update model card README.md

README.md

@@ -22,16 +22,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9372405777851569
+      value: 0.9396951623591783
     - name: Recall
       type: recall
-      value: 0.9500168293503871
+      value: 0.9545607539548974
     - name: F1
       type: f1
-      value: 0.943585457584622
+      value: 0.947069627650693
     - name: Accuracy
       type: accuracy
-      value: 0.9856507917819509
+      value: 0.9872843939483135
 ---
 
 <!-- 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: 0.0645
-- Precision: 0.9372
-- Recall: 0.9500
-- F1: 0.9436
-- Accuracy: 0.9857
+- Loss: 0.0596
+- Precision: 0.9397
+- Recall: 0.9546
+- F1: 0.9471
+- Accuracy: 0.9873
 
 ## Model description
 
@@ -76,9 +76,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0885        | 1.0   | 1756 | 0.0646          | 0.9199    | 0.9396 | 0.9296 | 0.9839   |
-| 0.0399        | 2.0   | 3512 | 0.0611          | 0.9248    | 0.9483 | 0.9364 | 0.9848   |
-| 0.0203        | 3.0   | 5268 | 0.0645          | 0.9372    | 0.9500 | 0.9436 | 0.9857   |
+| 0.0787        | 1.0   | 1756 | 0.0604          | 0.9250    | 0.9418 | 0.9333 | 0.9844   |
+| 0.0318        | 2.0   | 3512 | 0.0578          | 0.9291    | 0.9502 | 0.9395 | 0.9860   |
+| 0.0151        | 3.0   | 5268 | 0.0596          | 0.9397    | 0.9546 | 0.9471 | 0.9873   |
 
 
 ### Framework versions