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: 0.84
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: 0.5973
- Accuracy: 0.84
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|
| 1.9359 | 1.0 | 57 | 1.7782 | 0.49 |
| 1.2053 | 2.0 | 114 | 1.1174 | 0.69 |
| 0.8559 | 3.0 | 171 | 0.8714 | 0.79 |
| 0.6889 | 4.0 | 228 | 0.7290 | 0.79 |
| 0.4995 | 5.0 | 285 | 0.5888 | 0.85 |
| 0.2781 | 6.0 | 342 | 0.6412 | 0.83 |
| 0.2084 | 7.0 | 399 | 0.5679 | 0.86 |
| 0.1132 | 8.0 | 456 | 0.5744 | 0.85 |
| 0.088 | 9.0 | 513 | 0.5985 | 0.84 |
| 0.046 | 10.0 | 570 | 0.5973 | 0.84 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.0
- Tokenizers 0.13.3