metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-ucf-crime-abnormal
results: []
videomae-base-finetuned-ucf-crime-abnormal
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: 1.9788
- Accuracy: 0.1143
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 |
|---|---|---|---|---|
| 1.9552 | 1.0 | 27 | 1.9623 | 0.1286 |
| 1.9448 | 2.0 | 54 | 1.9565 | 0.1429 |
| 1.917 | 3.0 | 81 | 1.9553 | 0.1571 |
| 1.8381 | 4.0 | 108 | 1.9563 | 0.0857 |
| 1.8197 | 5.0 | 135 | 1.9658 | 0.0857 |
| 1.7694 | 6.0 | 162 | 1.9656 | 0.1286 |
| 1.6977 | 7.0 | 189 | 1.9837 | 0.1429 |
| 1.6435 | 8.0 | 216 | 2.0436 | 0.1143 |
Framework versions
- Transformers 4.47.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3