<!-- 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-patch16-224-in21k-lcbsi
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0690
- Accuracy: 0.9853
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: 0.001
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5933 | 0.98 | 27 | 0.1754 | 0.9587 |
| 0.2672 | 1.98 | 54 | 0.1286 | 0.964 |
| 0.153 | 2.98 | 81 | 0.1375 | 0.9627 |
| 0.0838 | 3.98 | 108 | 0.1100 | 0.9733 |
| 0.0457 | 4.98 | 135 | 0.1678 | 0.952 |
| 0.0366 | 5.98 | 162 | 0.0744 | 0.9813 |
| 0.0108 | 6.98 | 189 | 0.0834 | 0.9827 |
| 0.0075 | 7.98 | 216 | 0.0690 | 0.9853 |
| 0.0051 | 8.98 | 243 | 0.0739 | 0.984 |
| 0.0028 | 9.98 | 270 | 0.0731 | 0.984 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2
