update model card README.md

README.md

@@ -22,16 +22,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9348474801061007
+      value: 0.9357296670531721
     - name: Recall
       type: recall
-      value: 0.9490070683271625
+      value: 0.9506900033658701
     - name: F1
       type: f1
-      value: 0.9418740604643394
+      value: 0.9431505133984472
     - name: Accuracy
       type: accuracy
-      value: 0.9854153175958086
+      value: 0.9857390946017542
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -41,11 +41,11 @@ 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: 0.0672
-- Precision: 0.9348
-- Recall: 0.9490
-- F1: 0.9419
-- Accuracy: 0.9854
+- Loss: 0.0639
+- Precision: 0.9357
+- Recall: 0.9507
+- F1: 0.9432
+- Accuracy: 0.9857
 
 ## Model description
 
@@ -76,9 +76,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0886        | 1.0   | 1756 | 0.0692          | 0.9165    | 0.9379 | 0.9271 | 0.9829   |
-| 0.0414        | 2.0   | 3512 | 0.0598          | 0.9316    | 0.9487 | 0.9400 | 0.9855   |
-| 0.0212        | 3.0   | 5268 | 0.0672          | 0.9348    | 0.9490 | 0.9419 | 0.9854   |
+| 0.0847        | 1.0   | 1756 | 0.0636          | 0.9150    | 0.9387 | 0.9267 | 0.9840   |
+| 0.0399        | 2.0   | 3512 | 0.0592          | 0.9302    | 0.9485 | 0.9393 | 0.9854   |
+| 0.0201        | 3.0   | 5268 | 0.0639          | 0.9357    | 0.9507 | 0.9432 | 0.9857   |
 
 
 ### Framework versions