Training complete

README.md

@@ -26,16 +26,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9328493647912885
+      value: 0.9376244193762442
     - name: Recall
       type: recall
-      value: 0.9515314708852238
+      value: 0.9511948838774823
     - name: F1
       type: f1
-      value: 0.942097808881113
+      value: 0.9443609022556392
     - name: Accuracy
       type: accuracy
-      value: 0.9867398598928593
+      value: 0.9862836286572084
 ---
 
 <!-- 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: 0.0587
-- Precision: 0.9328
-- Recall: 0.9515
-- F1: 0.9421
-- Accuracy: 0.9867
+- Loss: 0.0614
+- Precision: 0.9376
+- Recall: 0.9512
+- F1: 0.9444
+- Accuracy: 0.9863
 
 ## Model description
 
@@ -80,9 +80,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.077         | 1.0   | 1756 | 0.0651          | 0.9058    | 0.9350 | 0.9202 | 0.9815   |
-| 0.0347        | 2.0   | 3512 | 0.0612          | 0.9281    | 0.9475 | 0.9377 | 0.9856   |
-| 0.0206        | 3.0   | 5268 | 0.0587          | 0.9328    | 0.9515 | 0.9421 | 0.9867   |
+| 0.0754        | 1.0   | 1756 | 0.0645          | 0.9080    | 0.9382 | 0.9229 | 0.9820   |
+| 0.0346        | 2.0   | 3512 | 0.0661          | 0.9279    | 0.9460 | 0.9368 | 0.9846   |
+| 0.0225        | 3.0   | 5268 | 0.0614          | 0.9376    | 0.9512 | 0.9444 | 0.9863   |
 
 
 ### Framework versions