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: 1.6046
Answer: {'precision': 0.8879518072289156, 'recall': 0.9020807833537332, 'f1': 0.8949605343047966, 'number': 817}
Header: {'precision': 0.6761904761904762, 'recall': 0.5966386554621849, 'f1': 0.6339285714285715, 'number': 119}
Question: {'precision': 0.8968609865470852, 'recall': 0.9285051067780873, 'f1': 0.9124087591240877, 'number': 1077}
Overall Precision: 0.8820
Overall Recall: 0.8982
Overall F1: 0.8900
Overall Accuracy: 0.8187

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
0.3984	10.5263	200	0.9319	{'precision': 0.837129840546697, 'recall': 0.8996328029375765, 'f1': 0.8672566371681416, 'number': 817}	{'precision': 0.5238095238095238, 'recall': 0.46218487394957986, 'f1': 0.4910714285714286, 'number': 119}	{'precision': 0.8606060606060606, 'recall': 0.9229340761374187, 'f1': 0.8906810035842293, 'number': 1077}	0.8344	0.8862	0.8596	0.7926
0.0543	21.0526	400	1.1018	{'precision': 0.8492520138089759, 'recall': 0.9033047735618115, 'f1': 0.8754448398576511, 'number': 817}	{'precision': 0.5688073394495413, 'recall': 0.5210084033613446, 'f1': 0.543859649122807, 'number': 119}	{'precision': 0.8731277533039647, 'recall': 0.9201485608170845, 'f1': 0.8960216998191681, 'number': 1077}	0.8476	0.8897	0.8682	0.8133
0.0134	31.5789	600	1.5231	{'precision': 0.838963963963964, 'recall': 0.9118727050183598, 'f1': 0.873900293255132, 'number': 817}	{'precision': 0.5727272727272728, 'recall': 0.5294117647058824, 'f1': 0.5502183406113538, 'number': 119}	{'precision': 0.9149338374291115, 'recall': 0.8987929433611885, 'f1': 0.9067915690866512, 'number': 1077}	0.8638	0.8823	0.8729	0.8046
0.0101	42.1053	800	1.5678	{'precision': 0.8509895227008148, 'recall': 0.8947368421052632, 'f1': 0.8723150357995225, 'number': 817}	{'precision': 0.5700934579439252, 'recall': 0.5126050420168067, 'f1': 0.5398230088495575, 'number': 119}	{'precision': 0.8781770376862401, 'recall': 0.9303621169916435, 'f1': 0.9035166816952209, 'number': 1077}	0.8514	0.8912	0.8709	0.8052
0.0041	52.6316	1000	1.6538	{'precision': 0.8399558498896247, 'recall': 0.9314565483476133, 'f1': 0.8833430063842136, 'number': 817}	{'precision': 0.6705882352941176, 'recall': 0.4789915966386555, 'f1': 0.5588235294117647, 'number': 119}	{'precision': 0.9063386944181646, 'recall': 0.8895078922934077, 'f1': 0.8978444236176195, 'number': 1077}	0.8672	0.8823	0.8747	0.7979
0.0033	63.1579	1200	1.4464	{'precision': 0.875, 'recall': 0.9167686658506732, 'f1': 0.895397489539749, 'number': 817}	{'precision': 0.6049382716049383, 'recall': 0.4117647058823529, 'f1': 0.49000000000000005, 'number': 119}	{'precision': 0.8777292576419214, 'recall': 0.9331476323119777, 'f1': 0.9045904590459046, 'number': 1077}	0.8660	0.8957	0.8806	0.8152
0.0015	73.6842	1400	1.5128	{'precision': 0.8679906542056075, 'recall': 0.9094247246022031, 'f1': 0.8882247459653317, 'number': 817}	{'precision': 0.6511627906976745, 'recall': 0.47058823529411764, 'f1': 0.5463414634146342, 'number': 119}	{'precision': 0.8906810035842294, 'recall': 0.9229340761374187, 'f1': 0.9065207478340173, 'number': 1077}	0.8712	0.8907	0.8809	0.8213
0.0014	84.2105	1600	1.6089	{'precision': 0.8555176336746303, 'recall': 0.9204406364749081, 'f1': 0.8867924528301887, 'number': 817}	{'precision': 0.6074766355140186, 'recall': 0.5462184873949579, 'f1': 0.575221238938053, 'number': 119}	{'precision': 0.8891820580474934, 'recall': 0.9387186629526463, 'f1': 0.913279132791328, 'number': 1077}	0.8610	0.9081	0.8839	0.8172
0.0005	94.7368	1800	1.6500	{'precision': 0.865967365967366, 'recall': 0.9094247246022031, 'f1': 0.8871641791044775, 'number': 817}	{'precision': 0.6513761467889908, 'recall': 0.5966386554621849, 'f1': 0.6228070175438596, 'number': 119}	{'precision': 0.9027522935779817, 'recall': 0.9136490250696379, 'f1': 0.9081679741578219, 'number': 1077}	0.8741	0.8932	0.8835	0.8135
0.0005	105.2632	2000	1.6204	{'precision': 0.8909090909090909, 'recall': 0.8996328029375765, 'f1': 0.8952496954933008, 'number': 817}	{'precision': 0.6403508771929824, 'recall': 0.6134453781512605, 'f1': 0.6266094420600858, 'number': 119}	{'precision': 0.8925399644760214, 'recall': 0.9331476323119777, 'f1': 0.9123921924648207, 'number': 1077}	0.8780	0.9006	0.8892	0.8177
0.0004	115.7895	2200	1.6046	{'precision': 0.8879518072289156, 'recall': 0.9020807833537332, 'f1': 0.8949605343047966, 'number': 817}	{'precision': 0.6761904761904762, 'recall': 0.5966386554621849, 'f1': 0.6339285714285715, 'number': 119}	{'precision': 0.8968609865470852, 'recall': 0.9285051067780873, 'f1': 0.9124087591240877, 'number': 1077}	0.8820	0.8982	0.8900	0.8187
0.0002	126.3158	2400	1.6270	{'precision': 0.8790035587188612, 'recall': 0.9069767441860465, 'f1': 0.8927710843373493, 'number': 817}	{'precision': 0.6574074074074074, 'recall': 0.5966386554621849, 'f1': 0.6255506607929515, 'number': 119}	{'precision': 0.8972046889089269, 'recall': 0.9238625812441968, 'f1': 0.9103385178408051, 'number': 1077}	0.8772	0.8977	0.8873	0.8193

Framework versions

Transformers 4.41.1
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1