metadata
library_name: transformers
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: 0.7692307692307693
distilhubert-finetuned-gtzan
This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 1.2256
- Accuracy: 0.7692
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: 9e-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: 18
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.9893 | 1.0 | 70 | 1.9671 | 0.4615 |
| 1.1923 | 2.0 | 140 | 1.3634 | 0.5256 |
| 1.1937 | 3.0 | 210 | 1.0865 | 0.6154 |
| 0.5684 | 4.0 | 280 | 0.9352 | 0.6795 |
| 0.4571 | 5.0 | 350 | 0.7889 | 0.7564 |
| 0.1854 | 6.0 | 420 | 0.8209 | 0.7308 |
| 0.0688 | 7.0 | 490 | 0.9835 | 0.7692 |
| 0.087 | 8.0 | 560 | 1.1710 | 0.7179 |
| 0.0109 | 9.0 | 630 | 1.0900 | 0.7692 |
| 0.0049 | 10.0 | 700 | 1.2256 | 0.7692 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0