metadata
license: bsd-3-clause
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
base_model: MIT/ast-finetuned-audioset-10-10-0.4593
model-index:
- name: ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan
results: []
ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan
This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.4400
- Accuracy: 0.91
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6505 | 1.0 | 113 | 0.6775 | 0.77 |
| 0.2847 | 2.0 | 226 | 0.6989 | 0.78 |
| 0.4559 | 3.0 | 339 | 0.5821 | 0.85 |
| 0.1643 | 4.0 | 452 | 0.6462 | 0.85 |
| 0.0083 | 5.0 | 565 | 0.6071 | 0.87 |
| 0.0281 | 6.0 | 678 | 0.5648 | 0.87 |
| 0.0001 | 7.0 | 791 | 0.4394 | 0.92 |
| 0.0002 | 8.0 | 904 | 0.4378 | 0.9 |
| 0.1345 | 9.0 | 1017 | 0.4299 | 0.9 |
| 0.0002 | 10.0 | 1130 | 0.4400 | 0.91 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3