|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: google/vit-base-patch16-224 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- medmnist-v2 |
|
|
metrics: |
|
|
- accuracy |
|
|
- f1 |
|
|
model-index: |
|
|
- name: ViT_breastmnist_std_45 |
|
|
results: |
|
|
- task: |
|
|
name: Image Classification |
|
|
type: image-classification |
|
|
dataset: |
|
|
name: medmnist-v2 |
|
|
type: medmnist-v2 |
|
|
config: breastmnist |
|
|
split: validation |
|
|
args: breastmnist |
|
|
metrics: |
|
|
- name: Accuracy |
|
|
type: accuracy |
|
|
value: 0.782051282051282 |
|
|
- name: F1 |
|
|
type: f1 |
|
|
value: 0.6733185513673319 |
|
|
--- |
|
|
|
|
|
<!-- 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_breastmnist_std_45 |
|
|
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the medmnist-v2 dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.4752 |
|
|
- Accuracy: 0.7821 |
|
|
- F1: 0.6733 |
|
|
|
|
|
## 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: 2e-05 |
|
|
- train_batch_size: 64 |
|
|
- eval_batch_size: 16 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 10 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:| |
|
|
| 0.5115 | 0.2597 | 20 | 0.5292 | 0.7308 | 0.4222 | |
|
|
| 0.4949 | 0.5195 | 40 | 0.5229 | 0.7436 | 0.4708 | |
|
|
| 0.4099 | 0.7792 | 60 | 0.4728 | 0.7692 | 0.5568 | |
|
|
| 0.4461 | 1.0390 | 80 | 0.4428 | 0.8333 | 0.7247 | |
|
|
| 0.4201 | 1.2987 | 100 | 0.4311 | 0.8718 | 0.8120 | |
|
|
| 0.3532 | 1.5584 | 120 | 0.4206 | 0.8590 | 0.7886 | |
|
|
| 0.3586 | 1.8182 | 140 | 0.4292 | 0.8590 | 0.7886 | |
|
|
| 0.3412 | 2.0779 | 160 | 0.4541 | 0.8333 | 0.7247 | |
|
|
| 0.2945 | 2.3377 | 180 | 0.4179 | 0.8333 | 0.7606 | |
|
|
| 0.2555 | 2.5974 | 200 | 0.4331 | 0.8590 | 0.7886 | |
|
|
| 0.2753 | 2.8571 | 220 | 0.4310 | 0.8205 | 0.7367 | |
|
|
| 0.2079 | 3.1169 | 240 | 0.4152 | 0.8462 | 0.7833 | |
|
|
| 0.217 | 3.3766 | 260 | 0.4157 | 0.8718 | 0.8260 | |
|
|
| 0.167 | 3.6364 | 280 | 0.4259 | 0.8590 | 0.8051 | |
|
|
| 0.1976 | 3.8961 | 300 | 0.4346 | 0.8462 | 0.7913 | |
|
|
| 0.1376 | 4.1558 | 320 | 0.4341 | 0.8462 | 0.7913 | |
|
|
| 0.1301 | 4.4156 | 340 | 0.4418 | 0.8462 | 0.7983 | |
|
|
| 0.1503 | 4.6753 | 360 | 0.4375 | 0.8590 | 0.8120 | |
|
|
| 0.126 | 4.9351 | 380 | 0.4376 | 0.8590 | 0.8120 | |
|
|
| 0.098 | 5.1948 | 400 | 0.4310 | 0.8462 | 0.7983 | |
|
|
| 0.0675 | 5.4545 | 420 | 0.4545 | 0.8333 | 0.7849 | |
|
|
| 0.0618 | 5.7143 | 440 | 0.4587 | 0.8333 | 0.7849 | |
|
|
| 0.0572 | 5.9740 | 460 | 0.4629 | 0.8462 | 0.7983 | |
|
|
| 0.0283 | 6.2338 | 480 | 0.4778 | 0.8333 | 0.7849 | |
|
|
| 0.0337 | 6.4935 | 500 | 0.4820 | 0.8462 | 0.7983 | |
|
|
| 0.0416 | 6.7532 | 520 | 0.4794 | 0.8462 | 0.8045 | |
|
|
| 0.0535 | 7.0130 | 540 | 0.4811 | 0.8333 | 0.7849 | |
|
|
| 0.0146 | 7.2727 | 560 | 0.4780 | 0.8462 | 0.7983 | |
|
|
| 0.0205 | 7.5325 | 580 | 0.4889 | 0.8333 | 0.7849 | |
|
|
| 0.0118 | 7.7922 | 600 | 0.5004 | 0.8333 | 0.7913 | |
|
|
| 0.0148 | 8.0519 | 620 | 0.4974 | 0.8333 | 0.7849 | |
|
|
| 0.0078 | 8.3117 | 640 | 0.5009 | 0.8205 | 0.7719 | |
|
|
| 0.0101 | 8.5714 | 660 | 0.5079 | 0.8205 | 0.7719 | |
|
|
| 0.0042 | 8.8312 | 680 | 0.5178 | 0.8205 | 0.7719 | |
|
|
| 0.0047 | 9.0909 | 700 | 0.5186 | 0.8205 | 0.7719 | |
|
|
| 0.0029 | 9.3506 | 720 | 0.5217 | 0.8205 | 0.7719 | |
|
|
| 0.0042 | 9.6104 | 740 | 0.5238 | 0.8077 | 0.7592 | |
|
|
| 0.0038 | 9.8701 | 760 | 0.5246 | 0.8205 | 0.7719 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.45.1 |
|
|
- Pytorch 2.4.0 |
|
|
- Datasets 3.0.1 |
|
|
- Tokenizers 0.20.0 |
|
|
|
