update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9288420359084171
+      value: 0.9341931216931217
     - name: Recall
       type: recall
-      value: 0.9490070683271625
+      value: 0.9508582968697409
     - name: F1
       type: f1
-      value: 0.9388162823607757
+      value: 0.9424520433694746
     - name: Accuracy
       type: accuracy
-      value: 0.9860040030611644
+      value: 0.9865191028433508
 ---
 
 <!-- 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: 0.0617
-- Precision: 0.9288
-- Recall: 0.9490
-- F1: 0.9388
-- Accuracy: 0.9860
+- Loss: 0.0603
+- Precision: 0.9342
+- Recall: 0.9509
+- F1: 0.9425
+- Accuracy: 0.9865
 
 ## Model description
 
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0894        | 1.0   | 1756 | 0.0675          | 0.9175    | 0.9322 | 0.9248 | 0.9818   |
-| 0.0328        | 2.0   | 3512 | 0.0640          | 0.9232    | 0.9450 | 0.9340 | 0.9853   |
-| 0.0171        | 3.0   | 5268 | 0.0617          | 0.9288    | 0.9490 | 0.9388 | 0.9860   |
+| 0.0854        | 1.0   | 1756 | 0.0633          | 0.9203    | 0.9364 | 0.9283 | 0.9830   |
+| 0.034         | 2.0   | 3512 | 0.0626          | 0.9290    | 0.9493 | 0.9391 | 0.9863   |
+| 0.0166        | 3.0   | 5268 | 0.0603          | 0.9342    | 0.9509 | 0.9425 | 0.9865   |
 
 
 ### Framework versions