metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- audio-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: wav2vec2-base-ft-fake-detection
results: []
wav2vec2-base-ft-fake-detection
This model is a fine-tuned version of facebook/wav2vec2-base on the alexandreacff/kaggle-fake-detection dataset. It achieves the following results on the evaluation set:
- Loss: 0.6261
- Accuracy: 0.6523
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 |
|---|---|---|---|---|
| 0.6253 | 0.9851 | 33 | 0.6261 | 0.6523 |
| 0.4394 | 2.0 | 67 | 0.7140 | 0.5645 |
| 0.3685 | 2.9851 | 100 | 0.7181 | 0.5850 |
| 0.317 | 4.0 | 134 | 0.7291 | 0.6150 |
| 0.3027 | 4.9851 | 167 | 0.7457 | 0.6159 |
| 0.2672 | 6.0 | 201 | 0.7805 | 0.6243 |
| 0.2711 | 6.9851 | 234 | 0.8113 | 0.6215 |
| 0.2086 | 8.0 | 268 | 0.9130 | 0.5963 |
| 0.2077 | 8.9851 | 301 | 0.9042 | 0.6168 |
| 0.223 | 9.8507 | 330 | 0.8924 | 0.6178 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.1.0a0+32f93b1
- Datasets 2.19.1
- Tokenizers 0.19.1