---
library_name: transformers
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: videomae-tiny-binary-finetuned-xd-violence
  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. -->

# videomae-tiny-binary-finetuned-xd-violence

This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6057
- Accuracy: 0.6815
- F1: 0.5197
- Precision: 0.5965
- Recall: 0.4604
- Specificity: 0.8137
- True Positives: 6205
- True Negatives: 18337
- False Positives: 4197
- False Negatives: 7272

## 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: 0.0005
- train_batch_size: 8
- 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
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 1684

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     | Precision | Recall | Specificity | True Positives | True Negatives | False Positives | False Negatives |
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:-----------:|:--------------:|:--------------:|:---------------:|:---------------:|
| 0.698         | 0.2506 | 422  | 0.6440          | 0.6324   | 0.3758 | 0.5154    | 0.2957 | 0.8337      | 3985           | 18787          | 3747            | 9492            |
| 0.6132        | 1.2506 | 844  | 0.6481          | 0.6394   | 0.5759 | 0.5144    | 0.6540 | 0.6307      | 8814           | 14213          | 8321            | 4663            |
| 0.6364        | 2.2506 | 1266 | 0.6168          | 0.6617   | 0.5356 | 0.5508    | 0.5212 | 0.7458      | 7024           | 16805          | 5729            | 6453            |
| 0.5219        | 3.2482 | 1684 | 0.6057          | 0.6815   | 0.5197 | 0.5965    | 0.4604 | 0.8137      | 6205           | 18337          | 4197            | 7272            |


### Framework versions

- Transformers 4.51.3
- Pytorch 2.1.0+cu118
- Datasets 3.6.0
- Tokenizers 0.21.1