update model card README.md

README.md

@@ -5,9 +5,36 @@ tags:
 - generated_from_trainer
 datasets:
 - conll2003
+metrics:
+- precision
+- recall
+- f1
+- accuracy
 model-index:
 - name: bert-finetuned-ner
-  results: []
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: conll2003
+      type: conll2003
+      config: conll2003
+      split: validation
+      args: conll2003
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.9374896093100582
+    - name: Recall
+      type: recall
+      value: 0.9490070683271625
+    - name: F1
+      type: f1
+      value: 0.9432131805636865
+    - name: Accuracy
+      type: accuracy
+      value: 0.9873862137989102
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,6 +43,12 @@ should probably proofread and complete it, then remove this comment. -->
 # bert-finetuned-ner
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the conll2003 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0579
+- Precision: 0.9375
+- Recall: 0.9490
+- F1: 0.9432
+- Accuracy: 0.9874
 
 ## Model description
 
@@ -42,6 +75,15 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 3
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0729        | 1.0   | 1756 | 0.0607          | 0.9117    | 0.9366 | 0.9240 | 0.9839   |
+| 0.0361        | 2.0   | 3512 | 0.0538          | 0.9250    | 0.9468 | 0.9358 | 0.9864   |
+| 0.0205        | 3.0   | 5268 | 0.0579          | 0.9375    | 0.9490 | 0.9432 | 0.9874   |
+
+
 ### Framework versions
 
 - Transformers 4.31.0