metadata
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-crimevbinaryv5
results: []
videomae-base-finetuned-ucf-crimevbinaryv5
This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5233
- Accuracy: 0.8730
- Precision: 0.8739
- Recall: 0.8730
- Auc: 0.9382
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 |
|---|---|---|---|---|---|---|---|
| 0.5298 | 1.0 | 173 | 0.4598 | 0.7952 | 0.8100 | 0.7952 | 0.8607 |
| 0.3824 | 2.0 | 346 | 0.3941 | 0.8434 | 0.8456 | 0.8434 | 0.9138 |
| 0.4836 | 3.0 | 519 | 0.5244 | 0.8032 | 0.8348 | 0.8032 | 0.9153 |
| 0.5522 | 4.0 | 692 | 0.6005 | 0.7149 | 0.8064 | 0.7149 | 0.8669 |
| 0.3953 | 5.0 | 865 | 0.5102 | 0.8474 | 0.8512 | 0.8474 | 0.9071 |
| 0.4682 | 6.0 | 1038 | 0.5437 | 0.8715 | 0.8765 | 0.8715 | 0.9211 |
| 0.2755 | 7.0 | 1211 | 0.7215 | 0.8434 | 0.8668 | 0.8434 | 0.9279 |
| 0.0752 | 8.0 | 1384 | 0.8213 | 0.8554 | 0.8697 | 0.8554 | 0.9166 |
| 0.0448 | 9.0 | 1557 | 0.8370 | 0.8554 | 0.8571 | 0.8554 | 0.8999 |
| 0.0122 | 10.0 | 1730 | 0.7837 | 0.8715 | 0.8718 | 0.8715 | 0.9109 |
| 0.0294 | 11.0 | 1903 | 0.8141 | 0.8715 | 0.8718 | 0.8715 | 0.9079 |
Framework versions
- Transformers 4.47.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3