Ir para o conteúdo
ModelListadosExterno
Baixar

VideoMAE Kinetics Wlasl2000 CoR 20ep

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set: Loss: 2.4903 Accuracy: 0.4454

Fontehuggingface.co/Shawon16/videoMAE_kinetics_wlasl2000_coR_20ep/tree/05ac5aea2a3a71423e6e741b5b3d153a089f6fc0
TipoOtherModelo baseMCG-NJU/videomae-base-finetuned-kineticsVersãoRevision 05ac5aeBnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
335 MB
Modelo base
MCG-NJU/videomae-base-finetuned-kinetics
Versão
vRevision 05ac5ae
Atualizado
24 de out. de 2026
Downloads
37
Fonte
Hugging Face

Descrição da fonte

videoMAE_kinetics_wlasl2000_coR_20ep

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.4903
  • Accuracy: 0.4454

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: 35720
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossAccuracy
30.44550.0517867.58640.0010
29.13681.050035726.78720.0194
24.7872.050053585.80830.0884
20.2993.050071454.96450.1619
16.11784.0589314.26330.2370
12.32275.0500107173.66000.3029
9.12826.0500125033.23880.3460
6.54497.0500142902.93540.3897
4.60978.05160762.74350.4014
3.20819.0500178622.62470.4139
2.244610.0500196482.57070.4247
1.618111.0500214352.49440.4313
1.219612.05232212.49610.4318
0.968913.0500250072.48890.4339
0.80214.0500267932.49770.4408
0.6715.0500285802.48180.4346
0.584516.05303662.48010.4443
0.511917.0500321522.49240.4395
0.450418.0500339382.49300.4454
0.391119.0499357202.49030.4454

Framework versions

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

Fontes

1 fonte
Hugging FacePrimárioVersão 05ac5aea2a3a71423e6e741b5b3d153a089f6fc0
huggingface.co/Shawon16/videoMAE_kinetics_wlasl2000_coR_20ep/tree/05ac5aea2a3a71423e6e741b5b3d153a089f6fc0

Verificado 24 de out.

Artefatos de modelo

1 artefato

model.safetensors

safetensors · 335 MB · SHA-256 03a5b7c50c9b…4d07 · Hugging Face

Download file

Trechos de fonte

3 trechos
Readme6 de ago.huggingface.co/Shawon16/videoMAE_kinetics_wlasl2000_coR_20ep

--- library_name: transformers license: cc-by-nc-4.0 base_model: MCG-NJU/videomae-base-finetuned-kinetics tags: - generated_from_trainer metrics: - accuracy model-index: - name: videoMAE_kinetics_wlasl2000_coR_20ep 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. --> # videoMAE_kinetics_wlasl2000_coR_20ep This model is a fine-tuned version of [MCG-NJU/videomae-base-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-base-finetuned-kinetics) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.4903 - Accuracy: 0.4454 ## 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: 35720 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-------:|:-----:|:---------------:|:--------:| | 30.4455 | 0.05 | 1786 | 7.5864 | 0.0010 | | 29.1368 | 1.0500 | 3572 | 6.7872 | 0.0194 | | 24.787 | 2.0500 | 5358 | 5.8083 | 0.0884 | | 20.299 | 3.0500 | 7145 | 4.9645 | 0.1619 | | 16.1178 | 4.05 | 8931 | 4.2633 | 0.2370 | | 12.3227 | 5.0500 | 10717 | 3.6600 | 0.3029 | | 9.1282 | 6.0500 | 12503 | 3.2388 | 0.3460 | | 6.5449 | 7.0500 | 14290 | 2.9354 | 0.3897 | | 4.6097 | 8.05 | 16076 | 2.7435 | 0.4014 | | 3.2081 | 9.0500 | 17862 | 2.6247 | 0.4139 | | 2.2446 | 10.0500 | 19648 | 2.5707 | 0.4247 | | 1.6181 | 11.0500 | 21435 | 2.4944 | 0.4313 | | 1.2196 | 12.05 | 23221 | 2.4961 | 0.4318 | | 0.9689 | 13.0500 | 25007 | 2.4889 | 0.4339 | | 0.802 | 14.0500 | 26793 | 2.4977 | 0.4408 | | 0.67 | 15.0500 | 28580 | 2.4818 | 0.4346 | | 0.5845 | 16.05 | 30366 | 2.4801 | 0.4443 | | 0.5119 | 17.0500 | 32152 | 2.4924 | 0.4395 | | 0.4504 | 18.0500 | 33938 | 2.4930 | 0.4454 |...

Note24 de out.huggingface.co/Shawon16/videoMAE_kinetics_wlasl2000_coR_20ep

Source context: 37 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Shawon16/videoMAE_kinetics_wlasl2000_coR_20ep

Note6 de ago.huggingface.co/Shawon16/videoMAE_kinetics_wlasl2000_coR_20ep

Source context: 6 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Shawon16/videoMAE_kinetics_wlasl2000_coR_20ep