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: 0.6940
-- Accuracy: 0.5357
+- Loss: 0.7024
+- Accuracy: 0.2857
 
 ## Model description
 
@@ -45,16 +45,16 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 400
+- training_steps: 100
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 100.0 | 100  | 0.6943          | 0.4286   |
-| No log        | 200.0 | 200  | 0.6905          | 0.5      |
-| No log        | 300.0 | 300  | 0.6939          | 0.5714   |
-| No log        | 400.0 | 400  | 0.6940          | 0.5357   |
+| No log        | 25.0  | 25   | 0.7054          | 0.3214   |
+| No log        | 50.0  | 50   | 0.7030          | 0.3214   |
+| No log        | 75.0  | 75   | 0.7025          | 0.2857   |
+| No log        | 100.0 | 100  | 0.7024          | 0.2857   |
 
 
 ### Framework versions