vivit-vit-fc-loss-8-10-epochs-5_class_1_p3_min_0_splited-1792718756.841698
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: 0.1315
- Accuracy: 0.9279
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: 11000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0982 | 0.1001 | 1101 | 0.1730 | 0.8491 |
| 0.1904 | 1.1001 | 2202 | 0.1343 | 0.8960 |
| 0.0619 | 2.1001 | 3303 | 0.1702 | 0.8810 |
| 0.1067 | 3.1001 | 4404 | 0.1801 | 0.8782 |
| 0.0653 | 4.1001 | 5505 | 0.1065 | 0.9363 |
| 0.0440 | 5.1001 | 6606 | 0.1158 | 0.9260 |
| 0.0503 | 6.1001 | 7707 | 0.1678 | 0.9185 |
| 0.0847 | 7.1001 | 8808 | 0.1297 | 0.9316 |
| 0.0575 | 8.1001 | 9909 | 0.1688 | 0.9157 |
| 0.0341 | 9.0992 | 11000 | 0.1419 | 0.9297 |
Framework versions
- Transformers 5.18.0
- Pytorch 2.14.1+cu126
- Datasets 5.0.1
- Tokenizers 0.23.2