update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.8561754272815221
+      value: 0.8585940019348597
     - name: Recall
       type: recall
-      value: 0.8936385055536856
+      value: 0.8961629081117469
     - name: F1
       type: f1
-      value: 0.8745059288537548
+      value: 0.8769762845849803
     - name: Accuracy
       type: accuracy
-      value: 0.9760641784131923
+      value: 0.9764312118219713
 ---
 
 <!-- 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 [klue/bert-base](https://huggingface.co/klue/bert-base) on the conll2003 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0956
-- Precision: 0.8562
-- Recall: 0.8936
-- F1: 0.8745
-- Accuracy: 0.9761
+- Loss: 0.0967
+- Precision: 0.8586
+- Recall: 0.8962
+- F1: 0.8770
+- Accuracy: 0.9764
 
 ## Model description
 
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.1327        | 1.0   | 1756 | 0.0986          | 0.8001    | 0.8563 | 0.8272 | 0.9688   |
-| 0.0647        | 2.0   | 3512 | 0.0953          | 0.8533    | 0.8928 | 0.8726 | 0.9751   |
-| 0.0378        | 3.0   | 5268 | 0.0956          | 0.8562    | 0.8936 | 0.8745 | 0.9761   |
+| 0.1317        | 1.0   | 1756 | 0.1035          | 0.7946    | 0.8516 | 0.8221 | 0.9679   |
+| 0.0648        | 2.0   | 3512 | 0.0943          | 0.8420    | 0.8879 | 0.8644 | 0.9751   |
+| 0.0381        | 3.0   | 5268 | 0.0967          | 0.8586    | 0.8962 | 0.8770 | 0.9764   |
 
 
 ### Framework versions