|
--- |
|
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-biopsy |
|
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: 0.0838 |
|
- Accuracy: 0.9799 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.1862 | 1.0 | 42 | 1.1167 | 0.5611 | |
|
| 0.7235 | 2.0 | 84 | 0.6029 | 0.8543 | |
|
| 0.4286 | 3.0 | 126 | 0.3452 | 0.9280 | |
|
| 0.3612 | 4.0 | 168 | 0.3485 | 0.8945 | |
|
| 0.3015 | 5.0 | 210 | 0.2590 | 0.9296 | |
|
| 0.2917 | 6.0 | 252 | 0.2219 | 0.9414 | |
|
| 0.2312 | 7.0 | 294 | 0.2400 | 0.9280 | |
|
| 0.1708 | 8.0 | 336 | 0.2120 | 0.9414 | |
|
| 0.1806 | 9.0 | 378 | 0.1784 | 0.9514 | |
|
| 0.1703 | 10.0 | 420 | 0.1571 | 0.9481 | |
|
| 0.139 | 11.0 | 462 | 0.1544 | 0.9648 | |
|
| 0.1301 | 12.0 | 504 | 0.1431 | 0.9598 | |
|
| 0.122 | 13.0 | 546 | 0.1297 | 0.9631 | |
|
| 0.1104 | 14.0 | 588 | 0.1401 | 0.9598 | |
|
| 0.1075 | 15.0 | 630 | 0.1200 | 0.9665 | |
|
| 0.0986 | 16.0 | 672 | 0.1665 | 0.9581 | |
|
| 0.092 | 17.0 | 714 | 0.1399 | 0.9531 | |
|
| 0.1123 | 18.0 | 756 | 0.1122 | 0.9698 | |
|
| 0.0766 | 19.0 | 798 | 0.1337 | 0.9564 | |
|
| 0.0762 | 20.0 | 840 | 0.0974 | 0.9732 | |
|
| 0.0994 | 21.0 | 882 | 0.1023 | 0.9698 | |
|
| 0.0687 | 22.0 | 924 | 0.0976 | 0.9749 | |
|
| 0.0767 | 23.0 | 966 | 0.0952 | 0.9765 | |
|
| 0.0581 | 24.0 | 1008 | 0.1096 | 0.9665 | |
|
| 0.0544 | 25.0 | 1050 | 0.1123 | 0.9715 | |
|
| 0.079 | 26.0 | 1092 | 0.1040 | 0.9682 | |
|
| 0.0661 | 27.0 | 1134 | 0.0838 | 0.9799 | |
|
| 0.068 | 28.0 | 1176 | 0.1169 | 0.9715 | |
|
| 0.0722 | 29.0 | 1218 | 0.0897 | 0.9732 | |
|
| 0.048 | 30.0 | 1260 | 0.0864 | 0.9732 | |
|
| 0.0509 | 31.0 | 1302 | 0.0858 | 0.9749 | |
|
| 0.047 | 32.0 | 1344 | 0.0801 | 0.9782 | |
|
| 0.0411 | 33.0 | 1386 | 0.1221 | 0.9648 | |
|
| 0.0378 | 34.0 | 1428 | 0.1011 | 0.9648 | |
|
| 0.0358 | 35.0 | 1470 | 0.0834 | 0.9799 | |
|
| 0.0347 | 36.0 | 1512 | 0.0993 | 0.9715 | |
|
| 0.0434 | 37.0 | 1554 | 0.0938 | 0.9732 | |
|
| 0.0507 | 38.0 | 1596 | 0.0874 | 0.9782 | |
|
| 0.0466 | 39.0 | 1638 | 0.0932 | 0.9765 | |
|
| 0.0502 | 40.0 | 1680 | 0.1012 | 0.9698 | |
|
| 0.0289 | 41.0 | 1722 | 0.0841 | 0.9715 | |
|
| 0.0274 | 42.0 | 1764 | 0.0883 | 0.9682 | |
|
| 0.0251 | 43.0 | 1806 | 0.0843 | 0.9782 | |
|
| 0.0343 | 44.0 | 1848 | 0.0812 | 0.9782 | |
|
| 0.0289 | 45.0 | 1890 | 0.0805 | 0.9782 | |
|
| 0.0277 | 46.0 | 1932 | 0.0943 | 0.9698 | |
|
| 0.0332 | 47.0 | 1974 | 0.0807 | 0.9765 | |
|
| 0.0328 | 48.0 | 2016 | 0.0826 | 0.9749 | |
|
| 0.0257 | 49.0 | 2058 | 0.0852 | 0.9749 | |
|
| 0.0287 | 50.0 | 2100 | 0.0848 | 0.9782 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.20.1 |
|
|
