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: 0.72
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: 1.3187
- Accuracy: 0.72
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: 2e-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: 11
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.2889 | 0.9912 | 28 | 2.2613 | 0.38 |
| 2.1553 | 1.9823 | 56 | 2.0953 | 0.56 |
| 1.9626 | 2.9735 | 84 | 1.8820 | 0.54 |
| 1.7839 | 4.0 | 113 | 1.7308 | 0.61 |
| 1.6749 | 4.9912 | 141 | 1.5920 | 0.64 |
| 1.5595 | 5.9823 | 169 | 1.5004 | 0.68 |
| 1.5266 | 6.9735 | 197 | 1.4368 | 0.68 |
| 1.4459 | 8.0 | 226 | 1.3776 | 0.71 |
| 1.4152 | 8.9912 | 254 | 1.3481 | 0.71 |
| 1.3766 | 9.9823 | 282 | 1.3242 | 0.72 |
| 1.3682 | 10.9027 | 308 | 1.3187 | 0.72 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1