metadata
license: bsd-3-clause
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ast_10-finetuned-ICBHI
results: []
ast_10-finetuned-ICBHI
This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2536
- Accuracy: 0.6514
- Sensitivity: 0.4559
- Specificity: 0.8264
- Score: 0.6411
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Sensitivity | Specificity | Score |
|---|---|---|---|---|---|---|---|
| 0.9062 | 1.0 | 258 | 1.0048 | 0.5906 | 0.5257 | 0.6486 | 0.5872 |
| 0.8257 | 2.0 | 517 | 0.8676 | 0.6435 | 0.3645 | 0.8929 | 0.6287 |
| 0.6324 | 3.0 | 776 | 0.9607 | 0.6409 | 0.4912 | 0.7749 | 0.6330 |
| 0.1494 | 4.0 | 1035 | 1.2536 | 0.6514 | 0.4559 | 0.8264 | 0.6411 |
| 0.0472 | 4.99 | 1290 | 1.5260 | 0.6486 | 0.5035 | 0.7783 | 0.6409 |
Framework versions
- Transformers 4.29.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3