update model card README.md

README.md

@@ -13,8 +13,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Harveenchadha/vakyansh-wav2vec2-bengali-bnm-200](https://huggingface.co/Harveenchadha/vakyansh-wav2vec2-bengali-bnm-200) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 151.2085
-- Wer: 0.4699
+- Loss: 157.8652
+- Wer: 0.4507
 
 ## Model description
 
@@ -40,17 +40,21 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 1000
-- num_epochs: 35
+- num_epochs: 60
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 2598.842      | 7.46  | 500  | 241.7446        | 0.6716 |
-| 421.6865      | 14.93 | 1000 | 157.1855        | 0.5365 |
-| 251.789       | 22.39 | 1500 | 153.7565        | 0.5045 |
-| 160.1666      | 29.85 | 2000 | 151.2085        | 0.4699 |
+| 2601.5363     | 7.46  | 500  | 259.6630        | 0.6863 |
+| 417.7386      | 14.93 | 1000 | 156.6117        | 0.5275 |
+| 262.9455      | 22.39 | 1500 | 155.0886        | 0.5006 |
+| 178.7715      | 29.85 | 2000 | 155.1077        | 0.4840 |
+| 132.448       | 37.31 | 2500 | 163.8623        | 0.4770 |
+| 116.3943      | 44.78 | 3000 | 161.5531        | 0.4609 |
+| 87.1653       | 52.24 | 3500 | 165.6857        | 0.4597 |
+| 80.5606       | 59.7  | 4000 | 157.8652        | 0.4507 |
 
 
 ### Framework versions