Training complete

README.md

@@ -35,7 +35,7 @@ model-index:
       value: 0.9415692821368947
     - name: Accuracy
       type: accuracy
-      value: 0.9860923058809677
+      value: 0.9861511744275033
 ---
 
 <!-- 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: 0.0623
+- Loss: 0.0614
 - Precision: 0.9341
 - Recall: 0.9492
 - F1: 0.9416
-- Accuracy: 0.9861
+- Accuracy: 0.9862
 
 ## Model description
 
@@ -80,9 +80,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0765        | 1.0   | 1756 | 0.0667          | 0.9050    | 0.9334 | 0.9190 | 0.9803   |
-| 0.0356        | 2.0   | 3512 | 0.0690          | 0.9283    | 0.9438 | 0.9360 | 0.9846   |
-| 0.0222        | 3.0   | 5268 | 0.0623          | 0.9341    | 0.9492 | 0.9416 | 0.9861   |
+| 0.0761        | 1.0   | 1756 | 0.0618          | 0.9039    | 0.9372 | 0.9203 | 0.9829   |
+| 0.036         | 2.0   | 3512 | 0.0732          | 0.9228    | 0.9418 | 0.9322 | 0.9841   |
+| 0.0228        | 3.0   | 5268 | 0.0614          | 0.9341    | 0.9492 | 0.9416 | 0.9862   |
 
 
 ### Framework versions

runs/Sep11_08-38-28_65a578b1399b/events.out.tfevents.1726043910.65a578b1399b.1798.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:743b4e4aba6c955aaca604d8ce82ec4e60cb468bf2e2ee6bc520378a40893a6b
-size 8295
+oid sha256:23fb0ba4f17f15ae40c30f90328031ab7325741a8a16f7e38537f834bd199123
+size 9121