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: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.81
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: 1.0871
- Accuracy: 0.81
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: 0.0005
- 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: 13
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6787 | 1.0 | 113 | 1.4804 | 0.46 |
| 1.4134 | 2.0 | 226 | 1.6296 | 0.44 |
| 1.4536 | 3.0 | 339 | 1.3835 | 0.56 |
| 1.1097 | 4.0 | 452 | 1.1306 | 0.58 |
| 0.8519 | 5.0 | 565 | 0.8645 | 0.72 |
| 0.742 | 6.0 | 678 | 1.0428 | 0.65 |
| 0.6929 | 7.0 | 791 | 0.7206 | 0.77 |
| 0.4051 | 8.0 | 904 | 0.9420 | 0.73 |
| 0.2071 | 9.0 | 1017 | 1.0854 | 0.75 |
| 0.1246 | 10.0 | 1130 | 1.1561 | 0.79 |
| 0.0404 | 11.0 | 1243 | 1.1811 | 0.79 |
| 0.0137 | 12.0 | 1356 | 1.1096 | 0.8 |
| 0.0017 | 13.0 | 1469 | 1.0871 | 0.81 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3