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-88
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: 0.87
distilhubert-finetuned-gtzan-88
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: 0.6139
- Accuracy: 0.87
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: 8e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0172 | 1.0 | 112 | 1.8314 | 0.37 |
| 1.5433 | 2.0 | 225 | 1.2575 | 0.5 |
| 1.1517 | 3.0 | 337 | 0.9577 | 0.7 |
| 0.904 | 4.0 | 450 | 0.7582 | 0.77 |
| 0.4788 | 5.0 | 562 | 0.7504 | 0.79 |
| 0.3843 | 6.0 | 675 | 0.6265 | 0.79 |
| 0.3683 | 7.0 | 787 | 0.6683 | 0.8 |
| 0.2278 | 8.0 | 900 | 0.8167 | 0.77 |
| 0.4534 | 9.0 | 1012 | 0.6023 | 0.83 |
| 0.2357 | 10.0 | 1125 | 0.6185 | 0.83 |
| 0.3674 | 11.0 | 1237 | 0.6079 | 0.86 |
| 0.148 | 11.95 | 1344 | 0.6139 | 0.87 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3