End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.09
+      value: 0.29
 ---
 
 <!-- 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: 2.4089
-- Accuracy: 0.09
+- Loss: 2.2721
+- Accuracy: 0.29
 
 ## Model description
 
@@ -52,21 +52,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.05
+- learning_rate: 5e-07
 - train_batch_size: 2
 - eval_batch_size: 2
 - 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: 2
+- lr_scheduler_warmup_ratio: 0.3
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 5.3267        | 1.0   | 450  | 3.5987          | 0.1      |
-| 2.4901        | 2.0   | 900  | 2.4089          | 0.09     |
+| 2.3009        | 1.0   | 450  | 2.2923          | 0.15     |
+| 2.2868        | 2.0   | 900  | 2.2816          | 0.2      |
+| 2.2839        | 3.0   | 1350 | 2.2743          | 0.24     |
+| 2.2945        | 4.0   | 1800 | 2.2721          | 0.29     |
 
 
 ### Framework versions