| --- |
| license: cc-by-nc-4.0 |
| base_model: MCG-NJU/videomae-base |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: VideoMAE-MultipleCameraFall_UnrealFallDataset |
| 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-MultipleCameraFall_UnrealFallDataset |
| |
| 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: 0.1136 |
| - Accuracy: 0.9736 |
| |
| ## 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: 11950 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | |
| |:-------------:|:-----:|:-----:|:---------------:|:--------:| |
| | 1.9014 | 0.1 | 1196 | 2.1529 | 0.5014 | |
| | 0.8259 | 1.1 | 2392 | 1.0095 | 0.7478 | |
| | 0.4316 | 2.1 | 3588 | 0.6168 | 0.8361 | |
| | 0.0665 | 3.1 | 4784 | 0.3693 | 0.8952 | |
| | 0.3185 | 4.1 | 5980 | 0.2011 | 0.9456 | |
| | 0.2362 | 5.1 | 7176 | 0.2938 | 0.9211 | |
| | 0.0728 | 6.1 | 8372 | 0.1560 | 0.9563 | |
| | 0.0332 | 7.1 | 9568 | 0.1403 | 0.9620 | |
| | 0.0036 | 8.1 | 10764 | 0.1207 | 0.9705 | |
| | 0.0026 | 9.1 | 11950 | 0.1136 | 0.9736 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.38.0.dev0 |
| - Pytorch 2.1.2+cu121 |
| - Datasets 2.16.1 |
| - Tokenizers 0.15.1 |
|
|
