|
--- |
|
license: cc-by-nc-sa-4.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: layoutlmv3-base-ner |
|
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. --> |
|
|
|
# layoutlmv3-base-ner |
|
|
|
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.5413 |
|
- Footer: {'precision': 0.9381835473133618, 'recall': 0.8653508771929824, 'f1': 0.9002966005019393, 'number': 2280} |
|
- Header: {'precision': 0.6690058479532164, 'recall': 0.601472134595163, 'f1': 0.6334440753045404, 'number': 951} |
|
- Able: {'precision': 0.19949254678084363, 'recall': 0.5143090760425184, 'f1': 0.2874771480804387, 'number': 1223} |
|
- Aption: {'precision': 0.32124352331606215, 'recall': 0.07515151515151515, 'f1': 0.12180746561886051, 'number': 825} |
|
- Ext: {'precision': 0.34080531340805315, 'recall': 0.4647608264930654, 'f1': 0.39324631780625074, 'number': 3533} |
|
- Icture: {'precision': 0.0546448087431694, 'recall': 0.13157894736842105, 'f1': 0.0772200772200772, 'number': 608} |
|
- Itle: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} |
|
- Ootnote: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 145} |
|
- Ormula: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 360} |
|
- Overall Precision: 0.3939 |
|
- Overall Recall: 0.4936 |
|
- Overall F1: 0.4382 |
|
- Overall Accuracy: 0.7180 |
|
|
|
## 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: 3e-05 |
|
- 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 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Footer | Header | Able | Aption | Ext | Icture | Itle | Ootnote | Ormula | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------:|:-----------------------------------------------------------:|:-----------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:| |
|
| 0.4772 | 1.0 | 500 | 1.3891 | {'precision': 0.8112648221343873, 'recall': 0.7201754385964912, 'f1': 0.763011152416357, 'number': 2280} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 951} | {'precision': 0.13366666666666666, 'recall': 0.32788225674570726, 'f1': 0.1899123845607388, 'number': 1223} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 825} | {'precision': 0.2245841035120148, 'recall': 0.27512029436739316, 'f1': 0.24729678157995166, 'number': 3533} | {'precision': 0.022222222222222223, 'recall': 0.008223684210526315, 'f1': 0.012004801920768306, 'number': 608} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 145} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 360} | 0.3131 | 0.3007 | 0.3068 | 0.7042 | |
|
| 0.2598 | 2.0 | 1000 | 1.3046 | {'precision': 0.672650475184794, 'recall': 0.8381578947368421, 'f1': 0.7463386057410663, 'number': 2280} | {'precision': 0.28655597214783074, 'recall': 0.562565720294427, 'f1': 0.3797019162526614, 'number': 951} | {'precision': 0.12042429284525791, 'recall': 0.473426001635323, 'f1': 0.19200795887912453, 'number': 1223} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 825} | {'precision': 0.22616279069767442, 'recall': 0.4404189074440985, 'f1': 0.29885719773360225, 'number': 3533} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 608} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 145} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 360} | 0.2682 | 0.4561 | 0.3378 | 0.6730 | |
|
| 0.1936 | 3.0 | 1500 | 1.4208 | {'precision': 0.9038104089219331, 'recall': 0.8530701754385965, 'f1': 0.8777075812274369, 'number': 2280} | {'precision': 0.6213468869123253, 'recall': 0.5141955835962145, 'f1': 0.5627157652474108, 'number': 951} | {'precision': 0.16486261448792672, 'recall': 0.4856909239574816, 'f1': 0.2461665975963531, 'number': 1223} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 825} | {'precision': 0.2463847702727439, 'recall': 0.3809793376733654, 'f1': 0.2992441084926634, 'number': 3533} | {'precision': 0.02721774193548387, 'recall': 0.044407894736842105, 'f1': 0.03375, 'number': 608} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 145} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 360} | 0.3385 | 0.4382 | 0.3819 | 0.7043 | |
|
| 0.1392 | 4.0 | 2000 | 1.7208 | {'precision': 0.9363636363636364, 'recall': 0.8583333333333333, 'f1': 0.8956521739130435, 'number': 2280} | {'precision': 0.6706521739130434, 'recall': 0.6487907465825447, 'f1': 0.6595403527525386, 'number': 951} | {'precision': 0.15699904122722916, 'recall': 0.53556827473426, 'f1': 0.24281742354031513, 'number': 1223} | {'precision': 0.18992248062015504, 'recall': 0.059393939393939395, 'f1': 0.0904893813481071, 'number': 825} | {'precision': 0.2668534407284188, 'recall': 0.43136144919332015, 'f1': 0.3297273907399394, 'number': 3533} | {'precision': 0.046700507614213196, 'recall': 0.0756578947368421, 'f1': 0.05775266792215945, 'number': 608} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 145} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 360} | 0.3430 | 0.4827 | 0.4010 | 0.6703 | |
|
| 0.0899 | 5.0 | 2500 | 1.5413 | {'precision': 0.9381835473133618, 'recall': 0.8653508771929824, 'f1': 0.9002966005019393, 'number': 2280} | {'precision': 0.6690058479532164, 'recall': 0.601472134595163, 'f1': 0.6334440753045404, 'number': 951} | {'precision': 0.19949254678084363, 'recall': 0.5143090760425184, 'f1': 0.2874771480804387, 'number': 1223} | {'precision': 0.32124352331606215, 'recall': 0.07515151515151515, 'f1': 0.12180746561886051, 'number': 825} | {'precision': 0.34080531340805315, 'recall': 0.4647608264930654, 'f1': 0.39324631780625074, 'number': 3533} | {'precision': 0.0546448087431694, 'recall': 0.13157894736842105, 'f1': 0.0772200772200772, 'number': 608} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 145} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 360} | 0.3939 | 0.4936 | 0.4382 | 0.7180 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.0 |
|
- Pytorch 1.12.1 |
|
- Datasets 2.9.0 |
|
- Tokenizers 0.13.2 |
|
|