update model card README.md

README.md

@@ -18,8 +18,8 @@ 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 minds14 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.6444
-- Accuracy: 0.0354
+- Loss: nan
+- Accuracy: 0.1062
 
 ## Model description
 
@@ -53,16 +53,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.8   | 3    | 2.6433          | 0.0442   |
-| No log        | 1.8   | 6    | 2.6440          | 0.0354   |
-| No log        | 2.8   | 9    | 2.6439          | 0.0265   |
-| 3.2318        | 3.8   | 12   | 2.6441          | 0.0265   |
-| 3.2318        | 4.8   | 15   | 2.6444          | 0.0265   |
-| 3.2318        | 5.8   | 18   | 2.6444          | 0.0265   |
-| 3.2331        | 6.8   | 21   | 2.6444          | 0.0265   |
-| 3.2331        | 7.8   | 24   | 2.6444          | 0.0354   |
-| 3.2331        | 8.8   | 27   | 2.6444          | 0.0354   |
-| 3.2342        | 9.8   | 30   | 2.6444          | 0.0354   |
+| No log        | 0.8   | 3    | nan             | 0.1062   |
+| No log        | 1.8   | 6    | nan             | 0.1062   |
+| No log        | 2.8   | 9    | nan             | 0.1062   |
+| 936.7812      | 3.8   | 12   | nan             | 0.1062   |
+| 936.7812      | 4.8   | 15   | nan             | 0.1062   |
+| 936.7812      | 5.8   | 18   | nan             | 0.1062   |
+| 0.0           | 6.8   | 21   | nan             | 0.1062   |
+| 0.0           | 7.8   | 24   | nan             | 0.1062   |
+| 0.0           | 8.8   | 27   | nan             | 0.1062   |
+| 0.0           | 9.8   | 30   | nan             | 0.1062   |
 
 
 ### Framework versions