%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
EN
Layout Qa Hparam Tuning
L
Layout Qa Hparam Tuning
Developed by PrimWong
A document QA model fine-tuned based on microsoft/layoutlmv2-base-uncased, suitable for document layout understanding and QA tasks
Downloads 14
Release Time : 12/12/2023
Model Overview
This model is a document understanding model based on the LayoutLMv2 architecture, fine-tuned for document layout analysis and QA tasks.
Model Features
Document Layout Understanding
Capable of understanding text and layout information in documents
QA Capability
Can answer questions based on document content
Fine-tuning Optimization
Achieves better performance through hyperparameter tuning
Model Capabilities
Document Layout Analysis
Document Content QA
Text and Visual Information Fusion Processing
Use Cases
Document Processing
Form Understanding
Extract and answer questions from structured forms
Contract Analysis
Analyze contract documents and answer related questions
đ layout_qa_hparam_tuning
This model is a fine - tuned version of [microsoft/layoutlmv2 - base - uncased](https://huggingface.co/microsoft/layoutlmv2 - base - uncased) on an unknown dataset. It can achieve a loss of 3.3973 on the evaluation set.
đ Documentation
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
đ§ Technical Details
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e - 06
- train_batch_size: 5
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.0364 | 0.28 | 50 | 5.7109 |
| 5.6991 | 0.55 | 100 | 5.3444 |
| 5.3564 | 0.83 | 150 | 5.0481 |
| 5.1086 | 1.1 | 200 | 4.8591 |
| 4.8464 | 1.38 | 250 | 4.6824 |
| 4.7178 | 1.66 | 300 | 4.5995 |
| 4.6003 | 1.93 | 350 | 4.4761 |
| 4.4415 | 2.21 | 400 | 4.3781 |
| 4.3911 | 2.49 | 450 | 4.3017 |
| 4.2507 | 2.76 | 500 | 4.2496 |
| 4.1975 | 3.04 | 550 | 4.2142 |
| 4.0971 | 3.31 | 600 | 4.1524 |
| 4.0671 | 3.59 | 650 | 4.1038 |
| 4.0225 | 3.87 | 700 | 4.0486 |
| 3.9641 | 4.14 | 750 | 4.0478 |
| 3.9662 | 4.42 | 800 | 4.0082 |
| 3.8185 | 4.7 | 850 | 4.0001 |
| 3.8798 | 4.97 | 900 | 3.9235 |
| 3.7622 | 5.25 | 950 | 3.9549 |
| 3.7109 | 5.52 | 1000 | 3.8668 |
| 3.7218 | 5.8 | 1050 | 3.8849 |
| 3.6718 | 6.08 | 1100 | 3.9426 |
| 3.6925 | 6.35 | 1150 | 3.8288 |
| 3.5893 | 6.63 | 1200 | 3.8240 |
| 3.5545 | 6.91 | 1250 | 3.8149 |
| 3.4922 | 7.18 | 1300 | 3.8104 |
| 3.5117 | 7.46 | 1350 | 3.8128 |
| 3.3699 | 7.73 | 1400 | 3.7590 |
| 3.4538 | 8.01 | 1450 | 3.7577 |
| 3.3669 | 8.29 | 1500 | 3.7370 |
| 3.3516 | 8.56 | 1550 | 3.7278 |
| 3.3264 | 8.84 | 1600 | 3.6671 |
| 3.3102 | 9.12 | 1650 | 3.6953 |
| 3.241 | 9.39 | 1700 | 3.6474 |
| 3.278 | 9.67 | 1750 | 3.8793 |
| 3.2593 | 9.94 | 1800 | 3.6447 |
