metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vivit-b-16x2-kinetics400-ft-48192
results: []
vivit-b-16x2-kinetics400-ft-48192
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7749
- Accuracy: 0.6772
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: 16
- eval_batch_size: 16
- 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: 55
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6106 | 1.0 | 55 | 0.7749 | 0.6772 |
Framework versions
- Transformers 4.41.2
- Pytorch 1.13.0+cu117
- Datasets 2.20.0
- Tokenizers 0.19.1