ViViT_BdSLW60_FrameRate_Corrected_without_Augment_20_epch
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: 0.6841
- Accuracy: 0.86
- Precision: 0.8823
- Recall: 0.86
- F1: 0.8452
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- 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: 18560
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 3.1124 | 0.0501 | 929 | 1.5155 | 0.705 | 0.7529 | 0.705 | 0.6760 |
| 0.1216 | 1.0501 | 1858 | 0.6576 | 0.8167 | 0.8197 | 0.8167 | 0.7920 |
| 0.0048 | 2.0501 | 2787 | 0.4630 | 0.86 | 0.8868 | 0.86 | 0.8338 |
| 0.0086 | 3.0501 | 3716 | 0.4305 | 0.8733 | 0.8927 | 0.8733 | 0.8600 |
| 0.2527 | 4.0501 | 4645 | 1.0763 | 0.755 | 0.8136 | 0.755 | 0.7172 |
| 0.0681 | 5.0501 | 5574 | 0.7836 | 0.8283 | 0.8202 | 0.8283 | 0.8002 |
| 0.0256 | 6.0501 | 6503 | 0.7197 | 0.8333 | 0.8667 | 0.8333 | 0.8153 |
| 0.064 | 7.0501 | 7432 | 0.6918 | 0.8533 | 0.8730 | 0.8533 | 0.8374 |
| 0.0001 | 8.0501 | 8361 | 0.6841 | 0.86 | 0.8823 | 0.86 | 0.8452 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.1