metadata
license: apache-2.0
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: 0.87
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: 0.5542
- 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: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- 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: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0241 | 1.0 | 112 | 1.9155 | 0.4 |
| 1.5443 | 2.0 | 225 | 1.2937 | 0.65 |
| 1.1134 | 3.0 | 337 | 0.9665 | 0.71 |
| 0.7215 | 4.0 | 450 | 0.8201 | 0.74 |
| 0.4679 | 5.0 | 562 | 0.7616 | 0.75 |
| 0.3626 | 6.0 | 675 | 0.5217 | 0.85 |
| 0.1775 | 7.0 | 787 | 0.6748 | 0.81 |
| 0.1642 | 8.0 | 900 | 0.5287 | 0.86 |
| 0.0772 | 9.0 | 1012 | 0.5632 | 0.84 |
| 0.0478 | 10.0 | 1125 | 0.5576 | 0.85 |
| 0.0662 | 11.0 | 1237 | 0.5455 | 0.88 |
| 0.0446 | 11.95 | 1344 | 0.5542 | 0.87 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 1.13.1
- Datasets 2.8.0
- Tokenizers 0.13.2