End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8
+      value: 0.84
 ---
 
 <!-- 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: 0.5776
-- Accuracy: 0.8
+- Loss: 0.7155
+- Accuracy: 0.84
 
 ## Model description
 
@@ -52,31 +52,34 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
+- learning_rate: 5e-05
 - 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: 12
+- num_epochs: 15
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.1751        | 1.0   | 113  | 2.0617          | 0.39     |
-| 1.5894        | 2.0   | 226  | 1.4723          | 0.63     |
-| 1.2258        | 3.0   | 339  | 1.1671          | 0.69     |
-| 1.125         | 4.0   | 452  | 1.0775          | 0.69     |
-| 0.9434        | 5.0   | 565  | 0.8765          | 0.77     |
-| 0.6199        | 6.0   | 678  | 0.7735          | 0.75     |
-| 0.7675        | 7.0   | 791  | 0.6909          | 0.79     |
-| 0.4401        | 8.0   | 904  | 0.6303          | 0.82     |
-| 0.5256        | 9.0   | 1017 | 0.6248          | 0.78     |
-| 0.324         | 10.0  | 1130 | 0.6498          | 0.8      |
-| 0.2454        | 11.0  | 1243 | 0.5875          | 0.81     |
-| 0.2697        | 12.0  | 1356 | 0.5776          | 0.8      |
+| 2.1187        | 1.0   | 113  | 1.9789          | 0.29     |
+| 1.4634        | 2.0   | 226  | 1.3608          | 0.65     |
+| 1.0995        | 3.0   | 339  | 0.9572          | 0.72     |
+| 0.9411        | 4.0   | 452  | 0.8684          | 0.75     |
+| 0.6118        | 5.0   | 565  | 0.7153          | 0.75     |
+| 0.3329        | 6.0   | 678  | 0.6483          | 0.77     |
+| 0.4392        | 7.0   | 791  | 0.6914          | 0.77     |
+| 0.1126        | 8.0   | 904  | 0.5822          | 0.84     |
+| 0.1637        | 9.0   | 1017 | 0.6669          | 0.83     |
+| 0.0213        | 10.0  | 1130 | 0.6624          | 0.84     |
+| 0.0145        | 11.0  | 1243 | 0.6951          | 0.84     |
+| 0.0371        | 12.0  | 1356 | 0.6870          | 0.86     |
+| 0.009         | 13.0  | 1469 | 0.6963          | 0.85     |
+| 0.008         | 14.0  | 1582 | 0.6927          | 0.86     |
+| 0.0082        | 15.0  | 1695 | 0.7155          | 0.84     |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e689ae43c223cf949f75966ba2d80b49420becae782c9aa4cf1e9c9d8946796
+oid sha256:8ae540b893a61e6f0d62c5792aa0ab7211b02be4bdccd6dd520e16aaa5d883d8
 size 94783376