|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: vit-base-patch16-224-in21k-finetuned-papsmear |
|
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. --> |
|
|
|
# vit-base-patch16-224-in21k-finetuned-biopsy |
|
|
|
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: 0.1092 |
|
- Accuracy: 0.9732 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.1553 | 1.0 | 42 | 1.0950 | 0.5477 | |
|
| 0.7791 | 2.0 | 84 | 0.6486 | 0.8526 | |
|
| 0.433 | 3.0 | 126 | 0.3716 | 0.9129 | |
|
| 0.3495 | 4.0 | 168 | 0.2869 | 0.9347 | |
|
| 0.2556 | 5.0 | 210 | 0.2722 | 0.9280 | |
|
| 0.2791 | 6.0 | 252 | 0.2611 | 0.9330 | |
|
| 0.2343 | 7.0 | 294 | 0.2377 | 0.9380 | |
|
| 0.186 | 8.0 | 336 | 0.2158 | 0.9397 | |
|
| 0.1984 | 9.0 | 378 | 0.2222 | 0.9347 | |
|
| 0.1751 | 10.0 | 420 | 0.1993 | 0.9514 | |
|
| 0.1529 | 11.0 | 462 | 0.2101 | 0.9430 | |
|
| 0.1616 | 12.0 | 504 | 0.2543 | 0.9296 | |
|
| 0.1404 | 13.0 | 546 | 0.2029 | 0.9397 | |
|
| 0.1078 | 14.0 | 588 | 0.2087 | 0.9414 | |
|
| 0.1109 | 15.0 | 630 | 0.1381 | 0.9615 | |
|
| 0.1072 | 16.0 | 672 | 0.1895 | 0.9414 | |
|
| 0.0949 | 17.0 | 714 | 0.1981 | 0.9397 | |
|
| 0.0908 | 18.0 | 756 | 0.1608 | 0.9581 | |
|
| 0.0809 | 19.0 | 798 | 0.1764 | 0.9581 | |
|
| 0.0708 | 20.0 | 840 | 0.1512 | 0.9531 | |
|
| 0.0757 | 21.0 | 882 | 0.2027 | 0.9481 | |
|
| 0.0919 | 22.0 | 924 | 0.1487 | 0.9615 | |
|
| 0.07 | 23.0 | 966 | 0.1667 | 0.9615 | |
|
| 0.0629 | 24.0 | 1008 | 0.1904 | 0.9531 | |
|
| 0.0584 | 25.0 | 1050 | 0.1521 | 0.9631 | |
|
| 0.0666 | 26.0 | 1092 | 0.1326 | 0.9665 | |
|
| 0.062 | 27.0 | 1134 | 0.1772 | 0.9564 | |
|
| 0.0568 | 28.0 | 1176 | 0.1465 | 0.9564 | |
|
| 0.0453 | 29.0 | 1218 | 0.1347 | 0.9682 | |
|
| 0.0469 | 30.0 | 1260 | 0.1687 | 0.9631 | |
|
| 0.0541 | 31.0 | 1302 | 0.1390 | 0.9715 | |
|
| 0.0602 | 32.0 | 1344 | 0.1618 | 0.9615 | |
|
| 0.0497 | 33.0 | 1386 | 0.1415 | 0.9615 | |
|
| 0.0493 | 34.0 | 1428 | 0.1521 | 0.9631 | |
|
| 0.0606 | 35.0 | 1470 | 0.1429 | 0.9698 | |
|
| 0.0332 | 36.0 | 1512 | 0.1671 | 0.9648 | |
|
| 0.0432 | 37.0 | 1554 | 0.1441 | 0.9665 | |
|
| 0.0354 | 38.0 | 1596 | 0.1593 | 0.9682 | |
|
| 0.0432 | 39.0 | 1638 | 0.1395 | 0.9665 | |
|
| 0.0363 | 40.0 | 1680 | 0.1092 | 0.9732 | |
|
| 0.0288 | 41.0 | 1722 | 0.1550 | 0.9665 | |
|
| 0.0305 | 42.0 | 1764 | 0.1462 | 0.9682 | |
|
| 0.0326 | 43.0 | 1806 | 0.1343 | 0.9682 | |
|
| 0.027 | 44.0 | 1848 | 0.1109 | 0.9732 | |
|
| 0.0233 | 45.0 | 1890 | 0.1315 | 0.9732 | |
|
| 0.042 | 46.0 | 1932 | 0.1261 | 0.9732 | |
|
| 0.0251 | 47.0 | 1974 | 0.1320 | 0.9732 | |
|
| 0.041 | 48.0 | 2016 | 0.1282 | 0.9732 | |
|
| 0.0445 | 49.0 | 2058 | 0.1296 | 0.9732 | |
|
| 0.0308 | 50.0 | 2100 | 0.1325 | 0.9732 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.19.1 |
|
|