Training complete

README.md

@@ -26,16 +26,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9376037172253567
+      value: 0.9401794616151545
     - name: Recall
       type: recall
-      value: 0.9508582968697409
+      value: 0.9522046449007069
     - name: F1
       type: f1
-      value: 0.9441844919786097
+      value: 0.9461538461538462
     - name: Accuracy
       type: accuracy
-      value: 0.9868575969859305
+      value: 0.9871225054453405
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -45,11 +45,11 @@ 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: 0.0593
-- Precision: 0.9376
-- Recall: 0.9509
-- F1: 0.9442
-- Accuracy: 0.9869
+- Loss: 0.0603
+- Precision: 0.9402
+- Recall: 0.9522
+- F1: 0.9462
+- Accuracy: 0.9871
 
 ## Model description
 
@@ -80,9 +80,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0784        | 1.0   | 1756 | 0.0595          | 0.9189    | 0.9376 | 0.9281 | 0.9833   |
-| 0.0361        | 2.0   | 3512 | 0.0692          | 0.9298    | 0.9455 | 0.9376 | 0.9852   |
-| 0.0217        | 3.0   | 5268 | 0.0593          | 0.9376    | 0.9509 | 0.9442 | 0.9869   |
+| 0.0801        | 1.0   | 1756 | 0.0681          | 0.9112    | 0.9325 | 0.9217 | 0.9817   |
+| 0.0371        | 2.0   | 3512 | 0.0647          | 0.9340    | 0.9483 | 0.9411 | 0.9863   |
+| 0.0207        | 3.0   | 5268 | 0.0603          | 0.9402    | 0.9522 | 0.9462 | 0.9871   |
 
 
 ### Framework versions