---
license: cc-by-nc-sa-4.0
tags:
- generated_from_trainer
datasets:
- nielsr/funsd-layoutlmv3
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: pasha
  results:
  - task:
      name: Token Classification
      type: token-classification
    dataset:
      name: nielsr/funsd-layoutlmv3
      type: nielsr/funsd-layoutlmv3
      config: pasha
      split: test
      args: pasha
    metrics:
    - name: Precision
      type: precision
      value: 0.9845822875582646
    - name: Recall
      type: recall
      value: 0.989193083573487
    - name: F1
      type: f1
      value: 0.9868823000898472
    - name: Accuracy
      type: accuracy
      value: 0.9908389585342333
---

<!-- 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. -->

# pasha

This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the nielsr/funsd-layoutlmv3 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0558
- Precision: 0.9846
- Recall: 0.9892
- F1: 0.9869
- Accuracy: 0.9908

## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1000

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log        | 2.13  | 100  | 0.2662          | 0.9524    | 0.9442 | 0.9483 | 0.9566   |
| No log        | 4.26  | 200  | 0.1026          | 0.9771    | 0.9820 | 0.9795 | 0.9851   |
| No log        | 6.38  | 300  | 0.0722          | 0.9821    | 0.9878 | 0.9849 | 0.9884   |
| No log        | 8.51  | 400  | 0.0608          | 0.9852    | 0.9863 | 0.9858 | 0.9892   |
| 0.2962        | 10.64 | 500  | 0.0606          | 0.9849    | 0.9860 | 0.9854 | 0.9889   |
| 0.2962        | 12.77 | 600  | 0.0518          | 0.9860    | 0.9910 | 0.9885 | 0.9920   |
| 0.2962        | 14.89 | 700  | 0.0526          | 0.9864    | 0.9910 | 0.9887 | 0.9923   |
| 0.2962        | 17.02 | 800  | 0.0543          | 0.9849    | 0.9896 | 0.9872 | 0.9913   |
| 0.2962        | 19.15 | 900  | 0.0557          | 0.9846    | 0.9888 | 0.9867 | 0.9911   |
| 0.0255        | 21.28 | 1000 | 0.0558          | 0.9846    | 0.9892 | 0.9869 | 0.9908   |


### Framework versions

- Transformers 4.26.0.dev0
- Pytorch 1.12.1
- Datasets 2.6.1
- Tokenizers 0.13.2