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: 0.84
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: 0.6253
- Accuracy: 0.84
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.1493 | 1.0 | 56 | 2.0306 | 0.53 |
| 1.5907 | 1.99 | 112 | 1.4564 | 0.69 |
| 1.3192 | 2.99 | 168 | 1.1955 | 0.7 |
| 1.1758 | 4.0 | 225 | 1.0190 | 0.75 |
| 0.9033 | 5.0 | 281 | 0.8936 | 0.82 |
| 0.7127 | 5.99 | 337 | 0.7668 | 0.78 |
| 0.5503 | 6.99 | 393 | 0.7165 | 0.78 |
| 0.4843 | 8.0 | 450 | 0.6483 | 0.83 |
| 0.3883 | 9.0 | 506 | 0.6441 | 0.82 |
| 0.3674 | 9.96 | 560 | 0.6253 | 0.84 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3