update model card README.md

README.md

@@ -22,16 +22,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9248478140564471
+      value: 0.9273854328093868
     - name: Recall
       type: recall
-      value: 0.9347801767535519
+      value: 0.9372413021590782
     - name: F1
       type: f1
-      value: 0.9297874707911427
+      value: 0.9322873198686918
     - name: Accuracy
       type: accuracy
-      value: 0.983509936931069
+      value: 0.9840341874910639
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -41,11 +41,11 @@ 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: 0.9248
-- Recall: 0.9348
-- F1: 0.9298
-- Accuracy: 0.9835
+- Loss: 0.0599
+- Precision: 0.9274
+- Recall: 0.9372
+- F1: 0.9323
+- Accuracy: 0.9840
 
 ## Model description
 
@@ -76,9 +76,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.2438        | 1.0   | 878  | 0.0729          | 0.9100    | 0.9201 | 0.9151 | 0.9802   |
-| 0.0519        | 2.0   | 1756 | 0.0626          | 0.9162    | 0.9305 | 0.9233 | 0.9823   |
-| 0.0314        | 3.0   | 2634 | 0.0610          | 0.9248    | 0.9348 | 0.9298 | 0.9835   |
+| 0.2378        | 1.0   | 878  | 0.0719          | 0.9107    | 0.9200 | 0.9154 | 0.9801   |
+| 0.0509        | 2.0   | 1756 | 0.0620          | 0.9156    | 0.9311 | 0.9233 | 0.9821   |
+| 0.0307        | 3.0   | 2634 | 0.0599          | 0.9274    | 0.9372 | 0.9323 | 0.9840   |
 
 
 ### Framework versions