|
--- |
|
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: finetuned-arsenic |
|
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: 0.9993451211525868 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# finetuned-arsenic |
|
|
|
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: 0.0026 |
|
- Accuracy: 0.9993 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:| |
|
| 0.2214 | 0.1848 | 100 | 0.2314 | 0.9247 | |
|
| 0.2189 | 0.3697 | 200 | 0.1578 | 0.9404 | |
|
| 0.2104 | 0.5545 | 300 | 0.1063 | 0.9673 | |
|
| 0.2138 | 0.7394 | 400 | 0.0998 | 0.9718 | |
|
| 0.2149 | 0.9242 | 500 | 0.0644 | 0.9790 | |
|
| 0.1439 | 1.1091 | 600 | 0.0757 | 0.9646 | |
|
| 0.1038 | 1.2939 | 700 | 0.1316 | 0.9574 | |
|
| 0.0458 | 1.4787 | 800 | 0.0282 | 0.9902 | |
|
| 0.0078 | 1.6636 | 900 | 0.1226 | 0.9718 | |
|
| 0.0286 | 1.8484 | 1000 | 0.0584 | 0.9856 | |
|
| 0.0493 | 2.0333 | 1100 | 0.1419 | 0.9633 | |
|
| 0.0028 | 2.2181 | 1200 | 0.0232 | 0.9948 | |
|
| 0.0292 | 2.4030 | 1300 | 0.0171 | 0.9935 | |
|
| 0.0402 | 2.5878 | 1400 | 0.0061 | 0.9987 | |
|
| 0.043 | 2.7726 | 1500 | 0.0497 | 0.9889 | |
|
| 0.0224 | 2.9575 | 1600 | 0.0062 | 0.9987 | |
|
| 0.0021 | 3.1423 | 1700 | 0.0092 | 0.9974 | |
|
| 0.0025 | 3.3272 | 1800 | 0.0041 | 0.9987 | |
|
| 0.0018 | 3.5120 | 1900 | 0.0054 | 0.9974 | |
|
| 0.0034 | 3.6969 | 2000 | 0.0052 | 0.9980 | |
|
| 0.0072 | 3.8817 | 2100 | 0.0026 | 0.9993 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.19.1 |
|
|
