Model save

README.md

@@ -17,7 +17,7 @@ model-index:
       name: audiofolder
       type: audiofolder
       config: default
-      split: train[:80]
+      split: train[:90]
       args: default
     metrics:
     - name: Accuracy
@@ -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: 1.2731
+- Loss: 0.6583
 - 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: 0.0001
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -61,13 +61,16 @@ 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
-- num_epochs: 1
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.6725        | 1.0   | 2    | 1.2731          | 1.0      |
+| 1.781         | 0.89  | 2    | 1.3484          | 1.0      |
+| 1.2752        | 1.78  | 4    | 0.9439          | 1.0      |
+| 0.911         | 2.67  | 6    | 0.7337          | 1.0      |
+| 0.4377        | 3.56  | 8    | 0.6583          | 1.0      |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:699207e4b8f7c25f927129d3fc6486a57211d34d0f71d2e330bd5ec0dcc28d25
+oid sha256:e3bca8e9e5c75aeaed592e1ab67e5a6ab79581074ea2faee71d76c49de5f0fd0
 size 378305452