microsoft/qlib · error · ValueError

unknown loss `%s`

Error message

unknown loss `%s`

What it means

KRNNModel.loss_fn supports only 'mse' (masked mean squared error over non-NaN labels). Any other loss string raises ValueError on the first loss computation during fit().

Source

Thrown at qlib/contrib/model/pytorch_krnn.py:359

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

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

    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 get_daily_inter(self, df, shuffle=False):
        # organize the train data into daily batches
        daily_count = df.groupby(level=0, group_keys=False).size().values
        daily_index = np.roll(np.cumsum(daily_count), 1)
        daily_index[0] = 0
        if shuffle:
            # shuffle data
            daily_shuffle = list(zip(daily_index, daily_count))
            np.random.shuffle(daily_shuffle)

View on GitHub (pinned to 79633dd950)

Solutions

  1. Set loss='mse'
  2. Subclass and override loss_fn for custom losses

Example fix

# before
KRNNModel(loss="huber")

# after
KRNNModel(loss="mse")
Defensive patterns

Strategy: validation

Validate before calling

assert loss == "mse", "KRNNModel supports only loss='mse'"

Type guard

def is_supported_krnn_loss(name: str) -> bool:
    return name == "mse"

Prevention

When it happens

Trigger: KRNNModel(loss=anything != 'mse'), then fit(); also triggered by a hyperparameter-search grid containing unsupported loss values.

Common situations: Shared hyperparameter configs across model types where some models accept other losses; typos.

Related errors

AI-assisted analysis of microsoft/qlib@79633dd950 (2026-08-15). Data as JSON: /api/errors/a0f7e3b6f8625170. Report an issue: GitHub.