layoutlmv3-final-v5-BIE

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: 0.9239
• Precision: 0.9019
• Recall: 0.9013
• F1: 0.9016
• Accuracy: 0.7757

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	2.56	100	2.2304	0.6394	0.5974	0.6177	0.5199
No log	5.13	200	1.3910	0.8278	0.8224	0.8251	0.6924
No log	7.69	300	1.0866	0.8749	0.8743	0.8746	0.7385
No log	10.26	400	0.9587	0.8947	0.8941	0.8944	0.7663
1.6438	12.82	500	0.9239	0.9019	0.9013	0.9016	0.7757

Framework versions

• Transformers 4.30.0.dev0
• Pytorch 1.8.0+cu101
• Datasets 2.12.0
• Tokenizers 0.13.3