model-2024-06-06

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: 0.5257
• Precision: 0.7422
• Recall: 0.7427
• F1: 0.7424
• Accuracy: 0.8617

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: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	0.6	100	1.4725	0.2387	0.0987	0.1396	0.6316
No log	1.19	200	0.9815	0.5362	0.434	0.4797	0.7585
No log	1.79	300	0.7596	0.6422	0.5707	0.6043	0.8071
No log	2.38	400	0.6719	0.6739	0.6433	0.6583	0.8240
1.1397	2.98	500	0.5865	0.7118	0.7013	0.7065	0.8429
1.1397	3.57	600	0.5910	0.7293	0.722	0.7256	0.8505
1.1397	4.17	700	0.5456	0.7373	0.726	0.7316	0.8524
1.1397	4.76	800	0.5343	0.7376	0.7327	0.7351	0.8557
1.1397	5.36	900	0.5327	0.7283	0.7487	0.7383	0.8569
0.4593	5.95	1000	0.5257	0.7422	0.7427	0.7424	0.8617

Framework versions

• Transformers 4.29.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.13.3