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: 1.6381
Answer: {'precision': 0.8744075829383886, 'recall': 0.9033047735618115, 'f1': 0.8886213124623721, 'number': 817}
Header: {'precision': 0.6261682242990654, 'recall': 0.5630252100840336, 'f1': 0.5929203539823009, 'number': 119}
Question: {'precision': 0.8998194945848376, 'recall': 0.9257195914577531, 'f1': 0.9125858123569794, 'number': 1077}
Overall Precision: 0.8752
Overall Recall: 0.8952
Overall F1: 0.8851
Overall Accuracy: 0.8174

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
0.4236	10.53	200	0.9243	{'precision': 0.8401360544217688, 'recall': 0.9069767441860465, 'f1': 0.872277810476751, 'number': 817}	{'precision': 0.5333333333333333, 'recall': 0.40336134453781514, 'f1': 0.45933014354066987, 'number': 119}	{'precision': 0.8789571694599627, 'recall': 0.8765088207985144, 'f1': 0.8777312877731288, 'number': 1077}	0.8470	0.8609	0.8539	0.8079
0.0472	21.05	400	1.2753	{'precision': 0.8249721293199554, 'recall': 0.9057527539779682, 'f1': 0.8634772462077013, 'number': 817}	{'precision': 0.5, 'recall': 0.5798319327731093, 'f1': 0.5369649805447471, 'number': 119}	{'precision': 0.8778195488721805, 'recall': 0.8672237697307336, 'f1': 0.8724894908921065, 'number': 1077}	0.8304	0.8659	0.8478	0.7910
0.014	31.58	600	1.3381	{'precision': 0.8335233751425314, 'recall': 0.8947368421052632, 'f1': 0.8630460448642266, 'number': 817}	{'precision': 0.6292134831460674, 'recall': 0.47058823529411764, 'f1': 0.5384615384615384, 'number': 119}	{'precision': 0.8754416961130742, 'recall': 0.9201485608170845, 'f1': 0.8972385694884564, 'number': 1077}	0.8475	0.8833	0.8650	0.8046
0.0063	42.11	800	1.4519	{'precision': 0.8738095238095238, 'recall': 0.8984088127294981, 'f1': 0.8859384429692213, 'number': 817}	{'precision': 0.5833333333333334, 'recall': 0.6470588235294118, 'f1': 0.6135458167330677, 'number': 119}	{'precision': 0.9008341056533827, 'recall': 0.9025069637883009, 'f1': 0.901669758812616, 'number': 1077}	0.8693	0.8857	0.8775	0.8092
0.0036	52.63	1000	1.6211	{'precision': 0.8363228699551569, 'recall': 0.9130966952264382, 'f1': 0.8730251609128145, 'number': 817}	{'precision': 0.584070796460177, 'recall': 0.5546218487394958, 'f1': 0.5689655172413793, 'number': 119}	{'precision': 0.8984302862419206, 'recall': 0.903435468895079, 'f1': 0.900925925925926, 'number': 1077}	0.8549	0.8867	0.8705	0.8039
0.0029	63.16	1200	1.6274	{'precision': 0.871007371007371, 'recall': 0.8678090575275398, 'f1': 0.8694052728387494, 'number': 817}	{'precision': 0.5714285714285714, 'recall': 0.5042016806722689, 'f1': 0.5357142857142857, 'number': 119}	{'precision': 0.8844404003639672, 'recall': 0.9025069637883009, 'f1': 0.8933823529411765, 'number': 1077}	0.8627	0.8649	0.8638	0.8008
0.0018	73.68	1400	1.6562	{'precision': 0.8401360544217688, 'recall': 0.9069767441860465, 'f1': 0.872277810476751, 'number': 817}	{'precision': 0.6132075471698113, 'recall': 0.5462184873949579, 'f1': 0.5777777777777778, 'number': 119}	{'precision': 0.8892921960072595, 'recall': 0.9099350046425255, 'f1': 0.8994951812758146, 'number': 1077}	0.8545	0.8872	0.8706	0.8096
0.001	84.21	1600	1.6388	{'precision': 0.8534090909090909, 'recall': 0.9192166462668299, 'f1': 0.8850913376546846, 'number': 817}	{'precision': 0.63, 'recall': 0.5294117647058824, 'f1': 0.5753424657534247, 'number': 119}	{'precision': 0.9009174311926605, 'recall': 0.9117920148560817, 'f1': 0.9063221042916475, 'number': 1077}	0.8676	0.8922	0.8797	0.8103
0.0007	94.74	1800	1.6278	{'precision': 0.8545454545454545, 'recall': 0.9204406364749081, 'f1': 0.8862698880377136, 'number': 817}	{'precision': 0.6078431372549019, 'recall': 0.5210084033613446, 'f1': 0.5610859728506787, 'number': 119}	{'precision': 0.8909740840035746, 'recall': 0.9257195914577531, 'f1': 0.9080145719489982, 'number': 1077}	0.8620	0.8997	0.8804	0.8216
0.0002	105.26	2000	1.6381	{'precision': 0.8744075829383886, 'recall': 0.9033047735618115, 'f1': 0.8886213124623721, 'number': 817}	{'precision': 0.6261682242990654, 'recall': 0.5630252100840336, 'f1': 0.5929203539823009, 'number': 119}	{'precision': 0.8998194945848376, 'recall': 0.9257195914577531, 'f1': 0.9125858123569794, 'number': 1077}	0.8752	0.8952	0.8851	0.8174
0.0002	115.79	2200	1.6545	{'precision': 0.8757467144563919, 'recall': 0.8971848225214198, 'f1': 0.8863361547762998, 'number': 817}	{'precision': 0.625, 'recall': 0.5462184873949579, 'f1': 0.5829596412556054, 'number': 119}	{'precision': 0.8902765388046388, 'recall': 0.9266480965645311, 'f1': 0.908098271155596, 'number': 1077}	0.8710	0.8922	0.8815	0.8155
0.0002	126.32	2400	1.6477	{'precision': 0.8658823529411764, 'recall': 0.9008567931456548, 'f1': 0.8830233953209357, 'number': 817}	{'precision': 0.6116504854368932, 'recall': 0.5294117647058824, 'f1': 0.5675675675675675, 'number': 119}	{'precision': 0.8930817610062893, 'recall': 0.9229340761374187, 'f1': 0.9077625570776255, 'number': 1077}	0.8679	0.8907	0.8791	0.8167

Framework versions

Transformers 4.36.2
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.0

Oumay/lilT_fintuning

lilT_fintuning

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Oumay/
lilT_fintuning