update model card README.md

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [ai4bharat/indic-bert](https://huggingface.co/ai4bharat/indic-bert) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7472
+- Loss: 1.5324
 
 ## Model description
 
@@ -39,20 +39,23 @@ 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: 7
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 1.9853        | 1.0   | 3953  | 2.1213          |
-| 1.933         | 2.0   | 7906  | 1.9938          |
-| 1.8421        | 3.0   | 11859 | 1.9033          |
-| 1.783         | 4.0   | 15812 | 1.8523          |
-| 1.7702        | 5.0   | 19765 | 1.7833          |
-| 1.7579        | 6.0   | 23718 | 1.7677          |
-| 1.7167        | 7.0   | 27671 | 1.7393          |
+| 1.5835        | 1.0   | 3953  | 1.7985          |
+| 1.6098        | 2.0   | 7906  | 1.7434          |
+| 1.5266        | 3.0   | 11859 | 1.6934          |
+| 1.5179        | 4.0   | 15812 | 1.6665          |
+| 1.5459        | 5.0   | 19765 | 1.6135          |
+| 1.5511        | 6.0   | 23718 | 1.6002          |
+| 1.5209        | 7.0   | 27671 | 1.5657          |
+| 1.5413        | 8.0   | 31624 | 1.5578          |
+| 1.4828        | 9.0   | 35577 | 1.5465          |
+| 1.4651        | 10.0  | 39530 | 1.5451          |
 
 
 ### Framework versions