update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9382982252446509
+      value: 0.931799370965072
     - name: Recall
       type: recall
-      value: 0.9520363513968361
+      value: 0.9473241332884551
     - name: F1
       type: f1
-      value: 0.945117366970178
+      value: 0.9394976216306434
     - name: Accuracy
       type: accuracy
-      value: 0.9865485371166186
+      value: 0.9857538117383882
 ---
 
 <!-- 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: 0.0614
-- Precision: 0.9383
-- Recall: 0.9520
-- F1: 0.9451
-- Accuracy: 0.9865
+- Loss: 0.0629
+- Precision: 0.9318
+- Recall: 0.9473
+- F1: 0.9395
+- Accuracy: 0.9858
 
 ## Model description
 
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0896        | 1.0   | 1756 | 0.0665          | 0.9234    | 0.9350 | 0.9292 | 0.9833   |
-| 0.0355        | 2.0   | 3512 | 0.0638          | 0.9292    | 0.9492 | 0.9391 | 0.9858   |
-| 0.0181        | 3.0   | 5268 | 0.0614          | 0.9383    | 0.9520 | 0.9451 | 0.9865   |
+| 0.0872        | 1.0   | 1756 | 0.0716          | 0.9122    | 0.9285 | 0.9203 | 0.9814   |
+| 0.0335        | 2.0   | 3512 | 0.0631          | 0.9257    | 0.9456 | 0.9356 | 0.9854   |
+| 0.0164        | 3.0   | 5268 | 0.0629          | 0.9318    | 0.9473 | 0.9395 | 0.9858   |
 
 
 ### Framework versions