msi-vit-small-pretrain
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: 2.4835
- Accuracy: 0.6394
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 |
|---|---|---|---|---|
| 0.0897 | 1.0 | 781 | 1.7652 | 0.6574 |
| 0.0539 | 2.0 | 1562 | 2.5512 | 0.6017 |
| 0.0127 | 3.0 | 2343 | 2.4835 | 0.6394 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.0.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0