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: 1.2548
+- Loss: 1.2098
 - Accuracy: 1.0
 
 ## Model description
@@ -58,17 +58,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.1
+- lr_scheduler_warmup_ratio: 0.01
 - num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.591         | 1.0   | 8    | 1.5051          | 0.8519   |
-| 1.4364        | 2.0   | 16   | 1.3666          | 1.0      |
-| 1.3203        | 3.0   | 24   | 1.2839          | 1.0      |
-| 1.263         | 4.0   | 32   | 1.2548          | 1.0      |
+| 1.5504        | 1.0   | 8    | 1.4484          | 0.9630   |
+| 1.3809        | 2.0   | 16   | 1.3163          | 1.0      |
+| 1.2706        | 3.0   | 24   | 1.2381          | 1.0      |
+| 1.2157        | 4.0   | 32   | 1.2098          | 1.0      |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b088ec7413c478b2068b4423de8a26a83e704fa7885b8361d68aa6f293d88368
+oid sha256:9295f9682f48c6edd827358eb16cdd868ee5403da244af4a67ee332bf154d428
 size 94766588