vit-base-beans
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the beans dataset. It achieves the following results on the evaluation set:
- Loss: 0.0942
- Accuracy: 0.9774
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2809 | 1.0 | 130 | 0.2287 | 0.9699 |
| 0.1097 | 2.0 | 260 | 0.1676 | 0.9624 |
| 0.1027 | 3.0 | 390 | 0.0942 | 0.9774 |
| 0.0923 | 4.0 | 520 | 0.1104 | 0.9699 |
| 0.1726 | 5.0 | 650 | 0.1030 | 0.9699 |
Framework versions
- Transformers 4.10.0.dev0
- Pytorch 1.9.0+cu102
- Datasets 1.11.1.dev0
- Tokenizers 0.10.3
- Downloads last month
- 2,690
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Dataset used to train nateraw/vit-base-beans
Spaces using nateraw/vit-base-beans 11
Evaluation results
- Accuracy on beansself-reported0.977
- Accuracy on beanstest set verified0.945
- Precision Macro on beanstest set verified0.945
- Precision Micro on beanstest set verified0.945
- Precision Weighted on beanstest set verified0.945
- Recall Macro on beanstest set verified0.946
- Recall Micro on beanstest set verified0.945
- Recall Weighted on beanstest set verified0.945
- F1 Macro on beanstest set verified0.945
- F1 Micro on beanstest set verified0.945