JvThunder
/

distilhubert-finetuned-gtzan

Audio Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

JvThunder commited on Jun 23

Commit

c62c768

•

1 Parent(s): 1b63121

End of training

Files changed (1) hide show

README.md +14 -14

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.86
 ---
 <!-- 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: 0.5324
-- Accuracy: 0.86
 ## Model description
@@ -52,7 +52,7 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -66,16 +66,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.9201        | 1.0   | 113  | 1.8096          | 0.56     |
-| 1.2331        | 2.0   | 226  | 1.2709          | 0.6      |
-| 1.0386        | 3.0   | 339  | 0.9960          | 0.73     |
-| 0.6721        | 4.0   | 452  | 0.8535          | 0.72     |
-| 0.5598        | 5.0   | 565  | 0.7156          | 0.81     |
-| 0.4382        | 6.0   | 678  | 0.6253          | 0.83     |
-| 0.2701        | 7.0   | 791  | 0.5411          | 0.84     |
-| 0.1164        | 8.0   | 904  | 0.5460          | 0.83     |
-| 0.1872        | 9.0   | 1017 | 0.5464          | 0.84     |
-| 0.0898        | 10.0  | 1130 | 0.5324          | 0.86     |
 ### Framework versions

     metrics:
     - name: Accuracy
       type: accuracy
+      value: 0.78
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 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: 0.9204
+- Accuracy: 0.78
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 2e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.2131        | 1.0   | 113  | 2.0971          | 0.42     |
+| 1.786         | 2.0   | 226  | 1.6744          | 0.56     |
+| 1.5128        | 3.0   | 339  | 1.4491          | 0.66     |
+| 1.2987        | 4.0   | 452  | 1.2673          | 0.74     |
+| 1.1823        | 5.0   | 565  | 1.1610          | 0.71     |
+| 1.0707        | 6.0   | 678  | 1.0937          | 0.74     |
+| 1.0015        | 7.0   | 791  | 1.0214          | 0.75     |
+| 0.8765        | 8.0   | 904  | 0.9650          | 0.75     |
+| 0.833         | 9.0   | 1017 | 0.9415          | 0.75     |
+| 0.7924        | 10.0  | 1130 | 0.9204          | 0.78     |
 ### Framework versions