update model card README.md

README.md

@@ -14,8 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [scasutt/Prototype_training](https://huggingface.co/scasutt/Prototype_training) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7453
-- Wer: 0.7479
+- Loss: 0.6499
+- Wer: 0.6750
 
 ## Model description
 
@@ -47,11 +47,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 5.7276        | 0.74  | 100  | 3.2605          | 1.0    |
-| 2.7333        | 1.47  | 200  | 1.4019          | 0.8876 |
-| 1.0542        | 2.21  | 300  | 0.8402          | 0.7491 |
-| 0.9654        | 2.94  | 400  | 0.7722          | 0.7426 |
-| 0.846         | 3.68  | 500  | 0.7453          | 0.7479 |
+| 0.7181        | 0.74  | 100  | 0.6930          | 0.7074 |
+| 0.7046        | 1.47  | 200  | 0.6908          | 0.7231 |
+| 0.6519        | 2.21  | 300  | 0.6871          | 0.6943 |
+| 0.6481        | 2.94  | 400  | 0.6554          | 0.6848 |
+| 0.6087        | 3.68  | 500  | 0.6499          | 0.6750 |
 
 
 ### Framework versions