metadata
license: apache-2.0
base_model: asapp/sew-mid-100k
tags:
- audio-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: sew-ft-fake-detection
results: []
sew-ft-fake-detection
This model is a fine-tuned version of asapp/sew-mid-100k on the alexandreacff/kaggle-fake-detection dataset. It achieves the following results on the evaluation set:
- Loss: 0.6232
- Accuracy: 0.7439
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: 32
- eval_batch_size: 16
- seed: 0
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6344 | 0.9851 | 33 | 0.6395 | 0.6505 |
| 0.6157 | 2.0 | 67 | 0.6703 | 0.5215 |
| 0.5572 | 2.9851 | 100 | 0.5615 | 0.7131 |
| 0.4968 | 4.0 | 134 | 0.8149 | 0.6944 |
| 0.4988 | 4.9851 | 167 | 0.8099 | 0.7037 |
| 0.4756 | 6.0 | 201 | 0.8319 | 0.7103 |
| 0.4334 | 6.9851 | 234 | 0.7317 | 0.7336 |
| 0.4321 | 8.0 | 268 | 0.6548 | 0.7383 |
| 0.4436 | 8.9851 | 301 | 0.6232 | 0.7439 |
| 0.4493 | 9.8507 | 330 | 0.6278 | 0.7439 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.1.0a0+32f93b1
- Datasets 2.19.1
- Tokenizers 0.19.1