Training complete

README.md

@@ -26,16 +26,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9367949568679496
+      value: 0.9337190082644629
     - name: Recall
       type: recall
-      value: 0.9503534163581285
+      value: 0.9506900033658701
     - name: F1
       type: f1
-      value: 0.9435254803675855
+      value: 0.9421280853902602
     - name: Accuracy
       type: accuracy
-      value: 0.9859304173779949
+      value: 0.9864602342968152
 ---
 
 <!-- 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: 0.0632
-- Precision: 0.9368
-- Recall: 0.9504
-- F1: 0.9435
-- Accuracy: 0.9859
+- Loss: 0.0628
+- Precision: 0.9337
+- Recall: 0.9507
+- F1: 0.9421
+- Accuracy: 0.9865
 
 ## Model description
 
@@ -80,9 +80,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0764        | 1.0   | 1756 | 0.0685          | 0.9089    | 0.9347 | 0.9216 | 0.9810   |
-| 0.034         | 2.0   | 3512 | 0.0657          | 0.9282    | 0.9465 | 0.9373 | 0.9850   |
-| 0.0211        | 3.0   | 5268 | 0.0632          | 0.9368    | 0.9504 | 0.9435 | 0.9859   |
+| 0.0773        | 1.0   | 1756 | 0.0695          | 0.9043    | 0.9302 | 0.9170 | 0.9808   |
+| 0.0351        | 2.0   | 3512 | 0.0662          | 0.9337    | 0.9455 | 0.9395 | 0.9855   |
+| 0.0225        | 3.0   | 5268 | 0.0628          | 0.9337    | 0.9507 | 0.9421 | 0.9865   |
 
 
 ### Framework versions