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: 0.87
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: 0.5727
- Accuracy: 0.87
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: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|
| 1.9673 | 1.0 | 113 | 1.8630 | 0.52 |
| 1.2473 | 2.0 | 226 | 1.2624 | 0.65 |
| 1.0745 | 3.0 | 339 | 1.0512 | 0.68 |
| 0.7251 | 4.0 | 452 | 0.8825 | 0.75 |
| 0.5696 | 5.0 | 565 | 0.6549 | 0.85 |
| 0.3387 | 6.0 | 678 | 0.5806 | 0.84 |
| 0.2367 | 7.0 | 791 | 0.6163 | 0.83 |
| 0.13 | 8.0 | 904 | 0.6484 | 0.83 |
| 0.1232 | 9.0 | 1017 | 0.5800 | 0.85 |
| 0.1115 | 10.0 | 1130 | 0.5727 | 0.87 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1