Downloads · 30 days
7
1% of all-time downloads
exper2_mesum5
sudo-s/exper2_mesum5
exper2_mesum5 is a image classification model from sudo-s. 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
699
Public
Repo size
1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin344 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Jul 22, 2022
- Updated
- Jul 22, 2022
- SHA
- aded3072
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. -->
exper2_mesum5
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the sudo-s/herbier_mesuem5 dataset. It achieves the following results on the evaluation set:
- Loss: 3.4589
- Accuracy: 0.1308
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: 0.002
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.4265 | 0.23 | 100 | 4.3676 | 0.0296 |
| 4.1144 | 0.47 | 200 | 4.1606 | 0.0544 |
| 4.0912 | 0.7 | 300 | 4.1071 | 0.0509 |
| 4.0361 | 0.93 | 400 | 4.0625 | 0.0669 |
| 4.0257 | 1.16 | 500 | 3.9682 | 0.0822 |
| 3.8846 | 1.4 | 600 | 3.9311 | 0.0834 |
| 3.9504 | 1.63 | 700 | 3.9255 | 0.0698 |
| 3.9884 | 1.86 | 800 | 3.9404 | 0.0722 |
| 3.7191 | 2.09 | 900 | 3.8262 | 0.0935 |
| 3.7952 | 2.33 | 1000 | 3.8236 | 0.0734 |
| 3.8085 | 2.56 | 1100 | 3.7694 | 0.0964 |
| 3.7535 | 2.79 | 1200 | 3.6757 | 0.1059 |
| 3.4218 | 3.02 | 1300 | 3.6474 | 0.1095 |
| 3.5172 | 3.26 | 1400 | 3.5621 | 0.1166 |
| 3.5173 | 3.49 | 1500 | 3.5579 | 0.1207 |
| 3.4346 | 3.72 | 1600 | 3.4817 | 0.1249 |
| 3.3995 | 3.95 | 1700 | 3.4589 | 0.1308 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Jul 22, 2022
- Updated
- Jul 22, 2022