metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-large
tags:
- generated_from_trainer
model-index:
- name: violence_detection
results: []
violence_detection
This model is a fine-tuned version of MCG-NJU/videomae-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4693
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 35 | 0.7807 |
| No log | 2.0 | 70 | 0.9209 |
| No log | 3.0 | 105 | 0.5725 |
| No log | 4.0 | 140 | 0.5501 |
| No log | 5.0 | 175 | 0.5701 |
| No log | 6.0 | 210 | 0.6286 |
| No log | 7.0 | 245 | 0.7121 |
| No log | 8.0 | 280 | 0.4971 |
| No log | 9.0 | 315 | 0.5575 |
| No log | 10.0 | 350 | 0.6327 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1