Once a model has been trained you might want to evaluate its performance in a different dataset. For that reason, luz provides the ?evaluate function that takes a fitted model and a dataset and computes the metrics attached to the model.

Evaluate returns a luz_module_evaluation object that you can query for metrics using the get_metrics function or simply print to see the results.

For example:

evaluation <- fitted %>% evaluate(data = valid_dl)
metrics <- get_metrics(evaluation)
print(evaluation)

## A `luz_module_evaluation`
## ── Results ─────────────────────────────────────────────────────────────────────
## loss: 1.1253
## mae: 0.8735
## mse: 1.1946
## rmse: 1.093