Saltar al contenido
ModelPublicadoExterno
Descargar

Vit Wlasl 100 Signer 20ep CoR

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: 1.2249 Accuracy: 0.6893

Fuentehuggingface.co/Shawon16/vit_wlasl_100__signer_20ep_coR/tree/6a142d1a05e25675209d28321cf84f387394eadd
TipoOtherModelo basegoogle/vivit-b-16x2-kinetics400VersiónRevision 6a142d1Ccalidad

Fuente del modelo

Tipo
Other
Tamaño del archivo
338 MB
Modelo base
google/vivit-b-16x2-kinetics400
Versión
vRevision 6a142d1
Actualizado
24 oct 2026
Descargas
5
Fuente
Hugging Face

Descripción de la fuente

vit_wlasl_100__signer_20ep_coR

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: 1.2249
  • Accuracy: 0.6893

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: 3600
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossAccuracy
18.67660.051804.54040.0444
16.84261.04993603.88740.1598
12.36732.04995402.99660.3432
7.86213.05017212.40380.4852
4.83134.059012.04180.5592
2.77085.049910811.80760.5740
1.50356.049912611.56760.6243
0.83067.050114421.49170.6006
0.41518.0516221.40640.6420
0.26089.049918021.29110.6893
0.150210.049919821.26450.6746
0.090111.050121631.23360.6805
0.078712.0523431.25760.6834
0.063513.049925231.22860.6834
0.059714.049927031.22490.6893

Framework versions

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

Fuentes

1 fuente
Hugging FacePrincipalVersión 6a142d1a05e25675209d28321cf84f387394eadd
huggingface.co/Shawon16/vit_wlasl_100__signer_20ep_coR/tree/6a142d1a05e25675209d28321cf84f387394eadd

Verificado 24 oct

Artefactos del modelo

1 artefacto

model.safetensors

safetensors · 338 MB · SHA-256 e7461726eda7…f0dd · Hugging Face

Download file

Extractos de fuentes

3 extractos
Readme6 agohuggingface.co/Shawon16/vit_wlasl_100__signer_20ep_coR

--- library_name: transformers license: mit base_model: google/vivit-b-16x2-kinetics400 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit_wlasl_100__signer_20ep_coR 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. --> # vit_wlasl_100__signer_20ep_coR 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: 1.2249 - Accuracy: 0.6893 ## 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: 3600 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-------:|:----:|:---------------:|:--------:| | 18.6766 | 0.05 | 180 | 4.5404 | 0.0444 | | 16.8426 | 1.0499 | 360 | 3.8874 | 0.1598 | | 12.3673 | 2.0499 | 540 | 2.9966 | 0.3432 | | 7.8621 | 3.0501 | 721 | 2.4038 | 0.4852 | | 4.8313 | 4.05 | 901 | 2.0418 | 0.5592 | | 2.7708 | 5.0499 | 1081 | 1.8076 | 0.5740 | | 1.5035 | 6.0499 | 1261 | 1.5676 | 0.6243 | | 0.8306 | 7.0501 | 1442 | 1.4917 | 0.6006 | | 0.4151 | 8.05 | 1622 | 1.4064 | 0.6420 | | 0.2608 | 9.0499 | 1802 | 1.2911 | 0.6893 | | 0.1502 | 10.0499 | 1982 | 1.2645 | 0.6746 | | 0.0901 | 11.0501 | 2163 | 1.2336 | 0.6805 | | 0.0787 | 12.05 | 2343 | 1.2576 | 0.6834 | | 0.0635 | 13.0499 | 2523 | 1.2286 | 0.6834 | | 0.0597 | 14.0499 | 2703 | 1.2249 | 0.6893 | ### Framework versions - Transformers 4.46.1 - Pytorch 2.5.1+cu124 - Datasets 3.1.0 - Tokenizers 0.20.1

Note24 octhuggingface.co/Shawon16/vit_wlasl_100__signer_20ep_coR

Source context: 5 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Shawon16/vit_wlasl_100__signer_20ep_coR

Note6 agohuggingface.co/Shawon16/vit_wlasl_100__signer_20ep_coR

Source context: 2 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Shawon16/vit_wlasl_100__signer_20ep_coR