update model card README.md

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2866
-- Accuracy: 0.9146
+- Loss: 1.0848
+- Accuracy: 0.5581
 
 ## Model description
 
@@ -48,11 +48,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.3523        | 1.0   | 78   | 0.4442          | 0.8588   |
-| 0.3353        | 2.0   | 156  | 0.2978          | 0.9090   |
-| 0.3225        | 3.0   | 234  | 0.2732          | 0.9084   |
-| 0.2538        | 4.0   | 312  | 0.2866          | 0.9146   |
-| 0.2321        | 5.0   | 390  | 0.2664          | 0.8890   |
+| 1.1104        | 1.0   | 78   | 1.1484          | 0.1386   |
+| 1.1112        | 2.0   | 156  | 1.1241          | 0.3064   |
+| 1.1004        | 3.0   | 234  | 1.0979          | 0.3064   |
+| 1.0989        | 4.0   | 312  | 1.0848          | 0.5581   |
+| 1.1002        | 5.0   | 390  | 1.0949          | 0.5581   |
 
 
 ### Framework versions