layoutlmv3-er-ner

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

• Loss: 0.2025
• Precision: 0.6442
• Recall: 0.6761
• F1: 0.6598
• Accuracy: 0.9507

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: 5e-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
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	22	0.2940	0.4214	0.2956	0.3475	0.9147
No log	2.0	44	0.2487	0.4134	0.4526	0.4321	0.9175
No log	3.0	66	0.1922	0.5399	0.5460	0.5429	0.9392
No log	4.0	88	0.1977	0.5653	0.5813	0.5732	0.9434
No log	5.0	110	0.2018	0.6173	0.6252	0.6212	0.9477
No log	6.0	132	0.1823	0.6232	0.6153	0.6192	0.9485
No log	7.0	154	0.1972	0.6203	0.6238	0.6220	0.9477
No log	8.0	176	0.1952	0.6292	0.6407	0.6349	0.9511
No log	9.0	198	0.2070	0.6331	0.6492	0.6411	0.9489
No log	10.0	220	0.2025	0.6442	0.6761	0.6598	0.9507

Framework versions

• Transformers 4.20.0.dev0
• Pytorch 1.11.0
• Datasets 2.1.0
• Tokenizers 0.12.1