End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.67
+      value: 0.8
 ---
 
 <!-- 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: 1.2964
-- Accuracy: 0.67
+- Loss: 0.7457
+- Accuracy: 0.8
 
 ## Model description
 
@@ -52,26 +52,31 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- learning_rate: 0.001
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 32
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 5
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.1699        | 0.99  | 28   | 2.0590          | 0.44     |
-| 1.8177        | 1.98  | 56   | 1.6737          | 0.56     |
-| 1.5311        | 2.97  | 84   | 1.4527          | 0.64     |
-| 1.4022        | 4.0   | 113  | 1.3283          | 0.69     |
-| 1.3342        | 4.96  | 140  | 1.2964          | 0.67     |
+| 2.0883        | 0.98  | 14   | 1.7947          | 0.4      |
+| 1.6395        | 1.96  | 28   | 1.3638          | 0.48     |
+| 1.0982        | 2.95  | 42   | 1.0228          | 0.62     |
+| 1.1058        | 4.0   | 57   | 1.0306          | 0.63     |
+| 1.0458        | 4.98  | 71   | 0.8978          | 0.66     |
+| 0.5797        | 5.96  | 85   | 1.0714          | 0.69     |
+| 0.4266        | 6.95  | 99   | 0.8685          | 0.75     |
+| 0.3548        | 8.0   | 114  | 0.6180          | 0.85     |
+| 0.1839        | 8.98  | 128  | 0.8089          | 0.78     |
+| 0.1129        | 9.82  | 140  | 0.7457          | 0.8      |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e285681380a3a02d407eebaec5da8fcfe50007f08a984fa5be2f754794892a2
+oid sha256:871bcf2146abfb45e9e96db3c22b570bef857aab118934e1ce98c18376a0d746
 size 94783376