vivit-vit-8-10-epochs-5_class_2_p0_splited-1788627094.972628
This model is a fine-tuned version of google/vivit-b-16x2-kinetics400 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8171
- Accuracy: 0.7937
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: 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
- training_steps: 16220
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6857 | 0.1 | 1622 | 0.6011 | 0.7696 |
| 0.5432 | 1.1 | 3244 | 0.5661 | 0.7696 |
| 0.5385 | 2.1 | 4866 | 0.5613 | 0.7874 |
| 0.3539 | 3.1 | 6488 | 0.5449 | 0.7930 |
| 0.3533 | 4.1 | 8110 | 0.5845 | 0.8010 |
| 0.2800 | 5.1 | 9732 | 0.6588 | 0.7936 |
| 0.2659 | 6.1 | 11354 | 0.6819 | 0.8004 |
| 0.2779 | 7.1 | 12976 | 0.8279 | 0.7991 |
| 0.1264 | 8.1 | 14598 | 0.8096 | 0.8022 |
| 0.1146 | 9.1 | 16220 | 0.8185 | 0.8071 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.14.0+cu126
- Datasets 5.0.1
- Tokenizers 0.23.2