update model card README.md

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: indobenchmark/indobert-base-p2
+base_model: indobenchmark/indobert-large-p2
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Indonesian-LegalBERT-lite
 
-This model is a fine-tuned version of [indobenchmark/indobert-base-p2](https://huggingface.co/indobenchmark/indobert-base-p2) on an unknown dataset.
+This model is a fine-tuned version of [indobenchmark/indobert-large-p2](https://huggingface.co/indobenchmark/indobert-large-p2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7597
+- Loss: 1.0589
 
 ## Model description
 
@@ -40,13 +40,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.1802        | 1.0   | 5866 | 1.7617          |
+| 1.8363        | 1.0   | 2870 | 1.1978          |
+| 1.2286        | 2.0   | 5740 | 1.0848          |
+| 1.1488        | 3.0   | 8610 | 1.0526          |
 
 
 ### Framework versions