metadata
license: bsd-3-clause
base_model: MIT/ast-finetuned-audioset-10-10-0.4593
tags:
- generated_from_trainer
datasets:
- Nooon/Donate_a_cry
metrics:
- accuracy
model-index:
- name: ast-finetuned-cry
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: DonateACry
type: Nooon/Donate_a_cry
config: train
split: train
args: train
metrics:
- name: Accuracy
type: accuracy
value: 0.5454545454545454
ast-finetuned-cry
This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on the DonateACry dataset. It achieves the following results on the evaluation set:
- Loss: 1.6404
- Accuracy: 0.5455
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6297 | 1.0 | 11 | 1.6891 | 0.3636 |
| 1.1137 | 2.0 | 22 | 1.3156 | 0.4545 |
| 0.5047 | 3.0 | 33 | 1.3955 | 0.4545 |
| 0.2062 | 4.0 | 44 | 1.4002 | 0.6364 |
| 0.0613 | 5.0 | 55 | 1.6693 | 0.5455 |
| 0.0142 | 6.0 | 66 | 1.3452 | 0.6364 |
| 0.0053 | 7.0 | 77 | 1.6914 | 0.5455 |
| 0.0038 | 8.0 | 88 | 1.6689 | 0.5455 |
| 0.0027 | 9.0 | 99 | 1.6357 | 0.5455 |
| 0.002 | 10.0 | 110 | 1.6404 | 0.5455 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1