2025-02-05-14-22-36-vit-base-patch16-224
This model is a fine-tuned version of google/vit-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0410
- Precision: 0.9931
- Recall: 0.9927
- F1: 0.9927
- Accuracy: 0.9931
- Top1 Accuracy: 0.9927
- Error Rate: 0.0069
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: 32
- eval_batch_size: 32
- seed: 3407
- 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 | Precision | Recall | F1 | Accuracy | Top1 Accuracy | Error Rate |
|---|---|---|---|---|---|---|---|---|---|
| 0.9229 | 1.0 | 103 | 0.2079 | 0.9541 | 0.9366 | 0.9386 | 0.9333 | 0.9366 | 0.0667 |
| 0.1707 | 2.0 | 206 | 0.1222 | 0.9726 | 0.9707 | 0.9688 | 0.9664 | 0.9707 | 0.0336 |
| 0.0937 | 3.0 | 309 | 0.1807 | 0.9552 | 0.9512 | 0.9505 | 0.9561 | 0.9512 | 0.0439 |
| 0.0619 | 4.0 | 412 | 0.1122 | 0.9764 | 0.9756 | 0.9754 | 0.9778 | 0.9756 | 0.0222 |
| 0.0309 | 5.0 | 515 | 0.0803 | 0.9884 | 0.9878 | 0.9875 | 0.9863 | 0.9878 | 0.0137 |
| 0.0275 | 6.0 | 618 | 0.0437 | 0.9904 | 0.9902 | 0.9902 | 0.9905 | 0.9902 | 0.0095 |
| 0.0103 | 7.0 | 721 | 0.0426 | 0.9905 | 0.9902 | 0.9903 | 0.9908 | 0.9902 | 0.0092 |
| 0.0065 | 8.0 | 824 | 0.0414 | 0.9953 | 0.9951 | 0.9951 | 0.9949 | 0.9951 | 0.0051 |
| 0.004 | 9.0 | 927 | 0.0410 | 0.9931 | 0.9927 | 0.9927 | 0.9931 | 0.9927 | 0.0069 |
| 0.0007 | 10.0 | 1030 | 0.0416 | 0.9953 | 0.9951 | 0.9951 | 0.9949 | 0.9951 | 0.0051 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.20.3