LayoutLMv3_5_entities_1

This model is a fine-tuned version of microsoft/layoutlmv3-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2310
• Precision: 0.82
• Recall: 0.8119
• F1: 0.8159
• Accuracy: 0.9642

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-06
• 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	2.56	100	0.4044	0.5	0.0198	0.0381	0.8884
No log	5.13	200	0.2363	0.7571	0.5248	0.6199	0.9328
No log	7.69	300	0.1817	0.7083	0.6733	0.6904	0.9447
No log	10.26	400	0.1606	0.7551	0.7327	0.7437	0.9523
0.2439	12.82	500	0.1592	0.79	0.7822	0.7861	0.9577
0.2439	15.38	600	0.1676	0.8144	0.7822	0.7980	0.9621
0.2439	17.95	700	0.1912	0.7980	0.7822	0.7900	0.9588
0.2439	20.51	800	0.1860	0.8404	0.7822	0.8103	0.9642
0.2439	23.08	900	0.1990	0.7767	0.7921	0.7843	0.9567
0.0312	25.64	1000	0.2126	0.8081	0.7921	0.8000	0.9610
0.0312	28.21	1100	0.2105	0.8058	0.8218	0.8137	0.9621
0.0312	30.77	1200	0.2127	0.8119	0.8119	0.8119	0.9632
0.0312	33.33	1300	0.2308	0.81	0.8020	0.8060	0.9621
0.0312	35.9	1400	0.2211	0.82	0.8119	0.8159	0.9642
0.0126	38.46	1500	0.2244	0.82	0.8119	0.8159	0.9642
0.0126	41.03	1600	0.2241	0.82	0.8119	0.8159	0.9642
0.0126	43.59	1700	0.2332	0.82	0.8119	0.8159	0.9642
0.0126	46.15	1800	0.2345	0.82	0.8119	0.8159	0.9632
0.0126	48.72	1900	0.2318	0.82	0.8119	0.8159	0.9642
0.0069	51.28	2000	0.2310	0.82	0.8119	0.8159	0.9642

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3