metadata
license: apache-2.0
base_model: sanchit-gandhi/distilhubert-finetuned-gtzan-5-epochs
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan-5-epochs-finetuned-gtzan-QUIZ
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: 0.82
distilhubert-finetuned-gtzan-5-epochs-finetuned-gtzan-QUIZ
This model is a fine-tuned version of sanchit-gandhi/distilhubert-finetuned-gtzan-5-epochs on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.6130
- Accuracy: 0.82
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: 9e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2256 | 0.9956 | 14 | 0.9755 | 0.68 |
| 0.9523 | 1.9911 | 28 | 0.8490 | 0.75 |
| 0.6907 | 2.9867 | 42 | 0.7725 | 0.78 |
| 0.5448 | 3.9822 | 56 | 0.6968 | 0.81 |
| 0.4604 | 4.9778 | 70 | 0.6409 | 0.81 |
| 0.4355 | 5.9733 | 84 | 0.6271 | 0.81 |
| 0.375 | 6.9689 | 98 | 0.6130 | 0.82 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1