|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: vit-base-patch16-224-in21k-finetuned-papsmear |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: imagefolder |
|
type: imagefolder |
|
config: default |
|
split: train |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9338235294117647 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# vit-base-patch16-224-in21k-finetuned-papsmear |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2825 |
|
- Accuracy: 0.9338 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 50 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-------:|:----:|:---------------:|:--------:| |
|
| No log | 0.9231 | 9 | 1.7346 | 0.2647 | |
|
| 1.7645 | 1.9487 | 19 | 1.6152 | 0.3088 | |
|
| 1.661 | 2.9744 | 29 | 1.4663 | 0.4118 | |
|
| 1.496 | 4.0 | 39 | 1.2989 | 0.4853 | |
|
| 1.3097 | 4.9231 | 48 | 1.1491 | 0.5588 | |
|
| 1.091 | 5.9487 | 58 | 0.9933 | 0.7206 | |
|
| 0.9088 | 6.9744 | 68 | 0.9171 | 0.6985 | |
|
| 0.7858 | 8.0 | 78 | 0.8301 | 0.7721 | |
|
| 0.7016 | 8.9231 | 87 | 0.7925 | 0.7353 | |
|
| 0.6136 | 9.9487 | 97 | 0.6992 | 0.7647 | |
|
| 0.532 | 10.9744 | 107 | 0.6401 | 0.8309 | |
|
| 0.5018 | 12.0 | 117 | 0.5787 | 0.8382 | |
|
| 0.4279 | 12.9231 | 126 | 0.6130 | 0.8088 | |
|
| 0.4116 | 13.9487 | 136 | 0.5090 | 0.8382 | |
|
| 0.3848 | 14.9744 | 146 | 0.5165 | 0.8676 | |
|
| 0.3449 | 16.0 | 156 | 0.4843 | 0.8382 | |
|
| 0.3008 | 16.9231 | 165 | 0.5460 | 0.8456 | |
|
| 0.2797 | 17.9487 | 175 | 0.4985 | 0.8309 | |
|
| 0.2696 | 18.9744 | 185 | 0.5586 | 0.8456 | |
|
| 0.2633 | 20.0 | 195 | 0.4349 | 0.9044 | |
|
| 0.2569 | 20.9231 | 204 | 0.4017 | 0.8897 | |
|
| 0.27 | 21.9487 | 214 | 0.4758 | 0.8603 | |
|
| 0.2706 | 22.9744 | 224 | 0.4133 | 0.8897 | |
|
| 0.2211 | 24.0 | 234 | 0.3844 | 0.9118 | |
|
| 0.1977 | 24.9231 | 243 | 0.3497 | 0.9265 | |
|
| 0.1969 | 25.9487 | 253 | 0.3736 | 0.9044 | |
|
| 0.1776 | 26.9744 | 263 | 0.3797 | 0.9044 | |
|
| 0.1787 | 28.0 | 273 | 0.3949 | 0.8897 | |
|
| 0.18 | 28.9231 | 282 | 0.3278 | 0.9265 | |
|
| 0.1797 | 29.9487 | 292 | 0.3615 | 0.9044 | |
|
| 0.1665 | 30.9744 | 302 | 0.4174 | 0.8603 | |
|
| 0.163 | 32.0 | 312 | 0.3574 | 0.8971 | |
|
| 0.1498 | 32.9231 | 321 | 0.3591 | 0.9044 | |
|
| 0.1405 | 33.9487 | 331 | 0.3017 | 0.9191 | |
|
| 0.155 | 34.9744 | 341 | 0.3303 | 0.9265 | |
|
| 0.1519 | 36.0 | 351 | 0.3559 | 0.8971 | |
|
| 0.1415 | 36.9231 | 360 | 0.2890 | 0.9191 | |
|
| 0.1256 | 37.9487 | 370 | 0.3445 | 0.8897 | |
|
| 0.1217 | 38.9744 | 380 | 0.3435 | 0.9118 | |
|
| 0.1285 | 40.0 | 390 | 0.3025 | 0.9191 | |
|
| 0.1285 | 40.9231 | 399 | 0.3602 | 0.8824 | |
|
| 0.1301 | 41.9487 | 409 | 0.3336 | 0.8897 | |
|
| 0.1243 | 42.9744 | 419 | 0.2825 | 0.9338 | |
|
| 0.1191 | 44.0 | 429 | 0.2835 | 0.9265 | |
|
| 0.1221 | 44.9231 | 438 | 0.2724 | 0.9191 | |
|
| 0.1151 | 45.9487 | 448 | 0.2708 | 0.9191 | |
|
| 0.1195 | 46.1538 | 450 | 0.2707 | 0.9191 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.2 |
|
- Tokenizers 0.20.1 |
|
|
