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: 1.7584
• Answer: {'precision': 0.8773364485981309, 'recall': 0.9192166462668299, 'f1': 0.8977884040645547, 'number': 817}
• Header: {'precision': 0.6428571428571429, 'recall': 0.5294117647058824, 'f1': 0.5806451612903226, 'number': 119}
• Question: {'precision': 0.9097605893186004, 'recall': 0.9173630454967502, 'f1': 0.9135460009246417, 'number': 1077}
• Overall Precision: 0.8833
• Overall Recall: 0.8952
• Overall F1: 0.8892
• Overall Accuracy: 0.8076

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
0.3859	10.5263	200	1.1901	{'precision': 0.8349514563106796, 'recall': 0.8421052631578947, 'f1': 0.8385131017672149, 'number': 817}	{'precision': 0.42953020134228187, 'recall': 0.5378151260504201, 'f1': 0.47761194029850745, 'number': 119}	{'precision': 0.8739946380697051, 'recall': 0.9080779944289693, 'f1': 0.8907103825136613, 'number': 1077}	0.8270	0.8594	0.8429	0.7738
0.0461	21.0526	400	1.3985	{'precision': 0.8586448598130841, 'recall': 0.8996328029375765, 'f1': 0.8786610878661089, 'number': 817}	{'precision': 0.5, 'recall': 0.6050420168067226, 'f1': 0.5475285171102661, 'number': 119}	{'precision': 0.8864468864468864, 'recall': 0.8987929433611885, 'f1': 0.8925772245274319, 'number': 1077}	0.8485	0.8818	0.8648	0.7846
0.0139	31.5789	600	1.4340	{'precision': 0.8617021276595744, 'recall': 0.8922888616891065, 'f1': 0.8767288033674082, 'number': 817}	{'precision': 0.5263157894736842, 'recall': 0.5882352941176471, 'f1': 0.5555555555555555, 'number': 119}	{'precision': 0.8739946380697051, 'recall': 0.9080779944289693, 'f1': 0.8907103825136613, 'number': 1077}	0.8470	0.8828	0.8645	0.8029
0.0074	42.1053	800	1.5489	{'precision': 0.8450057405281286, 'recall': 0.9008567931456548, 'f1': 0.8720379146919431, 'number': 817}	{'precision': 0.6344086021505376, 'recall': 0.4957983193277311, 'f1': 0.5566037735849056, 'number': 119}	{'precision': 0.8733738074588031, 'recall': 0.9350046425255338, 'f1': 0.9031390134529148, 'number': 1077}	0.8512	0.8952	0.8726	0.7957
0.0026	52.6316	1000	1.6408	{'precision': 0.8661800486618005, 'recall': 0.8714810281517748, 'f1': 0.8688224527150702, 'number': 817}	{'precision': 0.5932203389830508, 'recall': 0.5882352941176471, 'f1': 0.5907172995780592, 'number': 119}	{'precision': 0.8859964093357271, 'recall': 0.9164345403899722, 'f1': 0.9009584664536742, 'number': 1077}	0.8612	0.8788	0.8699	0.7988
0.005	63.1579	1200	1.5299	{'precision': 0.8518518518518519, 'recall': 0.9008567931456548, 'f1': 0.875669244497323, 'number': 817}	{'precision': 0.6407766990291263, 'recall': 0.5546218487394958, 'f1': 0.5945945945945947, 'number': 119}	{'precision': 0.883128295254833, 'recall': 0.9331476323119777, 'f1': 0.90744920993228, 'number': 1077}	0.8584	0.8977	0.8776	0.8010
0.004	73.6842	1400	1.5962	{'precision': 0.8402699662542182, 'recall': 0.9143206854345165, 'f1': 0.8757327080890973, 'number': 817}	{'precision': 0.5625, 'recall': 0.5294117647058824, 'f1': 0.5454545454545455, 'number': 119}	{'precision': 0.8923076923076924, 'recall': 0.9155060352831941, 'f1': 0.9037580201649862, 'number': 1077}	0.8528	0.8922	0.8721	0.8084
0.0007	84.2105	1600	1.6587	{'precision': 0.8458904109589042, 'recall': 0.9069767441860465, 'f1': 0.8753691671588896, 'number': 817}	{'precision': 0.6355140186915887, 'recall': 0.5714285714285714, 'f1': 0.6017699115044248, 'number': 119}	{'precision': 0.8946894689468947, 'recall': 0.9229340761374187, 'f1': 0.9085923217550275, 'number': 1077}	0.8610	0.8957	0.8780	0.8051
0.0007	94.7368	1800	1.5919	{'precision': 0.8495475113122172, 'recall': 0.9192166462668299, 'f1': 0.8830099941211051, 'number': 817}	{'precision': 0.6055045871559633, 'recall': 0.5546218487394958, 'f1': 0.5789473684210525, 'number': 119}	{'precision': 0.9030797101449275, 'recall': 0.9257195914577531, 'f1': 0.9142595139844107, 'number': 1077}	0.8650	0.9011	0.8827	0.8102
0.0004	105.2632	2000	1.7501	{'precision': 0.8614318706697459, 'recall': 0.9130966952264382, 'f1': 0.8865121806298276, 'number': 817}	{'precision': 0.6052631578947368, 'recall': 0.5798319327731093, 'f1': 0.5922746781115881, 'number': 119}	{'precision': 0.9106976744186046, 'recall': 0.9090064995357474, 'f1': 0.9098513011152416, 'number': 1077}	0.8730	0.8912	0.8820	0.8070
0.0003	115.7895	2200	1.7584	{'precision': 0.8773364485981309, 'recall': 0.9192166462668299, 'f1': 0.8977884040645547, 'number': 817}	{'precision': 0.6428571428571429, 'recall': 0.5294117647058824, 'f1': 0.5806451612903226, 'number': 119}	{'precision': 0.9097605893186004, 'recall': 0.9173630454967502, 'f1': 0.9135460009246417, 'number': 1077}	0.8833	0.8952	0.8892	0.8076
0.0001	126.3158	2400	1.7527	{'precision': 0.8525714285714285, 'recall': 0.9130966952264382, 'f1': 0.8817966903073285, 'number': 817}	{'precision': 0.6237623762376238, 'recall': 0.5294117647058824, 'f1': 0.5727272727272728, 'number': 119}	{'precision': 0.8963963963963963, 'recall': 0.9238625812441968, 'f1': 0.9099222679469592, 'number': 1077}	0.8648	0.8962	0.8802	0.8057

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1