|
--- |
|
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_bloodmnist_std_45 |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: medmnist-v2 |
|
type: medmnist-v2 |
|
config: bloodmnist |
|
split: validation |
|
args: bloodmnist |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9064600993861444 |
|
- name: F1 |
|
type: f1 |
|
value: 0.8909233140229111 |
|
--- |
|
|
|
<!-- 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_bloodmnist_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: 0.2659 |
|
- Accuracy: 0.9065 |
|
- F1: 0.8909 |
|
|
|
## 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: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:------:|:-----:|:---------------:|:--------:|:------:| |
|
| 0.6113 | 0.0595 | 200 | 0.8908 | 0.6846 | 0.5917 | |
|
| 0.3578 | 0.1189 | 400 | 0.5958 | 0.7956 | 0.7548 | |
|
| 0.3118 | 0.1784 | 600 | 0.5688 | 0.7810 | 0.7132 | |
|
| 0.2815 | 0.2378 | 800 | 0.5227 | 0.7961 | 0.7645 | |
|
| 0.266 | 0.2973 | 1000 | 0.6554 | 0.7687 | 0.7229 | |
|
| 0.2353 | 0.3567 | 1200 | 0.3328 | 0.8838 | 0.8615 | |
|
| 0.2297 | 0.4162 | 1400 | 0.4696 | 0.8592 | 0.7990 | |
|
| 0.2267 | 0.4756 | 1600 | 0.4362 | 0.8493 | 0.8117 | |
|
| 0.2266 | 0.5351 | 1800 | 0.3286 | 0.8838 | 0.8407 | |
|
| 0.2047 | 0.5945 | 2000 | 0.3614 | 0.8697 | 0.8382 | |
|
| 0.1948 | 0.6540 | 2200 | 0.3144 | 0.8843 | 0.8546 | |
|
| 0.1953 | 0.7134 | 2400 | 0.3805 | 0.8657 | 0.8180 | |
|
| 0.1728 | 0.7729 | 2600 | 0.3364 | 0.8820 | 0.8339 | |
|
| 0.1658 | 0.8323 | 2800 | 0.2873 | 0.8978 | 0.8743 | |
|
| 0.1594 | 0.8918 | 3000 | 0.3062 | 0.8914 | 0.8580 | |
|
| 0.1649 | 0.9512 | 3200 | 0.3313 | 0.8867 | 0.8577 | |
|
| 0.1508 | 1.0107 | 3400 | 0.2117 | 0.9217 | 0.9133 | |
|
| 0.1062 | 1.0702 | 3600 | 0.2978 | 0.8919 | 0.8756 | |
|
| 0.1091 | 1.1296 | 3800 | 0.2832 | 0.9019 | 0.8831 | |
|
| 0.0993 | 1.1891 | 4000 | 0.3275 | 0.8943 | 0.8718 | |
|
| 0.1001 | 1.2485 | 4200 | 0.3420 | 0.8896 | 0.8568 | |
|
| 0.1092 | 1.3080 | 4400 | 0.2594 | 0.9130 | 0.8909 | |
|
| 0.092 | 1.3674 | 4600 | 0.3181 | 0.8966 | 0.8753 | |
|
| 0.1036 | 1.4269 | 4800 | 0.2721 | 0.9048 | 0.8852 | |
|
| 0.0896 | 1.4863 | 5000 | 0.3795 | 0.8820 | 0.8617 | |
|
| 0.0904 | 1.5458 | 5200 | 0.2382 | 0.9171 | 0.8980 | |
|
| 0.0864 | 1.6052 | 5400 | 0.3845 | 0.8814 | 0.8499 | |
|
| 0.0809 | 1.6647 | 5600 | 0.3189 | 0.8984 | 0.8758 | |
|
| 0.0764 | 1.7241 | 5800 | 0.3952 | 0.8843 | 0.8522 | |
|
| 0.0796 | 1.7836 | 6000 | 0.3656 | 0.8867 | 0.8460 | |
|
| 0.0695 | 1.8430 | 6200 | 0.3266 | 0.8925 | 0.8597 | |
|
| 0.0682 | 1.9025 | 6400 | 0.3247 | 0.8960 | 0.8647 | |
|
| 0.06 | 1.9620 | 6600 | 0.2349 | 0.9223 | 0.9055 | |
|
| 0.0498 | 2.0214 | 6800 | 0.2578 | 0.9176 | 0.8952 | |
|
| 0.0296 | 2.0809 | 7000 | 0.2592 | 0.9211 | 0.9070 | |
|
| 0.0251 | 2.1403 | 7200 | 0.3249 | 0.9048 | 0.8797 | |
|
| 0.02 | 2.1998 | 7400 | 0.2977 | 0.9165 | 0.8973 | |
|
| 0.0274 | 2.2592 | 7600 | 0.3411 | 0.9013 | 0.8730 | |
|
| 0.0241 | 2.3187 | 7800 | 0.3916 | 0.9013 | 0.8752 | |
|
| 0.0253 | 2.3781 | 8000 | 0.2919 | 0.9136 | 0.8939 | |
|
| 0.0197 | 2.4376 | 8200 | 0.3294 | 0.9077 | 0.8835 | |
|
| 0.0209 | 2.4970 | 8400 | 0.3709 | 0.8966 | 0.8652 | |
|
| 0.0175 | 2.5565 | 8600 | 0.3639 | 0.9001 | 0.8733 | |
|
| 0.0191 | 2.6159 | 8800 | 0.3706 | 0.9048 | 0.8790 | |
|
| 0.0167 | 2.6754 | 9000 | 0.3120 | 0.9171 | 0.8993 | |
|
| 0.0224 | 2.7348 | 9200 | 0.3493 | 0.9048 | 0.8799 | |
|
| 0.015 | 2.7943 | 9400 | 0.3398 | 0.9130 | 0.8889 | |
|
| 0.0155 | 2.8537 | 9600 | 0.3707 | 0.9036 | 0.8758 | |
|
| 0.0129 | 2.9132 | 9800 | 0.3467 | 0.9118 | 0.8909 | |
|
| 0.0126 | 2.9727 | 10000 | 0.3470 | 0.9095 | 0.8874 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.1 |
|
- Pytorch 2.4.0 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.20.0 |
|
|
