metadata

license: mit
base_model: SCUT-DLVCLab/lilt-roberta-en-base
tags:
  - generated_from_trainer
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 an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.6470
Answer: {'precision': 0.8841607565011821, 'recall': 0.9155446756425949, 'f1': 0.899579073962718, 'number': 817}
Header: {'precision': 0.6574074074074074, 'recall': 0.5966386554621849, 'f1': 0.6255506607929515, 'number': 119}
Question: {'precision': 0.900804289544236, 'recall': 0.935933147632312, 'f1': 0.9180327868852459, 'number': 1077}
Overall Precision: 0.8813
Overall Recall: 0.9076
Overall F1: 0.8943
Overall Accuracy: 0.8114

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: 8
eval_batch_size: 8
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
0.4017	10.53	200	1.0898	{'precision': 0.8257491675915649, 'recall': 0.9106487148102815, 'f1': 0.8661233993015134, 'number': 817}	{'precision': 0.49166666666666664, 'recall': 0.4957983193277311, 'f1': 0.4937238493723849, 'number': 119}	{'precision': 0.8689591078066915, 'recall': 0.8681522748375116, 'f1': 0.8685555039479796, 'number': 1077}	0.8288	0.8634	0.8457	0.7811
0.0453	21.05	400	1.1928	{'precision': 0.8400900900900901, 'recall': 0.9130966952264382, 'f1': 0.8750733137829912, 'number': 817}	{'precision': 0.5575221238938053, 'recall': 0.5294117647058824, 'f1': 0.543103448275862, 'number': 119}	{'precision': 0.8885869565217391, 'recall': 0.9108635097493036, 'f1': 0.8995873452544704, 'number': 1077}	0.8504	0.8892	0.8694	0.8044
0.0148	31.58	600	1.3654	{'precision': 0.8174946004319654, 'recall': 0.9265605875152999, 'f1': 0.8686173264486519, 'number': 817}	{'precision': 0.5391304347826087, 'recall': 0.5210084033613446, 'f1': 0.52991452991453, 'number': 119}	{'precision': 0.8866171003717472, 'recall': 0.8857938718662952, 'f1': 0.8862052949372968, 'number': 1077}	0.8375	0.8808	0.8586	0.8086
0.0073	42.11	800	1.4733	{'precision': 0.8653395784543325, 'recall': 0.9045287637698899, 'f1': 0.8845002992220227, 'number': 817}	{'precision': 0.6597938144329897, 'recall': 0.5378151260504201, 'f1': 0.5925925925925926, 'number': 119}	{'precision': 0.8881057268722466, 'recall': 0.935933147632312, 'f1': 0.9113924050632911, 'number': 1077}	0.8682	0.8997	0.8836	0.8111
0.008	52.63	1000	1.6415	{'precision': 0.864963503649635, 'recall': 0.8702570379436965, 'f1': 0.8676021964612569, 'number': 817}	{'precision': 0.5636363636363636, 'recall': 0.5210084033613446, 'f1': 0.5414847161572053, 'number': 119}	{'precision': 0.8630490956072352, 'recall': 0.9303621169916435, 'f1': 0.8954423592493298, 'number': 1077}	0.8481	0.8818	0.8646	0.7959
0.0026	63.16	1200	1.5876	{'precision': 0.8830049261083743, 'recall': 0.8776009791921665, 'f1': 0.8802946593001842, 'number': 817}	{'precision': 0.5564516129032258, 'recall': 0.5798319327731093, 'f1': 0.5679012345679013, 'number': 119}	{'precision': 0.8905693950177936, 'recall': 0.9294336118848654, 'f1': 0.9095865515674693, 'number': 1077}	0.8675	0.8877	0.8775	0.8032
0.0013	73.68	1400	1.5427	{'precision': 0.8733572281959379, 'recall': 0.8947368421052632, 'f1': 0.8839177750906893, 'number': 817}	{'precision': 0.6271186440677966, 'recall': 0.6218487394957983, 'f1': 0.6244725738396625, 'number': 119}	{'precision': 0.9108455882352942, 'recall': 0.9201485608170845, 'f1': 0.9154734411085451, 'number': 1077}	0.8791	0.8922	0.8856	0.8115
0.0012	84.21	1600	1.5540	{'precision': 0.8790035587188612, 'recall': 0.9069767441860465, 'f1': 0.8927710843373493, 'number': 817}	{'precision': 0.6216216216216216, 'recall': 0.5798319327731093, 'f1': 0.6000000000000001, 'number': 119}	{'precision': 0.9066543438077634, 'recall': 0.9108635097493036, 'f1': 0.9087540528022232, 'number': 1077}	0.8797	0.8897	0.8847	0.8096
0.0007	94.74	1800	1.6470	{'precision': 0.8841607565011821, 'recall': 0.9155446756425949, 'f1': 0.899579073962718, 'number': 817}	{'precision': 0.6574074074074074, 'recall': 0.5966386554621849, 'f1': 0.6255506607929515, 'number': 119}	{'precision': 0.900804289544236, 'recall': 0.935933147632312, 'f1': 0.9180327868852459, 'number': 1077}	0.8813	0.9076	0.8943	0.8114
0.0004	105.26	2000	1.6446	{'precision': 0.877906976744186, 'recall': 0.9241126070991432, 'f1': 0.9004174120453191, 'number': 817}	{'precision': 0.6739130434782609, 'recall': 0.5210084033613446, 'f1': 0.5876777251184835, 'number': 119}	{'precision': 0.8982142857142857, 'recall': 0.9340761374187558, 'f1': 0.915794264906691, 'number': 1077}	0.8798	0.9056	0.8925	0.8196
0.0003	115.79	2200	1.6375	{'precision': 0.8638443935926774, 'recall': 0.9241126070991432, 'f1': 0.892962743938498, 'number': 817}	{'precision': 0.7375, 'recall': 0.4957983193277311, 'f1': 0.592964824120603, 'number': 119}	{'precision': 0.8999098286744815, 'recall': 0.9266480965645311, 'f1': 0.9130832570905763, 'number': 1077}	0.8783	0.9001	0.8891	0.8225
0.0003	126.32	2400	1.6489	{'precision': 0.8751458576429405, 'recall': 0.9179926560587516, 'f1': 0.8960573476702508, 'number': 817}	{'precision': 0.6559139784946236, 'recall': 0.5126050420168067, 'f1': 0.5754716981132076, 'number': 119}	{'precision': 0.9026149684400361, 'recall': 0.9294336118848654, 'f1': 0.9158279963403477, 'number': 1077}	0.8800	0.9001	0.8900	0.8166

Framework versions

Transformers 4.38.0
Pytorch 2.1.0+cu121
Datasets 2.17.1
Tokenizers 0.15.2