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: 0.9359
- 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: 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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.2494 | 1.0 | 113 | 2.1568 | 0.36 |
| 1.7795 | 2.0 | 226 | 1.7904 | 0.38 |
| 1.5798 | 3.0 | 339 | 1.6144 | 0.5 |
| 1.6354 | 4.0 | 452 | 1.2584 | 0.66 |
| 0.9675 | 5.0 | 565 | 1.1453 | 0.64 |
| 0.995 | 6.0 | 678 | 0.9740 | 0.67 |
| 1.2052 | 7.0 | 791 | 1.0552 | 0.68 |
| 0.7028 | 8.0 | 904 | 0.8980 | 0.74 |
| 0.7472 | 9.0 | 1017 | 0.9431 | 0.72 |
| 0.3181 | 10.0 | 1130 | 0.8750 | 0.75 |
| 0.3948 | 11.0 | 1243 | 1.0047 | 0.73 |
| 0.3507 | 12.0 | 1356 | 0.8054 | 0.81 |
| 0.1785 | 13.0 | 1469 | 0.7866 | 0.84 |
| 0.2453 | 14.0 | 1582 | 0.8960 | 0.82 |
| 0.2832 | 15.0 | 1695 | 1.0770 | 0.81 |
| 0.2132 | 16.0 | 1808 | 0.9359 | 0.82 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1