metadata
license: mit
base_model: google/vivit-b-16x2-kinetics400
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vivit-b-16x2-kinetics400-finetuned-vivit-frequency
results: []
vivit-b-16x2-kinetics400-finetuned-vivit-frequency
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: 1.2570
- Accuracy: 0.7455
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: 1
- eval_batch_size: 1
- 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: 5920
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5871 | 0.1 | 592 | 1.1419 | 0.7706 |
| 0.5309 | 1.1 | 1184 | 1.1548 | 0.7634 |
| 0.8992 | 2.1 | 1776 | 1.1477 | 0.7742 |
| 0.5519 | 3.1 | 2368 | 1.0269 | 0.7957 |
| 1.366 | 4.1 | 2960 | 1.3621 | 0.7885 |
| 2.3144 | 5.1 | 3552 | 0.8907 | 0.7634 |
| 1.6161 | 6.1 | 4144 | 1.0485 | 0.7384 |
| 0.0673 | 7.1 | 4736 | 1.2847 | 0.7276 |
| 0.0042 | 8.1 | 5328 | 1.2755 | 0.7455 |
| 0.0017 | 9.1 | 5920 | 1.2570 | 0.7455 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.0.1+cu117
- Datasets 2.20.0
- Tokenizers 0.19.1