Training complete

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.935206611570248
+      value: 0.9336312479311486
     - name: Recall
       type: recall
-      value: 0.9522046449007069
+      value: 0.9493436553349041
     - name: F1
       type: f1
-      value: 0.9436290860573716
+      value: 0.9414218958611482
     - name: Accuracy
       type: accuracy
-      value: 0.9865926885265203
+      value: 0.9860923058809677
 ---
 
 <!-- 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: 0.0685
-- Precision: 0.9352
-- Recall: 0.9522
-- F1: 0.9436
-- Accuracy: 0.9866
+- Loss: 0.0607
+- Precision: 0.9336
+- Recall: 0.9493
+- F1: 0.9414
+- Accuracy: 0.9861
 
 ## Model description
 
@@ -79,9 +79,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0307        | 1.0   | 1756 | 0.0818          | 0.9220    | 0.9396 | 0.9307 | 0.9822   |
-| 0.0239        | 2.0   | 3512 | 0.0638          | 0.9287    | 0.9510 | 0.9397 | 0.9865   |
-| 0.0133        | 3.0   | 5268 | 0.0685          | 0.9352    | 0.9522 | 0.9436 | 0.9866   |
+| 0.0782        | 1.0   | 1756 | 0.0823          | 0.9064    | 0.9323 | 0.9192 | 0.9789   |
+| 0.0413        | 2.0   | 3512 | 0.0567          | 0.9285    | 0.9490 | 0.9387 | 0.9854   |
+| 0.0257        | 3.0   | 5268 | 0.0607          | 0.9336    | 0.9493 | 0.9414 | 0.9861   |
 
 
 ### Framework versions