|
--- |
|
license: apache-2.0 |
|
base_model: facebook/hubert-base-ls960 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- marsyas/gtzan |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: hubert-base-ls960-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: 0.86 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# hubert-base-ls960-finetuned-gtzan |
|
|
|
This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on the GTZAN dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6524 |
|
- Accuracy: 0.86 |
|
|
|
## 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: 10 |
|
- eval_batch_size: 10 |
|
- seed: 42 |
|
- 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 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 2.1626 | 1.0 | 90 | 2.0818 | 0.29 | |
|
| 1.6876 | 2.0 | 180 | 1.6356 | 0.46 | |
|
| 1.5907 | 3.0 | 270 | 1.4315 | 0.44 | |
|
| 1.1261 | 4.0 | 360 | 1.1621 | 0.59 | |
|
| 1.2327 | 5.0 | 450 | 1.0259 | 0.7 | |
|
| 0.787 | 6.0 | 540 | 1.0662 | 0.68 | |
|
| 0.9672 | 7.0 | 630 | 0.8381 | 0.77 | |
|
| 0.626 | 8.0 | 720 | 0.7148 | 0.83 | |
|
| 0.4198 | 9.0 | 810 | 0.8384 | 0.77 | |
|
| 0.3601 | 10.0 | 900 | 0.5700 | 0.82 | |
|
| 0.4672 | 11.0 | 990 | 0.8379 | 0.8 | |
|
| 0.3303 | 12.0 | 1080 | 0.5098 | 0.86 | |
|
| 0.2577 | 13.0 | 1170 | 0.8730 | 0.81 | |
|
| 0.3535 | 14.0 | 1260 | 0.8539 | 0.82 | |
|
| 0.2021 | 15.0 | 1350 | 0.8921 | 0.81 | |
|
| 0.1995 | 16.0 | 1440 | 0.4829 | 0.88 | |
|
| 0.3149 | 17.0 | 1530 | 0.6051 | 0.84 | |
|
| 0.0828 | 18.0 | 1620 | 0.5581 | 0.86 | |
|
| 0.0557 | 19.0 | 1710 | 0.5707 | 0.87 | |
|
| 0.1019 | 20.0 | 1800 | 0.6524 | 0.86 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
