update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9312964492155243
+      value: 0.9324078664683524
     - name: Recall
       type: recall
-      value: 0.9490070683271625
+      value: 0.9495119488387749
     - name: F1
       type: f1
-      value: 0.9400683504209385
+      value: 0.9408821812724089
     - name: Accuracy
       type: accuracy
-      value: 0.9867104256195914
+      value: 0.9862983457938423
 ---
 
 <!-- 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: 0.0573
-- Precision: 0.9313
-- Recall: 0.9490
-- F1: 0.9401
-- Accuracy: 0.9867
+- Loss: 0.0616
+- Precision: 0.9324
+- Recall: 0.9495
+- F1: 0.9409
+- Accuracy: 0.9863
 
 ## Model description
 
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0896        | 1.0   | 1756 | 0.0694          | 0.9190    | 0.9332 | 0.9260 | 0.9829   |
-| 0.032         | 2.0   | 3512 | 0.0613          | 0.9289    | 0.9492 | 0.9389 | 0.9861   |
-| 0.0187        | 3.0   | 5268 | 0.0573          | 0.9313    | 0.9490 | 0.9401 | 0.9867   |
+| 0.0872        | 1.0   | 1756 | 0.0712          | 0.9173    | 0.9332 | 0.9252 | 0.9815   |
+| 0.0333        | 2.0   | 3512 | 0.0648          | 0.9295    | 0.9493 | 0.9393 | 0.9861   |
+| 0.0174        | 3.0   | 5268 | 0.0616          | 0.9324    | 0.9495 | 0.9409 | 0.9863   |
 
 
 ### Framework versions