metadata
license: mit
base_model: google/vivit-b-16x2-kinetics400
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vivit-b-16x2-kinetics400-0508-checking-original_mediapipe
results: []
vivit-b-16x2-kinetics400-0508-checking-original_mediapipe
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: 0.8456
- Accuracy: 0.72
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: 500
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.3395 | 0.1 | 50 | 2.1400 | 0.16 |
| 1.4353 | 1.1 | 100 | 1.4633 | 0.56 |
| 0.3947 | 2.1 | 150 | 0.9567 | 0.68 |
| 0.1572 | 3.1 | 200 | 0.8107 | 0.8 |
| 0.0156 | 4.1 | 250 | 0.9614 | 0.62 |
| 0.0047 | 5.1 | 300 | 0.8670 | 0.72 |
| 0.0029 | 6.1 | 350 | 0.8325 | 0.76 |
| 0.0024 | 7.1 | 400 | 0.8589 | 0.74 |
| 0.002 | 8.1 | 450 | 0.8479 | 0.74 |
| 0.0017 | 9.1 | 500 | 0.8456 | 0.72 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1