metadata
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan-v2
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: gtzan
type: gtzan
config: all
split: train
args: all
metrics:
- name: Accuracy
type: accuracy
value: 0.83
distilhubert-finetuned-gtzan-v2
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: 0.6766
- Accuracy: 0.83
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: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0361 | 1.0 | 113 | 1.8915 | 0.41 |
| 1.3728 | 2.0 | 226 | 1.2725 | 0.64 |
| 1.0442 | 3.0 | 339 | 0.9188 | 0.78 |
| 0.9614 | 4.0 | 452 | 0.8790 | 0.7 |
| 0.6945 | 5.0 | 565 | 0.6933 | 0.79 |
| 0.3976 | 6.0 | 678 | 0.6891 | 0.79 |
| 0.345 | 7.0 | 791 | 0.6091 | 0.81 |
| 0.1068 | 8.0 | 904 | 0.5905 | 0.81 |
| 0.1646 | 9.0 | 1017 | 0.5809 | 0.82 |
| 0.1079 | 10.0 | 1130 | 0.6527 | 0.81 |
| 0.0311 | 11.0 | 1243 | 0.6393 | 0.86 |
| 0.0491 | 12.0 | 1356 | 0.6766 | 0.83 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.2
- Datasets 2.16.1
- Tokenizers 0.13.2