update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9266187050359712
+      value: 0.9264510412051395
     - name: Recall
       type: recall
-      value: 0.9365700861393892
+      value: 0.9356751314464705
     - name: F1
       type: f1
-      value: 0.9315678201847113
+      value: 0.9310402404408081
     - name: Accuracy
       type: accuracy
-      value: 0.9836370279759162
+      value: 0.9835417096922808
 ---
 
 <!-- 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: 0.0620
-- Precision: 0.9266
-- Recall: 0.9366
-- F1: 0.9316
-- Accuracy: 0.9836
+- Loss: 0.0629
+- Precision: 0.9265
+- Recall: 0.9357
+- F1: 0.9310
+- Accuracy: 0.9835
 
 ## Model description
 
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.239         | 1.0   | 878  | 0.0694          | 0.9132    | 0.9199 | 0.9165 | 0.9810   |
-| 0.0531        | 2.0   | 1756 | 0.0618          | 0.9247    | 0.9368 | 0.9307 | 0.9831   |
-| 0.0296        | 3.0   | 2634 | 0.0620          | 0.9266    | 0.9366 | 0.9316 | 0.9836   |
+| 0.2396        | 1.0   | 878  | 0.0706          | 0.9172    | 0.9186 | 0.9179 | 0.9810   |
+| 0.0539        | 2.0   | 1756 | 0.0627          | 0.9264    | 0.9334 | 0.9299 | 0.9831   |
+| 0.03          | 3.0   | 2634 | 0.0629          | 0.9265    | 0.9357 | 0.9310 | 0.9835   |
 
 
 ### Framework versions