update model card README.md

README.md

@@ -22,16 +22,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9350198412698413
+      value: 0.9343150231634679
     - name: Recall
       type: recall
-      value: 0.9516997643890945
+      value: 0.9503534163581285
     - name: F1
       type: f1
-      value: 0.9432860717264387
+      value: 0.9422659769731353
     - name: Accuracy
       type: accuracy
-      value: 0.9864160828869135
+      value: 0.9865926885265203
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -41,11 +41,11 @@ 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: 0.0584
-- Precision: 0.9350
-- Recall: 0.9517
-- F1: 0.9433
-- Accuracy: 0.9864
+- Loss: 0.0595
+- Precision: 0.9343
+- Recall: 0.9504
+- F1: 0.9423
+- Accuracy: 0.9866
 
 ## Model description
 
@@ -76,9 +76,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0858        | 1.0   | 1756 | 0.0630          | 0.9194    | 0.9371 | 0.9282 | 0.9832   |
-| 0.0334        | 2.0   | 3512 | 0.0634          | 0.9330    | 0.9465 | 0.9397 | 0.9850   |
-| 0.0234        | 3.0   | 5268 | 0.0584          | 0.9350    | 0.9517 | 0.9433 | 0.9864   |
+| 0.0834        | 1.0   | 1756 | 0.0621          | 0.9148    | 0.9381 | 0.9263 | 0.9833   |
+| 0.0321        | 2.0   | 3512 | 0.0615          | 0.9265    | 0.9482 | 0.9372 | 0.9851   |
+| 0.0218        | 3.0   | 5268 | 0.0595          | 0.9343    | 0.9504 | 0.9423 | 0.9866   |
 
 
 ### Framework versions