mridhulanatarajan/layoutlm-funsd-tf

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

• Train Loss: 0.2381
• Validation Loss: 1.2497
• Train Overall Precision: 0.5672
• Train Overall Recall: 0.6352
• Train Overall F1: 0.5993
• Train Overall Accuracy: 0.6689
• Epoch: 11

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:

• optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 3e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: mixed_float16

Training results

Train Loss	Validation Loss	Train Overall Precision	Train Overall Recall	Train Overall F1	Train Overall Accuracy	Epoch
1.0628	1.0944	0.3612	0.5354	0.4314	0.5849	0
0.9183	1.0225	0.4267	0.5580	0.4836	0.6221	1
0.8087	1.0060	0.4499	0.5364	0.4894	0.6207	2
0.6643	1.0055	0.4673	0.5840	0.5192	0.6509	3
0.5917	1.0958	0.4957	0.6096	0.5468	0.6404	4
0.5103	1.0582	0.5169	0.5981	0.5545	0.6389	5
0.4368	1.0593	0.5348	0.6242	0.5761	0.6630	6
0.3950	1.1941	0.5437	0.5810	0.5617	0.6543	7
0.3836	1.1152	0.5359	0.6066	0.5691	0.6509	8
0.3288	1.1746	0.5308	0.6147	0.5696	0.6438	9
0.2721	1.2269	0.5467	0.6407	0.5900	0.6630	10
0.2381	1.2497	0.5672	0.6352	0.5993	0.6689	11

Framework versions

• Transformers 4.37.2
• TensorFlow 2.15.0
• Datasets 2.17.1
• Tokenizers 0.15.2