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: None
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: 0.6435
- 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: 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: 0.11
- num_epochs: 12
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0583 | 1.0 | 113 | 1.8988 | 0.38 |
| 1.3639 | 2.0 | 226 | 1.3228 | 0.63 |
| 0.9073 | 3.0 | 339 | 1.0764 | 0.68 |
| 0.6992 | 4.0 | 452 | 0.8383 | 0.76 |
| 0.5049 | 5.0 | 565 | 0.6777 | 0.79 |
| 0.415 | 6.0 | 678 | 0.5827 | 0.81 |
| 0.3091 | 7.0 | 791 | 0.5524 | 0.86 |
| 0.1871 | 8.0 | 904 | 0.6074 | 0.85 |
| 0.1265 | 9.0 | 1017 | 0.6024 | 0.87 |
| 0.0883 | 10.0 | 1130 | 0.6710 | 0.85 |
| 0.0557 | 11.0 | 1243 | 0.6686 | 0.84 |
| 0.0677 | 12.0 | 1356 | 0.6435 | 0.85 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2