|
--- |
|
license: bsd-3-clause |
|
base_model: MIT/ast-finetuned-audioset-10-10-0.4593 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: SeizureClassifier_AST_B_43829950 |
|
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. --> |
|
|
|
# SeizureClassifier_AST_B_43829950 |
|
|
|
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: 0.0063 |
|
- Accuracy: 1.0 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 15 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.269 | 0.99 | 44 | 1.1676 | 0.8564 | |
|
| 0.7525 | 1.99 | 88 | 0.5446 | 0.9777 | |
|
| 0.3005 | 2.98 | 132 | 0.2273 | 0.9876 | |
|
| 0.185 | 4.0 | 177 | 0.1556 | 0.9653 | |
|
| 0.0935 | 4.99 | 221 | 0.0798 | 0.9901 | |
|
| 0.0545 | 5.99 | 265 | 0.0313 | 0.9950 | |
|
| 0.0416 | 6.98 | 309 | 0.0278 | 0.9950 | |
|
| 0.0264 | 8.0 | 354 | 0.0682 | 0.9851 | |
|
| 0.0109 | 8.99 | 398 | 0.0311 | 0.9950 | |
|
| 0.0104 | 9.99 | 442 | 0.0085 | 1.0 | |
|
| 0.0083 | 10.98 | 486 | 0.0143 | 0.9975 | |
|
| 0.0067 | 12.0 | 531 | 0.0070 | 1.0 | |
|
| 0.0063 | 12.99 | 575 | 0.0066 | 1.0 | |
|
| 0.006 | 13.99 | 619 | 0.0064 | 1.0 | |
|
| 0.0059 | 14.92 | 660 | 0.0063 | 1.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.2+cu118 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
