update model card README.md

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.79
+      value: 0.8
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ 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: 0.8911
-- Accuracy: 0.79
+- Loss: 0.6772
+- Accuracy: 0.8
 
 ## Model description
 
@@ -51,29 +51,27 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 4e-05
+- learning_rate: 5e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 10
+- num_epochs: 8
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.3956        | 1.0   | 100  | 0.8892          | 0.71     |
-| 0.6233        | 2.0   | 200  | 0.8383          | 0.75     |
-| 0.423         | 3.0   | 300  | 0.7178          | 0.79     |
-| 0.245         | 4.0   | 400  | 0.7681          | 0.775    |
-| 0.0596        | 5.0   | 500  | 0.7590          | 0.77     |
-| 0.0798        | 6.0   | 600  | 0.9023          | 0.78     |
-| 0.0174        | 7.0   | 700  | 0.9282          | 0.78     |
-| 0.0591        | 8.0   | 800  | 0.9256          | 0.775    |
-| 0.0088        | 9.0   | 900  | 0.8954          | 0.785    |
-| 0.0072        | 10.0  | 1000 | 0.8911          | 0.79     |
+| 1.8944        | 1.0   | 110  | 1.8362          | 0.5167   |
+| 1.4359        | 2.0   | 220  | 1.4329          | 0.5083   |
+| 0.9861        | 3.0   | 330  | 1.0460          | 0.7      |
+| 0.9073        | 4.0   | 440  | 0.8689          | 0.7417   |
+| 0.5268        | 5.0   | 550  | 0.8289          | 0.8      |
+| 0.4683        | 6.0   | 660  | 0.7483          | 0.7833   |
+| 0.2342        | 7.0   | 770  | 0.7025          | 0.8      |
+| 0.2886        | 8.0   | 880  | 0.6772          | 0.8      |
 
 
 ### Framework versions