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: 0.7
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: 1.6085
- Accuracy: 0.7
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: 1e-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 |
|---|---|---|---|---|
| 2.284 | 1.0 | 45 | 2.2715 | 0.28 |
| 2.2235 | 2.0 | 90 | 2.1789 | 0.47 |
| 2.0628 | 3.0 | 135 | 2.0368 | 0.63 |
| 1.9314 | 4.0 | 180 | 1.9068 | 0.66 |
| 1.8308 | 5.0 | 225 | 1.8077 | 0.66 |
| 1.7901 | 6.0 | 270 | 1.7276 | 0.7 |
| 1.7703 | 7.0 | 315 | 1.6747 | 0.69 |
| 1.7163 | 8.0 | 360 | 1.6382 | 0.69 |
| 1.6133 | 9.0 | 405 | 1.6154 | 0.7 |
| 1.6876 | 10.0 | 450 | 1.6085 | 0.7 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3