Update README.md

README.md

@@ -11,8 +11,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gbert-large
 
-This model was trained from scratch on the None dataset.
-It achieves the following results on the evaluation set:
+This model is a fine-tuned version of deepset/gbert-large 
+
+It was fine-tuned on poetry from Projekt Gutenberg in order to do masked language modeling tasks in poetry generation (synonym creation for rythm and to find rhyming pairs) 
+
 - Loss: 2.1519
 
 ## Model description