metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224-v21
results: []
vit-base-patch16-224-v21
This model is a fine-tuned version of google/vit-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0347
- Accuracy: 0.99
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: 0.0005
- 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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2951 | 1.0 | 190 | 0.1895 | 0.9333 |
| 0.2013 | 2.0 | 380 | 0.0813 | 0.9726 |
| 0.1935 | 3.0 | 570 | 0.0902 | 0.9681 |
| 0.1858 | 4.0 | 760 | 0.0916 | 0.9674 |
| 0.118 | 5.0 | 950 | 0.0481 | 0.9833 |
| 0.0834 | 6.0 | 1140 | 0.0578 | 0.9841 |
| 0.0986 | 7.0 | 1330 | 0.0418 | 0.9870 |
| 0.0737 | 8.0 | 1520 | 0.0347 | 0.99 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Tokenizers 0.13.3