Downloads · 30 days
5
13% of all-time downloads
vit-base-beans
nashirab/vit-base-beans
vit-base-beans is a image classification model from nashirab. Use it when you need a label for an image. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
39
Public
Parameters
86.6M
346 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors346 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Feb 12, 2024
- Updated
- Feb 12, 2024
- SHA
- cf560a37
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. -->
vit-base-beans
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.2658
- Accuracy: 0.4938
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.7295 | 0.25 | 10 | 2.7467 | 0.1875 |
| 2.3133 | 0.5 | 20 | 2.1258 | 0.2437 |
| 2.031 | 0.75 | 30 | 1.9442 | 0.3187 |
| 1.8773 | 1.0 | 40 | 1.6159 | 0.375 |
| 1.4132 | 1.25 | 50 | 1.5585 | 0.4188 |
| 1.4581 | 1.5 | 60 | 1.5269 | 0.35 |
| 1.4697 | 1.75 | 70 | 1.5535 | 0.3625 |
| 1.3575 | 2.0 | 80 | 1.3056 | 0.4375 |
| 1.0615 | 2.25 | 90 | 1.4774 | 0.4 |
| 1.1895 | 2.5 | 100 | 1.2384 | 0.45 |
| 1.0659 | 2.75 | 110 | 1.3315 | 0.4938 |
| 1.1517 | 3.0 | 120 | 1.1040 | 0.575 |
| 0.7957 | 3.25 | 130 | 1.3480 | 0.4375 |
| 0.8037 | 3.5 | 140 | 1.2879 | 0.525 |
| 1.0157 | 3.75 | 150 | 1.1900 | 0.5 |
| 0.7665 | 4.0 | 160 | 1.2039 | 0.4938 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Feb 12, 2024
- Updated
- Feb 12, 2024