test

This model is a fine-tuned version of microsoft/layoutlmv3-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4675
• Precision: 0.8
• Recall: 0.8649
• F1: 0.8312
• Accuracy: 0.8318

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: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	3.85	50	1.1808	0.7013	0.7297	0.7152	0.7196
No log	7.69	100	0.7117	0.7317	0.8108	0.7692	0.8037
No log	11.54	150	0.5580	0.7778	0.8514	0.8129	0.8224
No log	15.38	200	0.5009	0.8228	0.8784	0.8497	0.8411
No log	19.23	250	0.4659	0.8228	0.8784	0.8497	0.8505
No log	23.08	300	0.4734	0.7901	0.8649	0.8258	0.8318
No log	26.92	350	0.4496	0.8205	0.8649	0.8421	0.8318
No log	30.77	400	0.4619	0.8	0.8649	0.8312	0.8318
No log	34.62	450	0.4560	0.8125	0.8784	0.8442	0.8411
0.3885	38.46	500	0.4675	0.8	0.8649	0.8312	0.8318

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2