LayoutLMv3_5_entities_filtred_21

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

• Loss: 1.2156
• Precision: 0.5
• Recall: 0.4925
• F1: 0.4962
• Accuracy: 0.8423

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: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 2000

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	10.0	100	0.8223	0.3333	0.2239	0.2679	0.8054
No log	20.0	200	0.8614	0.4328	0.4328	0.4328	0.8221
No log	30.0	300	0.9427	0.5522	0.5522	0.5522	0.8456
No log	40.0	400	0.9633	0.5075	0.5075	0.5075	0.8356
0.3534	50.0	500	0.9632	0.5323	0.4925	0.5116	0.8490
0.3534	60.0	600	1.0486	0.5224	0.5224	0.5224	0.8456
0.3534	70.0	700	1.0959	0.4921	0.4627	0.4769	0.8356
0.3534	80.0	800	1.1039	0.5224	0.5224	0.5224	0.8389
0.3534	90.0	900	1.1153	0.5312	0.5075	0.5191	0.8423
0.0067	100.0	1000	1.1449	0.4921	0.4627	0.4769	0.8356
0.0067	110.0	1100	1.1629	0.5	0.4776	0.4885	0.8389
0.0067	120.0	1200	1.1738	0.5231	0.5075	0.5152	0.8490
0.0067	130.0	1300	1.1868	0.5385	0.5224	0.5303	0.8523
0.0067	140.0	1400	1.1994	0.5156	0.4925	0.5038	0.8456
0.0024	150.0	1500	1.2043	0.5077	0.4925	0.5	0.8423
0.0024	160.0	1600	1.2023	0.5077	0.4925	0.5	0.8423
0.0024	170.0	1700	1.2703	0.4928	0.5075	0.5	0.8356
0.0024	180.0	1800	1.2300	0.5303	0.5224	0.5263	0.8456
0.0024	190.0	1900	1.2256	0.5152	0.5075	0.5113	0.8423
0.0019	200.0	2000	1.2156	0.5	0.4925	0.4962	0.8423

Framework versions

• Transformers 4.29.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.13.3