|
--- |
|
license: bsd-3-clause |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: ast_binary_6-finetuned-ICBHI |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# ast_binary_6-finetuned-ICBHI |
|
|
|
This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6811 |
|
- Accuracy: 0.6 |
|
- Sensitivity: 0.6593 |
|
- Specificity: 0.5558 |
|
- Score: 0.6075 |
|
|
|
## 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: 7 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Sensitivity | Specificity | Score | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:-----------:|:------:| |
|
| 0.6592 | 1.0 | 259 | 0.6811 | 0.6 | 0.6593 | 0.5558 | 0.6075 | |
|
| 0.5766 | 2.0 | 518 | 0.7937 | 0.5779 | 0.5939 | 0.5659 | 0.5799 | |
|
| 0.5117 | 3.0 | 777 | 1.0242 | 0.5267 | 0.8139 | 0.3124 | 0.5632 | |
|
| 0.5407 | 4.0 | 1036 | 0.9152 | 0.5445 | 0.8088 | 0.3473 | 0.5781 | |
|
| 0.4504 | 5.0 | 1295 | 0.9963 | 0.5401 | 0.7596 | 0.3764 | 0.5680 | |
|
| 0.4304 | 6.0 | 1554 | 0.9598 | 0.5579 | 0.6814 | 0.4658 | 0.5736 | |
|
| 0.4132 | 7.0 | 1813 | 0.9771 | 0.5506 | 0.6950 | 0.4430 | 0.5690 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.29.2 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
