Adding some conclusions to text

app.py

@@ -238,7 +238,13 @@ In the demo below you can select among 4 different fine-tuning methods:
  
 And two different weighting schemes that were used in the loss function to nudge more toward the minority class in the dataset: 
 - female pronouns.
- 
+
+
+One trend that appears is: conditioning on `birth_date` metadata in both training and inference text has the largest dose-response relationship. This seems reasonable, as the fine-tuned model is able to ‘stratify’ a learned relationship between gender pronouns and dates, when both are present in the text.
+
+While conditioning on either no metadata or `birth_place` data training, have similar middle-ground effects for this inference task. 
+
+Finally,  conditioning on `name` metadata in training, (while again conditioning on `date` in inference) has almost no dose-response relationship. It appears the learning of a `name —> gender pronouns` relationship was sufficiently successful to overwhelm any potential more nuanced learning, such as that driven by `birth_date` or `place`. 
 """