VIVIT-d2
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: 2.9103
- Accuracy: 0.4210
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: 6650
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.556 | 0.1 | 665 | 2.3470 | 0.2123 |
| 2.0142 | 1.1 | 1330 | 2.1601 | 0.3180 |
| 2.122 | 2.1 | 1995 | 2.0851 | 0.4047 |
| 1.7405 | 3.1 | 2660 | 2.3452 | 0.4205 |
| 1.2998 | 4.1 | 3325 | 2.3814 | 0.4557 |
| 1.4591 | 5.1 | 3990 | 2.7093 | 0.3820 |
| 0.8984 | 6.1 | 4655 | 2.5562 | 0.3584 |
| 0.3971 | 7.1 | 5320 | 3.1583 | 0.4057 |
| 0.5996 | 8.1 | 5985 | 2.9134 | 0.4154 |
| 0.8684 | 9.1 | 6650 | 2.9103 | 0.4210 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3