metadata

license: cc-by-nc-sa-4.0
base_model: microsoft/layoutlmv3-base
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: primo_test
    results: []

primo_test

This model is a fine-tuned version of microsoft/layoutlmv3-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0105
Precision: 0.9744
Recall: 0.9902
F1: 0.9822
Accuracy: 0.9979

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: 2
eval_batch_size: 2
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	0.03	100	0.4646	0.8275	0.8656	0.8461	0.9306
No log	0.06	200	0.0824	0.9614	0.9722	0.9667	0.9948
No log	0.08	300	0.0363	0.9622	0.9859	0.9739	0.9951
No log	0.11	400	0.0182	0.9756	0.9912	0.9833	0.9980
0.3067	0.14	500	0.0217	0.9578	0.9813	0.9694	0.9960
0.3067	0.17	600	0.0106	0.9913	0.9946	0.9929	0.9988
0.3067	0.19	700	0.0121	0.9733	0.9894	0.9812	0.9977
0.3067	0.22	800	0.0126	0.9699	0.9881	0.9789	0.9975
0.3067	0.25	900	0.0098	0.9778	0.9915	0.9846	0.9982
0.0105	0.28	1000	0.0105	0.9744	0.9902	0.9822	0.9979

Framework versions

Transformers 4.36.1
Pytorch 2.1.1+cu121
Datasets 2.15.0
Tokenizers 0.15.0