metadata
library_name: transformers
license: mit
base_model: google/vivit-b-16x2-kinetics400
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ViViT_lsa64_coR
results: []
ViViT_lsa64_coR
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: 0.0008
- Accuracy: 1.0
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: 2880
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 12.7049 | 0.1 | 288 | 1.3316 | 0.8438 |
| 1.4335 | 1.1 | 576 | 0.0854 | 0.9922 |
| 0.0869 | 2.1 | 864 | 0.0054 | 1.0 |
| 0.0225 | 3.1 | 1152 | 0.0021 | 1.0 |
| 0.0057 | 4.1 | 1440 | 0.0012 | 1.0 |
| 0.0038 | 5.1 | 1728 | 0.0010 | 1.0 |
| 0.0024 | 6.1 | 2016 | 0.0008 | 1.0 |
| 0.0016 | 7.1 | 2304 | 0.0008 | 1.0 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.1