metadata
library_name: transformers
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: 0.75
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: 0.8728
- Accuracy: 0.75
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: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.2872 | 0.9956 | 14 | 2.1804 | 0.31 |
2.0327 | 1.9911 | 28 | 1.8048 | 0.55 |
1.6638 | 2.9867 | 42 | 1.5831 | 0.57 |
1.4257 | 3.9822 | 56 | 1.3604 | 0.66 |
1.1899 | 4.9778 | 70 | 1.1437 | 0.71 |
1.1012 | 5.9733 | 84 | 1.0711 | 0.69 |
0.9901 | 6.9689 | 98 | 0.9877 | 0.72 |
0.9088 | 7.9644 | 112 | 0.8899 | 0.79 |
0.7938 | 8.96 | 126 | 0.8887 | 0.75 |
0.8121 | 9.9556 | 140 | 0.8728 | 0.75 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1