Training complete

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9330024813895782
+      value: 0.935206611570248
     - name: Recall
       type: recall
-      value: 0.9491753618310333
+      value: 0.9522046449007069
     - name: F1
       type: f1
-      value: 0.9410194377242012
+      value: 0.9436290860573716
     - name: Accuracy
       type: accuracy
-      value: 0.9862541943839407
+      value: 0.9870636368988049
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,11 +44,11 @@ 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: 0.0604
-- Precision: 0.9330
-- Recall: 0.9492
-- F1: 0.9410
-- Accuracy: 0.9863
+- Loss: 0.0603
+- Precision: 0.9352
+- Recall: 0.9522
+- F1: 0.9436
+- Accuracy: 0.9871
 
 ## Model description
 
@@ -79,9 +79,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0765        | 1.0   | 1756 | 0.0666          | 0.9061    | 0.9367 | 0.9211 | 0.9818   |
-| 0.0354        | 2.0   | 3512 | 0.0634          | 0.9262    | 0.9440 | 0.9350 | 0.9845   |
-| 0.0219        | 3.0   | 5268 | 0.0604          | 0.9330    | 0.9492 | 0.9410 | 0.9863   |
+| 0.0757        | 1.0   | 1756 | 0.0642          | 0.9021    | 0.9323 | 0.9170 | 0.9818   |
+| 0.034         | 2.0   | 3512 | 0.0650          | 0.9274    | 0.9438 | 0.9355 | 0.9852   |
+| 0.0203        | 3.0   | 5268 | 0.0603          | 0.9352    | 0.9522 | 0.9436 | 0.9871   |
 
 
 ### Framework versions