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: 1.0002
- Accuracy: 0.7850
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7184 | 1.0 | 227 | 1.6196 | 0.7327 |
| 0.6575 | 2.0 | 455 | 1.6466 | 0.7102 |
| 0.6033 | 3.0 | 682 | 1.5743 | 0.7226 |
| 0.4692 | 4.0 | 910 | 1.4970 | 0.7289 |
| 0.3551 | 5.0 | 1137 | 1.4109 | 0.7393 |
| 0.4104 | 6.0 | 1365 | 1.3546 | 0.7352 |
| 0.3038 | 7.0 | 1592 | 1.3356 | 0.7393 |
| 0.3195 | 8.0 | 1820 | 1.3145 | 0.7371 |
| 0.3254 | 9.0 | 2047 | 1.2262 | 0.7580 |
| 0.3182 | 10.0 | 2275 | 1.1926 | 0.7630 |
| 0.3278 | 11.0 | 2502 | 1.1491 | 0.7704 |
| 0.2805 | 12.0 | 2730 | 1.1514 | 0.7627 |
| 0.3188 | 13.0 | 2957 | 1.0948 | 0.7795 |
| 0.3161 | 14.0 | 3185 | 1.1231 | 0.7685 |
| 0.229 | 15.0 | 3412 | 1.0588 | 0.7789 |
| 0.2544 | 16.0 | 3640 | 1.0311 | 0.7806 |
| 0.2872 | 17.0 | 3867 | 1.0586 | 0.7762 |
| 0.3974 | 18.0 | 4095 | 1.0341 | 0.7833 |
| 0.337 | 19.0 | 4322 | 0.9834 | 0.7891 |
| 0.3165 | 19.96 | 4540 | 1.0002 | 0.7850 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0