vit-base-patch16-224
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: 1.2817
- Accuracy: 0.7205
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: 0.001
- 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.8025 | 0.98 | 27 | 0.6852 | 0.6407 |
0.5648 | 1.98 | 54 | 0.7587 | 0.6971 |
0.2165 | 2.98 | 81 | 0.6410 | 0.7387 |
0.0587 | 3.98 | 108 | 1.9350 | 0.5682 |
0.041 | 4.98 | 135 | 0.9925 | 0.7348 |
0.013 | 5.98 | 162 | 1.3159 | 0.6980 |
0.025 | 6.98 | 189 | 1.4855 | 0.7456 |
0.0243 | 7.98 | 216 | 1.4230 | 0.7489 |
0.0016 | 8.98 | 243 | 1.2937 | 0.7117 |
0.0026 | 9.98 | 270 | 1.2817 | 0.7205 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2
- Downloads last month
- 3
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.