update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9317169717961405
+      value: 0.9350348027842227
     - name: Recall
       type: recall
-      value: 0.9506900033658701
+      value: 0.9495119488387749
     - name: F1
       type: f1
-      value: 0.9411078717201166
+      value: 0.9422177688710756
     - name: Accuracy
       type: accuracy
-      value: 0.9865632542532525
+      value: 0.9865779713898863
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,10 +43,10 @@ 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: 0.0623
-- Precision: 0.9317
-- Recall: 0.9507
-- F1: 0.9411
+- Loss: 0.0607
+- Precision: 0.9350
+- Recall: 0.9495
+- F1: 0.9422
 - Accuracy: 0.9866
 
 ## Model description
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.088         | 1.0   | 1756 | 0.0712          | 0.9107    | 0.9290 | 0.9198 | 0.9818   |
-| 0.033         | 2.0   | 3512 | 0.0683          | 0.9238    | 0.9467 | 0.9351 | 0.9856   |
-| 0.0183        | 3.0   | 5268 | 0.0623          | 0.9317    | 0.9507 | 0.9411 | 0.9866   |
+| 0.0909        | 1.0   | 1756 | 0.0701          | 0.9133    | 0.9303 | 0.9217 | 0.9815   |
+| 0.0342        | 2.0   | 3512 | 0.0614          | 0.9262    | 0.9460 | 0.9360 | 0.9858   |
+| 0.0172        | 3.0   | 5268 | 0.0607          | 0.9350    | 0.9495 | 0.9422 | 0.9866   |
 
 
 ### Framework versions