Improve error handling around non-number scores

spacy/cli/train.py

@@ -214,7 +214,12 @@ def create_evaluation_callback(
     def evaluate() -> Tuple[float, Dict[str, float]]:
         dev_examples = list(dev_corpus(nlp))
         scores = nlp.evaluate(dev_examples)
-        # Calculate a weighted sum based on score_weights for the main score
+        # Calculate a weighted sum based on score_weights for the main score.
+        # We can only consider scores that are ints/floats, not dicts like
+        # entity scores per type etc.
+        for key, value in scores.items():
+            if key in weights and not isinstance(value, (int, float)):
+                raise ValueError(Errors.E915.format(name=key, score_type=type(value)))
         try:
             weighted_score = sum(
                 scores.get(s, 0.0) * weights.get(s, 0.0) for s in weights

spacy/errors.py

@@ -480,6 +480,10 @@ class Errors:
     E201 = ("Span index out of range.")
 
     # TODO: fix numbering after merging develop into master
+    E915 = ("Can't use score '{name}' to calculate final weighted score. Expected "
+            "float or int but got: {score_type}. To exclude the score from the "
+            "final score, set its weight to null in the [training.score_weights] "
+            "section of your training config.")
     E916 = ("Can't log score for '{name}' in table: not a valid score ({score_type})")
     E917 = ("Received invalid value {value} for 'state_type' in "
             "TransitionBasedParser: only 'parser' or 'ner' are valid options.")

spacy/training/loggers.py

@@ -49,7 +49,7 @@ def console_logger():
                     scores.append("{0:.2f}".format(score))
                 except TypeError:
                     err = Errors.E916.format(name=col, score_type=type(score))
-                    raise TypeError(err) from None
+                    raise ValueError(err) from None
             data = (
                 [info["epoch"], info["step"]]
                 + losses