vit-base-patch16-224-finetune_test
This model is a fine-tuned version of google/vit-base-patch16-224 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1114
- Accuracy: 0.3030
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.8421 | 4 | 1.1605 | 0.3333 |
| No log | 1.8947 | 9 | 1.1242 | 0.3333 |
| 1.1465 | 2.5263 | 12 | 1.1114 | 0.3030 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0.dev20240710
- Datasets 3.3.2
- Tokenizers 0.19.1
- Downloads last month
- 51
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for CEBangu/vit-base-patch16-224-finetune_test
Base model
google/vit-base-patch16-224