Skip to content
ModelListedExternal
Download

Videomae Base Finetuned Kinetics 0404 Final 5sec 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: 0.7272 Accuracy: 0.7940

Sourcehuggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0404_final_5sec_bbox/tree/99a027a9cd5d0a33576bf91b0c6df2cb1d3c5ea2
KindOtherBase modelMCG-NJU/videomae-base-finetuned-kineticsVersionRevision 99a027a

Model source

Kind
Other
File size
329 MB
Base model
MCG-NJU/videomae-base-finetuned-kinetics
Version
vRevision 99a027a
Updated
Sep 18, 2026
Downloads
3
Source
Hugging Face

Source description

videomae-base-finetuned-kinetics-0404_final_5sec_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: 0.7272
  • Accuracy: 0.7940

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: 64400

Training results

Training LossEpochStepValidation LossAccuracy
0.64940.00875600.34400.9036
0.07361.008711200.66990.8073
0.00272.008716800.64210.8427
0.90993.008722400.42110.8809
0.0194.008728000.73630.8064
0.58775.008733600.57840.81
1.66836.008739201.83670.7073
0.02947.008744800.55840.87
0.09938.008750400.57060.8436
0.04229.008756001.36810.7082
0.00410.008761602.11660.6673
0.000111.008767201.08870.78
0.76612.008772800.97460.8127
0.000713.008778401.62200.7191
1.662114.008784000.88060.7973
0.000415.008789601.06320.79

Framework versions

  • Transformers 4.48.1
  • Pytorch 2.5.1+cu121
  • Datasets 3.2.0
  • Tokenizers 0.21.0

Sources

1 source
Hugging FacePrimaryVersion 99a027a9cd5d0a33576bf91b0c6df2cb1d3c5ea2
huggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0404_final_5sec_bbox/tree/99a027a9cd5d0a33576bf91b0c6df2cb1d3c5ea2

Verified Sep 18

Model artifacts

1 artifact

model.safetensors

safetensors · 329 MB · SHA-256 55b181d6d949…067e · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 18huggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0404_final_5sec_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-0404_final_5sec_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-0404_final_5sec_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: 0.7272 - Accuracy: 0.7940 ## 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: 64400 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-------:|:----:|:---------------:|:--------:| | 0.6494 | 0.0087 | 560 | 0.3440 | 0.9036 | | 0.0736 | 1.0087 | 1120 | 0.6699 | 0.8073 | | 0.0027 | 2.0087 | 1680 | 0.6421 | 0.8427 | | 0.9099 | 3.0087 | 2240 | 0.4211 | 0.8809 | | 0.019 | 4.0087 | 2800 | 0.7363 | 0.8064 | | 0.5877 | 5.0087 | 3360 | 0.5784 | 0.81 | | 1.6683 | 6.0087 | 3920 | 1.8367 | 0.7073 | | 0.0294 | 7.0087 | 4480 | 0.5584 | 0.87 | | 0.0993 | 8.0087 | 5040 | 0.5706 | 0.8436 | | 0.0422 | 9.0087 | 5600 | 1.3681 | 0.7082 | | 0.004 | 10.0087 | 6160 | 2.1166 | 0.6673 | | 0.0001 | 11.0087 | 6720 | 1.0887 | 0.78 | | 0.766 | 12.0087 | 7280 | 0.9746 | 0.8127 | | 0.0007 | 13.0087 | 7840 | 1.6220 | 0.7191 | | 1.6621 | 14.0087 | 8400 | 0.8806 | 0.7973 | | 0.0004 | 15.0087 | 8960 | 1.0632 | 0.79 | ### Framework versions - Transformers 4.48.1 - Pytorch 2.5.1+cu121 - Datasets 3.2.0 - Tokenizers 0.21.0

NoteSep 18huggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0404_final_5sec_bbox

Source context: 3 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo d2o2ji/videomae-base-finetuned-kinetics-0404_final_5sec_bbox