Skip to content
ModelListedExternal
Download

Videomae Base Finetuned Kinetics Allkisa Crop Background 0310 Clip Duration Kisapplcroppadding

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: 0.2341 Accuracy: 0.9172

Sourcehuggingface.co/d2o2ji/videomae-base-finetuned-kinetics-allkisa-crop-background-0310-clip_duration-kisapplcroppadding/tree/0af9ebb535104ec0686a456c26a04343f4e84283
KindOtherBase modelMCG-NJU/videomae-base-finetuned-kineticsVersionRevision 0af9ebb

Model source

Kind
Other
File size
329 MB
Base model
MCG-NJU/videomae-base-finetuned-kinetics
Version
vRevision 0af9ebb
Updated
Sep 18, 2026
Downloads
2
Source
Hugging Face

Source description

videomae-base-finetuned-kinetics-allkisa-crop-background-0310-clip_duration-kisapplcroppadding

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: 0.2341
  • Accuracy: 0.9172

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: 25400

Training results

Training LossEpochStepValidation LossAccuracy
0.00130.01002550.46740.8421
0.02741.01005100.45600.8289
0.14352.01007650.66630.7650
0.31433.010010201.50720.6504
0.00544.010012750.65560.7462
0.01625.010015300.40790.8759
0.00546.010017850.59680.8308
0.00017.010020400.70190.8158
0.00018.010022950.75520.8289
0.20859.010025500.47320.8628
0.196410.010028050.66530.8477
0.000511.010030600.60820.8383
0.001612.010033150.82310.8496
0.000213.010035701.12880.8195
0.000114.010038250.84570.8496
0.015.010040801.08480.8252

Framework versions

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

Sources

1 source
Hugging FacePrimaryVersion 0af9ebb535104ec0686a456c26a04343f4e84283
huggingface.co/d2o2ji/videomae-base-finetuned-kinetics-allkisa-crop-background-0310-clip_duration-kisapplcroppadding/tree/0af9ebb535104ec0686a456c26a04343f4e84283

Verified Sep 18

Model artifacts

1 artifact

model.safetensors

safetensors · 329 MB · SHA-256 af7bb4a59485…344c · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 18huggingface.co/d2o2ji/videomae-base-finetuned-kinetics-allkisa-crop-background-0310-clip_duration-kisapplcroppadding

--- 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-allkisa-crop-background-0310-clip_duration-kisapplcroppadding 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-allkisa-crop-background-0310-clip_duration-kisapplcroppadding 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: 0.2341 - Accuracy: 0.9172 ## 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: 25400 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-------:|:----:|:---------------:|:--------:| | 0.0013 | 0.0100 | 255 | 0.4674 | 0.8421 | | 0.0274 | 1.0100 | 510 | 0.4560 | 0.8289 | | 0.1435 | 2.0100 | 765 | 0.6663 | 0.7650 | | 0.3143 | 3.0100 | 1020 | 1.5072 | 0.6504 | | 0.0054 | 4.0100 | 1275 | 0.6556 | 0.7462 | | 0.0162 | 5.0100 | 1530 | 0.4079 | 0.8759 | | 0.0054 | 6.0100 | 1785 | 0.5968 | 0.8308 | | 0.0001 | 7.0100 | 2040 | 0.7019 | 0.8158 | | 0.0001 | 8.0100 | 2295 | 0.7552 | 0.8289 | | 0.2085 | 9.0100 | 2550 | 0.4732 | 0.8628 | | 0.1964 | 10.0100 | 2805 | 0.6653 | 0.8477 | | 0.0005 | 11.0100 | 3060 | 0.6082 | 0.8383 | | 0.0016 | 12.0100 | 3315 | 0.8231 | 0.8496 | | 0.0002 | 13.0100 | 3570 | 1.1288 | 0.8195 | | 0.0001 | 14.0100 | 3825 | 0.8457 | 0.8496 | | 0.0 | 15.0100 | 4080 | 1.0848 | 0.8252 | ### 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-allkisa-crop-background-0310-clip_duration-kisapplcroppadding

Source context: 2 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo d2o2ji/videomae-base-finetuned-kinetics-allkisa-crop-background-0310-clip_duration-kisapplcroppadding