metadata

license: mit
tags:
  - generated_from_trainer
datasets:
  - funsd-layoutlmv3
model-index:
  - name: lilt-en-funsd
    results: []

lilt-en-funsd

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

Loss: 1.4801
Answer: {'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817}
Header: {'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119}
Question: {'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077}
Overall Precision: 0.8720
Overall Recall: 0.8932
Overall F1: 0.8825
Overall Accuracy: 0.8040

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: 5e-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: 2500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Answer	Header	Question	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.0015	2.67	200	1.4801	{'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817}	{'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119}	{'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077}	0.8720	0.8932	0.8825	0.8040
0.0011	5.33	400	1.4801	{'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817}	{'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119}	{'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077}	0.8720	0.8932	0.8825	0.8040
0.0011	8.0	600	1.4801	{'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817}	{'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119}	{'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077}	0.8720	0.8932	0.8825	0.8040
0.0008	10.67	800	1.4801	{'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817}	{'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119}	{'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077}	0.8720	0.8932	0.8825	0.8040
0.0011	13.33	1000	1.4801	{'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817}	{'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119}	{'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077}	0.8720	0.8932	0.8825	0.8040
0.0011	16.0	1200	1.4801	{'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817}	{'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119}	{'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077}	0.8720	0.8932	0.8825	0.8040
0.0017	18.67	1400	1.4801	{'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817}	{'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119}	{'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077}	0.8720	0.8932	0.8825	0.8040
0.0008	21.33	1600	1.4801	{'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817}	{'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119}	{'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077}	0.8720	0.8932	0.8825	0.8040
0.0008	24.0	1800	1.4801	{'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817}	{'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119}	{'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077}	0.8720	0.8932	0.8825	0.8040
0.0009	26.67	2000	1.4801	{'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817}	{'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119}	{'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077}	0.8720	0.8932	0.8825	0.8040
0.0012	29.33	2200	1.4801	{'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817}	{'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119}	{'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077}	0.8720	0.8932	0.8825	0.8040
0.0009	32.0	2400	1.4801	{'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817}	{'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119}	{'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077}	0.8720	0.8932	0.8825	0.8040

Framework versions

Transformers 4.30.0.dev0
Pytorch 1.8.0+cu101
Datasets 2.12.0
Tokenizers 0.13.3