Skip to content
ModelListedExternal
Download

Videomae Base Finetuned Kinetics 0403 Final Bbox

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: 0.5415 Accuracy: 0.8825

Sourcehuggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0403_final_bbox/tree/b6b3047559e8b8a664dddbce3af60e957742b3a8
KindOtherBase modelMCG-NJU/videomae-base-finetuned-kineticsVersionRevision b6b3047

Model source

Kind
Other
File size
329 MB
Base model
MCG-NJU/videomae-base-finetuned-kinetics
Version
vRevision b6b3047
Updated
Sep 18, 2026
Downloads
3
Source
Hugging Face

Source description

videomae-base-finetuned-kinetics-0403_final_bbox

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: 0.5415
  • Accuracy: 0.8825

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: 72700

Training results

Training LossEpochStepValidation LossAccuracy
0.42070.00815860.57030.8194
0.06581.008111720.52230.8290
0.33872.008117580.82770.7941
0.01143.008123441.07230.7644
0.00124.008129300.55790.8796
0.01635.008135160.59380.8604
0.00536.008141020.88410.8255
0.01697.008146880.72730.8351
0.00088.008152740.65330.8429
0.00029.008158600.63990.8700
0.00210.008164460.74190.8534
0.000311.008170320.86810.8517
0.016412.008176181.22780.7871
0.000513.008182040.76400.8682
0.00114.008187900.83860.8325
0.008715.008193761.05030.8072
0.000316.008199621.23130.8159
1.007617.0081105480.91490.8508
0.000118.0081111341.39300.7932
0.000719.0081117201.34840.8037

Framework versions

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

Sources

1 source
Hugging FacePrimaryVersion b6b3047559e8b8a664dddbce3af60e957742b3a8
huggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0403_final_bbox/tree/b6b3047559e8b8a664dddbce3af60e957742b3a8

Verified Sep 18

Model artifacts

1 artifact

model.safetensors

safetensors · 329 MB · SHA-256 944429818b0f…1d0f · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 18huggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0403_final_bbox

--- 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-0403_final_bbox 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-0403_final_bbox 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: 0.5415 - Accuracy: 0.8825 ## 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: 72700 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-------:|:-----:|:---------------:|:--------:| | 0.4207 | 0.0081 | 586 | 0.5703 | 0.8194 | | 0.0658 | 1.0081 | 1172 | 0.5223 | 0.8290 | | 0.3387 | 2.0081 | 1758 | 0.8277 | 0.7941 | | 0.0114 | 3.0081 | 2344 | 1.0723 | 0.7644 | | 0.0012 | 4.0081 | 2930 | 0.5579 | 0.8796 | | 0.0163 | 5.0081 | 3516 | 0.5938 | 0.8604 | | 0.0053 | 6.0081 | 4102 | 0.8841 | 0.8255 | | 0.0169 | 7.0081 | 4688 | 0.7273 | 0.8351 | | 0.0008 | 8.0081 | 5274 | 0.6533 | 0.8429 | | 0.0002 | 9.0081 | 5860 | 0.6399 | 0.8700 | | 0.002 | 10.0081 | 6446 | 0.7419 | 0.8534 | | 0.0003 | 11.0081 | 7032 | 0.8681 | 0.8517 | | 0.0164 | 12.0081 | 7618 | 1.2278 | 0.7871 | | 0.0005 | 13.0081 | 8204 | 0.7640 | 0.8682 | | 0.001 | 14.0081 | 8790 | 0.8386 | 0.8325 | | 0.0087 | 15.0081 | 9376 | 1.0503 | 0.8072 | | 0.0003 | 16.0081 | 9962 | 1.2313 | 0.8159 | | 1.0076 | 17.0081 | 10548 | 0.9149 | 0.8508 | | 0.0001 | 18.0081 | 11134 | 1.3930 | 0.7932 | | 0.0007 | 19.0081 | 11720 | 1.3484 | 0.8037 | ### Framework versions - Transf...

NoteSep 18huggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0403_final_bbox

Source context: 3 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo d2o2ji/videomae-base-finetuned-kinetics-0403_final_bbox