|
--- |
|
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: all |
|
split: train |
|
args: all |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.85 |
|
--- |
|
|
|
<!-- 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: 0.5960 |
|
- Accuracy: 0.85 |
|
|
|
## 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 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 15 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 2.2592 | 0.99 | 28 | 2.2167 | 0.25 | |
|
| 1.8769 | 1.98 | 56 | 1.8139 | 0.49 | |
|
| 1.5783 | 2.97 | 84 | 1.5107 | 0.61 | |
|
| 1.3068 | 4.0 | 113 | 1.2779 | 0.68 | |
|
| 1.1062 | 4.99 | 141 | 1.0318 | 0.8 | |
|
| 1.0125 | 5.98 | 169 | 0.9156 | 0.83 | |
|
| 0.8787 | 6.97 | 197 | 0.8099 | 0.86 | |
|
| 0.7658 | 8.0 | 226 | 0.7804 | 0.85 | |
|
| 0.7811 | 8.99 | 254 | 0.7448 | 0.83 | |
|
| 0.6369 | 9.98 | 282 | 0.6841 | 0.84 | |
|
| 0.4859 | 10.97 | 310 | 0.6353 | 0.85 | |
|
| 0.4705 | 12.0 | 339 | 0.6193 | 0.87 | |
|
| 0.4571 | 12.99 | 367 | 0.6090 | 0.86 | |
|
| 0.3999 | 13.98 | 395 | 0.5912 | 0.86 | |
|
| 0.4007 | 14.87 | 420 | 0.5960 | 0.85 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.0 |
|
|
