|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: celebrity-classifier |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# celebrity-classifier |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 5.3150 |
|
- Accuracy: 0.2884 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 6.7567 | 1.0 | 227 | 6.7345 | 0.0162 | |
|
| 6.4167 | 2.0 | 455 | 6.4034 | 0.0619 | |
|
| 6.1297 | 3.0 | 682 | 6.1455 | 0.1213 | |
|
| 5.8636 | 4.0 | 910 | 5.9304 | 0.1705 | |
|
| 5.6383 | 5.0 | 1137 | 5.7413 | 0.2095 | |
|
| 5.4836 | 6.0 | 1365 | 5.5914 | 0.2417 | |
|
| 5.2885 | 7.0 | 1592 | 5.4827 | 0.2505 | |
|
| 5.2052 | 8.0 | 1820 | 5.3989 | 0.2678 | |
|
| 5.1256 | 9.0 | 2047 | 5.3312 | 0.2887 | |
|
| 5.0984 | 9.98 | 2270 | 5.3150 | 0.2884 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
