update model card README.md

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.81
+      value: 0.76
 ---
 
 <!-- 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: 0.6172
-- Accuracy: 0.81
+- Loss: 1.0703
+- Accuracy: 0.76
 
 ## Model description
 
@@ -51,41 +51,24 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.05
+- learning_rate: 5e-05
 - train_batch_size: 4
-- eval_batch_size: 4
+- eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
 - total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 20
+- num_epochs: 3
 
 ### Training results
 
-| Training Loss | Epoch | Step | Accuracy | Validation Loss |
-|:-------------:|:-----:|:----:|:--------:|:---------------:|
-| 1.9814        | 1.0   | 112  | 0.53     | 1.8342          |
-| 1.3136        | 2.0   | 225  | 0.66     | 1.2448          |
-| 1.023         | 3.0   | 337  | 0.73     | 0.9055          |
-| 0.6619        | 4.0   | 450  | 0.71     | 0.8979          |
-| 0.4521        | 5.0   | 562  | 0.74     | 0.7662          |
-| 0.421         | 6.0   | 675  | 0.78     | 0.6843          |
-| 0.2964        | 7.0   | 787  | 0.79     | 0.6774          |
-| 0.1895        | 8.0   | 900  | 0.82     | 0.6137          |
-| 0.187         | 9.0   | 1012 | 0.82     | 0.6087          |
-| 0.1317        | 9.96  | 1120 | 0.81     | 0.6173          |
-| 0.1001        | 11.0  | 1232 | 0.81     | 0.6172          |
-| 0.1812        | 12.0  | 1345 | 0.81     | 0.6172          |
-| 0.2104        | 13.0  | 1457 | 0.81     | 0.6172          |
-| 0.1317        | 14.0  | 1568 | 0.81     | 0.6172          |
-| 0.1101        | 15.0  | 1681 | 0.81     | 0.6172          |
-| 0.1625        | 16.0  | 1792 | 0.81     | 0.6172          |
-| 0.1848        | 17.0  | 1905 | 0.81     | 0.6172          |
-| 0.1169        | 18.0  | 2016 | 0.6172   | 0.81            |
-| 0.0976        | 19.0  | 2129 | 0.6172   | 0.81            |
-| 0.1375        | 19.99 | 2240 | 0.6172   | 0.81            |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.9146        | 1.0   | 112  | 1.5803          | 0.7      |
+| 1.2789        | 2.0   | 225  | 1.2035          | 0.67     |
+| 1.1288        | 2.99  | 336  | 1.0703          | 0.76     |
 
 
 ### Framework versions