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: 0.85
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: 0.6339
- 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
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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 |
|---|---|---|---|---|
| 0.3209 | 0.99 | 28 | 0.6060 | 0.79 |
| 0.2765 | 1.98 | 56 | 0.6062 | 0.8 |
| 0.1591 | 2.97 | 84 | 0.5890 | 0.82 |
| 0.1229 | 4.0 | 113 | 0.5589 | 0.85 |
| 0.1015 | 4.99 | 141 | 0.6551 | 0.87 |
| 0.0537 | 5.98 | 169 | 0.6066 | 0.84 |
| 0.0422 | 6.97 | 197 | 0.5947 | 0.84 |
| 0.0422 | 8.0 | 226 | 0.5898 | 0.85 |
| 0.0415 | 8.99 | 254 | 0.6020 | 0.85 |
| 0.0296 | 9.91 | 280 | 0.6339 | 0.85 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.3
- Tokenizers 0.13.3