Downloads · 30 days
6
7% of all-time downloads
videomae-base-finetuned-kinetics-0417_final_5sec_org_ab7_val_inside_train_balanced_allpretest_re
d2o2ji/videomae-base-finetuned-kinetics-0417_final_5sec_org_ab7_val_inside_train_balanced_allpretest_re
videomae-base-finetuned-kinetics-0417_final_5sec_org_ab7_val_inside_train_balanced_allpretest_re is a video classification model from d2o2ji. Use it for the video classification task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as cc-by-nc-4.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
83
Public
Parameters
86.2M
5.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors345 MB · 99%
At a glance
- Task
- Video Classification
- Library
- transformers
- License
- cc-by-nc-4.0
- Model type
- videomae
- Access
- Public
- Created
- Apr 17, 2025
- Updated
- Apr 17, 2025
- SHA
- b3c635ff
Base models
Model card
From the Hugging Face model README
<!-- 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-0417_final_5sec_org_ab7_val_inside_train_balanced_allpretest_re
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: 0.1627
- Accuracy: 0.9382
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: 86000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0088 | 0.0100 | 861 | 0.1426 | 0.9463 |
| 3.031 | 1.0100 | 1722 | 0.2207 | 0.9250 |
| 0.3094 | 2.0100 | 2583 | 0.5461 | 0.8349 |
| 0.0152 | 3.0100 | 3444 | 0.4200 | 0.8863 |
| 3.2919 | 4.0100 | 4305 | 0.3855 | 0.8973 |
| 0.0007 | 5.0100 | 5166 | 0.2005 | 0.9400 |
| 2.4368 | 6.0100 | 6027 | 0.7514 | 0.8239 |
| 0.0339 | 7.0100 | 6888 | 0.3068 | 0.9123 |
| 0.0082 | 8.0100 | 7749 | 0.3015 | 0.9147 |
| 0.0507 | 9.0100 | 8610 | 0.2606 | 0.9329 |
| 0.0003 | 10.0100 | 9471 | 0.4086 | 0.9171 |
| 0.0179 | 11.0100 | 10332 | 0.2585 | 0.9265 |
| 0.0054 | 12.0100 | 11193 | 0.3542 | 0.9155 |
| 0.0018 | 13.0100 | 12054 | 0.3996 | 0.9163 |
| 0.0728 | 14.0100 | 12915 | 0.4471 | 0.9155 |
| 0.0099 | 15.0100 | 13776 | 0.3036 | 0.9336 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Task
- Video Classification
- Library
- transformers
- Type
- videomae
- License
- cc-by-nc-4.0
- Created
- Apr 17, 2025
- Updated
- Apr 17, 2025