---
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: small-deepfake
  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. -->

# small-deepfake

This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7417
- Accuracy: 0.3

## 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: 0.0001
- 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: 16

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log        | 0.8   | 2    | 0.7128          | 0.3      |
| No log        | 2.0   | 5    | 0.7450          | 0.3      |
| No log        | 2.8   | 7    | 0.7814          | 0.3      |
| 0.6885        | 4.0   | 10   | 0.8762          | 0.3      |
| 0.6885        | 4.8   | 12   | 0.7284          | 0.3      |
| 0.6885        | 6.0   | 15   | 0.7457          | 0.3      |
| 0.6885        | 6.8   | 17   | 0.7277          | 0.3      |
| 0.6925        | 8.0   | 20   | 0.7421          | 0.3      |
| 0.6925        | 8.8   | 22   | 0.7391          | 0.3      |
| 0.6925        | 10.0  | 25   | 0.7539          | 0.3      |
| 0.6925        | 10.8  | 27   | 0.7482          | 0.3      |
| 0.6897        | 12.0  | 30   | 0.7440          | 0.3      |
| 0.6897        | 12.8  | 32   | 0.7417          | 0.3      |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2