|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: icdar23-entrydetector_plaintext_breaks_indents_left_ref_right_ref |
|
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. --> |
|
|
|
# icdar23-entrydetector_plaintext_breaks_indents_left_ref_right_ref |
|
|
|
This model is a fine-tuned version of [HueyNemud/das22-10-camembert_pretrained](https://huggingface.co/HueyNemud/das22-10-camembert_pretrained) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0063 |
|
- Ebegin: {'precision': 0.9877239548772395, 'recall': 0.991672218520986, 'f1': 0.9896941489361701, 'number': 3002} |
|
- Eend: {'precision': 0.9952893674293405, 'recall': 0.986, 'f1': 0.9906229068988612, 'number': 3000} |
|
- Overall Precision: 0.9915 |
|
- Overall Recall: 0.9888 |
|
- Overall F1: 0.9902 |
|
- Overall Accuracy: 0.9984 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- training_steps: 6000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 0.07 | 300 | 0.0267 | 0.9713 | 0.9924 | 0.9818 | 0.9969 | |
|
| 0.1477 | 0.14 | 600 | 0.0149 | 0.9818 | 0.9879 | 0.9848 | 0.9974 | |
|
| 0.1477 | 0.21 | 900 | 0.0159 | 0.9625 | 0.9913 | 0.9767 | 0.9960 | |
|
| 0.0165 | 0.29 | 1200 | 0.0062 | 0.9872 | 0.9923 | 0.9897 | 0.9983 | |
|
| 0.0083 | 0.36 | 1500 | 0.0075 | 0.9772 | 0.9962 | 0.9866 | 0.9977 | |
|
| 0.0083 | 0.43 | 1800 | 0.0058 | 0.9940 | 0.9852 | 0.9896 | 0.9983 | |
|
| 0.0068 | 0.5 | 2100 | 0.0062 | 0.9895 | 0.9911 | 0.9903 | 0.9984 | |
|
| 0.0068 | 0.57 | 2400 | 0.0054 | 0.9930 | 0.9867 | 0.9898 | 0.9983 | |
|
| 0.0054 | 0.64 | 2700 | 0.0058 | 0.9985 | 0.9815 | 0.9899 | 0.9983 | |
|
| 0.0061 | 0.72 | 3000 | 0.0053 | 0.9798 | 0.9961 | 0.9879 | 0.9980 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.0 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.9.0 |
|
- Tokenizers 0.13.2 |
|
|