| 3.1663 | 10.22 | 1850 | 3.8442 |
| 3.0952 | 10.5 | 1900 | 3.6431 |
| 3.1355 | 10.77 | 1950 | 3.6261 |
| 3.0874 | 11.05 | 2000 | 3.5631 |
| 3.0178 | 11.33 | 2050 | 3.5662 |
| 2.9257 | 11.6 | 2100 | 3.4744 |
| 2.9164 | 11.88 | 2150 | 3.4374 |
| 2.8061 | 12.15 | 2200 | 3.4550 |
| 2.8664 | 12.43 | 2250 | 3.4217 |
| 2.7886 | 12.71 | 2300 | 3.4294 |
| 2.8398 | 12.98 | 2350 | 3.3906 |
| 2.7823 | 13.26 | 2400 | 3.4311 |
| 2.7024 | 13.54 | 2450 | 3.4267 |
| 2.7443 | 13.81 | 2500 | 3.3412 |
| 2.6747 | 14.09 | 2550 | 3.3656 |
| 2.723 | 14.36 | 2600 | 3.5019 |
| 2.6278 | 14.64 | 2650 | 3.4287 |
| 2.5001 | 14.92 | 2700 | 3.5152 |
| 2.5718 | 15.19 | 2750 | 3.3615 |
| 2.5734 | 15.47 | 2800 | 3.3193 |
| 2.5112 | 15.75 | 2850 | 3.4028 |
| 2.4499 | 16.02 | 2900 | 3.4374 |
| 2.4631 | 16.3 | 2950 | 3.3910 |
| 2.4246 | 16.57 | 3000 | 3.2926 |
| 2.4075 | 16.85 | 3050 | 3.1869 |
| 2.3691 | 17.13 | 3100 | 3.2002 |
| 2.3557 | 17.4 | 3150 | 3.1995 |
| 2.309 | 17.68 | 3200 | 3.3596 |
| 2.2738 | 17.96 | 3250 | 3.2819 |
| 2.2371 | 18.23 | 3300 | 3.2793 |
| 2.2578 | 18.51 | 3350 | 3.1955 |
| 2.1887 | 18.78 | 3400 | 3.1516 |
| 2.2166 | 19.06 | 3450 | 3.1920 |
| 2.1767 | 19.34 | 3500 | 3.0891 |
| 2.1307 | 19.61 | 3550 | 3.1467 |
| 2.1769 | 19.89 | 3600 | 3.1935 |
| 2.0798 | 20.17 | 3650 | 3.2426 |
| 2.1029 | 20.44 | 3700 | 3.1828 |
| 2.0654 | 20.72 | 3750 | 3.2298 |
| 1.997 | 20.99 | 3800 | 3.2313 |
| 1.9933 | 21.27 | 3850 | 3.1501 |
| 2.0084 | 21.55 | 3900 | 3.0830 |
| 1.9963 | 21.82 | 3950 | 3.2029 |
| 1.889 | 22.1 | 4000 | 3.2676 |
| 2.0014 | 22.38 | 4050 | 3.0189 |
| 1.9031 | 22.65 | 4100 | 3.0549 |
| 1.9464 | 22.93 | 4150 | 3.2659 |
| 1.8972 | 23.2 | 4200 | 3.2271 |
| 1.8549 | 23.48 | 4250 | 3.0585 |
| 1.8106 | 23.76 | 4300 | 3.2286 |
| 1.8222 | 24.03 | 4350 | 3.2233 |
| 1.8537 | 24.31 | 4400 | 2.9525 |
| 1.7717 | 24.59 | 4450 | 3.1129 |
| 1.8045 | 24.86 | 4500 | 3.1795 |
| 1.7783 | 25.14 | 4550 | 3.1206 |
| 1.7119 | 25.41 | 4600 | 3.1325 |
| 1.6936 | 25.69 | 4650 | 3.0850 |
| 1.776 | 25.97 | 4700 | 2.8785 |
| 1.7269 | 26.24 | 4750 | 2.9847 |
| 1.6276 | 26.52 | 4800 | 3.0743 |
| 1.6228 | 26.8 | 4850 | 3.1257 |
| 1.7509 | 27.07 | 4900 | 3.0451 |
| 1.6658 | 27.35 | 4950 | 3.1540 |
| 1.6688 | 27.62 | 5000 | 2.9553 |
| 1.5576 | 27.9 | 5050 | 3.0843 |
| 1.5457 | 28.18 | 5100 | 3.1677 |
| 1.638 | 28.45 | 5150 | 3.0357 |
| 1.5004 | 28.73 | 5200 | 3.0918 |
| 1.6639 | 29.01 | 5250 | 3.0215 |
| 1.5465 | 29.28 | 5300 | 3.1257 |
| 1.4719 | 29.56 | 5350 | 3.0513 |
| 1.5599 | 29.83 | 5400 | 3.0366 |
| 1.5755 | 30.11 | 5450 | 2.9535 |
| 1.496 | 30.39 | 5500 | 3.0343 |
| 1.5915 | 30.66 | 5550 | 3.1121 |
| 1.4198 | 30.94 | 5600 | 3.0673 |
