return self.mse(pred[mask], label[mask])

        raise ValueError("unknown loss `%s`" % self.loss)

    def metric_fn(self, pred, label):
        mask = torch.isfinite(label)

        if self.metric in ("", "loss"):
            return -self.loss_fn(pred[mask], label[mask])

        raise ValueError("unknown metric `%s`" % self.metric)

    def train_epoch(self, x_train, y_train):
        x_train_values = x_train.values
        y_train_values = np.squeeze(y_train.values)

        self.gru_model.train()

        indices = np.arange(len(x_train_values))
        np.random.shuffle(indices)

        for i in range(len(indices))[:: self.batch_size]:
            if len(indices) - i < self.batch_size:
                break

            feature = torch.from_numpy(x_train_values[indices[i : i + self.batch_size]]).float().to(self.device)
            label = torch.from_numpy(y_train_values[indices[i : i + self.batch_size]]).float().to(self.device)

            pred = self.gru_model(feature)

View on GitHub (pinned to 79633dd950)

Solutions

  1. Use metric="" or metric="loss" for GRUModel.
  2. Subclass GRUModel and extend metric_fn (copy the IC computation from pytorch_hist.GRUModel's sibling class) if you need IC-based early stopping.

Example fix

# before
GRUModel(metric="ic", ...)  # ValueError: unknown metric `ic`

# after
GRUModel(metric="loss", ...)
Defensive patterns

Strategy: validation

Validate before calling

assert params.get("metric", "") in {"", "loss"}, "GRUModel metric must be '' or 'loss'"

Type guard

def is_supported_metric(metric: str) -> bool:
    return metric in {"", "loss"}

Try / catch

try:
    model.fit(dataset)
except ValueError as e:
    if "unknown metric" in str(e):
        params["metric"] = "loss"
        model = GRUModel(**params)
        model.fit(dataset)
    else:
        raise

Prevention

When it happens

Trigger: GRUModel(metric="ic") followed by fit() with a validation segment; any string other than ""/"loss" triggers it on the first validation batch.

Common situations: Assuming all qlib pytorch models accept metric="ic" because benchmarks use it; porting configs from ALSTM/GRU_TS where "ic" exists.

Related errors


AI-assisted analysis of microsoft/qlib@79633dd950 (2026-08-15). Data as JSON: /api/errors/40efdb660eef689d. Report an issue: GitHub.