msi-vit-pretrain_1218
This model is a fine-tuned version of WinKawaks/vit-small-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 2.7293
- Accuracy: 0.5866
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: 5e-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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1183 | 1.0 | 781 | 1.3771 | 0.6737 |
| 0.0548 | 2.0 | 1562 | 2.6272 | 0.5738 |
| 0.014 | 3.0 | 2343 | 2.7293 | 0.5866 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.0.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0