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: 0.88
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: 0.4870
- Accuracy: 0.88
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: 10
- eval_batch_size: 10
- 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 |
|---|---|---|---|---|
| 2.0372 | 1.0 | 90 | 1.9388 | 0.45 |
| 1.3497 | 2.0 | 180 | 1.3371 | 0.64 |
| 0.9339 | 3.0 | 270 | 1.0227 | 0.7 |
| 0.8379 | 4.0 | 360 | 0.8165 | 0.79 |
| 0.6075 | 5.0 | 450 | 0.6923 | 0.84 |
| 0.4431 | 6.0 | 540 | 0.5944 | 0.87 |
| 0.3309 | 7.0 | 630 | 0.5684 | 0.84 |
| 0.1852 | 8.0 | 720 | 0.4463 | 0.88 |
| 0.2007 | 9.0 | 810 | 0.4671 | 0.9 |
| 0.1486 | 10.0 | 900 | 0.4870 | 0.88 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.1+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0