|
|
--- |
|
|
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 |
|
|
config: default |
|
|
split: None |
|
|
args: default |
|
|
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: 0.5071 |
|
|
- 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: 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 |
|
|
- num_epochs: 15 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
|
| 1.7065 | 1.0 | 113 | 1.5003 | 0.61 | |
|
|
| 1.0785 | 2.0 | 226 | 1.0084 | 0.69 | |
|
|
| 0.8457 | 3.0 | 339 | 0.7742 | 0.79 | |
|
|
| 0.6696 | 4.0 | 452 | 0.6197 | 0.82 | |
|
|
| 0.5859 | 5.0 | 565 | 0.5071 | 0.87 | |
|
|
| 0.3813 | 6.0 | 678 | 0.5068 | 0.85 | |
|
|
| 0.4032 | 7.0 | 791 | 0.4872 | 0.87 | |
|
|
| 0.2352 | 8.0 | 904 | 0.5913 | 0.83 | |
|
|
| 0.1345 | 9.0 | 1017 | 0.6382 | 0.84 | |
|
|
| 0.1871 | 10.0 | 1130 | 0.5928 | 0.87 | |
|
|
| 0.1533 | 11.0 | 1243 | 0.5992 | 0.86 | |
|
|
| 0.108 | 12.0 | 1356 | 0.6503 | 0.83 | |
|
|
| 0.0642 | 13.0 | 1469 | 0.6233 | 0.86 | |
|
|
| 0.0419 | 14.0 | 1582 | 0.6289 | 0.86 | |
|
|
| 0.0461 | 15.0 | 1695 | 0.6338 | 0.87 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.54.1 |
|
|
- Pytorch 2.9.0.dev20250731+cu128 |
|
|
- Datasets 3.6.0 |
|
|
- Tokenizers 0.21.4 |
|
|
|
