Ir para o conteúdo
ModelListadosExterno
Baixar

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: 0.5214 Accuracy: 0.87

Fontehuggingface.co/beeneptune/distilhubert-finetuned-gtzan/tree/75c9a0a016aba5daf3844b82103298ec55a4ba91
TipoOtherModelo basentu-spml/distilhubertVersãoRevision 75c9a0a

Fonte do modelo

Tipo
Other
Tamanho do arquivo
90,4 MB
Modelo base
ntu-spml/distilhubert
Versão
vRevision 75c9a0a
Atualizado
19 de set. de 2026
Downloads
4
Fonte
Hugging Face

Descrição da fonte

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: 0.5214
  • Accuracy: 0.87

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: 2e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • optimizer: Use 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: 20
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossAccuracy
4.30621.01132.09140.54
3.27922.02261.64570.56
3.04383.03391.35420.65
2.21564.04521.14480.71
1.74115.05650.99000.79
1.76526.06780.86480.82
1.48727.07910.77790.79
1.07168.09040.73010.79
1.11729.010170.68420.83
0.747810.011300.64670.83
0.784211.012430.61590.82
0.643912.013560.60050.83
0.589213.014690.54910.85
0.861114.015820.61690.84
0.343315.016950.54070.85
0.264316.018080.53370.86
0.352217.019210.51810.87
0.192918.020340.52170.87
0.207219.021470.52600.88
0.152120.022600.52140.87

Framework versions

  • Transformers 5.1.0
  • Pytorch 2.10.0+cu128
  • Datasets 4.5.0
  • Tokenizers 0.22.2

Fontes

1 fonte
Hugging FacePrimárioVersão 75c9a0a016aba5daf3844b82103298ec55a4ba91
huggingface.co/beeneptune/distilhubert-finetuned-gtzan/tree/75c9a0a016aba5daf3844b82103298ec55a4ba91

Verificado 19 de set.

Artefatos de modelo

1 artefato

model.safetensors

safetensors · 90,4 MB · SHA-256 384327cf8c40…fba4 · Hugging Face

Baixar

Trechos de fonte

2 trechos
Readme19 de set.huggingface.co/beeneptune/distilhubert-finetuned-gtzan

--- library_name: transformers license: apache-2.0 base_model: ntu-spml/distilhubert tags: - generated_from_trainer datasets: - marsyas/gtzan metrics: - accuracy model-index: - name: distilhubert-finetuned-gtzan results: - task: name: Audio Classification type: audio-classification dataset: name: GTZAN type: marsyas/gtzan metrics: - name: Accuracy type: accuracy value: 0.87 --- <!-- 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: 0.5214 - Accuracy: 0.87 ## 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: 2e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 8 - optimizer: Use 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: 20 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 4.3062 | 1.0 | 113 | 2.0914 | 0.54 | | 3.2792 | 2.0 | 226 | 1.6457 | 0.56 | | 3.0438 | 3.0 | 339 | 1.3542 | 0.65 | | 2.2156 | 4.0 | 452 | 1.1448 | 0.71 | | 1.7411 | 5.0 | 565 | 0.9900 | 0.79 | | 1.7652 | 6.0 | 678 | 0.8648 | 0.82 | | 1.4872 | 7.0 | 791 | 0.7779 | 0.79 | | 1.0716 | 8.0 | 904 | 0.7301 | 0.79 | | 1.1172 | 9.0 | 1017 | 0.6842 | 0.83 | | 0.7478 | 10.0 | 1130 | 0.6467 | 0.83 | | 0.7842 | 11.0 | 1243 | 0.6159 | 0.82 | | 0.6439 | 12.0 | 1356 | 0.6005 | 0.83 | | 0.5892 | 13.0 | 1469 | 0.5491 | 0.85 | | 0.8611 | 14.0 | 1582 | 0.6169 | 0.84 | | 0.3433 | 15.0 | 1695 | 0.5407 | 0.85 | | 0.2643 | 16.0 | 1808 | 0.5337 | 0.86 | | 0.3522 | 17.0 | 1921 | 0.5181 | 0.87 | | 0.1929 | 18.0 | 2034 | 0.5217 | 0.87 | | 0.2072 | 19.0 | 2147 | 0.5260 | 0.88 |...

Note19 de set.huggingface.co/beeneptune/distilhubert-finetuned-gtzan

Source context: 4 downloads · 0 likes · Pipeline audio-classification · Library transformers · Repo beeneptune/distilhubert-finetuned-gtzan