Saltar al contenido
ModelPublicadoExterno
Descargar

VideoMAE Default Fold 7 10 Epoch Aug Batch 2 4 BdSLW60 SR 8 P2 KineticsFinetuned 18 25

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: 0.2243 Accuracy: 0.9498

Fuentehuggingface.co/Shawon16/VideoMAE_default_fold__7__10_epoch_Aug_batch_2_4_BdSLW60_SR_8_p2_kineticsFinetuned_18_25/tree/bb578df060afa15d1829bc3ab75bc62744943487
TipoOtherModelo baseMCG-NJU/videomae-base-finetuned-kineticsVersiónRevision bb578df

Fuente del modelo

Tipo
Other
Tamaño del archivo
329 MB
Modelo base
MCG-NJU/videomae-base-finetuned-kinetics
Versión
vRevision bb578df
Actualizado
18 sept 2026
Descargas
2
Fuente
Hugging Face

Descripción de la fuente

VideoMAE_default_fold__7__10_epoch_Aug_batch_2_4_BdSLW60_SR_8_p2_kineticsFinetuned_18_25

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: 0.2243
  • Accuracy: 0.9498

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: 9030
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossAccuracy
1.21650.19030.25240.9639
0.10051.100118070.05120.9863
0.08882.127100.07640.9851
0.00533.100136140.04770.9863
0.06334.145170.03940.9913
0.03915.100154210.02960.9925
0.01336.163240.02880.9950
0.04027.100172280.01580.9975
0.00028.181310.02380.9950
0.00029.099590300.02270.9950

Framework versions

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

Fuentes

1 fuente
Hugging FacePrincipalVersión bb578df060afa15d1829bc3ab75bc62744943487
huggingface.co/Shawon16/VideoMAE_default_fold__7__10_epoch_Aug_batch_2_4_BdSLW60_SR_8_p2_kineticsFinetuned_18_25/tree/bb578df060afa15d1829bc3ab75bc62744943487

Verificado 18 sept

Artefactos del modelo

1 artefacto

model.safetensors

safetensors · 329 MB · SHA-256 035838c4bc2e…9fe0 · Hugging Face

Descargar

Extractos de fuentes

2 extractos
Readme18 septhuggingface.co/Shawon16/VideoMAE_default_fold__7__10_epoch_Aug_batch_2_4_BdSLW60_SR_8_p2_kineticsFinetuned_18_25

--- 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_default_fold__7__10_epoch_Aug_batch_2_4_BdSLW60_SR_8_p2_kineticsFinetuned_18_25 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_default_fold__7__10_epoch_Aug_batch_2_4_BdSLW60_SR_8_p2_kineticsFinetuned_18_25 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: 0.2243 - Accuracy: 0.9498 ## 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: 9030 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:------:|:----:|:---------------:|:--------:| | 1.2165 | 0.1 | 903 | 0.2524 | 0.9639 | | 0.1005 | 1.1001 | 1807 | 0.0512 | 0.9863 | | 0.0888 | 2.1 | 2710 | 0.0764 | 0.9851 | | 0.0053 | 3.1001 | 3614 | 0.0477 | 0.9863 | | 0.0633 | 4.1 | 4517 | 0.0394 | 0.9913 | | 0.0391 | 5.1001 | 5421 | 0.0296 | 0.9925 | | 0.0133 | 6.1 | 6324 | 0.0288 | 0.9950 | | 0.0402 | 7.1001 | 7228 | 0.0158 | 0.9975 | | 0.0002 | 8.1 | 8131 | 0.0238 | 0.9950 | | 0.0002 | 9.0995 | 9030 | 0.0227 | 0.9950 | ### Framework versions - Transformers 4.46.1 - Pytorch 2.5.1+cu124 - Datasets 3.1.0 - Tokenizers 0.20.1

Note18 septhuggingface.co/Shawon16/VideoMAE_default_fold__7__10_epoch_Aug_batch_2_4_BdSLW60_SR_8_p2_kineticsFinetuned_18_25

Source context: 2 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Shawon16/VideoMAE_default_fold__7__10_epoch_Aug_batch_2_4_BdSLW60_SR_8_p2_kineticsFinetuned_18_25