update model card README.md

README.md

@@ -22,16 +22,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9271828665568369
+      value: 0.9314097279472382
     - name: Recall
       type: recall
-      value: 0.9471558397845843
+      value: 0.9506900033658701
     - name: F1
       type: f1
-      value: 0.937062937062937
+      value: 0.94095111185142
     - name: Accuracy
       type: accuracy
-      value: 0.9859598516512628
+      value: 0.9862541943839407
 ---
 
 <!-- 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: 0.0612
-- Precision: 0.9272
-- Recall: 0.9472
-- F1: 0.9371
-- Accuracy: 0.9860
+- Loss: 0.0622
+- Precision: 0.9314
+- Recall: 0.9507
+- F1: 0.9410
+- Accuracy: 0.9863
 
 ## Model description
 
@@ -76,9 +76,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0871        | 1.0   | 1756 | 0.0643          | 0.9158    | 0.9355 | 0.9256 | 0.9827   |
-| 0.0414        | 2.0   | 3512 | 0.0573          | 0.9308    | 0.9490 | 0.9398 | 0.9860   |
-| 0.0214        | 3.0   | 5268 | 0.0612          | 0.9272    | 0.9472 | 0.9371 | 0.9860   |
+| 0.0821        | 1.0   | 1756 | 0.0639          | 0.9108    | 0.9371 | 0.9238 | 0.9834   |
+| 0.0366        | 2.0   | 3512 | 0.0585          | 0.9310    | 0.9497 | 0.9403 | 0.9857   |
+| 0.019         | 3.0   | 5268 | 0.0622          | 0.9314    | 0.9507 | 0.9410 | 0.9863   |
 
 
 ### Framework versions