Downloads · 30 days
29
1% of all-time downloads
videomae-base-videoMAE
billskar23/videomae-base-videoMAE
videomae-base-videoMAE is a video classification model from billskar23. 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
2.2K
Public
Parameters
86.2M
397 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors345 MB · 97%
At a glance
- Task
- Video Classification
- Library
- transformers
- License
- cc-by-nc-4.0
- Model type
- videomae
- Access
- Public
- Created
- Sep 25, 2024
- Updated
- Sep 30, 2024
- SHA
- 68c7df94
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-videoMAE
This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6956
- Accuracy: 0.8571
- Precision: 0.8929
- Recall: 0.8571
- F1: 0.8571
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 12825
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.4984 | 1.0 | 514 | 1.3741 | 0.4286 | 0.1837 | 0.4286 | 0.2571 |
| 0.3492 | 2.0 | 1028 | 0.9819 | 0.4286 | 0.1837 | 0.4286 | 0.2571 |
| 0.4071 | 3.0 | 1542 | 2.8074 | 0.4286 | 0.1837 | 0.4286 | 0.2571 |
| 0.3151 | 4.0 | 2056 | 0.2223 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0053 | 5.0 | 2570 | 4.9944 | 0.4286 | 0.1837 | 0.4286 | 0.2571 |
| 0.0017 | 6.0 | 3084 | 0.3940 | 0.8571 | 0.8857 | 0.8571 | 0.8508 |
| 0.0092 | 7.0 | 3598 | 3.8118 | 0.4286 | 0.1837 | 0.4286 | 0.2571 |
| 0.0003 | 8.0 | 4112 | 4.5879 | 0.4286 | 0.1837 | 0.4286 | 0.2571 |
| 0.0973 | 9.0 | 4626 | 2.7723 | 0.4286 | 0.1837 | 0.4286 | 0.2571 |
| 0.0011 | 10.0 | 5140 | 4.0052 | 0.4286 | 0.1837 | 0.4286 | 0.2571 |
| 0.0 | 11.0 | 5654 | 1.5523 | 0.5714 | 0.7857 | 0.5714 | 0.5143 |
| 0.0 | 12.0 | 6168 | 1.4310 | 0.7143 | 0.8286 | 0.7143 | 0.7024 |
| 0.0 | 13.0 | 6682 | 1.4236 | 0.8571 | 0.8929 | 0.8571 | 0.8571 |
| 0.0 | 14.0 | 7196 | 1.4245 | 0.8571 | 0.8929 | 0.8571 | 0.8571 |
| 0.0 | 15.0 | 7710 | 1.4416 | 0.8571 | 0.8929 | 0.8571 | 0.8571 |
| 0.0 | 16.0 | 8224 | 1.4639 | 0.8571 | 0.8929 | 0.8571 | 0.8571 |
| 0.0 | 17.0 | 8738 | 1.4884 | 0.8571 | 0.8929 | 0.8571 | 0.8571 |
| 0.0 | 18.0 | 9252 | 1.5161 | 0.8571 | 0.8929 | 0.8571 | 0.8571 |
| 0.0 | 19.0 | 9766 | 1.5452 | 0.8571 | 0.8929 | 0.8571 | 0.8571 |
| 0.0 | 20.0 | 10280 | 1.5755 | 0.8571 | 0.8929 | 0.8571 | 0.8571 |
| 0.0 | 21.0 | 10794 | 1.6078 | 0.8571 | 0.8929 | 0.8571 | 0.8571 |
| 0.0 | 22.0 | 11308 | 1.6386 | 0.8571 | 0.8929 | 0.8571 | 0.8571 |
| 0.0 | 23.0 | 11822 | 1.6669 | 0.8571 | 0.8929 | 0.8571 | 0.8571 |
| 0.0 | 24.0 | 12336 | 1.6868 | 0.8571 | 0.8929 | 0.8571 | 0.8571 |
| 0.0 | 24.9514 | 12825 | 1.6956 | 0.8571 | 0.8929 | 0.8571 | 0.8571 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1
- Task
- Video Classification
- Library
- transformers
- Type
- videomae
- License
- cc-by-nc-4.0
- Created
- Sep 25, 2024
- Updated
- Sep 30, 2024