Training complete

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9308072487644151
+      value: 0.9299373557533795
     - name: Recall
       type: recall
-      value: 0.9508582968697409
+      value: 0.9493436553349041
     - name: F1
       type: f1
-      value: 0.9407259407259407
+      value: 0.9395403064623584
     - name: Accuracy
       type: accuracy
-      value: 0.9862394772473068
+      value: 0.9863130629304763
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -45,10 +45,10 @@ 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: nan
-- Precision: 0.9308
-- Recall: 0.9509
-- F1: 0.9407
-- Accuracy: 0.9862
+- Precision: 0.9299
+- Recall: 0.9493
+- F1: 0.9395
+- Accuracy: 0.9863
 
 ## Model description
 
@@ -79,9 +79,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.2131        | 1.0   | 878  | nan             | 0.9124    | 0.9379 | 0.9250 | 0.9824   |
-| 0.0444        | 2.0   | 1756 | nan             | 0.9316    | 0.9488 | 0.9401 | 0.9861   |
-| 0.0244        | 3.0   | 2634 | nan             | 0.9308    | 0.9509 | 0.9407 | 0.9862   |
+| 0.2268        | 1.0   | 878  | nan             | 0.9016    | 0.9362 | 0.9186 | 0.9820   |
+| 0.0462        | 2.0   | 1756 | nan             | 0.9283    | 0.9482 | 0.9381 | 0.9860   |
+| 0.0248        | 3.0   | 2634 | nan             | 0.9299    | 0.9493 | 0.9395 | 0.9863   |
 
 
 ### Framework versions