Training complete

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9317693705600528
+      value: 0.9340277777777778
     - name: Recall
       type: recall
-      value: 0.9491753618310333
+      value: 0.9506900033658701
     - name: F1
       type: f1
-      value: 0.9403918299291371
+      value: 0.9422852376980818
     - name: Accuracy
       type: accuracy
-      value: 0.9865338199799847
+      value: 0.9860187201977983
 ---
 
 <!-- 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: 0.0595
-- Precision: 0.9318
-- Recall: 0.9492
-- F1: 0.9404
-- Accuracy: 0.9865
+- Loss: 0.0630
+- Precision: 0.9340
+- Recall: 0.9507
+- F1: 0.9423
+- Accuracy: 0.9860
 
 ## Model description
 
@@ -79,9 +79,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0757        | 1.0   | 1756 | 0.0603          | 0.9045    | 0.9320 | 0.9180 | 0.9817   |
-| 0.0382        | 2.0   | 3512 | 0.0615          | 0.9334    | 0.9460 | 0.9397 | 0.9854   |
-| 0.0213        | 3.0   | 5268 | 0.0595          | 0.9318    | 0.9492 | 0.9404 | 0.9865   |
+| 0.0764        | 1.0   | 1756 | 0.0631          | 0.9077    | 0.9381 | 0.9226 | 0.9824   |
+| 0.0377        | 2.0   | 3512 | 0.0628          | 0.9327    | 0.9488 | 0.9407 | 0.9853   |
+| 0.0234        | 3.0   | 5268 | 0.0630          | 0.9340    | 0.9507 | 0.9423 | 0.9860   |
 
 
 ### Framework versions