---
license: cc-by-nc-sa-4.0
tags:
- generated_from_trainer
datasets:
- cord-layoutlmv3
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: layoutlmv3-finetuned-cord_100
  results:
  - task:
      name: Token Classification
      type: token-classification
    dataset:
      name: cord-layoutlmv3
      type: cord-layoutlmv3
      config: cord
      split: test
      args: cord
    metrics:
    - name: Precision
      type: precision
      value: 0.9394387001477105
    - name: Recall
      type: recall
      value: 0.9520958083832335
    - name: F1
      type: f1
      value: 0.9457249070631969
    - name: Accuracy
      type: accuracy
      value: 0.9550084889643463
---

<!-- 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-cord_100

This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the cord-layoutlmv3 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2186
- Precision: 0.9394
- Recall: 0.9521
- F1: 0.9457
- Accuracy: 0.9550

## 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: 1e-05
- train_batch_size: 5
- eval_batch_size: 5
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 2500

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log        | 1.56  | 250  | 1.0245          | 0.7265    | 0.7874 | 0.7557 | 0.7950   |
| 1.4012        | 3.12  | 500  | 0.5634          | 0.8336    | 0.8660 | 0.8495 | 0.8765   |
| 1.4012        | 4.69  | 750  | 0.4155          | 0.8823    | 0.9034 | 0.8928 | 0.9143   |
| 0.4012        | 6.25  | 1000 | 0.3149          | 0.9263    | 0.9319 | 0.9291 | 0.9359   |
| 0.4012        | 7.81  | 1250 | 0.2733          | 0.9295    | 0.9379 | 0.9337 | 0.9410   |
| 0.2147        | 9.38  | 1500 | 0.2501          | 0.9319    | 0.9416 | 0.9367 | 0.9448   |
| 0.2147        | 10.94 | 1750 | 0.2390          | 0.9319    | 0.9424 | 0.9371 | 0.9508   |
| 0.1472        | 12.5  | 2000 | 0.2231          | 0.9386    | 0.9499 | 0.9442 | 0.9542   |
| 0.1472        | 14.06 | 2250 | 0.2174          | 0.9408    | 0.9521 | 0.9464 | 0.9563   |
| 0.1096        | 15.62 | 2500 | 0.2186          | 0.9394    | 0.9521 | 0.9457 | 0.9550   |


### Framework versions

- Transformers 4.26.1
- Pytorch 1.13.0
- Datasets 2.10.1
- Tokenizers 0.13.2