update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9337967560410461
+      value: 0.928983358049102
     - name: Recall
       type: recall
-      value: 0.9495119488387749
+      value: 0.9488387748232918
     - name: F1
       type: f1
-      value: 0.941588785046729
+      value: 0.9388060944134544
     - name: Accuracy
       type: accuracy
-      value: 0.9861658915641373
+      value: 0.9858568316948254
 ---
 
 <!-- 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: 0.0637
-- Precision: 0.9338
-- Recall: 0.9495
-- F1: 0.9416
-- Accuracy: 0.9862
+- Loss: 0.0658
+- Precision: 0.9290
+- Recall: 0.9488
+- F1: 0.9388
+- Accuracy: 0.9859
 
 ## Model description
 
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0908        | 1.0   | 1756 | 0.0675          | 0.9165    | 0.9329 | 0.9246 | 0.9819   |
-| 0.0358        | 2.0   | 3512 | 0.0630          | 0.9248    | 0.9463 | 0.9355 | 0.9853   |
-| 0.0171        | 3.0   | 5268 | 0.0637          | 0.9338    | 0.9495 | 0.9416 | 0.9862   |
+| 0.0863        | 1.0   | 1756 | 0.0697          | 0.9110    | 0.9317 | 0.9212 | 0.9815   |
+| 0.0327        | 2.0   | 3512 | 0.0690          | 0.9297    | 0.9482 | 0.9388 | 0.9858   |
+| 0.0164        | 3.0   | 5268 | 0.0658          | 0.9290    | 0.9488 | 0.9388 | 0.9859   |
 
 
 ### Framework versions