Fine-Tuned_Model3
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: 0.7362
- Accuracy: 0.608
- F1: 0.5096
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
3.2255 | 5.0 | 20 | 1.9574 | 0.512 | 0.3083 |
1.3773 | 10.0 | 40 | 0.8854 | 0.584 | 0.4617 |
0.869 | 15.0 | 60 | 0.7880 | 0.608 | 0.4795 |
0.7966 | 20.0 | 80 | 0.7732 | 0.6 | 0.4846 |
0.8458 | 25.0 | 100 | 0.7795 | 0.576 | 0.4112 |
0.8135 | 30.0 | 120 | 0.7362 | 0.608 | 0.5096 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1
- Downloads last month
- 20
Finetuned from
Evaluation results
- Accuracy on imagefolderself-reported0.608
- F1 on imagefolderself-reported0.510