vit-finetuned-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: 0.1157
- Accuracy: 0.9712
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.193 | 1.0 | 117 | 0.1099 | 0.9808 |
| 0.0462 | 2.0 | 234 | 0.0857 | 0.9808 |
| 0.0171 | 3.0 | 351 | 0.1237 | 0.9712 |
| 0.0123 | 4.0 | 468 | 0.1088 | 0.9712 |
| 0.0095 | 5.0 | 585 | 0.1135 | 0.9712 |
| 0.0081 | 6.0 | 702 | 0.1162 | 0.9712 |
| 0.0073 | 7.0 | 819 | 0.1158 | 0.9712 |
| 0.0066 | 8.0 | 936 | 0.1152 | 0.9712 |
| 0.0061 | 9.0 | 1053 | 0.1160 | 0.9712 |
| 0.0061 | 10.0 | 1170 | 0.1157 | 0.9712 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
- Downloads last month
- 10