Timesformer-vivit-d1
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: 1.7607
- Accuracy: 0.7557
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 12010
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0024 | 0.1 | 1201 | 2.5898 | 0.6116 |
| 0.7957 | 1.1 | 2402 | 1.8821 | 0.6666 |
| 0.5344 | 2.1 | 3603 | 1.7371 | 0.6686 |
| 0.2148 | 3.1 | 4804 | 1.4470 | 0.7413 |
| 0.883 | 4.1 | 6005 | 1.7974 | 0.6735 |
| 0.0012 | 5.1 | 7206 | 1.5739 | 0.7386 |
| 0.0008 | 6.1 | 8407 | 1.7734 | 0.7307 |
| 1.8254 | 7.1 | 9608 | 1.4496 | 0.7704 |
| 0.6005 | 8.1 | 10809 | 1.8740 | 0.7504 |
| 0.0002 | 9.1 | 12010 | 1.7607 | 0.7557 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3