Train-Augmentation-vit-base
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: 0.9262
- Accuracy: 0.7866
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.6254 | 0.99 | 93 | 0.8623 | 0.7194 |
0.2129 | 2.0 | 187 | 0.7057 | 0.7510 |
0.0877 | 2.99 | 280 | 0.8545 | 0.7194 |
0.0164 | 4.0 | 374 | 0.9221 | 0.7549 |
0.0057 | 4.99 | 467 | 0.8149 | 0.7708 |
0.0021 | 6.0 | 561 | 0.8764 | 0.7866 |
0.0016 | 6.99 | 654 | 0.9059 | 0.7905 |
0.0013 | 8.0 | 748 | 0.9132 | 0.7866 |
0.0011 | 8.99 | 841 | 0.9236 | 0.7866 |
0.0013 | 9.95 | 930 | 0.9262 | 0.7866 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.15.2
- Downloads last month
- 2
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.