layoutlmv3-finetuned-cord_100

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

• Loss: 0.1994
• Precision: 0.9444
• Recall: 0.9552
• F1: 0.9498
• Accuracy: 0.9606

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: 5
• eval_batch_size: 5
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 2500

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	2.0833	250	0.6541	0.8122	0.8116	0.8119	0.8439
0.9666	4.1667	500	0.3834	0.8660	0.8739	0.8699	0.9029
0.9666	6.25	750	0.2589	0.9136	0.9240	0.9188	0.9398
0.2307	8.3333	1000	0.2444	0.9246	0.9316	0.9281	0.9470
0.2307	10.4167	1250	0.2125	0.9311	0.9445	0.9378	0.9508
0.1035	12.5	1500	0.1878	0.9301	0.9498	0.9398	0.9572
0.1035	14.5833	1750	0.2201	0.9240	0.9422	0.9330	0.9521
0.0557	16.6667	2000	0.1962	0.9393	0.9529	0.9461	0.9601
0.0557	18.75	2250	0.1945	0.9452	0.9567	0.9509	0.9627
0.0388	20.8333	2500	0.1994	0.9444	0.9552	0.9498	0.9606

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1