|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- image-classification |
|
- vision |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
model-index: |
|
- name: donut-base-beans |
|
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. --> |
|
|
|
# donut-base-beans |
|
|
|
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: 0.0548 |
|
- F1: 0.3303 |
|
|
|
## 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: 3e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 1337 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Accuracy | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:--------:|:---------------:| |
|
| 0.0769 | 1.0 | 6733 | 0.4973 | 0.0657 | |
|
| 0.0729 | 2.0 | 13466 | 0.4973 | 0.0613 | |
|
| 0.0564 | 3.0 | 20199 | 0.4973 | 0.0621 | |
|
| 0.0534 | 4.0 | 26932 | 0.4973 | 0.0572 | |
|
| 0.0511 | 5.0 | 33665 | 0.4973 | 0.0562 | |
|
| 0.0659 | 6.0 | 40398 | 0.4973 | 0.0577 | |
|
| 0.0623 | 7.0 | 47131 | 0.4973 | 0.0567 | |
|
| 0.0575 | 8.0 | 53864 | 0.4973 | 0.0555 | |
|
| 0.048 | 9.0 | 60597 | 0.4973 | 0.0548 | |
|
| 0.0389 | 10.0 | 67330 | 0.4973 | 0.0548 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.43.0.dev0 |
|
- Pytorch 2.1.2+cu118 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
