Downloads · 30 days
47
2% of all-time downloads
BEiT-finetuned
jadohu/BEiT-finetuned
BEiT-finetuned is a image classification model from jadohu. 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
2.7K
Public
Repo size
2.1 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin347 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- beit
- Access
- Public
- Created
- May 18, 2022
- Updated
- May 18, 2022
- SHA
- 2f708c7f
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. -->
BEiT-finetuned
This model is a fine-tuned version of microsoft/beit-base-patch16-224 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0256
- Accuracy: 0.9918
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3296 | 1.0 | 351 | 0.0492 | 0.9862 |
| 0.2353 | 2.0 | 702 | 0.0331 | 0.9894 |
| 0.2127 | 3.0 | 1053 | 0.0256 | 0.9918 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.1
- Tokenizers 0.12.1
- Task
- Image Classification
- Library
- transformers
- Type
- beit
- License
- apache-2.0
- Created
- May 18, 2022
- Updated
- May 18, 2022