Aller au contenu
ModelPrésentéExterne
Télécharger

VideoMAE Default Fold 6 10 Epoch Bdslw60 Kinetics 25 2 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: 0.3015 Accuracy: 0.9326

Sourcehuggingface.co/Shawon16/VideoMAE_default_fold__6__10_epoch_bdslw60_kinetics_25_2_25/tree/67e48d612a477daf00b64b66f90552a2db20aed7
TypeOtherModèle de baseMCG-NJU/videomae-base-finetuned-kineticsVersionRevision 67e48d6

Source du modèle

Type
Other
Taille du fichier
329 MB
Modèle de base
MCG-NJU/videomae-base-finetuned-kinetics
Version
vRevision 67e48d6
Mis à jour
18 sept. 2026
Téléchargements
3
Source
Hugging Face

Description de la source

VideoMAE_default_fold__6__10_epoch_bdslw60_kinetics_25_2_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: 0.3015
  • Accuracy: 0.9326

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
1.29170.19030.27890.9601
0.12581.100118070.05990.9888
0.11422.127100.06140.9900
0.00843.100136140.06840.9875
0.04414.145170.05660.9888
0.00625.100154210.06470.9900
0.00356.163240.05730.9900
0.00167.100172280.04170.9938
0.02648.181310.05680.9925
0.00029.099590300.03900.9938

Framework versions

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

Sources

1 source
Hugging FacePrincipalVersion 67e48d612a477daf00b64b66f90552a2db20aed7
huggingface.co/Shawon16/VideoMAE_default_fold__6__10_epoch_bdslw60_kinetics_25_2_25/tree/67e48d612a477daf00b64b66f90552a2db20aed7

Vérifié 18 sept.

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 329 MB · SHA-256 f7d47897282b…447d · Hugging Face

Download file

Extraits de sources

2 extraits
Readme18 sept.huggingface.co/Shawon16/VideoMAE_default_fold__6__10_epoch_bdslw60_kinetics_25_2_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__6__10_epoch_bdslw60_kinetics_25_2_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__6__10_epoch_bdslw60_kinetics_25_2_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: 0.3015 - Accuracy: 0.9326 ## 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 | |:-------------:|:------:|:----:|:---------------:|:--------:| | 1.2917 | 0.1 | 903 | 0.2789 | 0.9601 | | 0.1258 | 1.1001 | 1807 | 0.0599 | 0.9888 | | 0.1142 | 2.1 | 2710 | 0.0614 | 0.9900 | | 0.0084 | 3.1001 | 3614 | 0.0684 | 0.9875 | | 0.0441 | 4.1 | 4517 | 0.0566 | 0.9888 | | 0.0062 | 5.1001 | 5421 | 0.0647 | 0.9900 | | 0.0035 | 6.1 | 6324 | 0.0573 | 0.9900 | | 0.0016 | 7.1001 | 7228 | 0.0417 | 0.9938 | | 0.0264 | 8.1 | 8131 | 0.0568 | 0.9925 | | 0.0002 | 9.0995 | 9030 | 0.0390 | 0.9938 | ### Framework versions - Transformers 4.46.1 - Pytorch 2.5.1+cu124 - Datasets 3.1.0 - Tokenizers 0.20.1

Note18 sept.huggingface.co/Shawon16/VideoMAE_default_fold__6__10_epoch_bdslw60_kinetics_25_2_25

Source context: 3 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Shawon16/VideoMAE_default_fold__6__10_epoch_bdslw60_kinetics_25_2_25