<!-- 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-v25
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: 0.1940
- Accuracy: 0.9370
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: 0.0005
- 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: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.2144 | 1.0 | 190 | 0.3728 | 0.8770 |
0.1232 | 2.0 | 380 | 0.2233 | 0.9274 |
0.0706 | 3.0 | 570 | 0.3211 | 0.8985 |
0.0261 | 4.0 | 760 | 0.1940 | 0.9370 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Tokenizers 0.13.3