metadata
license: apache-2.0
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: 0.84
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: 0.9253
- Accuracy: 0.84
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: 2
- eval_batch_size: 2
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3972 | 1.0 | 450 | 1.4662 | 0.65 |
| 0.7118 | 2.0 | 900 | 0.9103 | 0.69 |
| 0.4653 | 3.0 | 1350 | 0.8097 | 0.73 |
| 0.934 | 4.0 | 1800 | 0.7674 | 0.83 |
| 0.3231 | 5.0 | 2250 | 1.2025 | 0.73 |
| 0.0038 | 6.0 | 2700 | 1.1013 | 0.8 |
| 0.002 | 7.0 | 3150 | 0.8540 | 0.86 |
| 0.0022 | 8.0 | 3600 | 0.8067 | 0.85 |
| 0.0013 | 9.0 | 4050 | 0.8682 | 0.86 |
| 0.0016 | 10.0 | 4500 | 0.9253 | 0.84 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.0
- Tokenizers 0.13.3