update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9295125164690382
+      value: 0.932077342588002
     - name: Recall
       type: recall
-      value: 0.9498485358465163
+      value: 0.9491753618310333
     - name: F1
       type: f1
-      value: 0.939570501082071
+      value: 0.940548653381139
     - name: Accuracy
       type: accuracy
-      value: 0.9863866486136458
+      value: 0.9859745687878966
 ---
 
 <!-- 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: 0.0618
-- Precision: 0.9295
-- Recall: 0.9498
-- F1: 0.9396
-- Accuracy: 0.9864
+- Loss: 0.0637
+- Precision: 0.9321
+- Recall: 0.9492
+- F1: 0.9405
+- Accuracy: 0.9860
 
 ## Model description
 
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0907        | 1.0   | 1756 | 0.0672          | 0.9137    | 0.9322 | 0.9229 | 0.9822   |
-| 0.0346        | 2.0   | 3512 | 0.0616          | 0.9294    | 0.9487 | 0.9390 | 0.9860   |
-| 0.0181        | 3.0   | 5268 | 0.0618          | 0.9295    | 0.9498 | 0.9396 | 0.9864   |
+| 0.0887        | 1.0   | 1756 | 0.0657          | 0.9155    | 0.9322 | 0.9238 | 0.9819   |
+| 0.0334        | 2.0   | 3512 | 0.0653          | 0.9263    | 0.9470 | 0.9365 | 0.9855   |
+| 0.0179        | 3.0   | 5268 | 0.0637          | 0.9321    | 0.9492 | 0.9405 | 0.9860   |
 
 
 ### Framework versions