Saltar al contenido
ModelPublicadoExterno
Descargar

VideoMAE BdSLW60 FrameRate Corrected WIT Augment 20 Epoch RQ

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: 0.7434 Accuracy: 0.8667 Precision: 0.9146 Recall: 0.8667 F1: 0.8638

Fuentehuggingface.co/Shawon16/VideoMAE_BdSLW60_FrameRate_Corrected_WIT_Augment_20_epoch_RQ_/tree/d46208b60323e10d2c344dbc39ef4ec7d53d144f
TipoOtherModelo baseMCG-NJU/videomae-baseVersiónRevision d46208b

Fuente del modelo

Tipo
Other
Tamaño del archivo
329 MB
Modelo base
MCG-NJU/videomae-base
Versión
vRevision d46208b
Actualizado
18 sept 2026
Descargas
4
Fuente
Hugging Face

Descripción de la fuente

VideoMAE_BdSLW60_FrameRate_Corrected_WIT_Augment_20_epoch_RQ_

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: 0.7434
  • Accuracy: 0.8667
  • Precision: 0.9146
  • Recall: 0.8667
  • F1: 0.8638

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: 18560
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossAccuracyPrecisionRecallF1
9.25090.05019292.22230.4950.49600.4950.4501
2.3271.050118580.75850.78670.79890.78670.7675
0.79522.050127870.52300.84170.88840.84170.8337
0.30563.050137160.47150.88330.91100.88330.8768
0.38524.050146450.47160.88670.89550.88670.8772
0.38655.050155740.38870.91670.93540.91670.9125
0.15976.050165030.68150.88330.87940.88330.8678
0.2587.050174320.74170.890.92230.890.8762
0.14668.050183610.58510.89830.93040.89830.8892
0.10289.050192900.63760.8950.92340.8950.8876
0.048910.0501102190.74340.86670.91460.86670.8638

Framework versions

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

Fuentes

1 fuente
Hugging FacePrincipalVersión d46208b60323e10d2c344dbc39ef4ec7d53d144f
huggingface.co/Shawon16/VideoMAE_BdSLW60_FrameRate_Corrected_WIT_Augment_20_epoch_RQ_/tree/d46208b60323e10d2c344dbc39ef4ec7d53d144f

Verificado 18 sept

Artefactos del modelo

1 artefacto

model.safetensors

safetensors · 329 MB · SHA-256 664c3cd9eed2…bb4e · Hugging Face

Descargar

Extractos de fuentes

2 extractos
Readme18 septhuggingface.co/Shawon16/VideoMAE_BdSLW60_FrameRate_Corrected_WIT_Augment_20_epoch_RQ_

--- library_name: transformers license: cc-by-nc-4.0 base_model: MCG-NJU/videomae-base tags: - generated_from_trainer metrics: - accuracy - precision - recall - f1 model-index: - name: VideoMAE_BdSLW60_FrameRate_Corrected_WIT_Augment_20_epoch_RQ_ 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_BdSLW60_FrameRate_Corrected_WIT_Augment_20_epoch_RQ_ 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: 0.7434 - Accuracy: 0.8667 - Precision: 0.9146 - Recall: 0.8667 - F1: 0.8638 ## 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: 18560 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |:-------------:|:-------:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:| | 9.2509 | 0.0501 | 929 | 2.2223 | 0.495 | 0.4960 | 0.495 | 0.4501 | | 2.327 | 1.0501 | 1858 | 0.7585 | 0.7867 | 0.7989 | 0.7867 | 0.7675 | | 0.7952 | 2.0501 | 2787 | 0.5230 | 0.8417 | 0.8884 | 0.8417 | 0.8337 | | 0.3056 | 3.0501 | 3716 | 0.4715 | 0.8833 | 0.9110 | 0.8833 | 0.8768 | | 0.3852 | 4.0501 | 4645 | 0.4716 | 0.8867 | 0.8955 | 0.8867 | 0.8772 | | 0.3865 | 5.0501 | 5574 | 0.3887 | 0.9167 | 0.9354 | 0.9167 | 0.9125 | | 0.1597 | 6.0501 | 6503 | 0.6815 | 0.8833 | 0.8794 | 0.8833 | 0.8678 | | 0.258 | 7.0501 | 7432 | 0.7417 | 0.89 | 0.9223 | 0.89 | 0.8762 | | 0.1466 | 8.0501 | 8361 | 0.5851 | 0.8983 | 0.9304 | 0.8983 | 0.8892 | | 0.1028 | 9.0501 | 9290 | 0.6376 | 0.895 | 0.9234 | 0.895 | 0.8876 | | 0.0489 | 10.0501 | 10219 | 0.743...

Note18 septhuggingface.co/Shawon16/VideoMAE_BdSLW60_FrameRate_Corrected_WIT_Augment_20_epoch_RQ_

Source context: 4 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Shawon16/VideoMAE_BdSLW60_FrameRate_Corrected_WIT_Augment_20_epoch_RQ_