vivit-b-16x2-kinetics400-finetuned-vivit-diagnose
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: 1.8988
- Accuracy: 0.6953
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 3430
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.8386 | 0.1 | 343 | 1.5448 | 0.5448 |
| 1.1419 | 1.1 | 686 | 1.2918 | 0.5412 |
| 0.778 | 2.1 | 1029 | 1.4229 | 0.7240 |
| 0.7591 | 3.1 | 1372 | 1.5418 | 0.6918 |
| 0.8103 | 4.1 | 1715 | 1.3608 | 0.6810 |
| 0.3701 | 5.1 | 2058 | 1.6575 | 0.6810 |
| 0.2027 | 6.1 | 2401 | 1.8233 | 0.6774 |
| 0.0002 | 7.1 | 2744 | 1.9324 | 0.6738 |
| 0.1793 | 8.1 | 3087 | 1.8483 | 0.6953 |
| 0.0007 | 9.1 | 3430 | 1.8988 | 0.6953 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.0.1+cu117
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 5
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for yangboyuan/vivit-b-16x2-kinetics400-finetuned-vivit-diagnose
Base model
google/vivit-b-16x2-kinetics400