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 [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0001
+- Loss: 0.0023
 - Accuracy: 1.0
 
 ## Model description
@@ -52,7 +52,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0005
+- learning_rate: 0.0003
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -65,10 +65,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.8112        | 1.0   | 8    | 0.0346          | 1.0      |
-| 0.0108        | 2.0   | 16   | 0.0004          | 1.0      |
-| 0.0003        | 3.0   | 24   | 0.0001          | 1.0      |
-| 0.0001        | 4.0   | 32   | 0.0001          | 1.0      |
+| 1.0263        | 1.0   | 8    | 0.2218          | 1.0      |
+| 0.104         | 2.0   | 16   | 0.0153          | 1.0      |
+| 0.0099        | 3.0   | 24   | 0.0034          | 1.0      |
+| 0.0036        | 4.0   | 32   | 0.0023          | 1.0      |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dba30ea999aafa830e93dbba0d7f6bfe4a63d6720b7b58c5a20af5a3b142d3d
+oid sha256:e1a2524598088ac754a37d8ed9076efac9bf225b94751b95e072043f7a74f5b6
 size 94766588