metadata

library_name: transformers
license: cc-by-nc-sa-4.0
base_model: microsoft/layoutlmv3-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: layoutlmv3_document_classification
    results: []

layoutlmv3_document_classification

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: 0.6852
Accuracy: 0.8480
F1: 0.8373

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: 3e-05
train_batch_size: 24
eval_batch_size: 24
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.06
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
4.1758	0.5	100	3.6479	0.1754	0.0743
3.1634	1.0	200	2.5074	0.4645	0.3598
2.2494	1.5	300	1.9309	0.5856	0.4950
1.8063	2.0	400	1.5119	0.6817	0.6152
1.458	2.5	500	1.2952	0.7126	0.6529
1.2453	3.0	600	1.1118	0.7728	0.7327
1.046	3.5	700	1.0126	0.7987	0.7681
0.966	4.0	800	0.9096	0.8154	0.7929
0.7941	4.5	900	0.8714	0.8179	0.7972
0.7796	5.0	1000	0.8019	0.8329	0.8126
0.6561	5.5	1100	0.7623	0.8421	0.8235
0.6419	6.0	1200	0.7399	0.8421	0.8262
0.5715	6.5	1300	0.7127	0.8480	0.8321
0.4991	7.0	1400	0.7502	0.8396	0.8257
0.4697	7.5	1500	0.7124	0.8429	0.8305
0.4618	8.0	1600	0.6976	0.8463	0.8330
0.4117	8.5	1700	0.6892	0.8546	0.8429
0.4274	9.0	1800	0.6915	0.8496	0.8390
0.383	9.5	1900	0.6830	0.8471	0.8349
0.3604	10.0	2000	0.6852	0.8480	0.8373

Framework versions

Transformers 4.47.1
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0