test

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

• Loss: 3.1824
• Precision: 0.0
• Recall: 0.0
• F1: 0.0
• Accuracy: 0.6923

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: 0.00011
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 400

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	5.0	20	3.5946	0.0	0.0	0.0	0.5641
No log	10.0	40	4.0548	0.0	0.0	0.0	0.5897
No log	15.0	60	3.0002	0.0	0.0	0.0	0.5897
No log	20.0	80	2.1386	0.0	0.0	0.0	0.6667
No log	25.0	100	2.3658	0.0	0.0	0.0	0.6667
No log	30.0	120	2.8136	0.0	0.0	0.0	0.6410
No log	35.0	140	3.3828	0.0	0.0	0.0	0.5897
No log	40.0	160	2.6686	0.0	0.0	0.0	0.6923
No log	45.0	180	2.9943	0.0	0.0	0.0	0.6667
No log	50.0	200	2.9472	0.0	0.0	0.0	0.6923
No log	55.0	220	3.0009	0.0	0.0	0.0	0.6923
No log	60.0	240	3.0470	0.0	0.0	0.0	0.6923
No log	65.0	260	3.0742	0.0	0.0	0.0	0.6923
No log	70.0	280	3.3041	0.0	0.0	0.0	0.6667
No log	75.0	300	3.1925	0.0	0.0	0.0	0.6923
No log	80.0	320	3.1618	0.0	0.0	0.0	0.6923
No log	85.0	340	3.1684	0.0	0.0	0.0	0.6923
No log	90.0	360	3.1765	0.0	0.0	0.0	0.6923
No log	95.0	380	3.1813	0.0	0.0	0.0	0.6923
No log	100.0	400	3.1824	0.0	0.0	0.0	0.6923

Framework versions

• Transformers 4.45.0.dev0
• Pytorch 2.4.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1