Downloads · 30 days
4
3% of all-time downloads
ALL_RGBCROP_ori16F-8B16F-GACWDlrDO2-cosine
TanAlexanderlz/ALL_RGBCROP_ori16F-8B16F-GACWDlrDO2-cosine
ALL_RGBCROP_ori16F-8B16F-GACWDlrDO2-cosine is a video classification model from TanAlexanderlz. 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
139
Public
Parameters
86.2M
4.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors345 MB · 100%
At a glance
- Task
- Video Classification
- Library
- transformers
- License
- cc-by-nc-4.0
- Model type
- videomae
- Access
- Public
- Created
- May 28, 2025
- Updated
- May 28, 2025
- SHA
- 05fecd77
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. -->
ALL_RGBCROP_ori16F-8B16F-GACWDlrDO2-cosine
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: 0.4551
- Accuracy: 0.7904
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 960
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.693 | 0.05 | 48 | 0.6962 | 0.5061 |
| 0.5698 | 1.05 | 96 | 0.6468 | 0.6037 |
| 0.386 | 2.05 | 144 | 0.5518 | 0.7317 |
| 0.3362 | 3.05 | 192 | 0.5194 | 0.7439 |
| 0.2304 | 4.05 | 240 | 0.4915 | 0.7622 |
| 0.1812 | 5.05 | 288 | 0.4888 | 0.7561 |
| 0.184 | 6.05 | 336 | 0.5179 | 0.7561 |
| 0.156 | 7.05 | 384 | 0.5182 | 0.7805 |
| 0.1027 | 8.05 | 432 | 0.5171 | 0.7622 |
| 0.0751 | 9.05 | 480 | 0.5690 | 0.7317 |
| 0.041 | 10.05 | 528 | 0.7000 | 0.7439 |
| 0.056 | 11.05 | 576 | 0.6516 | 0.7378 |
| 0.0309 | 12.05 | 624 | 0.7192 | 0.7378 |
Framework versions
- Transformers 4.52.2
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1
- Task
- Video Classification
- Library
- transformers
- Type
- videomae
- License
- cc-by-nc-4.0
- Created
- May 28, 2025
- Updated
- May 28, 2025