---
library_name: transformers
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: videomae-base-finetuned-ucf-crimevbinary-balanced-vwandb
  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-base-finetuned-ucf-crimevbinary-balanced-vwandb

This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2106
- Accuracy: 0.9444
- Precision: 0.9444
- Recall: 0.9444
- Auc: 0.9815

## 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
- 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_steps: 500
- num_epochs: 30

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | Auc    |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.6542        | 1.0   | 29   | 0.6413          | 0.6389   | 0.7217    | 0.6389 | 0.8056 |
| 0.574         | 2.0   | 58   | 0.5412          | 0.75     | 0.7945    | 0.75   | 0.8827 |
| 0.4214        | 3.0   | 87   | 0.4414          | 0.8611   | 0.8714    | 0.8611 | 0.9228 |
| 0.4331        | 4.0   | 116  | 0.4604          | 0.8056   | 0.8311    | 0.8056 | 0.8889 |
| 0.2981        | 5.0   | 145  | 0.3923          | 0.8889   | 0.8937    | 0.8889 | 0.9321 |
| 0.2615        | 6.0   | 174  | 0.5136          | 0.8333   | 0.8506    | 0.8333 | 0.8735 |
| 0.1896        | 7.0   | 203  | 0.4989          | 0.8889   | 0.9091    | 0.8889 | 0.9105 |
| 0.5031        | 8.0   | 232  | 0.3814          | 0.9167   | 0.9180    | 0.9167 | 0.9321 |
| 0.0947        | 9.0   | 261  | 0.4635          | 0.8889   | 0.8937    | 0.8889 | 0.9290 |
| 0.3865        | 10.0  | 290  | 0.5199          | 0.8889   | 0.9091    | 0.8889 | 0.8951 |
| 0.187         | 11.0  | 319  | 0.6748          | 0.8611   | 0.8622    | 0.8611 | 0.9136 |
| 0.0408        | 12.0  | 348  | 1.0193          | 0.8056   | 0.8143    | 0.8056 | 0.9012 |
| 0.3851        | 13.0  | 377  | 0.3708          | 0.8889   | 0.8889    | 0.8889 | 0.9630 |


### Framework versions

- Transformers 4.47.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3