update model card README.md

README.md

@@ -18,8 +18,8 @@ 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: 0.9118
-- Accuracy: 0.86
+- Loss: 0.6633
+- Accuracy: 0.84
 
 ## Model description
 
@@ -38,24 +38,26 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 8e-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: 4
+- num_epochs: 6
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.0452        | 1.0   | 113  | 0.9822          | 0.85     |
-| 0.0089        | 2.0   | 226  | 0.9121          | 0.86     |
-| 0.0004        | 3.0   | 339  | 0.8943          | 0.86     |
-| 0.0002        | 4.0   | 452  | 0.9118          | 0.86     |
+| 1.3806        | 1.0   | 113  | 1.5601          | 0.53     |
+| 0.9388        | 2.0   | 226  | 1.1111          | 0.67     |
+| 0.8746        | 3.0   | 339  | 0.9314          | 0.71     |
+| 0.5114        | 4.0   | 452  | 0.8017          | 0.75     |
+| 0.4226        | 5.0   | 565  | 0.7738          | 0.81     |
+| 0.23          | 6.0   | 678  | 0.6633          | 0.84     |
 
 
 ### Framework versions