|
--- |
|
license: bsd-3-clause |
|
base_model: MIT/ast-finetuned-audioset-10-10-0.4593 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- recall |
|
- precision |
|
model-index: |
|
- name: ast-finetuned-audioset-10-10-0.4593-finetuned-common_voice |
|
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-finetuned-audioset-10-10-0.4593-finetuned-common_voice |
|
|
|
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: 0.5704 |
|
- Accuracy: 0.8775 |
|
- F1: 0.8773 |
|
- Recall: 0.8775 |
|
- Precision: 0.8773 |
|
- Mcc: 0.8469 |
|
- Auc: 0.9835 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- 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 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision | Mcc | Auc | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|:------:|:------:| |
|
| 1.0165 | 1.0 | 200 | 1.2394 | 0.5575 | 0.4931 | 0.5575 | 0.4662 | 0.4677 | 0.8879 | |
|
| 0.8119 | 2.0 | 400 | 0.5971 | 0.7575 | 0.7576 | 0.7575 | 0.7668 | 0.6992 | 0.9592 | |
|
| 0.1652 | 3.0 | 600 | 0.5719 | 0.815 | 0.8161 | 0.8150 | 0.8273 | 0.7711 | 0.9713 | |
|
| 0.0829 | 4.0 | 800 | 0.8850 | 0.8 | 0.8017 | 0.8 | 0.8346 | 0.7590 | 0.9730 | |
|
| 0.0102 | 5.0 | 1000 | 0.7974 | 0.8375 | 0.8386 | 0.8375 | 0.8590 | 0.8024 | 0.9778 | |
|
| 0.0004 | 6.0 | 1200 | 0.5919 | 0.86 | 0.8607 | 0.86 | 0.8632 | 0.8254 | 0.9815 | |
|
| 0.0 | 7.0 | 1400 | 0.5652 | 0.88 | 0.8798 | 0.8800 | 0.8803 | 0.8502 | 0.9833 | |
|
| 0.0 | 8.0 | 1600 | 0.5665 | 0.875 | 0.8749 | 0.875 | 0.8749 | 0.8438 | 0.9834 | |
|
| 0.0 | 9.0 | 1800 | 0.5695 | 0.8775 | 0.8773 | 0.8775 | 0.8773 | 0.8469 | 0.9835 | |
|
| 0.0 | 10.0 | 2000 | 0.5704 | 0.8775 | 0.8773 | 0.8775 | 0.8773 | 0.8469 | 0.9835 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.0 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|