update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9322314049586777
+      value: 0.9331789612967251
     - name: Recall
       type: recall
-      value: 0.9491753618310333
+      value: 0.9495119488387749
     - name: F1
       type: f1
-      value: 0.9406270847231488
+      value: 0.9412746079412746
     - name: Accuracy
       type: accuracy
-      value: 0.9861511744275033
+      value: 0.9867545770294931
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,11 +43,11 @@ 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: 0.0631
-- Precision: 0.9322
-- Recall: 0.9492
-- F1: 0.9406
-- Accuracy: 0.9862
+- Loss: 0.0584
+- Precision: 0.9332
+- Recall: 0.9495
+- F1: 0.9413
+- Accuracy: 0.9868
 
 ## Model description
 
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0889        | 1.0   | 1756 | 0.0640          | 0.9239    | 0.9355 | 0.9297 | 0.9831   |
-| 0.0361        | 2.0   | 3512 | 0.0649          | 0.9251    | 0.9461 | 0.9355 | 0.9849   |
-| 0.0185        | 3.0   | 5268 | 0.0631          | 0.9322    | 0.9492 | 0.9406 | 0.9862   |
+| 0.0861        | 1.0   | 1756 | 0.0718          | 0.9142    | 0.9303 | 0.9222 | 0.9814   |
+| 0.0341        | 2.0   | 3512 | 0.0592          | 0.9359    | 0.9504 | 0.9431 | 0.9867   |
+| 0.018         | 3.0   | 5268 | 0.0584          | 0.9332    | 0.9495 | 0.9413 | 0.9868   |
 
 
 ### Framework versions