Skip to content
ModelListedExternal
Download

Videomae Base Finetuned Kinetics 0407 Final 5sec Org

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: 0.3338 Accuracy: 0.9182

Sourcehuggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0407_final_5sec_org/tree/8f409f5e06117ede68082a4ec366743acb1ecad0
KindOtherBase modelMCG-NJU/videomae-base-finetuned-kineticsVersionRevision 8f409f5

Model source

Kind
Other
File size
329 MB
Base model
MCG-NJU/videomae-base-finetuned-kinetics
Version
vRevision 8f409f5
Updated
Sep 18, 2026
Downloads
4
Source
Hugging Face

Source description

videomae-base-finetuned-kinetics-0407_final_5sec_org

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: 0.3338
  • Accuracy: 0.9182

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: 64900

Training results

Training LossEpochStepValidation LossAccuracy
0.28340.01006500.18240.9424
0.0021.010013000.19670.9360
0.012.010019500.15810.9478
0.01513.010026000.23910.9012
1.13464.010032500.15450.9561
0.02465.010039000.30490.9076
0.09976.010045500.23670.9195
0.03067.010052000.25350.9369
0.00978.010058500.29170.9277
0.00129.010065000.43100.8481
0.002110.010071500.41850.8948
0.009111.010078000.30660.9204
0.001412.010084500.46660.8792
0.003913.010091000.26380.9305
0.006514.010097500.54200.8792
0.011115.0100104000.24320.9167
0.000416.0100110500.26060.9323
0.000117.0100117000.38250.9241
0.000418.0100123500.34930.9186
0.015519.0100130000.46390.9103

Framework versions

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

Sources

1 source
Hugging FacePrimaryVersion 8f409f5e06117ede68082a4ec366743acb1ecad0
huggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0407_final_5sec_org/tree/8f409f5e06117ede68082a4ec366743acb1ecad0

Verified Sep 18

Model artifacts

1 artifact

model.safetensors

safetensors · 329 MB · SHA-256 0669bb6130b6…e224 · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 18huggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0407_final_5sec_org

--- 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-0407_final_5sec_org 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-0407_final_5sec_org 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: 0.3338 - Accuracy: 0.9182 ## 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: 64900 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-------:|:-----:|:---------------:|:--------:| | 0.2834 | 0.0100 | 650 | 0.1824 | 0.9424 | | 0.002 | 1.0100 | 1300 | 0.1967 | 0.9360 | | 0.01 | 2.0100 | 1950 | 0.1581 | 0.9478 | | 0.0151 | 3.0100 | 2600 | 0.2391 | 0.9012 | | 1.1346 | 4.0100 | 3250 | 0.1545 | 0.9561 | | 0.0246 | 5.0100 | 3900 | 0.3049 | 0.9076 | | 0.0997 | 6.0100 | 4550 | 0.2367 | 0.9195 | | 0.0306 | 7.0100 | 5200 | 0.2535 | 0.9369 | | 0.0097 | 8.0100 | 5850 | 0.2917 | 0.9277 | | 0.0012 | 9.0100 | 6500 | 0.4310 | 0.8481 | | 0.0021 | 10.0100 | 7150 | 0.4185 | 0.8948 | | 0.0091 | 11.0100 | 7800 | 0.3066 | 0.9204 | | 0.0014 | 12.0100 | 8450 | 0.4666 | 0.8792 | | 0.0039 | 13.0100 | 9100 | 0.2638 | 0.9305 | | 0.0065 | 14.0100 | 9750 | 0.5420 | 0.8792 | | 0.0111 | 15.0100 | 10400 | 0.2432 | 0.9167 | | 0.0004 | 16.0100 | 11050 | 0.2606 | 0.9323 | | 0.0001 | 17.0100 | 11700 | 0.3825 | 0.9241 | | 0.0004 | 18.0100 | 12350 | 0.3493 | 0.9186 | | 0.0155 | 19.0100 | 13000 | 0.4639 | 0.9103 | ### Framework versions...

NoteSep 18huggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0407_final_5sec_org

Source context: 4 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo d2o2ji/videomae-base-finetuned-kinetics-0407_final_5sec_org