Downloads · 30 days
4
6% of all-time downloads
Dataset2-ViT
Nicole-M/Dataset2-ViT
Dataset2-ViT is a image classification model from Nicole-M. Use it when you need a label for an image.
should probably proofread and complete it, then remove this comment. --
All-time downloads
65
Public
Parameters
85.8M
1.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors343 MB · 100%
At a glance
- Task
- Image Classification
- Model type
- vit
- Access
- Public
- Created
- Aug 14, 2024
- Updated
- Aug 21, 2024
- SHA
- b3a4857a
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. -->
Vit-CBIS
This model is a fine-tuned version of VIT on the CBIS-DDSM dataset. It achieves the following results on the evaluation set:
- Loss: 0.6894
- Accuracy: 0.6032
- Precision: 0.6313
- Recall: 0.6032
- F1: 0.6083
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
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.698 | 1.0 | 165 | 0.7030 | 0.4550 | 0.5327 | 0.4550 | 0.4356 |
| 0.692 | 2.0 | 330 | 0.6853 | 0.5714 | 0.5532 | 0.5714 | 0.5578 |
| 0.6999 | 3.0 | 495 | 0.6894 | 0.6032 | 0.6313 | 0.6032 | 0.6083 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Task
- Image Classification
- Type
- vit
- Created
- Aug 14, 2024
- Updated
- Aug 21, 2024