metadata

library_name: transformers
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: 0.9515865227347072
          - name: Recall
            type: recall
            value: 0.9645225464190982
          - name: F1
            type: f1
            value: 0.9580108677753993
          - name: Accuracy
            type: accuracy
            value: 0.9870755974971792

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: 0.0596
Precision: 0.9516
Recall: 0.9645
F1: 0.9580
Accuracy: 0.9871

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	0.0548	0.9415	0.9453	0.9434	0.9830
No log	3.1746	200	0.0531	0.9377	0.9625	0.9499	0.9847
No log	4.7619	300	0.0550	0.9414	0.9595	0.9504	0.9851
No log	6.3492	400	0.0560	0.9500	0.9645	0.9572	0.9868
0.0464	7.9365	500	0.0596	0.9516	0.9645	0.9580	0.9871
0.0464	9.5238	600	0.0630	0.9502	0.9622	0.9562	0.9865
0.0464	11.1111	700	0.0707	0.9489	0.9658	0.9573	0.9868
0.0464	12.6984	800	0.0726	0.9515	0.9629	0.9572	0.9868
0.0464	14.2857	900	0.0765	0.9510	0.9652	0.9580	0.9871
0.0048	15.8730	1000	0.0773	0.9500	0.9645	0.9572	0.9868

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu118
Datasets 2.21.0
Tokenizers 0.19.1