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: apv53-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: 0.8
apv53-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: 0.7063
- Accuracy: 0.8
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.5
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.2776 | 1.0 | 113 | 2.2687 | 0.2 |
| 2.0615 | 2.0 | 226 | 2.0397 | 0.55 |
| 1.8286 | 3.0 | 339 | 1.7089 | 0.56 |
| 1.4052 | 4.0 | 452 | 1.3901 | 0.66 |
| 1.232 | 5.0 | 565 | 1.1751 | 0.69 |
| 0.9855 | 6.0 | 678 | 0.9499 | 0.74 |
| 0.8087 | 7.0 | 791 | 0.8492 | 0.75 |
| 0.5098 | 8.0 | 904 | 0.7997 | 0.77 |
| 0.5883 | 9.0 | 1017 | 0.7144 | 0.77 |
| 0.4644 | 10.0 | 1130 | 0.7063 | 0.8 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0