update model card README.md

README.md

@@ -22,16 +22,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9278202147680726
+      value: 0.9290544285555925
     - name: Recall
       type: recall
       value: 0.9375769101689228
     - name: F1
       type: f1
-      value: 0.9326730469619409
+      value: 0.9332962138084633
     - name: Accuracy
       type: accuracy
-      value: 0.9839706419686403
+      value: 0.9841136193940935
 ---
 
 <!-- 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: 0.0595
-- Precision: 0.9278
+- Loss: 0.0604
+- Precision: 0.9291
 - Recall: 0.9376
-- F1: 0.9327
-- Accuracy: 0.9840
+- F1: 0.9333
+- Accuracy: 0.9841
 
 ## Model description
 
@@ -76,9 +76,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.2414        | 1.0   | 878  | 0.0702          | 0.9143    | 0.9223 | 0.9182 | 0.9808   |
-| 0.0503        | 2.0   | 1756 | 0.0603          | 0.9186    | 0.9337 | 0.9260 | 0.9831   |
-| 0.0306        | 3.0   | 2634 | 0.0595          | 0.9278    | 0.9376 | 0.9327 | 0.9840   |
+| 0.2412        | 1.0   | 878  | 0.0688          | 0.9178    | 0.9246 | 0.9212 | 0.9815   |
+| 0.0514        | 2.0   | 1756 | 0.0608          | 0.9251    | 0.9344 | 0.9298 | 0.9832   |
+| 0.0304        | 3.0   | 2634 | 0.0604          | 0.9291    | 0.9376 | 0.9333 | 0.9841   |
 
 
 ### Framework versions