Training complete

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9347898047004303
+      value: 0.9285596436231645
     - name: Recall
       type: recall
-      value: 0.9505217098619994
+      value: 0.9471558397845843
     - name: F1
       type: f1
-      value: 0.9425901201602136
+      value: 0.9377655586103474
     - name: Accuracy
       type: accuracy
-      value: 0.9871813739918761
+      value: 0.9859892859245305
 ---
 
 <!-- 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: 0.0597
-- Precision: 0.9348
-- Recall: 0.9505
-- F1: 0.9426
-- Accuracy: 0.9872
+- Loss: 0.0617
+- Precision: 0.9286
+- Recall: 0.9472
+- F1: 0.9378
+- 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 |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.078         | 1.0   | 1756 | 0.0798          | 0.8891    | 0.9233 | 0.9059 | 0.9789   |
-| 0.035         | 2.0   | 3512 | 0.0640          | 0.9290    | 0.9468 | 0.9378 | 0.9856   |
-| 0.0222        | 3.0   | 5268 | 0.0597          | 0.9348    | 0.9505 | 0.9426 | 0.9872   |
+| 0.0778        | 1.0   | 1756 | 0.0717          | 0.9074    | 0.9337 | 0.9204 | 0.9803   |
+| 0.0347        | 2.0   | 3512 | 0.0705          | 0.9266    | 0.9440 | 0.9352 | 0.9848   |
+| 0.0214        | 3.0   | 5268 | 0.0617          | 0.9286    | 0.9472 | 0.9378 | 0.9860   |
 
 
 ### Framework versions