---
license: cc-by-nc-sa-4.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: layoutlmv3-finetuned-funsd
  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-finetuned-funsd

This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8292
- Precision: 0.8993
- Recall: 0.915
- F1: 0.9071
- Accuracy: 0.8473

## 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: 2e-05
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 400

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log        | 1.67  | 25   | 0.8680          | 0.7229    | 0.7345 | 0.7287 | 0.7439   |
| No log        | 3.33  | 50   | 0.5806          | 0.7987    | 0.859  | 0.8278 | 0.8218   |
| No log        | 5.0   | 75   | 0.5964          | 0.8169    | 0.89   | 0.8519 | 0.8143   |
| No log        | 6.67  | 100  | 0.5635          | 0.8563    | 0.9085 | 0.8816 | 0.8249   |
| No log        | 8.33  | 125  | 0.6466          | 0.8571    | 0.9055 | 0.8806 | 0.8344   |
| No log        | 10.0  | 150  | 0.6587          | 0.8806    | 0.907  | 0.8936 | 0.8326   |
| No log        | 11.67 | 175  | 0.6984          | 0.8826    | 0.9135 | 0.8978 | 0.8376   |
| No log        | 13.33 | 200  | 0.6967          | 0.9003    | 0.926  | 0.9130 | 0.8437   |
| No log        | 15.0  | 225  | 0.7260          | 0.8979    | 0.9105 | 0.9042 | 0.8451   |
| No log        | 16.67 | 250  | 0.7543          | 0.8881    | 0.913  | 0.9004 | 0.8511   |
| No log        | 18.33 | 275  | 0.7765          | 0.8862    | 0.911  | 0.8984 | 0.8449   |
| No log        | 20.0  | 300  | 0.8024          | 0.9007    | 0.907  | 0.9038 | 0.8474   |
| No log        | 21.67 | 325  | 0.8147          | 0.9038    | 0.916  | 0.9099 | 0.8509   |
| No log        | 23.33 | 350  | 0.8134          | 0.9042    | 0.9155 | 0.9098 | 0.8511   |
| No log        | 25.0  | 375  | 0.8294          | 0.9027    | 0.914  | 0.9083 | 0.8467   |
| No log        | 26.67 | 400  | 0.8292          | 0.8993    | 0.915  | 0.9071 | 0.8473   |


### Framework versions

- Transformers 4.12.5
- Pytorch 1.10.0+cu111
- Datasets 2.13.2
- Tokenizers 0.10.1