metadata

base_model: layoutlmv3
tags:
  - generated_from_trainer
datasets:
  - not-lain/sroie
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: layoutlmv3-finetuned-sroie
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: not-lain/sroie
          type: not-lain/sroie
        metrics:
          - name: Precision
            type: precision
            value: 0.9435600578871202
          - name: Recall
            type: recall
            value: 0.9421965317919075
          - name: F1
            type: f1
            value: 0.9428778018799712
          - name: Accuracy
            type: accuracy
            value: 0.9952312354080771

layoutlmv3-finetuned-sroie

This model is a fine-tuned version of layoutlmv3 on the not-lain/sroie dataset. It achieves the following results on the evaluation set:

Loss: 0.0319
Precision: 0.9436
Recall: 0.9422
F1: 0.9429
Accuracy: 0.9952

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: 5e-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: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.5873	100	0.0429	0.8634	0.8772	0.8703	0.9896
No log	3.1746	200	0.0222	0.9079	0.9408	0.9241	0.9947
No log	4.7619	300	0.0285	0.9232	0.9379	0.9305	0.9939
No log	6.3492	400	0.0291	0.9393	0.9393	0.9393	0.9947
0.0408	7.9365	500	0.0295	0.9223	0.9436	0.9329	0.9945
0.0408	9.5238	600	0.0356	0.9223	0.9436	0.9329	0.9936
0.0408	11.1111	700	0.0318	0.9397	0.9451	0.9424	0.9952
0.0408	12.6984	800	0.0311	0.9312	0.9393	0.9353	0.9948
0.0408	14.2857	900	0.0324	0.9394	0.9408	0.9401	0.9950
0.0035	15.8730	1000	0.0319	0.9436	0.9422	0.9429	0.9952

Framework versions

Transformers 4.44.0
Pytorch 2.4.0+cu118
Datasets 2.20.0
Tokenizers 0.19.1