<!-- 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-type
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.7556
- Accuracy: 0.7424
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: 3e-05
- 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 |
|---|---|---|---|---|
| 0.5461 | 1.0 | 62 | 0.7743 | 0.7230 |
| 0.4924 | 1.99 | 124 | 0.7858 | 0.7248 |
| 0.5121 | 2.99 | 186 | 0.7973 | 0.7330 |
| 0.5216 | 4.0 | 249 | 0.7749 | 0.7289 |
| 0.5788 | 5.0 | 311 | 0.7801 | 0.7312 |
| 0.5863 | 5.99 | 373 | 0.7705 | 0.7424 |
| 0.5862 | 6.99 | 435 | 0.7560 | 0.7424 |
| 0.5327 | 8.0 | 498 | 0.7631 | 0.7365 |
| 0.5155 | 9.0 | 560 | 0.7560 | 0.7406 |
| 0.511 | 9.96 | 620 | 0.7556 | 0.7424 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
