vit-base-patch16-224-RU4-10
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: 0.5903
- Accuracy: 0.8333
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: 5.5e-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: 0.05
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.37 | 0.99 | 19 | 1.1940 | 0.6167 |
1.1393 | 1.97 | 38 | 0.9231 | 0.7 |
0.8115 | 2.96 | 57 | 0.7924 | 0.7667 |
0.5507 | 4.0 | 77 | 0.6691 | 0.75 |
0.4093 | 4.99 | 96 | 0.6462 | 0.8167 |
0.2869 | 5.97 | 115 | 0.5903 | 0.8333 |
0.2347 | 6.96 | 134 | 0.7096 | 0.7333 |
0.2148 | 8.0 | 154 | 0.6362 | 0.7833 |
0.1868 | 8.99 | 173 | 0.6496 | 0.8 |
0.1977 | 9.87 | 190 | 0.6368 | 0.7667 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 0
Finetuned from
Evaluation results
- Accuracy on imagefoldervalidation set self-reported0.833