update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.929726162982514
+      value: 0.937448149991704
     - name: Recall
       type: recall
-      value: 0.9485021878155503
+      value: 0.9508582968697409
     - name: F1
       type: f1
-      value: 0.939020326557814
+      value: 0.9441056061492189
     - name: Accuracy
       type: accuracy
-      value: 0.9867398598928593
+      value: 0.9864308000235474
 ---
 
 <!-- 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: 0.0589
-- Precision: 0.9297
-- Recall: 0.9485
-- F1: 0.9390
-- Accuracy: 0.9867
+- Loss: 0.0614
+- Precision: 0.9374
+- Recall: 0.9509
+- F1: 0.9441
+- Accuracy: 0.9864
 
 ## Model description
 
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0878        | 1.0   | 1756 | 0.0769          | 0.9169    | 0.9281 | 0.9225 | 0.9807   |
-| 0.0335        | 2.0   | 3512 | 0.0612          | 0.9266    | 0.9472 | 0.9368 | 0.9859   |
-| 0.0172        | 3.0   | 5268 | 0.0589          | 0.9297    | 0.9485 | 0.9390 | 0.9867   |
+| 0.089         | 1.0   | 1756 | 0.0749          | 0.9104    | 0.9280 | 0.9191 | 0.9812   |
+| 0.0331        | 2.0   | 3512 | 0.0614          | 0.9299    | 0.9470 | 0.9384 | 0.9858   |
+| 0.0169        | 3.0   | 5268 | 0.0614          | 0.9374    | 0.9509 | 0.9441 | 0.9864   |
 
 
 ### Framework versions