Aller au contenu
ModelPrésentéExterne
Télécharger

Distilhubert Finetuned Gtzan

This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set: Loss: 0.7623 Accuracy: 0.76

Sourcehuggingface.co/rafaelaraujo13/distilhubert-finetuned-gtzan/tree/9b39373af99342101bb5cf0582757610baa2d409
TypeOtherModèle de basentu-spml/distilhubertVersionRevision 9b39373

Source du modèle

Type
Other
Taille du fichier
90,4 MB
Modèle de base
ntu-spml/distilhubert
Version
vRevision 9b39373
Mis à jour
19 sept. 2026
Téléchargements
6
Source
Hugging Face

Description de la source

distilhubert-finetuned-gtzan

This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7623
  • Accuracy: 0.76

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossAccuracy
1.93181.01001.90050.41
1.33622.02001.36150.64
1.02783.03001.18660.665
0.66674.04001.01350.675
0.49445.05000.94870.7
0.40936.06000.85470.745
0.37647.07000.79080.745
0.35518.08000.73260.79
0.21079.09000.74630.765
0.191910.010000.76230.76

Framework versions

  • Transformers 5.0.0
  • Pytorch 2.9.0+cu126
  • Datasets 4.0.0
  • Tokenizers 0.22.2

Sources

1 source
Hugging FacePrincipalVersion 9b39373af99342101bb5cf0582757610baa2d409
huggingface.co/rafaelaraujo13/distilhubert-finetuned-gtzan/tree/9b39373af99342101bb5cf0582757610baa2d409

Vérifié 19 sept.

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 90,4 MB · SHA-256 c30537ff9afe…4202 · Hugging Face

Télécharger

Extraits de sources

2 extraits
Readme19 sept.huggingface.co/rafaelaraujo13/distilhubert-finetuned-gtzan

--- library_name: transformers license: apache-2.0 base_model: ntu-spml/distilhubert tags: - generated_from_trainer datasets: - sanchit-gandhi/gtzan metrics: - accuracy model-index: - name: distilhubert-finetuned-gtzan results: - task: name: Audio Classification type: audio-classification dataset: name: GTZAN type: sanchit-gandhi/gtzan metrics: - name: Accuracy type: accuracy value: 0.76 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilhubert-finetuned-gtzan 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: 0.7623 - Accuracy: 0.76 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 100 - num_epochs: 10 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 1.9318 | 1.0 | 100 | 1.9005 | 0.41 | | 1.3362 | 2.0 | 200 | 1.3615 | 0.64 | | 1.0278 | 3.0 | 300 | 1.1866 | 0.665 | | 0.6667 | 4.0 | 400 | 1.0135 | 0.675 | | 0.4944 | 5.0 | 500 | 0.9487 | 0.7 | | 0.4093 | 6.0 | 600 | 0.8547 | 0.745 | | 0.3764 | 7.0 | 700 | 0.7908 | 0.745 | | 0.3551 | 8.0 | 800 | 0.7326 | 0.79 | | 0.2107 | 9.0 | 900 | 0.7463 | 0.765 | | 0.1919 | 10.0 | 1000 | 0.7623 | 0.76 | ### Framework versions - Transformers 5.0.0 - Pytorch 2.9.0+cu126 - Datasets 4.0.0 - Tokenizers 0.22.2

Note19 sept.huggingface.co/rafaelaraujo13/distilhubert-finetuned-gtzan

Source context: 6 downloads · 0 likes · Pipeline audio-classification · Library transformers · Repo rafaelaraujo13/distilhubert-finetuned-gtzan