End of training

README.md

@@ -26,16 +26,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.7202368365404949
+      value: 0.7331490537954497
     - name: Recall
       type: recall
-      value: 0.7826286764705882
+      value: 0.7922794117647058
     - name: F1
       type: f1
-      value: 0.750137650038542
+      value: 0.7615681943677526
     - name: Accuracy
       type: accuracy
-      value: 0.9648077333695674
+      value: 0.9655162373585419
 ---
 
 <!-- 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 [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the conll2002 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1386
-- Precision: 0.7202
-- Recall: 0.7826
-- F1: 0.7501
-- Accuracy: 0.9648
+- Loss: 0.1391
+- Precision: 0.7331
+- Recall: 0.7923
+- F1: 0.7616
+- Accuracy: 0.9655
 
 ## Model description
 
@@ -80,8 +80,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.102         | 1.0   | 1041 | 0.1425          | 0.7041    | 0.7551 | 0.7287 | 0.9610   |
-| 0.0665        | 2.0   | 2082 | 0.1386          | 0.7202    | 0.7826 | 0.7501 | 0.9648   |
+| 0.1028        | 1.0   | 1041 | 0.1424          | 0.7051    | 0.7603 | 0.7317 | 0.9618   |
+| 0.0678        | 2.0   | 2082 | 0.1391          | 0.7331    | 0.7923 | 0.7616 | 0.9655   |
 
 
 ### Framework versions

runs/Nov16_01-49-22_9d65af7b14f6/events.out.tfevents.1731721770.9d65af7b14f6.202.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c4557b30a710b20935516fbe9894adc397f27cd7ecac9732659d69fa8995a35
-size 6737
+oid sha256:be924e367d11b9e307234a6b6d38a3aacf3c812aeb67168044b0397a3e708704
+size 7563