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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9906
-- Accuracy: 0.0
+- Loss: 1.8769
+- Accuracy: 0.625
 
 ## Model description
 
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 1    | 1.9906          | 0.0      |
-| No log        | 2.0   | 2    | 1.9750          | 0.0      |
-| No log        | 3.0   | 3    | 1.9612          | 0.0      |
-| No log        | 4.0   | 4    | 1.9507          | 0.0      |
-| No log        | 5.0   | 5    | 1.9448          | 0.0      |
+| No log        | 1.0   | 1    | 1.9637          | 0.0417   |
+| No log        | 2.0   | 2    | 1.9137          | 0.4167   |
+| No log        | 3.0   | 3    | 1.8769          | 0.625    |
+| No log        | 4.0   | 4    | 1.8548          | 0.625    |
+| No log        | 5.0   | 5    | 1.8428          | 0.625    |
 
 
 ### Framework versions
 
 - Transformers 4.20.1
-- Pytorch 1.11.0+cu113
+- Pytorch 1.11.0+cu102
 - Datasets 2.3.2
 - Tokenizers 0.12.1