|
--- |
|
license: cc-by-nc-4.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: videomae-base-finetuned-ucf_crime |
|
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_crime |
|
|
|
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: 1.4776 |
|
- Accuracy: 0.3720 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 5 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- training_steps: 640 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.9349 | 0.06 | 40 | 1.9845 | 0.2332 | |
|
| 1.8834 | 1.06 | 80 | 1.9134 | 0.3009 | |
|
| 1.7506 | 2.06 | 120 | 1.8460 | 0.3080 | |
|
| 1.6494 | 3.06 | 160 | 1.7691 | 0.2624 | |
|
| 1.6189 | 4.06 | 200 | 1.7939 | 0.2537 | |
|
| 1.6895 | 5.06 | 240 | 1.7809 | 0.2706 | |
|
| 1.517 | 6.06 | 280 | 1.6773 | 0.3244 | |
|
| 1.308 | 7.06 | 320 | 1.8364 | 0.3152 | |
|
| 1.2267 | 8.06 | 360 | 2.0392 | 0.2440 | |
|
| 1.4347 | 9.06 | 400 | 1.9110 | 0.2450 | |
|
| 1.1567 | 10.06 | 440 | 1.7606 | 0.2840 | |
|
| 1.1937 | 11.06 | 480 | 1.9803 | 0.2737 | |
|
| 1.0729 | 12.06 | 520 | 1.8355 | 0.3352 | |
|
| 1.0721 | 13.06 | 560 | 1.7808 | 0.3311 | |
|
| 0.6594 | 14.06 | 600 | 1.8175 | 0.3060 | |
|
| 0.7636 | 15.06 | 640 | 1.8409 | 0.3409 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.29.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
