End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.83
+      value: 0.9
 ---
 
 <!-- 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: 0.7984
-- Accuracy: 0.83
+- Loss: 0.5825
+- Accuracy: 0.9
 
 ## Model description
 
@@ -53,11 +53,9 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- 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
@@ -67,26 +65,26 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.1366        | 1.0   | 112  | 2.0054          | 0.29     |
-| 1.4511        | 2.0   | 225  | 1.3306          | 0.63     |
-| 0.941         | 3.0   | 337  | 0.9689          | 0.7      |
-| 0.7428        | 4.0   | 450  | 0.9399          | 0.69     |
-| 0.4607        | 5.0   | 562  | 0.8357          | 0.73     |
-| 0.3398        | 6.0   | 675  | 0.7089          | 0.81     |
-| 0.2055        | 7.0   | 787  | 0.7338          | 0.81     |
-| 0.1662        | 8.0   | 900  | 0.7718          | 0.81     |
-| 0.0939        | 9.0   | 1012 | 0.6441          | 0.85     |
-| 0.028         | 10.0  | 1125 | 0.7501          | 0.83     |
-| 0.0144        | 11.0  | 1237 | 0.8078          | 0.82     |
-| 0.01          | 12.0  | 1350 | 0.7597          | 0.83     |
-| 0.0095        | 13.0  | 1462 | 0.7818          | 0.83     |
-| 0.0092        | 14.0  | 1575 | 0.7901          | 0.83     |
-| 0.0078        | 14.93 | 1680 | 0.7984          | 0.83     |
+| 2.1105        | 1.0   | 113  | 1.9598          | 0.46     |
+| 1.4314        | 2.0   | 226  | 1.2930          | 0.66     |
+| 1.0984        | 3.0   | 339  | 0.9178          | 0.78     |
+| 0.8948        | 4.0   | 452  | 0.8796          | 0.7      |
+| 0.5238        | 5.0   | 565  | 0.6836          | 0.79     |
+| 0.323         | 6.0   | 678  | 0.6542          | 0.77     |
+| 0.432         | 7.0   | 791  | 0.5248          | 0.86     |
+| 0.1875        | 8.0   | 904  | 0.4550          | 0.88     |
+| 0.1141        | 9.0   | 1017 | 0.4728          | 0.89     |
+| 0.0841        | 10.0  | 1130 | 0.5757          | 0.85     |
+| 0.0147        | 11.0  | 1243 | 0.5412          | 0.88     |
+| 0.1028        | 12.0  | 1356 | 0.5960          | 0.85     |
+| 0.0107        | 13.0  | 1469 | 0.5774          | 0.88     |
+| 0.0087        | 14.0  | 1582 | 0.5779          | 0.89     |
+| 0.0085        | 15.0  | 1695 | 0.5825          | 0.9      |
 
 
 ### Framework versions
 
 - Transformers 4.32.1
-- Pytorch 2.0.1+cu118
+- Pytorch 2.0.0
 - Datasets 2.14.4
 - Tokenizers 0.13.3