update model card README.md

README.md

@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Sameen53/facebook_large_CV_bn3](https://huggingface.co/Sameen53/facebook_large_CV_bn3) on the common_voice dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2655
-- Wer: 0.2402
+- Loss: 0.1780
+- Wer: 0.2315
 
 ## Model description
 
@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 5e-06
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
@@ -51,12 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| No log        | 0.87  | 1000 | 0.2746          | 0.2451 |
-| 0.1547        | 1.73  | 2000 | 0.2351          | 0.2386 |
-| 0.1684        | 2.6   | 3000 | 0.2335          | 0.2311 |
-| 0.1721        | 3.47  | 4000 | 0.2073          | 0.2314 |
-| 0.187         | 4.33  | 5000 | 0.1984          | 0.2349 |
-| 0.2468        | 5.2   | 6000 | 0.2655          | 0.2402 |
+| 0.1588        | 1.3   | 1500 | 0.2097          | 0.2315 |
+| 0.2126        | 2.6   | 3000 | 0.1941          | 0.2310 |
+| 0.2242        | 3.9   | 4500 | 0.1834          | 0.2307 |
+| 0.2303        | 5.2   | 6000 | 0.1780          | 0.2315 |
 
 
 ### Framework versions