Downloads · 30 days
10
2% of all-time downloads
checkpoint-100
nomis15/checkpoint-100
checkpoint-100 is a image classification model from nomis15. 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
411
Public
Parameters
85.8M
1.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt687 MB · 67%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Jan 22, 2024
- Updated
- Jan 22, 2024
- SHA
- 9b5f54fb
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. -->
checkpoint-100
This model is a fine-tuned version of facebook/deit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.5022
- Accuracy: 0.8050
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: 1e-05
- train_batch_size: 20
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 80
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2967 | 1.24 | 50 | 0.9589 | 0.5975 |
| 0.721 | 2.48 | 100 | 0.6094 | 0.7528 |
| 0.5443 | 3.73 | 150 | 0.5702 | 0.7702 |
| 0.4597 | 4.97 | 200 | 0.5168 | 0.7938 |
| 0.3985 | 6.21 | 250 | 0.5091 | 0.7925 |
| 0.3407 | 7.45 | 300 | 0.5011 | 0.8 |
| 0.2989 | 8.7 | 350 | 0.5031 | 0.7963 |
| 0.271 | 9.94 | 400 | 0.4951 | 0.8012 |
| 0.2355 | 11.18 | 450 | 0.4973 | 0.8050 |
| 0.2047 | 12.42 | 500 | 0.5011 | 0.8025 |
| 0.1934 | 13.66 | 550 | 0.5018 | 0.8037 |
| 0.1861 | 14.91 | 600 | 0.5022 | 0.8050 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Jan 22, 2024
- Updated
- Jan 22, 2024