update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: icdar23-entrydetector_plaintext_breaks_indents_left_ref
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# icdar23-entrydetector_plaintext_breaks_indents_left_ref
|
| 13 |
+
|
| 14 |
+
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.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 0.0059
|
| 17 |
+
- Ebegin: {'precision': 0.9926347505858721, 'recall': 0.9876748834110592, 'f1': 0.9901486057772583, 'number': 3002}
|
| 18 |
+
- Eend: {'precision': 0.9861111111111112, 'recall': 0.994, 'f1': 0.9900398406374502, 'number': 3000}
|
| 19 |
+
- Overall Precision: 0.9894
|
| 20 |
+
- Overall Recall: 0.9908
|
| 21 |
+
- Overall F1: 0.9901
|
| 22 |
+
- Overall Accuracy: 0.9983
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0001
|
| 42 |
+
- train_batch_size: 2
|
| 43 |
+
- eval_batch_size: 2
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- training_steps: 6000
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 53 |
+
| No log | 0.07 | 300 | 0.0322 | 0.9652 | 0.9774 | 0.9713 | 0.9951 |
|
| 54 |
+
| 0.1545 | 0.14 | 600 | 0.0134 | 0.9816 | 0.9908 | 0.9862 | 0.9975 |
|
| 55 |
+
| 0.1545 | 0.21 | 900 | 0.0095 | 0.9846 | 0.9900 | 0.9873 | 0.9978 |
|
| 56 |
+
| 0.0161 | 0.29 | 1200 | 0.0090 | 0.9824 | 0.9927 | 0.9875 | 0.9977 |
|
| 57 |
+
| 0.0097 | 0.36 | 1500 | 0.0078 | 0.9893 | 0.9896 | 0.9894 | 0.9981 |
|
| 58 |
+
| 0.0097 | 0.43 | 1800 | 0.0079 | 0.9935 | 0.9816 | 0.9875 | 0.9978 |
|
| 59 |
+
| 0.009 | 0.5 | 2100 | 0.0071 | 0.9885 | 0.9928 | 0.9906 | 0.9983 |
|
| 60 |
+
| 0.009 | 0.57 | 2400 | 0.0060 | 0.9859 | 0.9947 | 0.9903 | 0.9983 |
|
| 61 |
+
| 0.0071 | 0.64 | 2700 | 0.0069 | 0.9982 | 0.9763 | 0.9871 | 0.9977 |
|
| 62 |
+
| 0.0057 | 0.72 | 3000 | 0.0065 | 0.9909 | 0.9893 | 0.9901 | 0.9982 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.26.0
|
| 68 |
+
- Pytorch 1.13.1+cu116
|
| 69 |
+
- Datasets 2.9.0
|
| 70 |
+
- Tokenizers 0.13.2
|