project_name
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the fl_image_category_ds dataset. It achieves the following results on the evaluation set:
- Loss: 0.9537
- Accuracy: 0.6622
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3368 | 1.0 | 88 | 1.2575 | 0.5448 |
| 1.1146 | 2.0 | 176 | 1.0928 | 0.6038 |
| 0.9667 | 3.0 | 264 | 1.0195 | 0.6223 |
| 0.9005 | 4.0 | 352 | 0.9832 | 0.6373 |
| 0.8432 | 5.0 | 440 | 0.9537 | 0.6622 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1
- Datasets 2.8.0
- Tokenizers 0.13.2
- Downloads last month
- 1