update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9333774177550008
+      value: 0.9337180544105523
     - name: Recall
       type: recall
-      value: 0.9501851228542578
+      value: 0.9530461124200605
     - name: F1
       type: f1
-      value: 0.9417062797097824
+      value: 0.9432830848671608
     - name: Accuracy
       type: accuracy
-      value: 0.9861953258374051
+      value: 0.9872843939483135
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,11 +43,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0590
-- Precision: 0.9334
-- Recall: 0.9502
-- F1: 0.9417
-- Accuracy: 0.9862
+- Loss: 0.0575
+- Precision: 0.9337
+- Recall: 0.9530
+- F1: 0.9433
+- Accuracy: 0.9873
 
 ## Model description
 
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0855        | 1.0   | 1756 | 0.0693          | 0.9127    | 0.9337 | 0.9231 | 0.9817   |
-| 0.0352        | 2.0   | 3512 | 0.0629          | 0.9305    | 0.9487 | 0.9395 | 0.9861   |
-| 0.0186        | 3.0   | 5268 | 0.0590          | 0.9334    | 0.9502 | 0.9417 | 0.9862   |
+| 0.0868        | 1.0   | 1756 | 0.0651          | 0.9158    | 0.9371 | 0.9263 | 0.9828   |
+| 0.0351        | 2.0   | 3512 | 0.0635          | 0.9286    | 0.9493 | 0.9388 | 0.9864   |
+| 0.0182        | 3.0   | 5268 | 0.0575          | 0.9337    | 0.9530 | 0.9433 | 0.9873   |
 
 
 ### Framework versions