Downloads · 30 days
12
4% of all-time downloads
videomae-base-finetuned-scratch
dat96/videomae-base-finetuned-scratch
videomae-base-finetuned-scratch is a video classification model from dat96. 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
335
Public
Parameters
86.2M
32.1 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
- Mar 25, 2024
- Updated
- Mar 27, 2024
- SHA
- f3a65088
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-scratch
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: 0.9263
- Accuracy: 0.7994
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: 12
- eval_batch_size: 12
- 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: 3952
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6869 | 0.08 | 330 | 0.6326 | 0.6490 |
| 0.6342 | 1.08 | 660 | 0.6356 | 0.6447 |
| 0.6718 | 2.08 | 990 | 0.6112 | 0.6648 |
| 0.5003 | 3.08 | 1320 | 0.5741 | 0.6991 |
| 0.4131 | 4.08 | 1650 | 0.5480 | 0.7077 |
| 0.3233 | 5.08 | 1980 | 0.5564 | 0.7464 |
| 0.2411 | 6.08 | 2310 | 0.4929 | 0.7923 |
| 0.3402 | 7.08 | 2640 | 0.7592 | 0.7593 |
| 0.2174 | 8.08 | 2970 | 0.7752 | 0.7779 |
| 0.1706 | 9.08 | 3300 | 0.8511 | 0.7923 |
| 0.1127 | 10.08 | 3630 | 0.9263 | 0.7994 |
| 0.062 | 11.08 | 3952 | 1.0187 | 0.7808 |
Framework versions
- Transformers 4.39.0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Video Classification
- Library
- transformers
- Type
- videomae
- License
- cc-by-nc-4.0
- Created
- Mar 25, 2024
- Updated
- Mar 27, 2024