ast-finetuned-audioset-10-10-0.4593-heart-sounds
This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1499
- Accuracy: 0.9695
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2135 | 1.0 | 83 | 0.1724 | 0.9390 |
| 0.1655 | 2.0 | 166 | 0.2276 | 0.8918 |
| 0.0959 | 3.0 | 249 | 0.1166 | 0.9527 |
| 0.04 | 4.0 | 332 | 0.1106 | 0.9634 |
| 0.0142 | 5.0 | 415 | 0.1317 | 0.9634 |
| 0.0186 | 6.0 | 498 | 0.1424 | 0.9665 |
| 0.0022 | 7.0 | 581 | 0.1433 | 0.9695 |
| 0.0009 | 7.9119 | 656 | 0.1499 | 0.9680 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.0.1+cu118
- Datasets 3.3.2
- Tokenizers 0.21.0