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: 0.6728
+- Loss: 1.1661
 - Accuracy: 0.84
 
 ## Model description
@@ -52,29 +52,24 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 2e-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: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.5457        | 1.0   | 113  | 1.3306          | 0.64     |
-| 1.1454        | 2.0   | 226  | 0.9869          | 0.69     |
-| 0.7376        | 3.0   | 339  | 0.8281          | 0.74     |
-| 0.6605        | 4.0   | 452  | 0.7396          | 0.76     |
-| 0.4134        | 5.0   | 565  | 0.6014          | 0.85     |
-| 0.2691        | 6.0   | 678  | 0.6167          | 0.82     |
-| 0.3029        | 7.0   | 791  | 0.6141          | 0.82     |
-| 0.098         | 8.0   | 904  | 0.5634          | 0.89     |
-| 0.1085        | 9.0   | 1017 | 0.6662          | 0.84     |
-| 0.0527        | 10.0  | 1130 | 0.6728          | 0.84     |
+| 0.0016        | 1.0   | 113  | 1.1432          | 0.85     |
+| 0.0013        | 2.0   | 226  | 0.9959          | 0.85     |
+| 0.1731        | 3.0   | 339  | 1.0637          | 0.84     |
+| 0.0007        | 4.0   | 452  | 1.2187          | 0.84     |
+| 0.0005        | 5.0   | 565  | 1.1661          | 0.84     |
 
 
 ### Framework versions