Downloads · 30 days
17
2% of all-time downloads
videomae-base-finetuned-rwf2000-subset
DanJoshua/videomae-base-finetuned-rwf2000-subset
videomae-base-finetuned-rwf2000-subset is a video classification model from DanJoshua. 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
846
Public
Parameters
86.2M
10 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
- Jul 12, 2024
- Updated
- Jul 22, 2024
- SHA
- 6dfe962e
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-rwf2000-subset
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: 0.6551
- Accuracy: 0.8187
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 2790
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3956 | 0.0670 | 187 | 0.7066 | 0.7179 |
| 0.4019 | 1.0670 | 374 | 0.6282 | 0.7115 |
| 0.4473 | 2.0670 | 561 | 0.4394 | 0.7692 |
| 0.3309 | 3.0670 | 748 | 0.4782 | 0.7821 |
| 0.4007 | 4.0670 | 935 | 0.4135 | 0.8462 |
| 0.3772 | 5.0670 | 1122 | 0.4329 | 0.8462 |
| 0.4685 | 6.0670 | 1309 | 0.4191 | 0.8654 |
| 0.4056 | 7.0670 | 1496 | 0.5650 | 0.8013 |
| 0.2306 | 8.0670 | 1683 | 0.7093 | 0.8077 |
| 0.304 | 9.0670 | 1870 | 0.3939 | 0.8782 |
| 0.2418 | 10.0670 | 2057 | 0.5525 | 0.8333 |
| 0.2089 | 11.0670 | 2244 | 0.5139 | 0.8590 |
| 0.3158 | 12.0670 | 2431 | 0.5392 | 0.8590 |
| 0.1726 | 13.0670 | 2618 | 0.5430 | 0.8333 |
| 0.2543 | 14.0616 | 2790 | 0.4978 | 0.8718 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.0.1+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1
- Task
- Video Classification
- Library
- transformers
- Type
- videomae
- License
- cc-by-nc-4.0
- Created
- Jul 12, 2024
- Updated
- Jul 22, 2024