End of training

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.85
+      value: 0.86
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ 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: 0.7505
-- Accuracy: 0.85
+- Loss: 0.7073
+- Accuracy: 0.86
 
 ## Model description
 
@@ -53,20 +53,30 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-06
+- learning_rate: 9e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 1
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.0055        | 1.0   | 113  | 0.7505          | 0.85     |
+| 1.6909        | 1.0   | 113  | 1.6624          | 0.57     |
+| 0.89          | 2.0   | 226  | 1.1358          | 0.67     |
+| 0.748         | 3.0   | 339  | 0.8551          | 0.75     |
+| 0.5167        | 4.0   | 452  | 0.8564          | 0.71     |
+| 0.3093        | 5.0   | 565  | 0.6230          | 0.78     |
+| 0.2078        | 6.0   | 678  | 0.6165          | 0.81     |
+| 0.0857        | 7.0   | 791  | 0.7213          | 0.85     |
+| 0.0133        | 8.0   | 904  | 0.7519          | 0.83     |
+| 0.0127        | 9.0   | 1017 | 0.7289          | 0.84     |
+| 0.0088        | 10.0  | 1130 | 0.7073          | 0.86     |
 
 
 ### Framework versions