update model card README.md

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9314955430835259
+      value: 0.9348906560636183
     - name: Recall
       type: recall
       value: 0.9496802423426456
     - name: F1
       type: f1
-      value: 0.9404999999999999
+      value: 0.9422274169310403
     - name: Accuracy
       type: accuracy
-      value: 0.9862836286572084
+      value: 0.986342497203744
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,10 +44,10 @@ 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: 0.0581
-- Precision: 0.9315
+- Loss: 0.0597
+- Precision: 0.9349
 - Recall: 0.9497
-- F1: 0.9405
+- F1: 0.9422
 - Accuracy: 0.9863
 
 ## Model description
@@ -79,9 +79,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0768        | 1.0   | 1756 | 0.0701          | 0.9052    | 0.9332 | 0.9190 | 0.9804   |
-| 0.04          | 2.0   | 3512 | 0.0557          | 0.9277    | 0.9483 | 0.9379 | 0.9862   |
-| 0.0258        | 3.0   | 5268 | 0.0581          | 0.9315    | 0.9497 | 0.9405 | 0.9863   |
+| 0.0766        | 1.0   | 1756 | 0.0722          | 0.9131    | 0.9320 | 0.9225 | 0.9803   |
+| 0.0415        | 2.0   | 3512 | 0.0580          | 0.9300    | 0.9487 | 0.9393 | 0.9858   |
+| 0.0265        | 3.0   | 5268 | 0.0597          | 0.9349    | 0.9497 | 0.9422 | 0.9863   |
 
 
 ### Framework versions