update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.2323943661971831
+      value: 0.21232876712328766
     - name: Recall
       type: recall
-      value: 0.20754716981132076
+      value: 0.1949685534591195
     - name: F1
       type: f1
-      value: 0.21926910299003324
+      value: 0.20327868852459016
     - name: Accuracy
       type: accuracy
-      value: 0.9187922608288144
+      value: 0.9177880431144139
 ---
 
 <!-- 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: 0.3314
-- Precision: 0.2324
-- Recall: 0.2075
-- F1: 0.2193
-- Accuracy: 0.9188
+- Loss: 0.3309
+- Precision: 0.2123
+- Recall: 0.1950
+- F1: 0.2033
+- Accuracy: 0.9178
 
 ## Model description
 
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 100  | 0.3818          | 0.1463    | 0.1132 | 0.1277 | 0.9173   |
-| No log        | 2.0   | 200  | 0.3373          | 0.2148    | 0.1824 | 0.1973 | 0.9189   |
-| No log        | 3.0   | 300  | 0.3314          | 0.2324    | 0.2075 | 0.2193 | 0.9188   |
+| No log        | 1.0   | 100  | 0.3799          | 0.1043    | 0.0755 | 0.0876 | 0.9133   |
+| No log        | 2.0   | 200  | 0.3364          | 0.1608    | 0.1447 | 0.1523 | 0.9177   |
+| No log        | 3.0   | 300  | 0.3309          | 0.2123    | 0.1950 | 0.2033 | 0.9178   |
 
 
 ### Framework versions