Downloads · 30 days
8
4% of all-time downloads
378A1_results_coord
wuru330/378A1_results_coord
378A1_results_coord 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
211
Public
Repo size
10.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin343 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Aug 3, 2023
- Updated
- Aug 3, 2023
- SHA
- 1907c30f
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_coord
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4924
- Accuracy: 0.8946
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 |
|---|---|---|---|---|
| 1.2529 | 1.0 | 37 | 1.0701 | 0.6207 |
| 0.6771 | 2.0 | 74 | 0.6678 | 0.7687 |
| 0.4363 | 3.0 | 111 | 0.5622 | 0.8010 |
| 0.2884 | 4.0 | 148 | 0.3808 | 0.8690 |
| 0.2382 | 5.0 | 185 | 0.3492 | 0.8810 |
| 0.1213 | 6.0 | 222 | 0.3485 | 0.8895 |
| 0.1238 | 7.0 | 259 | 0.4012 | 0.8827 |
| 0.0878 | 8.0 | 296 | 0.4311 | 0.8639 |
| 0.0839 | 9.0 | 333 | 0.4417 | 0.8656 |
| 0.0406 | 10.0 | 370 | 0.3993 | 0.8844 |
| 0.0509 | 11.0 | 407 | 0.4922 | 0.8690 |
| 0.0347 | 12.0 | 444 | 0.4840 | 0.8741 |
| 0.033 | 13.0 | 481 | 0.4572 | 0.8827 |
| 0.0222 | 14.0 | 518 | 0.4376 | 0.8861 |
| 0.0197 | 15.0 | 555 | 0.4397 | 0.8912 |
| 0.0179 | 16.0 | 592 | 0.4464 | 0.8946 |
| 0.0167 | 17.0 | 629 | 0.4526 | 0.8946 |
| 0.0154 | 18.0 | 666 | 0.4588 | 0.8929 |
| 0.0148 | 19.0 | 703 | 0.4642 | 0.8929 |
| 0.0135 | 20.0 | 740 | 0.4691 | 0.8929 |
| 0.0131 | 21.0 | 777 | 0.4732 | 0.8946 |
| 0.0125 | 22.0 | 814 | 0.4776 | 0.8946 |
| 0.0119 | 23.0 | 851 | 0.4809 | 0.8946 |
| 0.0116 | 24.0 | 888 | 0.4841 | 0.8946 |
| 0.0112 | 25.0 | 925 | 0.4863 | 0.8946 |
| 0.0111 | 26.0 | 962 | 0.4885 | 0.8946 |
| 0.0108 | 27.0 | 999 | 0.4903 | 0.8946 |
| 0.0108 | 28.0 | 1036 | 0.4912 | 0.8946 |
| 0.0105 | 29.0 | 1073 | 0.4921 | 0.8946 |
| 0.0108 | 30.0 | 1110 | 0.4924 | 0.8946 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Aug 3, 2023
- Updated
- Aug 3, 2023