metadata
license: mit
base_model: google/vivit-b-16x2-kinetics400
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vivit-b-16x2-mixed-dataset
results: []
vivit-b-16x2-mixed-dataset
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: 0.1118
- Accuracy: 0.9740
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 7044
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2111 | 0.17 | 1174 | 0.8879 | 0.7863 |
| 0.0911 | 1.17 | 2348 | 0.5390 | 0.8831 |
| 0.0021 | 2.17 | 3522 | 0.2326 | 0.9355 |
| 0.0028 | 3.17 | 4696 | 0.3125 | 0.9395 |
| 0.0008 | 4.17 | 5870 | 0.3077 | 0.9476 |
| 0.125 | 5.17 | 7044 | 0.1982 | 0.9617 |
Framework versions
- Transformers 4.39.0
- Pytorch 2.1.0
- Datasets 2.18.0
- Tokenizers 0.15.2