wavLM-base-DeepFake_UTCN
This model is a fine-tuned version of microsoft/wavLM-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9119
- Accuracy: 0.73
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0316 | 1.0 | 281 | 1.0076 | 0.6022 |
| 0.0486 | 2.0 | 562 | 1.2997 | 0.4522 |
| 0.0788 | 3.0 | 843 | 1.1793 | 0.6089 |
| 0.0559 | 4.0 | 1125 | 1.0675 | 0.6678 |
| 0.0396 | 5.0 | 1405 | 0.9119 | 0.73 |
Framework versions
- Transformers 4.30.0
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.13.3