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: test
    results: []

test

This model is a fine-tuned version of microsoft/layoutlmv3-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6850
Precision: 0.8936
Recall: 0.9136
F1: 0.9035
Accuracy: 0.8445

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	1.33	100	0.6682	0.7574	0.8311	0.7925	0.7658
No log	2.67	200	0.4970	0.8289	0.8833	0.8552	0.8339
No log	4.0	300	0.5550	0.8398	0.8882	0.8634	0.8128
No log	5.33	400	0.5001	0.8800	0.9106	0.8950	0.8500
0.5341	6.67	500	0.5645	0.8947	0.9036	0.8992	0.8456
0.5341	8.0	600	0.5797	0.8847	0.9190	0.9016	0.8537
0.5341	9.33	700	0.6635	0.8816	0.9101	0.8956	0.8421
0.5341	10.67	800	0.6857	0.8939	0.9126	0.9031	0.8452
0.5341	12.0	900	0.6777	0.8941	0.9146	0.9042	0.8438
0.1335	13.33	1000	0.6850	0.8936	0.9136	0.9035	0.8445

Framework versions

Transformers 4.37.0.dev0
Pytorch 2.1.0+cu121
Datasets 2.16.0
Tokenizers 0.15.0