Downloads · 30 days
5
33% of all-time downloads
videomae-base-zhe5
xixi1031/videomae-base-zhe5
videomae-base-zhe5 is a machine learning model from xixi1031. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
should probably proofread and complete it, then remove this comment. --
All-time downloads
15
Public
Parameters
86.2M
9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors345 MB · 98%
At a glance
- Model type
- videomae
- Access
- Public
- Created
- Aug 20, 2024
- Updated
- Sep 1, 2024
- SHA
- 22e6cdaf
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-zhe5
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6870
- Accuracy: 0.5029
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: 16
- eval_batch_size: 16
- 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: 3020
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.085 | 0.0503 | 152 | 2.9848 | 0.4941 |
| 0.0325 | 1.0503 | 304 | 2.6870 | 0.5029 |
| 0.0336 | 2.0503 | 456 | 4.3851 | 0.3366 |
| 0.0507 | 3.0503 | 608 | 3.9365 | 0.4980 |
| 0.0027 | 4.0503 | 760 | 3.6407 | 0.4966 |
| 0.0294 | 5.0503 | 912 | 4.5018 | 0.4956 |
| 0.0032 | 6.0503 | 1064 | 4.3951 | 0.4956 |
| 0.0923 | 7.0503 | 1216 | 4.5640 | 0.4980 |
| 0.0005 | 8.0503 | 1368 | 4.5948 | 0.4980 |
| 0.0008 | 9.0503 | 1520 | 4.5939 | 0.4980 |
| 0.0004 | 10.0503 | 1672 | 4.7403 | 0.4976 |
| 0.0485 | 11.0503 | 1824 | 4.6948 | 0.4980 |
| 0.0039 | 12.0503 | 1976 | 4.7846 | 0.4980 |
| 0.0001 | 13.0503 | 2128 | 4.9544 | 0.4980 |
| 0.0001 | 14.0503 | 2280 | 4.9890 | 0.4980 |
| 0.0001 | 15.0503 | 2432 | 5.0184 | 0.4980 |
| 0.0001 | 16.0503 | 2584 | 4.9908 | 0.4980 |
| 0.0003 | 17.0503 | 2736 | 4.9993 | 0.4980 |
| 0.0222 | 18.0503 | 2888 | 5.0218 | 0.4980 |
| 0.0003 | 19.0437 | 3020 | 5.0292 | 0.4980 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Type
- videomae
- Created
- Aug 20, 2024
- Updated
- Sep 1, 2024