metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: VideoMAE-URFall_UnrealFallDataset
results: []
VideoMAE-URFall_UnrealFallDataset
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: 0.1220
- Accuracy: 0.9691
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: 11820
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.2186 | 0.1 | 1183 | 2.0737 | 0.5172 |
| 0.8664 | 1.1 | 2366 | 0.6972 | 0.8211 |
| 0.3324 | 2.1 | 3549 | 0.6007 | 0.8372 |
| 0.1919 | 3.1 | 4732 | 0.5145 | 0.8651 |
| 0.1457 | 4.1 | 5915 | 0.2822 | 0.9221 |
| 0.0996 | 5.1 | 7098 | 0.2434 | 0.9359 |
| 0.0159 | 6.1 | 8281 | 0.1729 | 0.9547 |
| 0.0018 | 7.1 | 9464 | 0.1307 | 0.9649 |
| 0.001 | 8.1 | 10647 | 0.1524 | 0.9640 |
| 0.0013 | 9.1 | 11820 | 0.1220 | 0.9691 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1