metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: VideoMAE-URFall
results: []
VideoMAE-URFall
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: 0.1003
- Accuracy: 0.9722
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: 8
- 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: 11650
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.1435 | 0.1 | 1165 | 2.2165 | 0.4536 |
| 0.8432 | 1.1 | 2330 | 0.7595 | 0.8010 |
| 0.4293 | 2.1 | 3495 | 0.5219 | 0.8578 |
| 0.2377 | 3.1 | 4660 | 0.3852 | 0.8972 |
| 0.1604 | 4.1 | 5825 | 0.2505 | 0.9349 |
| 0.0418 | 5.1 | 6990 | 0.2070 | 0.9431 |
| 0.0048 | 6.1 | 8155 | 0.1811 | 0.9520 |
| 0.0051 | 7.1 | 9320 | 0.1311 | 0.9634 |
| 0.0012 | 8.1 | 10485 | 0.1096 | 0.9698 |
| 0.0857 | 9.1 | 11650 | 0.1003 | 0.9722 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1