metadata
library_name: transformers
license: apache-2.0
base_model: sanchit-gandhi/distilhubert-finetuned-gtzan
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: Mawaddaa/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: 0.83
Mawaddaa/distilhubert-finetuned-gtzan
This model is a fine-tuned version of sanchit-gandhi/distilhubert-finetuned-gtzan on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.8145
- Accuracy: 0.83
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: 4
- seed: 42
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.9096 | 1.0 | 225 | 1.7239 | 0.49 |
| 1.056 | 2.0 | 450 | 1.1898 | 0.66 |
| 0.5824 | 3.0 | 675 | 0.7905 | 0.74 |
| 0.2286 | 4.0 | 900 | 0.7436 | 0.8 |
| 0.3129 | 5.0 | 1125 | 0.5656 | 0.84 |
| 0.046 | 6.0 | 1350 | 0.6575 | 0.83 |
| 0.1413 | 7.0 | 1575 | 0.6421 | 0.83 |
| 0.0208 | 8.0 | 1800 | 0.8335 | 0.84 |
| 0.0088 | 9.0 | 2025 | 0.8039 | 0.85 |
| 0.0087 | 10.0 | 2250 | 0.8145 | 0.83 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1