metadata
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: 0.85
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: 0.5146
- Accuracy: 0.85
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: 6
- eval_batch_size: 6
- 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: 12
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.9404 | 1.0 | 150 | 1.8960 | 0.45 |
| 1.1667 | 2.0 | 300 | 1.2573 | 0.64 |
| 0.9325 | 3.0 | 450 | 0.9343 | 0.71 |
| 0.7688 | 4.0 | 600 | 0.9460 | 0.73 |
| 0.5211 | 5.0 | 750 | 0.6388 | 0.78 |
| 0.2001 | 6.0 | 900 | 0.5689 | 0.8 |
| 0.4134 | 7.0 | 1050 | 0.5351 | 0.82 |
| 0.2026 | 8.0 | 1200 | 0.6032 | 0.82 |
| 0.036 | 9.0 | 1350 | 0.5002 | 0.82 |
| 0.1023 | 10.0 | 1500 | 0.5171 | 0.82 |
| 0.0773 | 11.0 | 1650 | 0.5088 | 0.86 |
| 0.0147 | 12.0 | 1800 | 0.5146 | 0.85 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2