layoutlmv3-finetuned-cord_vimal

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

• Loss: 1.8321
• Precision: 0.7179
• Recall: 0.7368
• F1: 0.7273
• Accuracy: 0.7333

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	125.0	250	1.2027	0.7564	0.7763	0.7662	0.7481
0.8449	250.0	500	1.3990	0.7089	0.7368	0.7226	0.7333
0.8449	375.0	750	1.5343	0.7179	0.7368	0.7273	0.7333
0.0296	500.0	1000	1.6144	0.75	0.75	0.75	0.7407
0.0296	625.0	1250	1.6898	0.7179	0.7368	0.7273	0.7333
0.0134	750.0	1500	1.7402	0.7179	0.7368	0.7273	0.7333
0.0134	875.0	1750	1.7888	0.7179	0.7368	0.7273	0.7333
0.0089	1000.0	2000	1.8041	0.7179	0.7368	0.7273	0.7333
0.0089	1125.0	2250	1.8209	0.7179	0.7368	0.7273	0.7333
0.0073	1250.0	2500	1.8321	0.7179	0.7368	0.7273	0.7333

Framework versions

• Transformers 4.26.0
• Pytorch 1.13.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2