metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: celebrity-classifier
results: []
celebrity-classifier
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.8884
- Accuracy: 0.4847
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 |
|---|---|---|---|---|
| 5.0138 | 1.0 | 227 | 5.2286 | 0.2802 |
| 4.7675 | 2.0 | 455 | 4.9884 | 0.3151 |
| 4.4753 | 3.0 | 682 | 4.7386 | 0.3547 |
| 4.1843 | 4.0 | 910 | 4.5348 | 0.3852 |
| 3.9013 | 5.0 | 1137 | 4.3369 | 0.4185 |
| 3.7744 | 6.0 | 1365 | 4.1786 | 0.4363 |
| 3.5452 | 7.0 | 1592 | 4.0784 | 0.4520 |
| 3.472 | 8.0 | 1820 | 3.9941 | 0.4680 |
| 3.3858 | 9.0 | 2047 | 3.9071 | 0.4834 |
| 3.3678 | 9.98 | 2270 | 3.8884 | 0.4847 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0