<!-- 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. -->
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: 0.0226
- Accuracy: 0.9925
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: 0.0002
- 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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3365 | 0.38 | 50 | 0.2455 | 0.9323 |
| 0.1728 | 0.77 | 100 | 0.1544 | 0.9549 |
| 0.1519 | 1.15 | 150 | 0.1072 | 0.9624 |
| 0.0209 | 1.54 | 200 | 0.1594 | 0.9624 |
| 0.0206 | 1.92 | 250 | 0.0913 | 0.9699 |
| 0.0135 | 2.31 | 300 | 0.1488 | 0.9624 |
| 0.0079 | 2.69 | 350 | 0.0226 | 0.9925 |
| 0.0074 | 3.08 | 400 | 0.0582 | 0.9925 |
| 0.0064 | 3.46 | 450 | 0.0984 | 0.9774 |
| 0.0061 | 3.85 | 500 | 0.1151 | 0.9699 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu117
- Datasets 2.11.0
- Tokenizers 0.13.3