| 1.5062 | 31.22 | 5650 | 2.9743 |
| 1.3817 | 31.49 | 5700 | 3.0471 |
| 1.4361 | 31.77 | 5750 | 2.9827 |
| 1.4624 | 32.04 | 5800 | 3.2212 |
| 1.4895 | 32.32 | 5850 | 3.0745 |
| 1.4598 | 32.6 | 5900 | 3.0424 |
| 1.4379 | 32.87 | 5950 | 3.0214 |
| 1.429 | 33.15 | 6000 | 3.9556 |
| 1.4837 | 33.43 | 6050 | 3.0527 |
| 1.4427 | 33.7 | 6100 | 3.0360 |
| 1.6037 | 33.98 | 6150 | 3.0011 |
| 1.3789 | 34.25 | 6200 | 2.9842 |
| 1.4559 | 34.53 | 6250 | 2.9825 |
| 1.3494 | 34.81 | 6300 | 3.0216 |
| 1.3313 | 35.08 | 6350 | 2.9506 |
| 1.3074 | 35.36 | 6400 | 2.9899 |
| 1.3534 | 35.64 | 6450 | 3.3824 |
| 1.4189 | 35.91 | 6500 | 2.9109 |
| 1.2795 | 36.19 | 6550 | 3.2013 |
| 1.377 | 36.46 | 6600 | 3.1894 |
| 1.3627 | 36.74 | 6650 | 3.0203 |
| 1.3731 | 37.02 | 6700 | 3.0597 |
| 1.2557 | 37.29 | 6750 | 3.1781 |
| 1.362 | 37.57 | 6800 | 3.3320 |
| 1.3448 | 37.85 | 6850 | 3.0893 |
| 1.3337 | 38.12 | 6900 | 3.3698 |
| 1.3455 | 38.4 | 6950 | 3.0614 |
| 1.3397 | 38.67 | 7000 | 3.2179 |
| 1.2439 | 38.95 | 7050 | 3.1908 |
| 1.25 | 39.23 | 7100 | 3.3292 |
| 1.3099 | 39.5 | 7150 | 3.1604 |
| 1.3465 | 39.78 | 7200 | 3.1365 |
| 1.2703 | 40.06 | 7250 | 3.2937 |
| 1.2662 | 40.33 | 7300 | 3.3199 |
| 1.233 | 40.61 | 7350 | 3.1995 |
| 1.2786 | 40.88 | 7400 | 3.1360 |
| 1.3409 | 41.16 | 7450 | 3.1513 |
| 1.2395 | 41.44 | 7500 | 3.2488 |
| 1.1858 | 41.71 | 7550 | 3.3637 |
| 1.3312 | 41.99 | 7600 | 3.2043 |
| 1.2245 | 42.27 | 7650 | 3.3381 |
| 1.2631 | 42.54 | 7700 | 3.3504 |
| 1.257 | 42.82 | 7750 | 3.1843 |
| 1.1715 | 43.09 | 7800 | 3.3320 |
| 1.2017 | 43.37 | 7850 | 3.1980 |
| 1.2711 | 43.65 | 7900 | 3.2528 |
| 1.2091 | 43.92 | 7950 | 3.1928 |
| 1.2574 | 44.2 | 8000 | 3.4765 |
| 1.1915 | 44.48 | 8050 | 3.2830 |
| 1.1754 | 44.75 | 8100 | 3.3196 |
| 1.263 | 45.03 | 8150 | 3.2323 |
| 1.1522 | 45.3 | 8200 | 3.2954 |
| 1.1563 | 45.58 | 8250 | 3.3078 |
| 1.2196 | 45.86 | 8300 | 3.4295 |
| 1.2375 | 46.13 | 8350 | 3.3431 |
| 1.2307 | 46.41 | 8400 | 3.3140 |
| 1.1926 | 46.69 | 8450 | 3.3558 |
| 1.1743 | 46.96 | 8500 | 3.2817 |
| 1.1721 | 47.24 | 8550 | 3.2732 |
| 1.192 | 47.51 | 8600 | 3.3022 |
| 1.1642 | 47.79 | 8650 | 3.3513 |
| 1.2049 | 48.07 | 8700 | 3.3494 |
| 1.1157 | 48.34 | 8750 | 3.3900 |
| 1.2006 | 48.62 | 8800 | 3.3109 |
| 1.1384 | 48.9 | 8850 | 3.3915 |
| 1.1437 | 49.17 | 8900 | 3.4193 |
| 1.2226 | 49.45 | 8950 | 3.3782 |
| 1.1074 | 49.72 | 9000 | 3.3965 |
| 1.1955 | 50.0 | 9050 | 3.3973 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
đ License
This model is released under the CC - BY - NC - SA 4.0 license.
Distilbert Base Cased Distilled Squad
Apache-2.0
