{"record":{"id":"51b44182a8b4beab","repo":"microsoft/qlib","slug":"unknown-loss-s-51b441","errorCode":null,"errorMessage":"unknown loss `%s`","messagePattern":"unknown loss `(.+?)`","errorType":"exception","errorClass":"ValueError","httpStatus":null,"severity":"error","filePath":"qlib/contrib/model/pytorch_tcn.py","lineNumber":154,"sourceCode":"\n        self.fitted = False\n        self.tcn_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):\n        loss = (pred - label) ** 2\n        return torch.mean(loss)\n\n    def loss_fn(self, pred, label):\n        mask = ~torch.isnan(label)\n\n        if self.loss == \"mse\":\n            return self.mse(pred[mask], label[mask])\n\n        raise ValueError(\"unknown loss `%s`\" % self.loss)\n\n    def metric_fn(self, pred, label):\n        mask = torch.isfinite(label)\n\n        if self.metric in (\"\", \"loss\"):\n            return -self.loss_fn(pred[mask], label[mask])\n\n        raise ValueError(\"unknown metric `%s`\" % self.metric)\n\n    def train_epoch(self, x_train, y_train):\n        x_train_values = x_train.values\n        y_train_values = np.squeeze(y_train.values)\n\n        self.tcn_model.train()\n\n        indices = np.arange(len(x_train_values))\n        np.random.shuffle(indices)\n","sourceCodeStart":136,"sourceCodeEnd":172,"githubUrl":"https://github.com/microsoft/qlib/blob/79633dd9506ea689e5400dea0197717b5b3d74b7/qlib/contrib/model/pytorch_tcn.py#L136-L172","documentation":"Raised by TCN model loss_fn in qlib/contrib/model/pytorch_tcn.py:154 when self.loss is not 'mse'. The TCN model implements a single supervised loss — MSE over non-NaN (masked) labels; any other value raises ValueError. metric_fn (''/'loss') delegates to loss_fn, so the bad value also breaks early-stopping evaluation.","triggerScenarios":"loss='mae', 'huber', 'binary', etc. in TCN kwargs, then fit(); the first loss evaluation in train_epoch raises.","commonSituations":"Copying kwargs from DNNModelPytorch configs (which allow 'binary'); case typos like 'MSE'.","solutions":["Set loss: 'mse' (only supported value).","Subclass the TCN model and override loss_fn(), keeping the NaN mask semantics."],"exampleFix":"# before\nkwargs:\n  loss: binary\n\n# after\nkwargs:\n  loss: mse","handlingStrategy":"validation","validationCode":"assert config.get(\"loss\", \"mse\") == \"mse\", \"TCN model only supports loss='mse'\"","typeGuard":"def is_supported_tcn_loss(loss: str) -> bool:\n    return loss == \"mse\"","tryCatchPattern":"try:\n    model.fit(dataset)\nexcept ValueError as e:\n    if \"unknown loss\" in str(e):\n        raise ValueError(\"TCN supports only loss='mse'; subclass to change\") from e\n    raise","preventionTips":["Keep loss kwarg per-model; do not share config blocks across qlib models.","Default to 'mse' and only deviate via subclass overrides."],"tags":["qlib","pytorch","loss-function","config","tcn"],"backgroundTag":null,"analyzedSha":"79633dd9506ea689e5400dea0197717b5b3d74b7","analyzedAt":"2026-08-15T07:01:27.511Z","schemaVersion":2},"datasetVersion":"2026-08-15T22:17:37.221Z"}