|
--- |
|
license: apache-2.0 |
|
base_model: ntu-spml/distilhubert |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- marsyas/gtzan |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
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: 0.7733333333333333 |
|
- name: Precision |
|
type: precision |
|
value: 0.775454513809777 |
|
- name: Recall |
|
type: recall |
|
value: 0.7733333333333333 |
|
- name: F1 |
|
type: f1 |
|
value: 0.7708532203254443 |
|
--- |
|
|
|
<!-- 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/raspuntinov_ai/huggingface/runs/xti2wn9w) |
|
# 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: 0.7448 |
|
- Accuracy: 0.7733 |
|
- Precision: 0.7755 |
|
- Recall: 0.7733 |
|
- F1: 0.7709 |
|
|
|
## 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: 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 | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| 2.0182 | 1.0 | 88 | 2.0020 | 0.3333 | 0.3990 | 0.3333 | 0.2547 | |
|
| 1.6019 | 2.0 | 176 | 1.4794 | 0.5333 | 0.6597 | 0.5333 | 0.4789 | |
|
| 1.0733 | 3.0 | 264 | 1.2329 | 0.6133 | 0.6930 | 0.6133 | 0.5993 | |
|
| 0.9451 | 4.0 | 352 | 1.1227 | 0.64 | 0.7214 | 0.64 | 0.6289 | |
|
| 0.9232 | 5.0 | 440 | 0.9426 | 0.7133 | 0.7398 | 0.7133 | 0.7071 | |
|
| 0.6552 | 6.0 | 528 | 0.8132 | 0.78 | 0.7795 | 0.78 | 0.7768 | |
|
| 0.4019 | 7.0 | 616 | 0.8478 | 0.7333 | 0.7428 | 0.7333 | 0.7285 | |
|
| 0.2836 | 8.0 | 704 | 0.7369 | 0.7933 | 0.8025 | 0.7933 | 0.7915 | |
|
| 0.207 | 9.0 | 792 | 0.7440 | 0.7933 | 0.7926 | 0.7933 | 0.7879 | |
|
| 0.3091 | 10.0 | 880 | 0.7448 | 0.7733 | 0.7755 | 0.7733 | 0.7709 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
