Downloads · 30 days
7
7% of all-time downloads
videomae-base-finetuned-kinetics-0321-abnormal_val02_pretest_addnon
d2o2ji/videomae-base-finetuned-kinetics-0321-abnormal_val02_pretest_addnon
videomae-base-finetuned-kinetics-0321-abnormal_val02_pretest_addnon 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
106
Public
Parameters
86.2M
6.2 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
- Mar 21, 2025
- Updated
- Mar 21, 2025
- SHA
- bde89cfd
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-0321-abnormal_val02_pretest_addnon
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: 0.3683
- Accuracy: 0.9010
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: 83700
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6666 | 0.0100 | 838 | 0.3534 | 0.8740 |
| 0.0454 | 1.0100 | 1676 | 0.2409 | 0.8967 |
| 0.0079 | 2.0100 | 2514 | 0.4467 | 0.8316 |
| 0.0207 | 3.0100 | 3352 | 0.4880 | 0.8740 |
| 0.0013 | 4.0100 | 4190 | 0.2610 | 0.9172 |
| 0.5462 | 5.0100 | 5028 | 0.3095 | 0.8818 |
| 0.0099 | 6.0100 | 5866 | 0.3489 | 0.8868 |
| 0.001 | 7.0100 | 6704 | 0.2514 | 0.9314 |
| 0.0006 | 8.0100 | 7542 | 0.3673 | 0.9144 |
| 0.0001 | 9.0100 | 8380 | 0.3359 | 0.9073 |
| 0.1953 | 10.0100 | 9218 | 0.3062 | 0.9271 |
| 0.0005 | 11.0100 | 10056 | 0.3899 | 0.9151 |
| 0.0267 | 12.0100 | 10894 | 0.3479 | 0.9222 |
| 0.0005 | 13.0100 | 11732 | 0.3962 | 0.9186 |
| 0.0001 | 14.0100 | 12570 | 0.3964 | 0.9193 |
| 0.0004 | 15.0100 | 13408 | 0.5327 | 0.9052 |
| 0.0 | 16.0100 | 14246 | 0.3658 | 0.9299 |
| 0.0008 | 17.0100 | 15084 | 0.5465 | 0.9087 |
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
- Mar 21, 2025
- Updated
- Mar 21, 2025