update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9328259430840503
+      value: 0.9432576769025367
     - name: Recall
       type: recall
-      value: 0.9488387748232918
+      value: 0.9511948838774823
     - name: F1
       type: f1
-      value: 0.9407642249290838
+      value: 0.947209653092006
     - name: Accuracy
       type: accuracy
-      value: 0.986342497203744
+      value: 0.9913165375180094
 ---
 
 <!-- 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: 0.0290
-- Precision: 0.9328
-- Recall: 0.9488
-- F1: 0.9408
-- Accuracy: 0.9863
+- Loss: 0.0137
+- Precision: 0.9433
+- Recall: 0.9512
+- F1: 0.9472
+- Accuracy: 0.9913
 
 ## Model description
 
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0406        | 1.0   | 1756 | 0.0323          | 0.9111    | 0.9352 | 0.9230 | 0.9823   |
-| 0.015         | 2.0   | 3512 | 0.0293          | 0.9250    | 0.9448 | 0.9348 | 0.9856   |
-| 0.0074        | 3.0   | 5268 | 0.0290          | 0.9328    | 0.9488 | 0.9408 | 0.9863   |
+| 0.0179        | 1.0   | 1756 | 0.0141          | 0.9337    | 0.9416 | 0.9377 | 0.9901   |
+| 0.0071        | 2.0   | 3512 | 0.0135          | 0.9442    | 0.9512 | 0.9477 | 0.9915   |
+| 0.0036        | 3.0   | 5268 | 0.0137          | 0.9433    | 0.9512 | 0.9472 | 0.9913   |
 
 
 ### Framework versions