---
tags:
- generated_from_trainer
model-index:
- name: icdar23-entrydetector_plaintext_breaks_indents_left_diff
  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_diff

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: 0.0058
- Ebegin: {'precision': 0.9973404255319149, 'recall': 0.9872132380594209, 'f1': 0.9922509922509923, 'number': 2659}
- Eend: {'precision': 0.9950924877312193, 'recall': 0.9850523168908819, 'f1': 0.9900469483568075, 'number': 2676}
- Overall Precision: 0.9962
- Overall Recall: 0.9861
- Overall F1: 0.9911
- Overall Accuracy: 0.9985

## 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: 7500

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log        | 0.07  | 300  | 0.0372          | 0.9749    | 0.9785 | 0.9767 | 0.9961   |
| 0.186         | 0.14  | 600  | 0.0149          | 0.9920    | 0.9876 | 0.9898 | 0.9981   |
| 0.186         | 0.21  | 900  | 0.0093          | 0.9901    | 0.9896 | 0.9898 | 0.9982   |
| 0.0196        | 0.29  | 1200 | 0.0109          | 0.9830    | 0.9937 | 0.9883 | 0.9979   |
| 0.0101        | 0.36  | 1500 | 0.0091          | 0.9877    | 0.9926 | 0.9901 | 0.9982   |
| 0.0101        | 0.43  | 1800 | 0.0095          | 0.9953    | 0.9820 | 0.9886 | 0.9980   |
| 0.0108        | 0.5   | 2100 | 0.0055          | 0.9947    | 0.9922 | 0.9935 | 0.9988   |
| 0.0108        | 0.57  | 2400 | 0.0052          | 0.9932    | 0.9928 | 0.9930 | 0.9988   |
| 0.008         | 0.64  | 2700 | 0.0054          | 0.9906    | 0.9900 | 0.9903 | 0.9983   |
| 0.0064        | 0.72  | 3000 | 0.0066          | 0.9953    | 0.9911 | 0.9932 | 0.9988   |
| 0.0064        | 0.79  | 3300 | 0.0093          | 0.9903    | 0.9838 | 0.9870 | 0.9977   |
| 0.0095        | 0.86  | 3600 | 0.0092          | 0.9899    | 0.9863 | 0.9881 | 0.9978   |


### Framework versions

- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2