update model card README.md

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 GTZAN dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6180
+- Loss: 1.1019
 - Accuracy: 0.83
 
 ## Model description
@@ -59,19 +59,21 @@ 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: 7
+- num_epochs: 9
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.6805        | 1.0   | 225  | 1.4984          | 0.64     |
-| 0.8767        | 2.0   | 450  | 1.0174          | 0.67     |
-| 0.9691        | 3.0   | 675  | 0.8688          | 0.73     |
-| 0.6252        | 4.0   | 900  | 0.7695          | 0.77     |
-| 0.2577        | 5.0   | 1125 | 0.6340          | 0.81     |
-| 0.076         | 6.0   | 1350 | 0.6358          | 0.8      |
-| 0.1941        | 7.0   | 1575 | 0.6180          | 0.83     |
+| 0.1326        | 1.0   | 225  | 0.6275          | 0.81     |
+| 0.32          | 2.0   | 450  | 0.9461          | 0.78     |
+| 0.4269        | 3.0   | 675  | 0.8966          | 0.84     |
+| 0.1847        | 4.0   | 900  | 1.3268          | 0.8      |
+| 0.0009        | 5.0   | 1125 | 1.0639          | 0.81     |
+| 0.0006        | 6.0   | 1350 | 1.3213          | 0.81     |
+| 0.0006        | 7.0   | 1575 | 1.1195          | 0.81     |
+| 0.0004        | 8.0   | 1800 | 1.0799          | 0.83     |
+| 0.0004        | 9.0   | 2025 | 1.1019          | 0.83     |
 
 
 ### Framework versions