update model card README.md

README.md

@@ -22,16 +22,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9362582781456954
+      value: 0.9317394888705688
     - name: Recall
       type: recall
-      value: 0.9516997643890945
+      value: 0.9510265903736116
     - name: F1
       type: f1
-      value: 0.9439158738107161
+      value: 0.9412842508536686
     - name: Accuracy
       type: accuracy
-      value: 0.9870342026255372
+      value: 0.9865779713898863
 ---
 
 <!-- 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 [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0602
-- Precision: 0.9363
-- Recall: 0.9517
-- F1: 0.9439
-- Accuracy: 0.9870
+- Loss: 0.0603
+- Precision: 0.9317
+- Recall: 0.9510
+- F1: 0.9413
+- Accuracy: 0.9866
 
 ## Model description
 
@@ -76,9 +76,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0892        | 1.0   | 1756 | 0.0628          | 0.9100    | 0.9345 | 0.9221 | 0.9831   |
-| 0.0387        | 2.0   | 3512 | 0.0585          | 0.9370    | 0.9507 | 0.9438 | 0.9869   |
-| 0.0203        | 3.0   | 5268 | 0.0602          | 0.9363    | 0.9517 | 0.9439 | 0.9870   |
+| 0.0872        | 1.0   | 1756 | 0.0660          | 0.9152    | 0.9350 | 0.9250 | 0.9827   |
+| 0.0386        | 2.0   | 3512 | 0.0579          | 0.9374    | 0.9498 | 0.9436 | 0.9864   |
+| 0.0225        | 3.0   | 5268 | 0.0603          | 0.9317    | 0.9510 | 0.9413 | 0.9866   |
 
 
 ### Framework versions