Aller au contenu
ModelPrésentéExterne
Télécharger

Videomae Base Finetuned Kinetics 0321 Abnormal Val02 Pretest Addnon

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: 0.3683 Accuracy: 0.9010

Sourcehuggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0321-abnormal_val02_pretest_addnon/tree/bde89cfdcc65d2962ec730097b81e0b57706447a
TypeOtherModèle de baseMCG-NJU/videomae-base-finetuned-kineticsVersionRevision bde89cf

Source du modèle

Type
Other
Taille du fichier
329 MB
Modèle de base
MCG-NJU/videomae-base-finetuned-kinetics
Version
vRevision bde89cf
Mis à jour
18 sept. 2026
Téléchargements
2
Source
Hugging Face

Description de la source

videomae-base-finetuned-kinetics-0321-abnormal_val02_pretest_addnon

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: 0.3683
  • Accuracy: 0.9010

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: 8
  • eval_batch_size: 8
  • seed: 42
  • 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: 0.05
  • training_steps: 83700

Training results

Training LossEpochStepValidation LossAccuracy
0.66660.01008380.35340.8740
0.04541.010016760.24090.8967
0.00792.010025140.44670.8316
0.02073.010033520.48800.8740
0.00134.010041900.26100.9172
0.54625.010050280.30950.8818
0.00996.010058660.34890.8868
0.0017.010067040.25140.9314
0.00068.010075420.36730.9144
0.00019.010083800.33590.9073
0.195310.010092180.30620.9271
0.000511.0100100560.38990.9151
0.026712.0100108940.34790.9222
0.000513.0100117320.39620.9186
0.000114.0100125700.39640.9193
0.000415.0100134080.53270.9052
0.016.0100142460.36580.9299
0.000817.0100150840.54650.9087

Framework versions

  • Transformers 4.48.0
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.0

Sources

1 source
Hugging FacePrincipalVersion bde89cfdcc65d2962ec730097b81e0b57706447a
huggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0321-abnormal_val02_pretest_addnon/tree/bde89cfdcc65d2962ec730097b81e0b57706447a

Vérifié 18 sept.

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 329 MB · SHA-256 535d5816d5f9…7f13 · Hugging Face

Télécharger

Extraits de sources

2 extraits
Readme18 sept.huggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0321-abnormal_val02_pretest_addnon

--- 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-base-finetuned-kinetics-0321-abnormal_val02_pretest_addnon 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-finetuned-kinetics-0321-abnormal_val02_pretest_addnon 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: 0.3683 - Accuracy: 0.9010 ## 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: 8 - eval_batch_size: 8 - seed: 42 - 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: 0.05 - training_steps: 83700 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-------:|:-----:|:---------------:|:--------:| | 0.6666 | 0.0100 | 838 | 0.3534 | 0.8740 | | 0.0454 | 1.0100 | 1676 | 0.2409 | 0.8967 | | 0.0079 | 2.0100 | 2514 | 0.4467 | 0.8316 | | 0.0207 | 3.0100 | 3352 | 0.4880 | 0.8740 | | 0.0013 | 4.0100 | 4190 | 0.2610 | 0.9172 | | 0.5462 | 5.0100 | 5028 | 0.3095 | 0.8818 | | 0.0099 | 6.0100 | 5866 | 0.3489 | 0.8868 | | 0.001 | 7.0100 | 6704 | 0.2514 | 0.9314 | | 0.0006 | 8.0100 | 7542 | 0.3673 | 0.9144 | | 0.0001 | 9.0100 | 8380 | 0.3359 | 0.9073 | | 0.1953 | 10.0100 | 9218 | 0.3062 | 0.9271 | | 0.0005 | 11.0100 | 10056 | 0.3899 | 0.9151 | | 0.0267 | 12.0100 | 10894 | 0.3479 | 0.9222 | | 0.0005 | 13.0100 | 11732 | 0.3962 | 0.9186 | | 0.0001 | 14.0100 | 12570 | 0.3964 | 0.9193 | | 0.0004 | 15.0100 | 13408 | 0.5327 | 0.9052 | | 0.0 | 16.0100 | 14246 | 0.3658 | 0.9299 | | 0.0008 | 17.0100 | 15084 | 0.5465 | 0.9087 | ### Framework versions - Transformers 4.48.0 - Pytorch 2.5.1+cu124 - Datasets 3.2.0...

Note18 sept.huggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0321-abnormal_val02_pretest_addnon

Source context: 2 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo d2o2ji/videomae-base-finetuned-kinetics-0321-abnormal_val02_pretest_addnon