Update README.md

README.md

@@ -1,35 +1,25 @@
-<!-- ---
+---
 license: mit
-
 base_model:
 - google-bert/bert-base-cased
 tags:
 - generated_from_trainer
 - finetune
---- -->
-
----
-tags:
-- generated_from_trainer
-- finetune
-model-index:
-- name: fine-tune-sinhala-bert-v2
-  results: []
 datasets:
 - vrclc/dakshina-lexicons-ml
-base_model:
+language:
+- si
+new_version: google-bert/bert-base-cased
+base-model:
 - Ransaka/sinhala-bert-medium-v2
-widget:
+wedget:
 - text: "අපි තමයි [MASK] කරේ."
 - text: "මට හෙට එන්න වෙන්නේ [MASK]."
 - text: "අපි ගෙදර [MASK]."
 - text: 'සිංහල සහ [MASK] අලුත් අවුරුද්ද.'
-license: mit
-language:
-- si
 ---
 
-# sinhala-bert-medium
+# fine-tune-sinhala-bert
 
 This model is pretrained on Sinhala data resources.
 
@@ -55,13 +45,14 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
 - train_batch_size: 64
-- eval_batch_size: 8
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 6
 
 ### Training results
+
 Epoch	Training Loss	Validation Loss
 1	    3.946600	    3.898129
 2	    3.782100	    3.800080
@@ -70,12 +61,9 @@ Epoch	Training Loss	Validation Loss
 5	    3.480900	    3.601913
 6	    3.420000	    3.615573
 
-
-
 ### Framework versions
 
-- Transformers 4.33.3
+- Transformers 4.47.0
 - Pytorch 2.0.0
-- Datasets 2.14.5
-- Tokenizers 0.13.3
-
+- Datasets 3.2.0
+- Tokenizers 0.21.0