End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Ransaka/sinhala-bert-medium-v2](https://huggingface.co/Ransaka/sinhala-bert-medium-v2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1118
-- Accuracy: 0.9736
+- Loss: 0.1610
+- Accuracy: 0.9692
 
 ## Model description
 
@@ -37,22 +37,24 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 0.0002
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.7   | 100  | 0.1270          | 0.9561   |
-| No log        | 1.4   | 200  | 0.1239          | 0.9649   |
-| No log        | 2.1   | 300  | 0.1114          | 0.9719   |
-| No log        | 2.8   | 400  | 0.1118          | 0.9736   |
+| 0.279         | 0.78  | 100  | 0.2297          | 0.9441   |
+| 0.1572        | 1.56  | 200  | 0.1215          | 0.9635   |
+| 0.0823        | 2.34  | 300  | 0.1393          | 0.9635   |
+| 0.0557        | 3.12  | 400  | 0.1206          | 0.9669   |
+| 0.0209        | 3.91  | 500  | 0.1480          | 0.9692   |
+| 0.0059        | 4.69  | 600  | 0.1610          | 0.9692   |
 
 
 ### Framework versions

runs/Dec02_18-06-51_0c1b7c8a2656/events.out.tfevents.1701540412.0c1b7c8a2656.1555.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46e090a672efb088511de33c61af024a63c82198ce714ce7004af5bf77cdf559
-size 6750
+oid sha256:3a6fcd4d0f43f1dbb1180ebd55fc63a1e4b7007a86e57ff12c53898ac1024df5
+size 7584