|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: donut_finetuned_chart |
|
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_finetuned_chart |
|
|
|
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co./naver-clova-ix/donut-base) on an chart images dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4957 |
|
- Cer: 0.2318 |
|
|
|
## 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: 2.3e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 3 |
|
- total_train_batch_size: 24 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Cer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 3.4943 | 1.0 | 166 | 0.6634 | 0.2341 | |
|
| 0.475 | 2.0 | 333 | 0.5370 | 0.2320 | |
|
| 0.3009 | 3.0 | 500 | 0.5051 | 0.2318 | |
|
| 0.2611 | 3.98 | 664 | 0.4957 | 0.2318 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|
