update model card README.md

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9366920782234007
+      value: 0.9345670852610707
     - name: Recall
       type: recall
-      value: 0.9511948838774823
+      value: 0.9518680578929654
     - name: F1
       type: f1
-      value: 0.9438877755511023
+      value: 0.9431382357845589
     - name: Accuracy
       type: accuracy
-      value: 0.9865779713898863
+      value: 0.9866957084829575
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,11 +44,11 @@ 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: 0.0609
-- Precision: 0.9367
-- Recall: 0.9512
-- F1: 0.9439
-- Accuracy: 0.9866
+- Loss: 0.0581
+- Precision: 0.9346
+- Recall: 0.9519
+- F1: 0.9431
+- Accuracy: 0.9867
 
 ## Model description
 
@@ -79,9 +79,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0772        | 1.0   | 1756 | 0.0700          | 0.9129    | 0.9347 | 0.9237 | 0.9815   |
-| 0.043         | 2.0   | 3512 | 0.0574          | 0.9281    | 0.9465 | 0.9372 | 0.9855   |
-| 0.023         | 3.0   | 5268 | 0.0609          | 0.9367    | 0.9512 | 0.9439 | 0.9866   |
+| 0.0786        | 1.0   | 1756 | 0.0778          | 0.9167    | 0.9359 | 0.9262 | 0.9812   |
+| 0.0418        | 2.0   | 3512 | 0.0554          | 0.9270    | 0.9461 | 0.9365 | 0.9860   |
+| 0.0217        | 3.0   | 5268 | 0.0581          | 0.9346    | 0.9519 | 0.9431 | 0.9867   |
 
 
 ### Framework versions