Update README.md

README.md

@@ -6,18 +6,18 @@ language:
 - en
 metrics:
   - type: f1         
-    value: 0.XX 
+    value: 0.8188 
     name: micro F1
     args:
-      threshold: 0.XX
+      threshold: 0.41
   - type: NDCG@3         
-    value: 0.X  
+    value: 0.8778  
     name: NDCG@5
   - type: NDCG@5         
-    value: 0.XX 
+    value: 0.8625 
     name: NDCG@5
   - type: NDCG@10         
-    value: 0.XX  
+    value: 0.8711 
     name: NDCG@10
 tags:
 - eurovoc
@@ -53,14 +53,17 @@ model = EurovocTagger.from_pretrained("EuropeanParliament/eurovoc_eu")
 ## Metrics
 
 
-### Eurlex57k Dataset
+### Eurovoc Dataset version 23.08
 
-| Metric     | Value    | Threshold Value |
-|------------|----------|-----------------|
-| Micro F1   | 0.XX     | 0.XX            |
-| NDCG@3     | 0.XX     | -               |
-| NDCG@5     | 0.XX     | -               |
-| NDCG@10    | 0.XX     | -               |
+Stratification ratio 90/10 for training/test and training/validation 
+
+
+| Metric     | Value      | Threshold Value |
+|------------|------------|-----------------|
+| Micro F1   | 0.8188     | 0.41            |
+| NDCG@3     | 0.8778     | -               |
+| NDCG@5     | 0.8625     | -               |
+| NDCG@10    | 0.8711     | -               |
 
 These values are in line with the state of the art in the field, see the publication [Large Scale Legal Text Classification Using Transformer Models](https://arxiv.org/pdf/2010.12871.pdf).