Training complete

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9333112692371339
+      value: 0.9366523321204102
     - name: Recall
       type: recall
-      value: 0.9491753618310333
+      value: 0.9530461124200605
     - name: F1
       type: f1
-      value: 0.9411764705882354
+      value: 0.9447781114447781
     - name: Accuracy
       type: accuracy
-      value: 0.9861070230176017
+      value: 0.986489668570083
 ---
 
 <!-- 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: 0.0624
-- Precision: 0.9333
-- Recall: 0.9492
-- F1: 0.9412
-- Accuracy: 0.9861
+- Loss: 0.0826
+- Precision: 0.9367
+- Recall: 0.9530
+- F1: 0.9448
+- Accuracy: 0.9865
 
 ## Model description
 
@@ -79,9 +79,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.075         | 1.0   | 1756 | 0.0679          | 0.8953    | 0.9307 | 0.9126 | 0.9810   |
-| 0.035         | 2.0   | 3512 | 0.0682          | 0.9284    | 0.9443 | 0.9363 | 0.9842   |
-| 0.0214        | 3.0   | 5268 | 0.0624          | 0.9333    | 0.9492 | 0.9412 | 0.9861   |
+| 0.0161        | 1.0   | 1756 | 0.0801          | 0.9255    | 0.9445 | 0.9349 | 0.9847   |
+| 0.0087        | 2.0   | 3512 | 0.0894          | 0.9366    | 0.9492 | 0.9428 | 0.9855   |
+| 0.0063        | 3.0   | 5268 | 0.0826          | 0.9367    | 0.9530 | 0.9448 | 0.9865   |
 
 
 ### Framework versions