metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- image_folder
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224-in21k-finetuned-cxr
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: image_folder
type: image_folder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9356966199505359
vit-base-patch16-224-in21k-finetuned-cxr
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the image_folder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1758
- Accuracy: 0.9357
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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2994 | 0.99 | 85 | 0.3337 | 0.8854 |
| 0.2806 | 2.0 | 171 | 0.2670 | 0.9101 |
| 0.2519 | 2.99 | 256 | 0.2495 | 0.9134 |
| 0.2456 | 4.0 | 342 | 0.2450 | 0.9143 |
| 0.2094 | 4.99 | 427 | 0.2105 | 0.9258 |
| 0.1808 | 6.0 | 513 | 0.1984 | 0.9308 |
| 0.1959 | 6.99 | 598 | 0.2022 | 0.9258 |
| 0.179 | 8.0 | 684 | 0.1980 | 0.9299 |
| 0.1915 | 8.99 | 769 | 0.1889 | 0.9308 |
| 0.1735 | 10.0 | 855 | 0.1931 | 0.9324 |
| 0.174 | 10.99 | 940 | 0.1872 | 0.9324 |
| 0.167 | 12.0 | 1026 | 0.1758 | 0.9357 |
| 0.1408 | 12.99 | 1111 | 0.1890 | 0.9349 |
| 0.1442 | 14.0 | 1197 | 0.1849 | 0.9324 |
| 0.1661 | 14.91 | 1275 | 0.1879 | 0.9266 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.15.0