update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9307273626917367
+      value: 0.9339607066204392
     - name: Recall
       type: recall
-      value: 0.9496802423426456
+      value: 0.9520363513968361
     - name: F1
       type: f1
-      value: 0.9401082882132445
+      value: 0.9429119093257772
     - name: Accuracy
       type: accuracy
-      value: 0.9865779713898863
+      value: 0.9870636368988049
 ---
 
 <!-- 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: 0.0591
-- Precision: 0.9307
-- Recall: 0.9497
-- F1: 0.9401
-- Accuracy: 0.9866
+- Loss: 0.0599
+- Precision: 0.9340
+- Recall: 0.9520
+- F1: 0.9429
+- Accuracy: 0.9871
 
 ## Model description
 
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0866        | 1.0   | 1756 | 0.0741          | 0.9203    | 0.9312 | 0.9257 | 0.9814   |
-| 0.0331        | 2.0   | 3512 | 0.0645          | 0.9286    | 0.9473 | 0.9379 | 0.9855   |
-| 0.018         | 3.0   | 5268 | 0.0591          | 0.9307    | 0.9497 | 0.9401 | 0.9866   |
+| 0.0894        | 1.0   | 1756 | 0.0696          | 0.9194    | 0.9332 | 0.9263 | 0.9821   |
+| 0.0344        | 2.0   | 3512 | 0.0658          | 0.9276    | 0.9493 | 0.9384 | 0.9856   |
+| 0.0177        | 3.0   | 5268 | 0.0599          | 0.9340    | 0.9520 | 0.9429 | 0.9871   |
 
 
 ### Framework versions