Update model-card with final training output

README.md

@@ -70,6 +70,9 @@ predictions = fillmask(masked_text, top_k=3)
 	- fp16: `True`
 	- fp16_opt_level: `'01'`
 	- seed: `42`
+- Output
+    - global_step: `210890`
+    - training_loss: `3.5964575726682155`
 
 ## Evaluation