improve error message for malformed validation arguments in fit (kera…

…s-team#5141)

* improve error message for incorrect validation arguments

* make formatting consistent per comments in keras-team#5141

keras/engine/training.py

@@ -1124,7 +1124,12 @@ class indices (integers) to
             elif len(validation_data) == 3:
                 val_x, val_y, val_sample_weight = validation_data
             else:
-                raise
+                raise ValueError('When passing validation_data, '
+                                 'it must contain 2 (x_val, y_val) '
+                                 'or 3 (x_val, y_val, val_sample_weights) '
+                                 'items, however it contains %d items' %
+                                 len(validation_data))
+
             val_x, val_y, val_sample_weights = self._standardize_user_data(
                 val_x, val_y,
                 sample_weight=val_sample_weight,