update model card README.md

README.md

@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [cahya/xlm-roberta-base-indonesian-NER](https://huggingface.co/cahya/xlm-roberta-base-indonesian-NER) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1412
-- Precision: 0.8542
-- Recall: 0.9047
-- F1: 0.8787
-- Accuracy: 0.9589
+- Loss: 0.1480
+- Precision: 0.8193
+- Recall: 0.8765
+- F1: 0.8470
+- Accuracy: 0.9521
 
 ## Model description
 
@@ -53,8 +53,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 120  | 0.1804          | 0.7482    | 0.8497 | 0.7957 | 0.9347   |
-| No log        | 2.0   | 240  | 0.1412          | 0.8542    | 0.9047 | 0.8787 | 0.9589   |
+| No log        | 1.0   | 120  | 0.1731          | 0.7970    | 0.8644 | 0.8294 | 0.9441   |
+| No log        | 2.0   | 240  | 0.1480          | 0.8193    | 0.8765 | 0.8470 | 0.9521   |
 
 
 ### Framework versions