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: 0.9125
+- Loss: 0.9968
 - Accuracy: 1.0
 
 ## Model description
@@ -65,11 +65,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.576         | 1.0   | 8    | 1.4789          | 0.9630   |
-| 1.3986        | 2.0   | 16   | 1.3052          | 1.0      |
-| 1.2328        | 3.0   | 24   | 1.1507          | 1.0      |
-| 1.0964        | 4.0   | 32   | 1.0213          | 1.0      |
-| 0.9796        | 5.0   | 40   | 0.9125          | 1.0      |
+| 1.5532        | 1.0   | 8    | 1.4353          | 1.0      |
+| 1.3622        | 2.0   | 16   | 1.2647          | 1.0      |
+| 1.2044        | 3.0   | 24   | 1.1227          | 1.0      |
+| 1.0728        | 4.0   | 32   | 0.9968          | 1.0      |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd37b0b34bd31b64d3b6764efd4cc448c80b00e2fb6c12096c0b1de400c05945
+oid sha256:1f4668c3d34334911eb6d3b0e47b4bee873cea7a5bc06a53c49c04ea70348384
 size 94766588