LayoutLMv3_5_entities_3

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: 0.2107
• Precision: 0.8835
• Recall: 0.8426
• F1: 0.8626
• Accuracy: 0.9729

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-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	0.1391	0.78	0.7222	0.7500	0.9575
No log	5.13	200	0.1103	0.8725	0.8241	0.8476	0.9720
No log	7.69	300	0.1415	0.8922	0.8426	0.8667	0.9739
No log	10.26	400	0.1649	0.8378	0.8611	0.8493	0.9710
0.0838	12.82	500	0.1545	0.8713	0.8148	0.8421	0.9729
0.0838	15.38	600	0.1396	0.8545	0.8704	0.8624	0.9749
0.0838	17.95	700	0.1523	0.8942	0.8611	0.8774	0.9768
0.0838	20.51	800	0.1718	0.8519	0.8519	0.8519	0.9710
0.0838	23.08	900	0.2242	0.87	0.8056	0.8365	0.9700
0.0044	25.64	1000	0.2165	0.88	0.8148	0.8462	0.9710
0.0044	28.21	1100	0.2235	0.8866	0.7963	0.8390	0.9681
0.0044	30.77	1200	0.2174	0.9	0.8333	0.8654	0.9739
0.0044	33.33	1300	0.1991	0.8692	0.8611	0.8651	0.9729
0.0044	35.9	1400	0.1986	0.8762	0.8519	0.8638	0.9739
0.0015	38.46	1500	0.2061	0.8713	0.8148	0.8421	0.9700
0.0015	41.03	1600	0.1970	0.8641	0.8241	0.8436	0.9710
0.0015	43.59	1700	0.2127	0.8614	0.8056	0.8325	0.9700
0.0015	46.15	1800	0.2070	0.875	0.8426	0.8585	0.9729
0.0015	48.72	1900	0.2097	0.8835	0.8426	0.8626	0.9729
0.0008	51.28	2000	0.2107	0.8835	0.8426	0.8626	0.9729

Framework versions

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