Downloads · 30 days
11
10% of all-time downloads
videomae-base-finetuned-kinetics-0416_final_5sec_org_balanced_replacecroppretest_new
d2o2ji/videomae-base-finetuned-kinetics-0416_final_5sec_org_balanced_replacecroppretest_new
videomae-base-finetuned-kinetics-0416_final_5sec_org_balanced_replacecroppretest_new 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
107
Public
Parameters
86.2M
9.3 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 16, 2025
- Updated
- Apr 16, 2025
- SHA
- ee7e7807
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-0416_final_5sec_org_balanced_replacecroppretest_new
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: 1.1095
- Accuracy: 0.7619
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: 60000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1298 | 0.0100 | 601 | 0.3606 | 0.8818 |
| 0.0011 | 1.0100 | 1202 | 0.5411 | 0.8584 |
| 0.0027 | 2.0100 | 1803 | 0.5689 | 0.8775 |
| 0.0012 | 3.0100 | 2404 | 0.5217 | 0.8775 |
| 0.0005 | 4.0100 | 3005 | 1.1761 | 0.8002 |
| 0.0007 | 5.0100 | 3606 | 0.9414 | 0.8367 |
| 0.2225 | 6.0100 | 4207 | 0.9050 | 0.8575 |
| 0.0011 | 7.0100 | 4808 | 1.3420 | 0.7732 |
| 0.001 | 8.0100 | 5409 | 0.9292 | 0.7854 |
| 0.0014 | 9.0100 | 6010 | 0.9622 | 0.8471 |
| 0.003 | 10.0100 | 6611 | 0.5940 | 0.8297 |
| 0.2395 | 11.0100 | 7212 | 0.4645 | 0.9018 |
| 0.1462 | 12.0100 | 7813 | 1.0455 | 0.8036 |
| 0.0079 | 13.0100 | 8414 | 0.6113 | 0.8697 |
| 0.0004 | 14.0100 | 9015 | 0.6680 | 0.8679 |
| 0.2853 | 15.0100 | 9616 | 0.9481 | 0.8384 |
| 0.0019 | 16.0100 | 10217 | 0.6528 | 0.8775 |
| 0.0012 | 17.0100 | 10818 | 1.2236 | 0.8175 |
| 0.004 | 18.0100 | 11419 | 0.6866 | 0.8732 |
| 0.009 | 19.0100 | 12020 | 0.8545 | 0.8566 |
| 0.0001 | 20.0100 | 12621 | 0.8797 | 0.8732 |
| 0.0023 | 21.0100 | 13222 | 0.9283 | 0.8575 |
| 0.0124 | 22.0100 | 13823 | 0.9179 | 0.8540 |
| 0.0002 | 23.0100 | 14424 | 1.2224 | 0.8401 |
| 0.0 | 24.0100 | 15025 | 1.0134 | 0.8454 |
| 0.0005 | 25.0100 | 15626 | 0.7990 | 0.8836 |
| 0.0001 | 26.0100 | 16227 | 0.9930 | 0.8714 |
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 16, 2025
- Updated
- Apr 16, 2025