metadata
license: mit
base_model: google/vivit-b-16x2-kinetics400
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vivit-b-16x2-kinetics400-finetuned-0505-original
results: []
vivit-b-16x2-kinetics400-finetuned-0505-original
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: 0.7704
- Accuracy: 0.74
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: 520
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.4346 | 0.1019 | 53 | 2.1892 | 0.18 |
| 1.2302 | 1.1019 | 106 | 1.6488 | 0.44 |
| 0.7052 | 2.1019 | 159 | 1.1180 | 0.66 |
| 0.1088 | 3.1019 | 212 | 0.7580 | 0.74 |
| 0.0163 | 4.1019 | 265 | 0.9034 | 0.72 |
| 0.0039 | 5.1019 | 318 | 0.8373 | 0.8 |
| 0.0024 | 6.1019 | 371 | 0.7717 | 0.76 |
| 0.0019 | 7.1019 | 424 | 0.7680 | 0.74 |
| 0.0016 | 8.1019 | 477 | 0.7709 | 0.74 |
| 0.0017 | 9.0827 | 520 | 0.7704 | 0.74 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1