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: 0.81
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: 0.5579
- Accuracy: 0.81
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 |
|---|---|---|---|---|
| 1.9224 | 1.0 | 113 | 1.8645 | 0.55 |
| 1.1747 | 2.0 | 226 | 1.2232 | 0.66 |
| 1.0823 | 3.0 | 339 | 1.0418 | 0.69 |
| 0.6272 | 4.0 | 452 | 0.7845 | 0.75 |
| 0.5903 | 5.0 | 565 | 0.6946 | 0.78 |
| 0.4248 | 6.0 | 678 | 0.6238 | 0.8 |
| 0.2714 | 7.0 | 791 | 0.5388 | 0.84 |
| 0.133 | 8.0 | 904 | 0.5809 | 0.84 |
| 0.2107 | 9.0 | 1017 | 0.5785 | 0.83 |
| 0.103 | 10.0 | 1130 | 0.5579 | 0.81 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.4.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1