Update README.md

README.md

@@ -17,10 +17,18 @@ model-index:
         name: SentiNews
         config: sentence_level
       metrics:
+        - type: f1
+          value: 0.6851357247321056
+          name: Test macro F1
+        - type: accuracy
+          value: 0.7158081705150977
+          name: Test accuracy
         - type: f1
           value: 0.6934678744913757
           name: Validation macro F1
-      
+        - type: accuracy
+          value: 0.7207815275310835
+          name: Validation accuracy 
 ---
 
 # sloberta-sentinews-sentence
@@ -63,7 +71,7 @@ test_data = data.select(split["test_indices"])
 
 ## Evaluation results
 
-Best validation results:
+Best validation set results:
 ```
 {
   "eval_accuracy": 0.7207815275310835,
@@ -79,4 +87,22 @@ Best validation results:
   "eval_recall_neutral": 0.7438413361169103,
   "eval_recall_positive": 0.6031746031746031
 }
+```
+
+Test set results:
+```
+{
+  "test_loss": 0.6395984888076782,
+  "test_accuracy": 0.7158081705150977,
+  "test_precision_negative": 0.6570397111913358,
+  "test_recall_negative": 0.7292965271593945,
+  "test_f1_negative": 0.6912850812407682,
+  "test_precision_neutral": 0.7748017998714377,
+  "test_recall_neutral": 0.7418957734919983,
+  "test_f1_neutral": 0.7579918247563149,
+  "test_precision_positive": 0.6155642023346304,
+  "test_recall_positive": 0.5969811320754717,
+  "test_f1_positive": 0.6061302681992337,
+  "test_f1_macro": 0.6851357247321056,
+}
 ```