DistilBERT is a lightweight distilled version of BERT, with 40% fewer parameters, 60% faster speed, while retaining over 95% performance. This model is a question-answering specialized version fine-tuned on the SQuAD v1.1 dataset.
Question Answering System English
D
distilbert
220.76k
244
Distilbert Base Uncased Distilled Squad
Apache-2.0
DistilBERT is a lightweight distilled version of BERT, with 40% fewer parameters and 60% faster speed, maintaining over 95% of BERT's performance on the GLUE benchmark. This model is fine-tuned specifically for question answering tasks.
Question Answering System
Transformers English
Transformers EnglishD
distilbert
154.39k
115
Tapas Large Finetuned Wtq
Apache-2.0
TAPAS is a table question answering model based on the BERT architecture, pre-trained in a self-supervised manner on Wikipedia table data, supporting natural language question answering on table content
Question Answering System Transformers English
Transformers EnglishT
google
124.85k
141
T5 Base Question Generator
A question generation model based on t5-base. Input the answer and context, and output the corresponding question.
Question Answering System Transformers
TransformersT
iarfmoose
122.74k
57
Bert Base Cased Qa Evaluator
A BERT-base-cased based QA pair evaluation model for determining semantic relevance between questions and answers
Question Answering System
B
iarfmoose
122.54k
9
Tiny Doc Qa Vision Encoder Decoder
MIT
A document Q&A model based on the MIT License, primarily for testing purposes.
Question Answering System Transformers
TransformersT
fxmarty
41.08k
16
Dpr Question Encoder Single Nq Base
DPR (Dense Passage Retrieval) is a tool and model for open-domain question answering research. This model is a BERT-based question encoder trained on the Natural Questions (NQ) dataset.
Question Answering System Transformers English
Transformers EnglishD
facebook
32.90k
30
Mobilebert Uncased Squad V2
MIT
MobileBERT is a lightweight version of BERT_LARGE, fine-tuned on the SQuAD2.0 dataset for question answering systems.
Question Answering System Transformers English
Transformers EnglishM
csarron
29.11k
7
Tapas Base Finetuned Wtq
Apache-2.0
TAPAS is a Transformer-based table question answering model, pre-trained on Wikipedia table data through self-supervised learning and fine-tuned on datasets like WTQ.
Question Answering System Transformers English
Transformers EnglishT
google
23.03k
217
Dpr Question Encoder Multiset Base
BERT-based Dense Passage Retrieval (DPR) question encoder for open-domain QA research, trained on multiple QA datasets
Question Answering System Transformers English
Transformers EnglishD
facebook
17.51k
4
Featured Recommended AI Models
Š 2025AIbase