metadata
license: bsd-3-clause
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ast_7-finetuned-ICBHI
results: []
ast_7-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: 1.3090
- Accuracy: 0.6511
- Sensitivity: 0.5012
- Specificity: 0.7852
- Score: 0.6432
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 |
|---|---|---|---|---|---|---|---|
| 0.9395 | 1.0 | 258 | 1.0192 | 0.5859 | 0.5157 | 0.6486 | 0.5822 |
| 0.8124 | 2.0 | 517 | 0.8565 | 0.6471 | 0.3461 | 0.9163 | 0.6312 |
| 0.6617 | 3.0 | 776 | 0.9657 | 0.6308 | 0.5810 | 0.6754 | 0.6282 |
| 0.2333 | 4.0 | 1035 | 1.1466 | 0.6504 | 0.4482 | 0.8312 | 0.6397 |
| 0.0711 | 4.99 | 1290 | 1.3090 | 0.6511 | 0.5012 | 0.7852 | 0.6432 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3