metadata
license: apache-2.0
base_model: facebook/hubert-base-ls960
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: hubert-base-ls960-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: 0.82
hubert-base-ls960-finetuned-gtzan
This model is a fine-tuned version of facebook/hubert-base-ls960 on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.5845
- Accuracy: 0.82
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 10
- total_train_batch_size: 10
- 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 |
|---|---|---|---|---|
| 2.0942 | 0.99 | 89 | 2.0216 | 0.33 |
| 1.713 | 1.99 | 179 | 1.5801 | 0.43 |
| 1.3519 | 2.99 | 269 | 1.2871 | 0.62 |
| 1.182 | 3.99 | 359 | 1.1647 | 0.65 |
| 1.0645 | 4.99 | 449 | 0.9332 | 0.71 |
| 0.8777 | 6.0 | 539 | 0.8251 | 0.77 |
| 0.7 | 7.0 | 629 | 0.8725 | 0.77 |
| 0.4387 | 8.0 | 719 | 0.8215 | 0.77 |
| 0.567 | 9.0 | 809 | 0.5571 | 0.85 |
| 0.5342 | 9.9 | 890 | 0.5845 | 0.82 |
Framework versions
- Transformers 4.31.0
- Pytorch 1.13.1
- Datasets 2.13.1
- Tokenizers 0.13.3