Downloads · 30 days
3
1% of all-time downloads
378A1_results_384_4cate_1
wuru330/378A1_results_384_4cate_1
378A1_results_384_4cate_1 is a image classification model from wuru330. 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
247
Public
Repo size
10.7 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
- Sep 22, 2023
- Updated
- Sep 25, 2023
- SHA
- 7fc6e571
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. -->
378A1_results_384_4cate_1
This model is a fine-tuned version of google/vit-base-patch16-384 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4707
- Accuracy: 0.8997
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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.8756 | 1.0 | 37 | 0.5714 | 0.7908 |
| 0.4508 | 2.0 | 74 | 0.3688 | 0.8418 |
| 0.2344 | 3.0 | 111 | 0.3064 | 0.8741 |
| 0.1445 | 4.0 | 148 | 0.2948 | 0.8946 |
| 0.0774 | 5.0 | 185 | 0.3461 | 0.8793 |
| 0.0393 | 6.0 | 222 | 0.3229 | 0.8997 |
| 0.0164 | 7.0 | 259 | 0.3441 | 0.9048 |
| 0.0222 | 8.0 | 296 | 0.4192 | 0.9099 |
| 0.0125 | 9.0 | 333 | 0.4443 | 0.8810 |
| 0.0029 | 10.0 | 370 | 0.4007 | 0.9116 |
| 0.0014 | 11.0 | 407 | 0.4277 | 0.9150 |
| 0.0003 | 12.0 | 444 | 0.4445 | 0.9014 |
| 0.0002 | 13.0 | 481 | 0.4437 | 0.9031 |
| 0.0002 | 14.0 | 518 | 0.4481 | 0.9048 |
| 0.0002 | 15.0 | 555 | 0.4512 | 0.9031 |
| 0.0002 | 16.0 | 592 | 0.4537 | 0.9014 |
| 0.0002 | 17.0 | 629 | 0.4562 | 0.9014 |
| 0.0002 | 18.0 | 666 | 0.4583 | 0.9014 |
| 0.0001 | 19.0 | 703 | 0.4594 | 0.9014 |
| 0.0001 | 20.0 | 740 | 0.4615 | 0.9031 |
| 0.0001 | 21.0 | 777 | 0.4635 | 0.9031 |
| 0.0001 | 22.0 | 814 | 0.4652 | 0.9031 |
| 0.0001 | 23.0 | 851 | 0.4659 | 0.9031 |
| 0.0001 | 24.0 | 888 | 0.4679 | 0.8997 |
| 0.0001 | 25.0 | 925 | 0.4681 | 0.9014 |
| 0.0001 | 26.0 | 962 | 0.4688 | 0.8997 |
| 0.0001 | 27.0 | 999 | 0.4695 | 0.8997 |
| 0.0001 | 28.0 | 1036 | 0.4701 | 0.8997 |
| 0.0001 | 29.0 | 1073 | 0.4706 | 0.8997 |
| 0.0001 | 30.0 | 1110 | 0.4707 | 0.8997 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Sep 22, 2023
- Updated
- Sep 25, 2023