|
--- |
|
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: 0.78 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/scott-poynts-nil/huggingface/runs/mvcwa6jm) |
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/scott-poynts-nil/huggingface/runs/mvcwa6jm) |
|
# 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: 0.9511 |
|
- Accuracy: 0.78 |
|
|
|
## 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: 2 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:| |
|
| 0.6478 | 0.9912 | 56 | 0.7848 | 0.77 | |
|
| 0.4009 | 2.0 | 113 | 0.8213 | 0.73 | |
|
| 0.2155 | 2.9912 | 169 | 0.7877 | 0.76 | |
|
| 0.1813 | 4.0 | 226 | 0.8529 | 0.75 | |
|
| 0.0851 | 4.9912 | 282 | 0.8632 | 0.73 | |
|
| 0.063 | 6.0 | 339 | 0.9026 | 0.78 | |
|
| 0.0372 | 6.9912 | 395 | 0.8418 | 0.8 | |
|
| 0.021 | 8.0 | 452 | 0.8672 | 0.79 | |
|
| 0.0113 | 8.9912 | 508 | 0.9186 | 0.79 | |
|
| 0.0098 | 9.9115 | 560 | 0.9511 | 0.78 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
