update model card README.md

README.md

@@ -22,16 +22,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9347249834327369
+      value: 0.9323407775020678
     - name: Recall
       type: recall
-      value: 0.9495119488387749
+      value: 0.9485021878155503
     - name: F1
       type: f1
-      value: 0.942060444147604
+      value: 0.9403520480520563
     - name: Accuracy
       type: accuracy
-      value: 0.9860775887443339
+      value: 0.9859304173779949
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -42,10 +42,10 @@ 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: 0.0624
-- Precision: 0.9347
-- Recall: 0.9495
-- F1: 0.9421
-- Accuracy: 0.9861
+- Precision: 0.9323
+- Recall: 0.9485
+- F1: 0.9404
+- Accuracy: 0.9859
 
 ## Model description
 
@@ -76,9 +76,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0837        | 1.0   | 1756 | 0.0636          | 0.9211    | 0.9367 | 0.9288 | 0.9832   |
-| 0.0385        | 2.0   | 3512 | 0.0597          | 0.9260    | 0.9460 | 0.9359 | 0.9854   |
-| 0.0196        | 3.0   | 5268 | 0.0624          | 0.9347    | 0.9495 | 0.9421 | 0.9861   |
+| 0.087         | 1.0   | 1756 | 0.0696          | 0.9183    | 0.9406 | 0.9293 | 0.9832   |
+| 0.0378        | 2.0   | 3512 | 0.0564          | 0.9355    | 0.9502 | 0.9428 | 0.9863   |
+| 0.0194        | 3.0   | 5268 | 0.0624          | 0.9323    | 0.9485 | 0.9404 | 0.9859   |
 
 
 ### Framework versions