End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.58
+      value: 0.77
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ 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: 1.7506
-- Accuracy: 0.58
+- Loss: 0.9423
+- Accuracy: 0.77
 
 ## Model description
 
@@ -52,23 +52,27 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 5e-06
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 100
+- training_steps: 3000
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.2637        | 0.44  | 25   | 2.1478          | 0.39     |
-| 2.0908        | 0.88  | 50   | 1.9407          | 0.51     |
-| 1.8916        | 1.32  | 75   | 1.7992          | 0.55     |
-| 1.798         | 1.75  | 100  | 1.7506          | 0.58     |
+| 2.1574        | 8.85  | 500  | 1.8008          | 0.66     |
+| 1.5882        | 17.7  | 1000 | 1.3509          | 0.7      |
+| 1.2416        | 26.55 | 1500 | 1.1347          | 0.72     |
+| 1.037         | 35.4  | 2000 | 1.0163          | 0.74     |
+| 0.9152        | 44.25 | 2500 | 0.9583          | 0.76     |
+| 0.8556        | 53.1  | 3000 | 0.9423          | 0.77     |
 
 
 ### Framework versions