|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
base_model: google/vit-base-patch16-224-in21k |
|
model-index: |
|
- name: chest-vit-base-finetuned |
|
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-vit-base-finetuned |
|
|
|
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: 0.0982 |
|
- Accuracy: 0.9639 |
|
- Precision: 0.9419 |
|
- Recall: 0.9703 |
|
- F1: 0.9548 |
|
|
|
## 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: 0.005 |
|
- 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 |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| 0.211 | 0.99 | 63 | 0.1140 | 0.9605 | 0.9401 | 0.9616 | 0.9501 | |
|
| 0.1911 | 1.99 | 127 | 0.1517 | 0.9330 | 0.8989 | 0.9483 | 0.9186 | |
|
| 0.1695 | 3.0 | 191 | 0.1163 | 0.9579 | 0.9354 | 0.9609 | 0.9471 | |
|
| 0.1556 | 4.0 | 255 | 0.1159 | 0.9571 | 0.9669 | 0.9220 | 0.9417 | |
|
| 0.173 | 4.99 | 318 | 0.1166 | 0.9502 | 0.9229 | 0.9578 | 0.9381 | |
|
| 0.1485 | 5.99 | 382 | 0.0825 | 0.9717 | 0.9578 | 0.9702 | 0.9638 | |
|
| 0.1854 | 7.0 | 446 | 0.0878 | 0.9717 | 0.9578 | 0.9702 | 0.9638 | |
|
| 0.1353 | 8.0 | 510 | 0.1060 | 0.9588 | 0.9351 | 0.9647 | 0.9484 | |
|
| 0.1196 | 8.99 | 573 | 0.0882 | 0.9691 | 0.9527 | 0.9695 | 0.9607 | |
|
| 0.1218 | 9.88 | 630 | 0.0982 | 0.9639 | 0.9419 | 0.9703 | 0.9548 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.9.0 |
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
