test

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

• Loss: 0.6509
• Precision: 0.8926
• Recall: 0.9165
• F1: 0.9044
• Accuracy: 0.8601

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	1.33	100	0.7445	0.7475	0.7869	0.7667	0.7630
No log	2.67	200	0.5447	0.8075	0.8793	0.8419	0.8194
No log	4.0	300	0.5183	0.8425	0.8957	0.8683	0.8418
No log	5.33	400	0.5603	0.8281	0.8952	0.8603	0.8307
0.5735	6.67	500	0.5571	0.8535	0.9001	0.8762	0.8376
0.5735	8.0	600	0.5647	0.8824	0.9096	0.8958	0.8536
0.5735	9.33	700	0.5896	0.8802	0.9121	0.8958	0.8547
0.5735	10.67	800	0.6298	0.8935	0.9165	0.9049	0.8587
0.5735	12.0	900	0.6280	0.8965	0.9210	0.9086	0.8615
0.1395	13.33	1000	0.6509	0.8926	0.9165	0.9044	0.8601

Framework versions

• Transformers 4.34.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3