Hemg
/

heartbeat-detection

Audio Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Hemg commited on Apr 4

Commit

ce0c973

•

1 Parent(s): 7f6c4ba

Model save

Files changed (1) hide show

README.md +3 -6

README.md CHANGED Viewed

@@ -32,7 +32,7 @@ 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 audiofolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0159
 - Accuracy: 1.0
 ## Model description
@@ -59,16 +59,13 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 16
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.4705        | 1.0   | 9    | 1.0780          | 1.0      |
-| 0.7128        | 2.0   | 18   | 0.2813          | 1.0      |
-| 0.1842        | 3.0   | 27   | 0.0639          | 1.0      |
-| 0.0451        | 4.0   | 36   | 0.0159          | 1.0      |
 ### Framework versions

 This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.7540
 - Accuracy: 1.0
 ## Model description
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.1681        | 1.0   | 9    | 0.7540          | 1.0      |
 ### Framework versions