---
library_name: transformers
license: mit
base_model: google/vivit-b-16x2-kinetics400
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: ViViT_WLASL_100_SR_4_ep200_p20
  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_WLASL_100_SR_4_ep200_p20

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: 1.7950
- Accuracy: 0.6272
- Precision: 0.6755
- Recall: 0.6272
- F1: 0.6047

## 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
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 36000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
|:-------------:|:-------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 18.9788       | 0.005   | 180  | 4.6909          | 0.0266   | 0.0055    | 0.0266 | 0.0082 |
| 18.6803       | 1.0050  | 360  | 4.6180          | 0.0266   | 0.0034    | 0.0266 | 0.0058 |
| 18.0341       | 2.0050  | 540  | 4.5181          | 0.0473   | 0.0205    | 0.0473 | 0.0238 |
| 17.0617       | 3.0050  | 721  | 4.3376          | 0.0740   | 0.0541    | 0.0740 | 0.0478 |
| 15.6302       | 4.005   | 901  | 4.0709          | 0.1183   | 0.0772    | 0.1183 | 0.0815 |
| 14.0851       | 5.0050  | 1081 | 3.7552          | 0.1864   | 0.1536    | 0.1864 | 0.1449 |
| 11.953        | 6.0050  | 1261 | 3.4065          | 0.2663   | 0.2643    | 0.2663 | 0.2221 |
| 9.8223        | 7.0050  | 1442 | 3.1038          | 0.3373   | 0.3284    | 0.3373 | 0.2944 |
| 7.8126        | 8.005   | 1622 | 2.7834          | 0.4142   | 0.4201    | 0.4142 | 0.3676 |
| 6.0952        | 9.0050  | 1802 | 2.5129          | 0.4763   | 0.4950    | 0.4763 | 0.4368 |
| 4.3155        | 10.0050 | 1982 | 2.2757          | 0.5059   | 0.5594    | 0.5059 | 0.4894 |
| 3.0214        | 11.0050 | 2163 | 2.0460          | 0.5473   | 0.5640    | 0.5473 | 0.5178 |
| 2.0687        | 12.005  | 2343 | 1.8803          | 0.5917   | 0.6184    | 0.5917 | 0.5731 |
| 1.3523        | 13.0050 | 2523 | 1.7261          | 0.5917   | 0.6065    | 0.5917 | 0.5601 |
| 0.7828        | 14.0050 | 2703 | 1.6275          | 0.6036   | 0.6644    | 0.6036 | 0.5924 |
| 0.4222        | 15.0050 | 2884 | 1.5284          | 0.6420   | 0.6756    | 0.6420 | 0.6245 |
| 0.3113        | 16.005  | 3064 | 1.5459          | 0.6272   | 0.6664    | 0.6272 | 0.6092 |
| 0.2021        | 17.0050 | 3244 | 1.4441          | 0.6657   | 0.6991    | 0.6657 | 0.6484 |
| 0.1698        | 18.0050 | 3424 | 1.5340          | 0.6124   | 0.6511    | 0.6124 | 0.5942 |
| 0.1199        | 19.0050 | 3605 | 1.3935          | 0.6509   | 0.6746    | 0.6509 | 0.6288 |
| 0.0244        | 20.005  | 3785 | 1.4782          | 0.6686   | 0.7130    | 0.6686 | 0.6574 |
| 0.0407        | 21.0050 | 3965 | 1.3890          | 0.6686   | 0.7149    | 0.6686 | 0.6557 |
| 0.0719        | 22.0050 | 4145 | 1.4897          | 0.6598   | 0.7189    | 0.6598 | 0.6477 |
| 0.1163        | 23.0050 | 4326 | 1.3919          | 0.6716   | 0.7218    | 0.6716 | 0.6639 |
| 0.1167        | 24.005  | 4506 | 1.5690          | 0.6538   | 0.7189    | 0.6538 | 0.6380 |
| 0.0366        | 25.0050 | 4686 | 1.5032          | 0.6746   | 0.6979    | 0.6746 | 0.6541 |
| 0.1065        | 26.0050 | 4866 | 1.4893          | 0.6391   | 0.6475    | 0.6391 | 0.6135 |
| 0.0454        | 27.0050 | 5047 | 1.5013          | 0.6243   | 0.6601    | 0.6243 | 0.6022 |
| 0.0844        | 28.005  | 5227 | 1.5609          | 0.6598   | 0.6974    | 0.6598 | 0.6388 |
| 0.109         | 29.0050 | 5407 | 1.4840          | 0.6657   | 0.7151    | 0.6657 | 0.6507 |
| 0.1508        | 30.0050 | 5587 | 1.8017          | 0.6036   | 0.6784    | 0.6036 | 0.5903 |
| 0.1114        | 31.0050 | 5768 | 1.6676          | 0.6391   | 0.6721    | 0.6391 | 0.6134 |
| 0.0931        | 32.005  | 5948 | 1.5345          | 0.6746   | 0.7082    | 0.6746 | 0.6520 |
| 0.0619        | 33.0050 | 6128 | 1.7462          | 0.6302   | 0.6424    | 0.6302 | 0.6008 |
| 0.2698        | 34.0050 | 6308 | 1.7032          | 0.6331   | 0.6711    | 0.6331 | 0.6126 |
| 0.1108        | 35.0050 | 6489 | 1.7695          | 0.6538   | 0.6784    | 0.6538 | 0.6265 |
| 0.1006        | 36.005  | 6669 | 2.0188          | 0.5828   | 0.6289    | 0.5828 | 0.5661 |
| 0.0823        | 37.0050 | 6849 | 1.6487          | 0.6568   | 0.6874    | 0.6568 | 0.6425 |
| 0.0632        | 38.0050 | 7029 | 1.8014          | 0.6361   | 0.6917    | 0.6361 | 0.6253 |
| 0.1162        | 39.0050 | 7210 | 1.6741          | 0.6450   | 0.6672    | 0.6450 | 0.6196 |
| 0.0846        | 40.005  | 7390 | 1.8032          | 0.6361   | 0.6948    | 0.6361 | 0.6205 |
| 0.1528        | 41.0050 | 7570 | 1.8375          | 0.6331   | 0.6732    | 0.6331 | 0.6102 |
| 0.0695        | 42.0050 | 7750 | 1.6722          | 0.6568   | 0.7030    | 0.6568 | 0.6417 |
| 0.1516        | 43.0050 | 7931 | 1.7811          | 0.6716   | 0.7009    | 0.6716 | 0.6495 |
| 0.1565        | 44.005  | 8111 | 1.8077          | 0.6538   | 0.6884    | 0.6538 | 0.6347 |
| 0.0728        | 45.0050 | 8291 | 1.7950          | 0.6272   | 0.6755    | 0.6272 | 0.6047 |


### Framework versions

- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.1