update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.932035631804685
+      value: 0.9341366787718719
     - name: Recall
       type: recall
-      value: 0.9508582968697409
+      value: 0.9523729384045776
     - name: F1
       type: f1
-      value: 0.9413528823725424
+      value: 0.9431666666666666
     - name: Accuracy
       type: accuracy
-      value: 0.9866368399364219
+      value: 0.9866221227997881
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,10 +43,10 @@ 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: 0.0627
-- Precision: 0.9320
-- Recall: 0.9509
-- F1: 0.9414
+- Loss: 0.0605
+- Precision: 0.9341
+- Recall: 0.9524
+- 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 |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.088         | 1.0   | 1756 | 0.0655          | 0.9181    | 0.9344 | 0.9262 | 0.9823   |
-| 0.0338        | 2.0   | 3512 | 0.0620          | 0.9248    | 0.9477 | 0.9361 | 0.9857   |
-| 0.0185        | 3.0   | 5268 | 0.0627          | 0.9320    | 0.9509 | 0.9414 | 0.9866   |
+| 0.0883        | 1.0   | 1756 | 0.0719          | 0.9152    | 0.9330 | 0.924  | 0.9818   |
+| 0.0325        | 2.0   | 3512 | 0.0657          | 0.9290    | 0.9472 | 0.938  | 0.9855   |
+| 0.0169        | 3.0   | 5268 | 0.0605          | 0.9341    | 0.9524 | 0.9432 | 0.9866   |
 
 
 ### Framework versions