update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9312675127740234
+      value: 0.9366127434796963
     - name: Recall
       type: recall
-      value: 0.9508582968697409
+      value: 0.9548973409626389
     - name: F1
       type: f1
-      value: 0.9409609459571988
+      value: 0.9456666666666668
     - name: Accuracy
       type: accuracy
-      value: 0.9866368399364219
+      value: 0.9875198681344558
 ---
 
 <!-- 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: 0.0598
-- Precision: 0.9313
-- Recall: 0.9509
-- F1: 0.9410
-- Accuracy: 0.9866
+- Loss: 0.0611
+- Precision: 0.9366
+- Recall: 0.9549
+- F1: 0.9457
+- Accuracy: 0.9875
 
 ## Model description
 
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0888        | 1.0   | 1756 | 0.0651          | 0.9107    | 0.9323 | 0.9214 | 0.9822   |
-| 0.0339        | 2.0   | 3512 | 0.0597          | 0.9315    | 0.9500 | 0.9407 | 0.9864   |
-| 0.0175        | 3.0   | 5268 | 0.0598          | 0.9313    | 0.9509 | 0.9410 | 0.9866   |
+| 0.089         | 1.0   | 1756 | 0.0596          | 0.9187    | 0.9409 | 0.9297 | 0.9836   |
+| 0.0346        | 2.0   | 3512 | 0.0614          | 0.9351    | 0.9522 | 0.9436 | 0.9864   |
+| 0.0174        | 3.0   | 5268 | 0.0611          | 0.9366    | 0.9549 | 0.9457 | 0.9875   |
 
 
 ### Framework versions