|
--- |
|
license: bsd-3-clause |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: ast_22-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_22-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: 2.5036 |
|
- Accuracy: 0.6867 |
|
- Sensitivity: 0.5346 |
|
- Specificity: 0.8228 |
|
- Score: 0.6787 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Sensitivity | Specificity | Score | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:-----------:|:------:| |
|
| 1.0662 | 1.0 | 345 | 0.9169 | 0.6389 | 0.3963 | 0.8558 | 0.6260 | |
|
| 0.7055 | 2.0 | 690 | 0.8638 | 0.6512 | 0.4516 | 0.8297 | 0.6406 | |
|
| 0.5748 | 3.0 | 1035 | 0.9060 | 0.6599 | 0.4409 | 0.8558 | 0.6483 | |
|
| 0.3318 | 4.0 | 1380 | 1.1034 | 0.6555 | 0.3641 | 0.9162 | 0.6401 | |
|
| 0.1411 | 5.0 | 1725 | 1.3586 | 0.6838 | 0.5346 | 0.8173 | 0.6759 | |
|
| 0.0854 | 6.0 | 2070 | 2.1432 | 0.6759 | 0.4608 | 0.8681 | 0.6645 | |
|
| 0.0186 | 7.0 | 2415 | 2.3421 | 0.6715 | 0.5545 | 0.7761 | 0.6653 | |
|
| 0.0417 | 8.0 | 2760 | 2.4426 | 0.6824 | 0.5361 | 0.8132 | 0.6746 | |
|
| 0.0001 | 9.0 | 3105 | 2.4895 | 0.6831 | 0.5346 | 0.8159 | 0.6752 | |
|
| 0.0 | 10.0 | 3450 | 2.5036 | 0.6867 | 0.5346 | 0.8228 | 0.6787 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.29.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
