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: 0.79
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: 0.6862
- Accuracy: 0.79
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: 20
- eval_batch_size: 20
- 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 |
|---|---|---|---|---|
| 2.1654 | 1.0 | 45 | 2.0737 | 0.46 |
| 1.6926 | 2.0 | 90 | 1.5669 | 0.55 |
| 1.2793 | 3.0 | 135 | 1.1986 | 0.77 |
| 1.0386 | 4.0 | 180 | 1.0169 | 0.78 |
| 0.9172 | 5.0 | 225 | 0.9652 | 0.71 |
| 0.7859 | 6.0 | 270 | 0.7929 | 0.79 |
| 0.7468 | 7.0 | 315 | 0.7860 | 0.75 |
| 0.6594 | 8.0 | 360 | 0.7388 | 0.79 |
| 0.471 | 9.0 | 405 | 0.6955 | 0.79 |
| 0.5886 | 10.0 | 450 | 0.6862 | 0.79 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3