update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9245303867403315
+      value: 0.9284605146406388
     - name: Recall
       type: recall
-      value: 0.9360107394563151
+      value: 0.9364582168027744
     - name: F1
       type: f1
-      value: 0.9302351436989272
+      value: 0.932442216652743
     - name: Accuracy
       type: accuracy
-      value: 0.9833987322668276
+      value: 0.983668800737128
 ---
 
 <!-- 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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the conll2003 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0610
-- Precision: 0.9245
-- Recall: 0.9360
-- F1: 0.9302
-- Accuracy: 0.9834
+- Loss: 0.0599
+- Precision: 0.9285
+- Recall: 0.9365
+- F1: 0.9324
+- Accuracy: 0.9837
 
 ## Model description
 
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.2422        | 1.0   | 878  | 0.0714          | 0.9125    | 0.9177 | 0.9151 | 0.9805   |
-| 0.0541        | 2.0   | 1756 | 0.0620          | 0.9234    | 0.9334 | 0.9284 | 0.9831   |
-| 0.0305        | 3.0   | 2634 | 0.0610          | 0.9245    | 0.9360 | 0.9302 | 0.9834   |
+| 0.2277        | 1.0   | 878  | 0.0667          | 0.9179    | 0.9218 | 0.9198 | 0.9815   |
+| 0.0527        | 2.0   | 1756 | 0.0594          | 0.9253    | 0.9341 | 0.9297 | 0.9833   |
+| 0.03          | 3.0   | 2634 | 0.0599          | 0.9285    | 0.9365 | 0.9324 | 0.9837   |
 
 
 ### Framework versions