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
Model description
This model classifies a face to a celebrity. It is trained on tonyassi/celebrity-1000 and fine-tuned on google/vit-base-patch16-224-in21k. It achieves the following results on the evaluation set:
- Loss: 0.9089
- Accuracy: 0.7982
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 |
|---|---|---|---|---|
| 0.2075 | 1.0 | 227 | 1.0255 | 0.7831 |
| 0.1359 | 2.0 | 455 | 1.1713 | 0.7517 |
| 0.1703 | 3.0 | 682 | 1.1582 | 0.7503 |
| 0.1052 | 4.0 | 910 | 1.1482 | 0.7567 |
| 0.0826 | 5.0 | 1137 | 1.1340 | 0.7514 |
| 0.1412 | 6.0 | 1365 | 1.1149 | 0.7514 |
| 0.105 | 7.0 | 1592 | 1.1071 | 0.7523 |
| 0.1067 | 8.0 | 1820 | 1.1161 | 0.7539 |
| 0.1329 | 9.0 | 2047 | 1.0587 | 0.7693 |
| 0.1196 | 10.0 | 2275 | 1.0416 | 0.7688 |
| 0.1368 | 11.0 | 2502 | 1.0618 | 0.7663 |
| 0.1162 | 12.0 | 2730 | 1.0285 | 0.7721 |
| 0.145 | 13.0 | 2957 | 1.0040 | 0.7776 |
| 0.1449 | 14.0 | 3185 | 0.9967 | 0.7800 |
| 0.1135 | 15.0 | 3412 | 0.9603 | 0.7842 |
| 0.1266 | 16.0 | 3640 | 0.9333 | 0.7861 |
| 0.1571 | 17.0 | 3867 | 0.9643 | 0.7836 |
| 0.278 | 18.0 | 4095 | 0.9526 | 0.7861 |
| 0.2596 | 19.0 | 4322 | 0.9022 | 0.7965 |
| 0.2432 | 19.96 | 4540 | 0.9089 | 0.7982 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0