update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.932980307794142
+      value: 0.9349917081260365
     - name: Recall
       type: recall
       value: 0.9488387748232918
     - name: F1
       type: f1
-      value: 0.94084272006675
+      value: 0.941864350150351
     - name: Accuracy
       type: accuracy
-      value: 0.9861806087007712
+      value: 0.9863130629304763
 ---
 
 <!-- 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: 0.0620
-- Precision: 0.9330
+- Loss: 0.0596
+- Precision: 0.9350
 - Recall: 0.9488
-- F1: 0.9408
-- Accuracy: 0.9862
+- F1: 0.9419
+- 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 |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0837        | 1.0   | 1756 | 0.0700          | 0.9214    | 0.9347 | 0.9280 | 0.9818   |
-| 0.0324        | 2.0   | 3512 | 0.0643          | 0.9259    | 0.9463 | 0.9360 | 0.9851   |
-| 0.0173        | 3.0   | 5268 | 0.0620          | 0.9330    | 0.9488 | 0.9408 | 0.9862   |
+| 0.0881        | 1.0   | 1756 | 0.0666          | 0.9162    | 0.9342 | 0.9251 | 0.9825   |
+| 0.0332        | 2.0   | 3512 | 0.0608          | 0.9272    | 0.9478 | 0.9374 | 0.9860   |
+| 0.0178        | 3.0   | 5268 | 0.0596          | 0.9350    | 0.9488 | 0.9419 | 0.9863   |
 
 
 ### Framework versions