Skip to content
ModelListedExternal
Download

Videomae Base Finetuned Kinetics 0407 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: 0.5217 Accuracy: 0.8412

Sourcehuggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0407_final_5sec_bbox/tree/14cf93e98ab6d13df25cb196c4905878b57c7fb1
KindOtherBase modelMCG-NJU/videomae-base-finetuned-kineticsVersionRevision 14cf93e

Model source

Kind
Other
File size
329 MB
Base model
MCG-NJU/videomae-base-finetuned-kinetics
Version
vRevision 14cf93e
Updated
Sep 18, 2026
Downloads
2
Source
Hugging Face

Source description

videomae-base-finetuned-kinetics-0407_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: 0.5217
  • Accuracy: 0.8412

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
0.00250.00875600.34720.8818
0.0711.008711200.40680.8745
0.00452.008716800.64080.8409
0.86643.008722400.72360.8118
0.0084.008728000.55440.8436
0.02535.008733600.50490.8755
0.12416.008739201.82050.6645
0.01547.008744801.05550.7545
0.08748.008750400.65770.8564
1.37399.008756001.62530.6809
0.001210.008761601.08500.7673
0.000511.008767201.02420.7809
0.972512.008772801.57500.73
0.000713.008778401.53010.7518
0.236814.008784001.04200.8209
0.000115.008789601.46750.7736

Framework versions

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

Sources

1 source
Hugging FacePrimaryVersion 14cf93e98ab6d13df25cb196c4905878b57c7fb1
huggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0407_final_5sec_bbox/tree/14cf93e98ab6d13df25cb196c4905878b57c7fb1

Verified Sep 18

Model artifacts

1 artifact

model.safetensors

safetensors · 329 MB · SHA-256 20bd4586557f…7de9 · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 18huggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0407_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-0407_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-0407_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: 0.5217 - Accuracy: 0.8412 ## 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 | |:-------------:|:-------:|:----:|:---------------:|:--------:| | 0.0025 | 0.0087 | 560 | 0.3472 | 0.8818 | | 0.071 | 1.0087 | 1120 | 0.4068 | 0.8745 | | 0.0045 | 2.0087 | 1680 | 0.6408 | 0.8409 | | 0.8664 | 3.0087 | 2240 | 0.7236 | 0.8118 | | 0.008 | 4.0087 | 2800 | 0.5544 | 0.8436 | | 0.0253 | 5.0087 | 3360 | 0.5049 | 0.8755 | | 0.1241 | 6.0087 | 3920 | 1.8205 | 0.6645 | | 0.0154 | 7.0087 | 4480 | 1.0555 | 0.7545 | | 0.0874 | 8.0087 | 5040 | 0.6577 | 0.8564 | | 1.3739 | 9.0087 | 5600 | 1.6253 | 0.6809 | | 0.0012 | 10.0087 | 6160 | 1.0850 | 0.7673 | | 0.0005 | 11.0087 | 6720 | 1.0242 | 0.7809 | | 0.9725 | 12.0087 | 7280 | 1.5750 | 0.73 | | 0.0007 | 13.0087 | 7840 | 1.5301 | 0.7518 | | 0.2368 | 14.0087 | 8400 | 1.0420 | 0.8209 | | 0.0001 | 15.0087 | 8960 | 1.4675 | 0.7736 | ### Framework versions - Transformers 4.48.0 - Pytorch 2.5.1+cu124 - Datasets 3.2.0 - Tokenizers 0.21.0

NoteSep 18huggingface.co/d2o2ji/videomae-base-finetuned-kinetics-0407_final_5sec_bbox

Source context: 2 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo d2o2ji/videomae-base-finetuned-kinetics-0407_final_5sec_bbox