|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: chest_xray_pneumonia |
|
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. --> |
|
|
|
# chest_xray_pneumonia |
|
|
|
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: 0.2508 |
|
- Accuracy: 0.9151 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.1091 | 0.99 | 81 | 0.2422 | 0.9119 | |
|
| 0.1085 | 2.0 | 163 | 0.2777 | 0.9167 | |
|
| 0.1131 | 2.99 | 244 | 0.1875 | 0.9407 | |
|
| 0.1129 | 4.0 | 326 | 0.2339 | 0.9183 | |
|
| 0.0698 | 4.99 | 407 | 0.2581 | 0.9263 | |
|
| 0.0904 | 6.0 | 489 | 0.2544 | 0.9167 | |
|
| 0.0851 | 6.99 | 570 | 0.2023 | 0.9407 | |
|
| 0.0833 | 8.0 | 652 | 0.2047 | 0.9327 | |
|
| 0.0604 | 8.99 | 733 | 0.2738 | 0.9199 | |
|
| 0.0671 | 9.94 | 810 | 0.2508 | 0.9151 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.0 |
|
|