---
tags:
- generated_from_trainer
model-index:
- name: icdar23-entrydetector_plaintext_breaks_indents_left_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

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: 0.0060
- Ebegin: {'precision': 0.9928166351606805, 'recall': 0.9875893192929672, 'f1': 0.9901960784313725, 'number': 2659}
- Eend: {'precision': 0.9984750285932139, 'recall': 0.9786995515695067, 'f1': 0.9884883940366107, 'number': 2676}
- Overall Precision: 0.9956
- Overall Recall: 0.9831
- Overall F1: 0.9893
- Overall Accuracy: 0.9982

## 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  | 0.0401          | 0.9408    | 0.9725 | 0.9564 | 0.9936   |
| 0.1602        | 0.14  | 600  | 0.0195          | 0.9896    | 0.9741 | 0.9818 | 0.9972   |
| 0.1602        | 0.21  | 900  | 0.0101          | 0.9949    | 0.9875 | 0.9911 | 0.9985   |
| 0.0205        | 0.29  | 1200 | 0.0117          | 0.9860    | 0.9894 | 0.9877 | 0.9979   |
| 0.0104        | 0.36  | 1500 | 0.0091          | 0.9819    | 0.9948 | 0.9883 | 0.9979   |
| 0.0104        | 0.43  | 1800 | 0.0058          | 0.9886    | 0.9933 | 0.9909 | 0.9984   |
| 0.0081        | 0.5   | 2100 | 0.0067          | 0.9892    | 0.9931 | 0.9911 | 0.9984   |
| 0.0081        | 0.57  | 2400 | 0.0049          | 0.9928    | 0.9939 | 0.9934 | 0.9988   |
| 0.0069        | 0.64  | 2700 | 0.0048          | 0.9895    | 0.9931 | 0.9913 | 0.9985   |
| 0.0066        | 0.72  | 3000 | 0.0061          | 0.9971    | 0.9865 | 0.9918 | 0.9985   |
| 0.0066        | 0.79  | 3300 | 0.0042          | 0.9954    | 0.9927 | 0.9940 | 0.9990   |
| 0.0046        | 0.86  | 3600 | 0.0039          | 0.9958    | 0.9923 | 0.9941 | 0.9990   |
| 0.0046        | 0.93  | 3900 | 0.0058          | 0.9835    | 0.9959 | 0.9896 | 0.9981   |
| 0.0052        | 1.0   | 4200 | 0.0055          | 0.9963    | 0.9892 | 0.9927 | 0.9987   |
| 0.003         | 1.07  | 4500 | 0.0051          | 0.9939    | 0.9929 | 0.9934 | 0.9988   |
| 0.003         | 1.14  | 4800 | 0.0075          | 0.9977    | 0.9871 | 0.9924 | 0.9987   |
| 0.0039        | 1.22  | 5100 | 0.0051          | 0.9952    | 0.9922 | 0.9937 | 0.9989   |


### Framework versions

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