End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.78
+      value: 0.87
 ---
 
 <!-- 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: 0.6981
-- Accuracy: 0.78
+- Loss: 0.4794
+- Accuracy: 0.87
 
 ## Model description
 
@@ -53,28 +53,30 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 6
-- eval_batch_size: 6
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 12
+- total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 8
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.9898        | 1.0   | 75   | 1.8469          | 0.48     |
-| 1.4763        | 2.0   | 150  | 1.4460          | 0.59     |
-| 1.0562        | 3.0   | 225  | 1.1996          | 0.65     |
-| 0.8981        | 4.0   | 300  | 1.0095          | 0.72     |
-| 0.8209        | 5.0   | 375  | 0.8204          | 0.77     |
-| 0.7009        | 6.0   | 450  | 0.8025          | 0.76     |
-| 0.5996        | 7.0   | 525  | 0.7113          | 0.78     |
-| 0.4759        | 8.0   | 600  | 0.6981          | 0.78     |
+| 1.9964        | 1.0   | 112  | 1.8442          | 0.5      |
+| 1.3501        | 2.0   | 225  | 1.2660          | 0.68     |
+| 0.921         | 3.0   | 337  | 0.9293          | 0.75     |
+| 0.655         | 4.0   | 450  | 0.9135          | 0.73     |
+| 0.3911        | 5.0   | 562  | 0.6855          | 0.76     |
+| 0.2286        | 6.0   | 675  | 0.5951          | 0.82     |
+| 0.2095        | 7.0   | 787  | 0.5583          | 0.82     |
+| 0.1798        | 8.0   | 900  | 0.4626          | 0.87     |
+| 0.2574        | 9.0   | 1012 | 0.5043          | 0.85     |
+| 0.1796        | 9.96  | 1120 | 0.4794          | 0.87     |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ad07a2451d1216c53dca7e3c4f5390ef6ea34da324895cd875bf0e961a63929
+oid sha256:9937303565546ce05d78a99fe421f4f3cbbc23746e38475b687e770a1347f4c6
 size 94783376