|
--- |
|
license: bsd-3-clause |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- marsyas/gtzan |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan |
|
|
|
This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on the GTZAN dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3882 |
|
- Accuracy: 0.9 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.4932 | 1.0 | 112 | 0.5325 | 0.86 | |
|
| 0.3541 | 2.0 | 225 | 0.6068 | 0.77 | |
|
| 0.5743 | 3.0 | 337 | 0.6356 | 0.83 | |
|
| 0.6256 | 4.0 | 450 | 0.4878 | 0.86 | |
|
| 0.0619 | 5.0 | 562 | 0.4262 | 0.88 | |
|
| 0.0044 | 6.0 | 675 | 0.3266 | 0.91 | |
|
| 0.0018 | 7.0 | 787 | 0.4827 | 0.87 | |
|
| 0.001 | 8.0 | 900 | 0.9245 | 0.82 | |
|
| 0.1854 | 9.0 | 1012 | 0.4256 | 0.89 | |
|
| 0.0001 | 10.0 | 1125 | 0.3898 | 0.9 | |
|
| 0.0001 | 11.0 | 1237 | 0.3873 | 0.9 | |
|
| 0.0001 | 12.0 | 1350 | 0.4064 | 0.91 | |
|
| 0.0 | 13.0 | 1462 | 0.3910 | 0.9 | |
|
| 0.0 | 14.0 | 1575 | 0.3924 | 0.9 | |
|
| 0.0001 | 15.0 | 1687 | 0.3917 | 0.91 | |
|
| 0.0 | 16.0 | 1800 | 0.3903 | 0.9 | |
|
| 0.0 | 17.0 | 1912 | 0.3900 | 0.89 | |
|
| 0.0 | 18.0 | 2025 | 0.3894 | 0.89 | |
|
| 0.0 | 19.0 | 2137 | 0.3886 | 0.9 | |
|
| 0.0 | 19.91 | 2240 | 0.3882 | 0.9 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.30.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.13.1 |
|
- Tokenizers 0.13.3 |
|
|
