|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
base_model: facebook/deit-base-patch16-224 |
|
model-index: |
|
- name: chest-deit-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-deit-base-finetuned |
|
|
|
This model is a fine-tuned version of [facebook/deit-base-patch16-224](https://huggingface.co/facebook/deit-base-patch16-224) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0979 |
|
- Accuracy: 0.9622 |
|
- Precision: 0.9531 |
|
- Recall: 0.9562 |
|
- F1: 0.9546 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| 0.2556 | 0.99 | 63 | 0.2019 | 0.9185 | 0.9446 | 0.8469 | 0.8822 | |
|
| 0.2302 | 1.99 | 127 | 0.1098 | 0.9614 | 0.9396 | 0.9654 | 0.9514 | |
|
| 0.2258 | 3.0 | 191 | 0.1151 | 0.9622 | 0.9641 | 0.9372 | 0.9496 | |
|
| 0.1465 | 4.0 | 255 | 0.0733 | 0.9725 | 0.9653 | 0.9633 | 0.9643 | |
|
| 0.1763 | 4.99 | 318 | 0.0763 | 0.9725 | 0.9703 | 0.9580 | 0.9639 | |
|
| 0.1627 | 5.99 | 382 | 0.1057 | 0.9571 | 0.9315 | 0.9656 | 0.9466 | |
|
| 0.1509 | 7.0 | 446 | 0.0701 | 0.9751 | 0.9638 | 0.9725 | 0.9680 | |
|
| 0.1209 | 8.0 | 510 | 0.1047 | 0.9571 | 0.9315 | 0.9656 | 0.9466 | |
|
| 0.0961 | 8.99 | 573 | 0.0721 | 0.9734 | 0.9577 | 0.9756 | 0.9662 | |
|
| 0.1063 | 9.88 | 630 | 0.0885 | 0.9622 | 0.9398 | 0.9681 | 0.9526 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.9.0 |
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |