vivit-vit-8-10-epochs-5_class_1_p0_splited-1788619611.183424
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: 1.0536
- Accuracy: 0.7373
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: 8660
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7354 | 0.1001 | 867 | 0.8522 | 0.6413 |
| 0.7735 | 1.1001 | 1734 | 0.8201 | 0.6621 |
| 0.4791 | 2.1001 | 2601 | 0.7485 | 0.6943 |
| 0.3786 | 3.1001 | 3468 | 0.8550 | 0.6943 |
| 0.2816 | 4.1001 | 4335 | 0.8086 | 0.7151 |
| 0.3757 | 5.1001 | 5202 | 0.8478 | 0.7290 |
| 0.2143 | 6.1001 | 6069 | 0.9925 | 0.7140 |
| 0.1964 | 7.1001 | 6936 | 1.1379 | 0.7197 |
| 0.2621 | 8.1001 | 7803 | 1.1154 | 0.7324 |
| 0.0921 | 9.0990 | 8660 | 1.1323 | 0.7370 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.14.0+cu126
- Datasets 5.0.1
- Tokenizers 0.23.2