---
license: mit
base_model: google/vivit-b-16x2-kinetics400
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vivit-b-16x2-kinetics400-0511-mediapipe
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# vivit-b-16x2-kinetics400-0511-mediapipe

This model is a fine-tuned version of [google/vivit-b-16x2-kinetics400](https://huggingface.co/google/vivit-b-16x2-kinetics400) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9073
- Accuracy: 0.82

## 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: 1400

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.2076        | 0.1   | 140  | 2.4158          | 0.15     |
| 1.184         | 1.1   | 280  | 1.2269          | 0.6      |
| 0.6475        | 2.1   | 420  | 0.7247          | 0.76     |
| 0.3137        | 3.1   | 560  | 0.7076          | 0.78     |
| 0.0356        | 4.1   | 700  | 0.7347          | 0.82     |
| 0.0017        | 5.1   | 840  | 0.8888          | 0.83     |
| 0.0007        | 6.1   | 980  | 0.9464          | 0.8      |
| 0.265         | 7.1   | 1120 | 1.0068          | 0.8      |
| 0.0012        | 8.1   | 1260 | 0.8982          | 0.82     |
| 0.0007        | 9.1   | 1400 | 0.9073          | 0.82     |


### Framework versions

- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1