---
library_name: transformers
base_model: nguyenkhoa/dinov2_Liveness_detection_v2.1.2
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- recall
- precision
model-index:
- name: dinov2_Liveness_detection_v2.1.3
  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. -->

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/nguyenkhoaht002/liveness_detection/runs/svxcqjbb)
# dinov2_Liveness_detection_v2.1.3

This model is a fine-tuned version of [nguyenkhoa/dinov2_Liveness_detection_v2.1.2](https://huggingface.co/nguyenkhoa/dinov2_Liveness_detection_v2.1.2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0123
- Accuracy: 0.9976
- F1: 0.9976
- Recall: 0.9976
- Precision: 0.9976

## 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: 5e-05
- train_batch_size: 768
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     | Recall | Precision |
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|
| 0.1276        | 0.3232 | 64   | 0.0239          | 0.992    | 0.9920 | 0.992  | 0.9921    |
| 0.0273        | 0.6465 | 128  | 0.0253          | 0.9908   | 0.9908 | 0.9908 | 0.9908    |
| 0.0236        | 0.9697 | 192  | 0.0257          | 0.9908   | 0.9908 | 0.9908 | 0.9908    |
| 0.015         | 1.2929 | 256  | 0.0223          | 0.9936   | 0.9936 | 0.9936 | 0.9936    |
| 0.0133        | 1.6162 | 320  | 0.0144          | 0.9954   | 0.9954 | 0.9954 | 0.9954    |
| 0.0149        | 1.9394 | 384  | 0.0271          | 0.9913   | 0.9913 | 0.9913 | 0.9914    |
| 0.0097        | 2.2626 | 448  | 0.0234          | 0.9922   | 0.9922 | 0.9922 | 0.9922    |
| 0.009         | 2.5859 | 512  | 0.0149          | 0.9954   | 0.9954 | 0.9954 | 0.9954    |
| 0.0076        | 2.9091 | 576  | 0.0184          | 0.9952   | 0.9952 | 0.9952 | 0.9952    |
| 0.0045        | 3.2323 | 640  | 0.0201          | 0.9951   | 0.9951 | 0.9951 | 0.9951    |
| 0.0032        | 3.5556 | 704  | 0.0169          | 0.9958   | 0.9958 | 0.9958 | 0.9958    |
| 0.0029        | 3.8788 | 768  | 0.0178          | 0.9961   | 0.9960 | 0.9961 | 0.9961    |
| 0.002         | 4.2020 | 832  | 0.0148          | 0.9969   | 0.9969 | 0.9969 | 0.9969    |
| 0.001         | 4.5253 | 896  | 0.0135          | 0.9973   | 0.9973 | 0.9973 | 0.9973    |
| 0.0007        | 4.8485 | 960  | 0.0123          | 0.9976   | 0.9976 | 0.9976 | 0.9976    |


### Framework versions

- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0