model-aya-1

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: 0.1465
• Precision: 0.9806
• Recall: 0.9775
• F1: 0.9791
• Accuracy: 0.9898

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	1.35	100	0.3124	0.9513	0.9421	0.9467	0.9676
No log	2.7	200	0.1877	0.9706	0.9550	0.9627	0.9778
No log	4.05	300	0.1754	0.9674	0.9550	0.9612	0.9778
No log	5.41	400	0.1325	0.9805	0.9678	0.9741	0.9863
0.4234	6.76	500	0.1303	0.9838	0.9775	0.9806	0.9898
0.4234	8.11	600	0.1322	0.9870	0.9775	0.9822	0.9915
0.4234	9.46	700	0.1478	0.9806	0.9775	0.9791	0.9898
0.4234	10.81	800	0.1481	0.9806	0.9775	0.9791	0.9898
0.4234	12.16	900	0.1425	0.9806	0.9775	0.9791	0.9898
0.0307	13.51	1000	0.1465	0.9806	0.9775	0.9791	0.9898

Framework versions

• Transformers 4.29.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.13.3