Ir para o conteúdo
ModelListadosExterno
Baixar

VideoMAE Base Wlasl 100 40ep CoR P10

This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set: Loss: 2.5702 Accuracy: 0.4645

Fontehuggingface.co/Shawon16/videoMAE_base_wlasl_100_40ep_coR_p10/tree/0866ef142cd94bb3e4cba033114038b83fd3498f
TipoOtherModelo baseMCG-NJU/videomae-baseVersãoRevision 0866ef1Bnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
329 MB
Modelo base
MCG-NJU/videomae-base
Versão
vRevision 0866ef1
Atualizado
24 de out. de 2026
Downloads
12
Fonte
Hugging Face

Descrição da fonte

videoMAE_base_wlasl_100_40ep_coR_p10

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

  • Loss: 2.5702
  • Accuracy: 0.4645

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: 7200
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossAccuracy
18.64620.0251804.63560.0178
18.55861.02503604.63070.0178
18.53362.02495404.61750.0178
18.40613.02507214.60100.0237
18.42964.0259014.61240.0178
18.20935.025010814.59840.0325
18.02376.024912614.55400.0148
17.41517.025014424.48700.0237
16.85838.02516224.38150.0266
16.19569.025018024.28020.0414
15.569510.024919824.13880.0473
14.573511.025021633.98900.0710
13.431212.02523433.72800.1065
12.033313.025025233.50960.1686
10.509614.024927033.36360.1805
8.921415.025028843.17670.2337
7.452116.02530642.97540.2781
6.161717.025032442.86870.2781
4.936818.024934242.74720.3343
3.795919.025036052.59180.3639
2.858520.02537852.66980.3432
2.197121.025039652.53680.3935
1.646422.024941452.52420.3935
1.176323.025043262.49090.4142
0.957524.02545062.47210.4260
0.645625.025046862.45600.4083
0.469926.024948662.41030.4053
0.363327.025050472.46890.4379
0.272628.02552272.36560.4379
0.204529.025054072.47190.4467
0.162930.024955872.49160.4438
0.119331.025057682.45690.4438
0.111632.02559482.50530.4527
0.072333.025061282.54590.4556
0.081834.024963082.53620.4645
0.058635.025064892.57500.4467
0.065136.02566692.58450.4527
0.06137.025068492.58800.4586
0.066438.024970292.56880.4734
0.041439.023672002.57020.4645

Framework versions

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

Fontes

1 fonte
Hugging FacePrimárioVersão 0866ef142cd94bb3e4cba033114038b83fd3498f
huggingface.co/Shawon16/videoMAE_base_wlasl_100_40ep_coR_p10/tree/0866ef142cd94bb3e4cba033114038b83fd3498f

Verificado 24 de out.

Artefatos de modelo

1 artefato

model.safetensors

safetensors · 329 MB · SHA-256 56466b30fe64…16fc · Hugging Face

Download file

Trechos de fonte

3 trechos
Readme6 de ago.huggingface.co/Shawon16/videoMAE_base_wlasl_100_40ep_coR_p10

--- library_name: transformers license: cc-by-nc-4.0 base_model: MCG-NJU/videomae-base tags: - generated_from_trainer metrics: - accuracy model-index: - name: videoMAE_base_wlasl_100_40ep_coR_p10 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_base_wlasl_100_40ep_coR_p10 This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.5702 - Accuracy: 0.4645 ## 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: 7200 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-------:|:----:|:---------------:|:--------:| | 18.6462 | 0.025 | 180 | 4.6356 | 0.0178 | | 18.5586 | 1.0250 | 360 | 4.6307 | 0.0178 | | 18.5336 | 2.0249 | 540 | 4.6175 | 0.0178 | | 18.4061 | 3.0250 | 721 | 4.6010 | 0.0237 | | 18.4296 | 4.025 | 901 | 4.6124 | 0.0178 | | 18.2093 | 5.0250 | 1081 | 4.5984 | 0.0325 | | 18.0237 | 6.0249 | 1261 | 4.5540 | 0.0148 | | 17.4151 | 7.0250 | 1442 | 4.4870 | 0.0237 | | 16.8583 | 8.025 | 1622 | 4.3815 | 0.0266 | | 16.1956 | 9.0250 | 1802 | 4.2802 | 0.0414 | | 15.5695 | 10.0249 | 1982 | 4.1388 | 0.0473 | | 14.5735 | 11.0250 | 2163 | 3.9890 | 0.0710 | | 13.4312 | 12.025 | 2343 | 3.7280 | 0.1065 | | 12.0333 | 13.0250 | 2523 | 3.5096 | 0.1686 | | 10.5096 | 14.0249 | 2703 | 3.3636 | 0.1805 | | 8.9214 | 15.0250 | 2884 | 3.1767 | 0.2337 | | 7.4521 | 16.025 | 3064 | 2.9754 | 0.2781 | | 6.1617 | 17.0250 | 3244 | 2.8687 | 0.2781 | | 4.9368 | 18.0249 | 3424 | 2.7472 | 0.3343 | | 3.7959 | 19.0250 | 3605 | 2.5918 | 0.3639 | | 2.8585 | 2...

Note24 de out.huggingface.co/Shawon16/videoMAE_base_wlasl_100_40ep_coR_p10

Source context: 12 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Shawon16/videoMAE_base_wlasl_100_40ep_coR_p10

Note6 de ago.huggingface.co/Shawon16/videoMAE_base_wlasl_100_40ep_coR_p10

Source context: 14 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Shawon16/videoMAE_base_wlasl_100_40ep_coR_p10