update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9356550580431178
+      value: 0.9352970378950852
     - name: Recall
       type: recall
-      value: 0.9495119488387749
+      value: 0.9511948838774823
     - name: F1
       type: f1
-      value: 0.9425325760106917
+      value: 0.9431789737171463
     - name: Accuracy
       type: accuracy
-      value: 0.9868723141225643
+      value: 0.9866368399364219
 ---
 
 <!-- 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: 0.0611
-- Precision: 0.9357
-- Recall: 0.9495
-- F1: 0.9425
-- Accuracy: 0.9869
+- Loss: 0.0612
+- Precision: 0.9353
+- Recall: 0.9512
+- F1: 0.9432
+- Accuracy: 0.9866
 
 ## Model description
 
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0863        | 1.0   | 1756 | 0.0689          | 0.9170    | 0.9318 | 0.9244 | 0.9822   |
-| 0.0335        | 2.0   | 3512 | 0.0602          | 0.9360    | 0.9497 | 0.9428 | 0.9867   |
-| 0.0181        | 3.0   | 5268 | 0.0611          | 0.9357    | 0.9495 | 0.9425 | 0.9869   |
+| 0.0876        | 1.0   | 1756 | 0.0698          | 0.9163    | 0.9307 | 0.9234 | 0.9817   |
+| 0.0347        | 2.0   | 3512 | 0.0643          | 0.9253    | 0.9478 | 0.9364 | 0.9857   |
+| 0.0191        | 3.0   | 5268 | 0.0612          | 0.9353    | 0.9512 | 0.9432 | 0.9866   |
 
 
 ### Framework versions