End of training

README.md

@@ -18,7 +18,7 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: nan
-- Accuracy: 0.0708
+- Accuracy: 0.0885
 
 ## Model description
 
@@ -52,14 +52,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.8   | 3    | nan             | 0.0708   |
-| No log        | 1.87  | 7    | nan             | 0.0708   |
-| 241.9899      | 2.93  | 11   | nan             | 0.0708   |
-| 241.9899      | 4.0   | 15   | nan             | 0.0708   |
-| 241.9899      | 4.8   | 18   | nan             | 0.0708   |
-| 0.0           | 5.87  | 22   | nan             | 0.0708   |
-| 0.0           | 6.93  | 26   | nan             | 0.0708   |
-| 0.0           | 8.0   | 30   | nan             | 0.0708   |
+| No log        | 0.8   | 3    | nan             | 0.0885   |
+| No log        | 1.87  | 7    | nan             | 0.0885   |
+| 241.3901      | 2.93  | 11   | nan             | 0.0885   |
+| 241.3901      | 4.0   | 15   | nan             | 0.0885   |
+| 241.3901      | 4.8   | 18   | nan             | 0.0885   |
+| 0.0           | 5.87  | 22   | nan             | 0.0885   |
+| 0.0           | 6.93  | 26   | nan             | 0.0885   |
+| 0.0           | 8.0   | 30   | nan             | 0.0885   |
 
 
 ### Framework versions