| --- |
| library_name: transformers |
| license: cc-by-nc-4.0 |
| base_model: MCG-NJU/videomae-base |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: shot_model |
| 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. --> |
|
|
| # shot_model |
| |
| 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: 1.4299 |
| - Accuracy: 0.692 |
| |
| ## 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: 2 |
| - eval_batch_size: 2 |
| - seed: 42 |
| - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: linear |
| - lr_scheduler_warmup_steps: 0.1 |
| - training_steps: 6250 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:| |
| | 1.6227 | 1.0 | 625 | 1.9235 | 0.228 | |
| | 1.4269 | 2.0 | 1250 | 1.4425 | 0.496 | |
| | 1.0222 | 3.0 | 1875 | 1.3376 | 0.5 | |
| | 1.0616 | 4.0 | 2500 | 1.6164 | 0.464 | |
| | 1.0547 | 5.0 | 3125 | 1.2287 | 0.552 | |
| | 0.6092 | 6.0 | 3750 | 1.3996 | 0.584 | |
| | 0.5217 | 7.0 | 4375 | 1.2899 | 0.644 | |
| | 0.7761 | 8.0 | 5000 | 1.5018 | 0.656 | |
| | 1.2009 | 9.0 | 5625 | 1.4867 | 0.676 | |
| | 0.2304 | 10.0 | 6250 | 1.4299 | 0.692 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 5.3.0 |
| - Pytorch 2.10.0 |
| - Datasets 4.6.1 |
| - Tokenizers 0.22.2 |
| |
