Training complete

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9340277777777778
+      value: 0.9348150605407198
     - name: Recall
       type: recall
-      value: 0.9506900033658701
+      value: 0.9485021878155503
     - name: F1
       type: f1
-      value: 0.9422852376980818
+      value: 0.9416088881463537
     - name: Accuracy
       type: accuracy
-      value: 0.9860187201977983
+      value: 0.9860040030611644
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,10 +44,10 @@ 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: 0.0630
-- Precision: 0.9340
-- Recall: 0.9507
-- F1: 0.9423
+- Loss: 0.0650
+- Precision: 0.9348
+- Recall: 0.9485
+- F1: 0.9416
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0764        | 1.0   | 1756 | 0.0631          | 0.9077    | 0.9381 | 0.9226 | 0.9824   |
-| 0.0377        | 2.0   | 3512 | 0.0628          | 0.9327    | 0.9488 | 0.9407 | 0.9853   |
-| 0.0234        | 3.0   | 5268 | 0.0630          | 0.9340    | 0.9507 | 0.9423 | 0.9860   |
+| 0.0743        | 1.0   | 1756 | 0.0605          | 0.9008    | 0.9367 | 0.9184 | 0.9829   |
+| 0.0364        | 2.0   | 3512 | 0.0664          | 0.9300    | 0.9473 | 0.9386 | 0.9850   |
+| 0.0232        | 3.0   | 5268 | 0.0650          | 0.9348    | 0.9485 | 0.9416 | 0.9860   |
 
 
 ### Framework versions