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: 0.3961
• Precision: 0.8673
• Recall: 0.8809
• F1: 0.8740
• Accuracy: 0.8943

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	0.6667	100	1.5629	0.4996	0.5327	0.5156	0.6029
No log	1.3333	200	0.9930	0.7471	0.7527	0.7499	0.7887
No log	2.0	300	0.7318	0.8310	0.8172	0.8240	0.8335
No log	2.6667	400	0.5813	0.8463	0.8337	0.84	0.8435
1.1111	3.3333	500	0.5164	0.8400	0.8379	0.8389	0.8509
1.1111	4.0	600	0.4977	0.8564	0.8536	0.8550	0.8605
1.1111	4.6667	700	0.4964	0.8596	0.8610	0.8603	0.8651
1.1111	5.3333	800	0.4481	0.8776	0.8776	0.8776	0.8820
1.1111	6.0	900	0.4096	0.8697	0.8776	0.8736	0.8898
0.3648	6.6667	1000	0.3961	0.8673	0.8809	0.8740	0.8943

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0