update model card

README.md

@@ -118,7 +118,7 @@ The following hyperparameters were set on the Fairseq toolkit:
 | Dropout                        	| 0.1                          	|
 | Label smoothing                	| 0.1                          	|
 
-The model was trained for a total of 16.000 updates. Weights were saved every 1000 updates and reported results are the average of the last 6 checkpoints.
+The model was trained for a total of 22.000 updates. Weights were saved every 1000 updates and reported results are the average of the last 3 checkpoints.
 
 ## Evaluation
 
@@ -132,10 +132,10 @@ Below are the evaluation results on the machine translation from Catalan to Germ
 
 | Test set         	| SoftCatalà | Google Translate |mt-aina-ca-de|
 |----------------------|------------|------------------|---------------|
-| Flores 101 dev   	| 26,2     	| **34,8**     	| 26,9     	|
-| Flores 101 devtest   |26,3   	| **34,0**     	| 26,4     	|
-| NTREX | 21,7 | **28,8** | 20,3 |
-| Average          	| 24,7   	| **32,5**     	| 24,5      	|
+| Flores 101 dev   	| 26,2     	| **34,8**     	| 27,5     	|
+| Flores 101 devtest   |26,3   	| **34,0**     	| 26,9     	|
+| NTREX | 21,7 | **28,8** | 20,4 |
+| Average          	| 24,7   	| **32,5**     	| 24,9      	|
 
 ## Additional information