metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: VideoMAE-MultipleCameraFall
results: []
VideoMAE-MultipleCameraFall
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: 0.0944
- Accuracy: 0.9752
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: 11770
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.801 | 0.1 | 1178 | 2.0143 | 0.5181 |
| 0.7407 | 1.1 | 2356 | 0.7707 | 0.8052 |
| 0.4488 | 2.1 | 3534 | 0.4310 | 0.8839 |
| 0.1402 | 3.1 | 4712 | 0.3790 | 0.8934 |
| 0.1608 | 4.1 | 5890 | 0.2916 | 0.9194 |
| 0.0133 | 5.1 | 7068 | 0.1776 | 0.9542 |
| 0.0806 | 6.1 | 8246 | 0.1715 | 0.9582 |
| 0.0132 | 7.1 | 9424 | 0.1474 | 0.9656 |
| 0.0017 | 8.1 | 10602 | 0.1038 | 0.9722 |
| 0.002 | 9.1 | 11770 | 0.0944 | 0.9752 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1