Downloads · 30 days
12
14% of all-time downloads
msi-dinat-mini-pretrain
aaa12963337/msi-dinat-mini-pretrain
msi-dinat-mini-pretrain is a image classification model from aaa12963337. Use it when you need a label for an image. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
84
Public
Parameters
19.5M
234 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors77.9 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- mit
- Model type
- dinat
- Access
- Public
- Created
- Dec 16, 2023
- Updated
- Dec 16, 2023
- SHA
- abfe3256
Base models
Datasets
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. -->
msi-dinat-mini-pretrain
This model is a fine-tuned version of shi-labs/dinat-mini-in1k-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.5378
- Accuracy: 0.8937
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1041 | 1.0 | 1562 | 0.4092 | 0.8756 |
| 0.0527 | 2.0 | 3125 | 0.6298 | 0.8765 |
| 0.0611 | 3.0 | 4686 | 0.5378 | 0.8937 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Task
- Image Classification
- Library
- transformers
- Type
- dinat
- License
- mit
- Created
- Dec 16, 2023
- Updated
- Dec 16, 2023