metadata
license: mit
base_model: google/vivit-b-16x2-kinetics400
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vivit-b-16x2-kinetics400-finetuned-elder
results: []
vivit-b-16x2-kinetics400-finetuned-elder
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: 1.6807
- Accuracy: 0.3205
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 576
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6183 | 0.25 | 145 | 1.6139 | 0.3360 |
| 1.5777 | 1.25 | 290 | 1.6061 | 0.3024 |
| 1.36 | 2.25 | 435 | 1.6442 | 0.2863 |
| 1.5395 | 3.24 | 576 | 1.6518 | 0.2688 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2