Model save

README.md

@@ -32,7 +32,7 @@ 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 the audiofolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2750
+- Loss: 0.1647
 - Accuracy: 1.0
 
 ## Model description
@@ -52,7 +52,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
+- learning_rate: 0.0005
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -60,17 +60,17 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.3
+- lr_scheduler_warmup_ratio: 0.5
 - num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.7738        | 0.89  | 2    | 1.3198          | 1.0      |
-| 1.1178        | 1.78  | 4    | 0.5868          | 1.0      |
-| 0.526         | 2.67  | 6    | 0.3511          | 1.0      |
-| 0.2101        | 3.56  | 8    | 0.2750          | 1.0      |
+| 1.7573        | 0.89  | 2    | 1.2997          | 1.0      |
+| 1.0518        | 1.78  | 4    | 0.5840          | 1.0      |
+| 0.4723        | 2.67  | 6    | 0.2595          | 1.0      |
+| 0.1425        | 3.56  | 8    | 0.1647          | 1.0      |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c00edf14b6a4fff451bb302f1e87de0252cc9bf74605cfdedbd615b3c744bc49
+oid sha256:88f42fa3bcb254a3b6cd089dcfdcebfdb1e1a0bfa95ee5121830738aca8dd5cc
 size 378305452