End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.82
+      value: 0.89
 ---
 
 <!-- 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: 1.2523
-- Accuracy: 0.82
+- Loss: 0.6889
+- Accuracy: 0.89
 
 ## Model description
 
@@ -52,39 +52,29 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 0.00018
 - 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: 20
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.7948        | 1.0   | 113  | 1.6788          | 0.46     |
-| 1.164         | 2.0   | 226  | 1.1871          | 0.54     |
-| 0.8531        | 3.0   | 339  | 1.0579          | 0.66     |
-| 0.8304        | 4.0   | 452  | 0.8808          | 0.73     |
-| 0.2531        | 5.0   | 565  | 0.9542          | 0.74     |
-| 0.3144        | 6.0   | 678  | 1.0149          | 0.78     |
-| 0.2775        | 7.0   | 791  | 0.8875          | 0.77     |
-| 0.0521        | 8.0   | 904  | 1.2458          | 0.78     |
-| 0.0106        | 9.0   | 1017 | 0.9013          | 0.81     |
-| 0.0088        | 10.0  | 1130 | 0.9802          | 0.84     |
-| 0.0023        | 11.0  | 1243 | 1.1693          | 0.82     |
-| 0.1901        | 12.0  | 1356 | 1.2588          | 0.82     |
-| 0.0006        | 13.0  | 1469 | 1.2267          | 0.8      |
-| 0.0005        | 14.0  | 1582 | 1.3400          | 0.81     |
-| 0.0005        | 15.0  | 1695 | 1.1049          | 0.83     |
-| 0.0004        | 16.0  | 1808 | 1.3025          | 0.8      |
-| 0.1313        | 17.0  | 1921 | 1.2627          | 0.81     |
-| 0.0003        | 18.0  | 2034 | 1.1620          | 0.84     |
-| 0.0003        | 19.0  | 2147 | 1.2217          | 0.82     |
-| 0.0003        | 20.0  | 2260 | 1.2523          | 0.82     |
+| 1.7089        | 1.0   | 113  | 1.3908          | 0.47     |
+| 1.0384        | 2.0   | 226  | 1.0306          | 0.65     |
+| 0.9678        | 3.0   | 339  | 0.9619          | 0.66     |
+| 0.9463        | 4.0   | 452  | 0.5874          | 0.8      |
+| 0.5288        | 5.0   | 565  | 0.6033          | 0.83     |
+| 0.1325        | 6.0   | 678  | 0.6730          | 0.87     |
+| 0.2124        | 7.0   | 791  | 0.7158          | 0.84     |
+| 0.0054        | 8.0   | 904  | 0.7187          | 0.86     |
+| 0.004         | 9.0   | 1017 | 0.6297          | 0.88     |
+| 0.0026        | 10.0  | 1130 | 0.6889          | 0.89     |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6dde7b56f1e5825509b7fbe6524bb897d60ddf532545ac05dea8275a6f57cff
+oid sha256:773cbdd4222742562d3de24f2dde22a5c14bf25a19fab44b2765a715e2f029a6
 size 94783376