This model is a fine-tuned version of distilbert-base-uncased on the nlpaueb/finer-139 dataset. It achieves the following results on the evaluation set:

Loss: 0.0027
Accuracy: 0.9992
Precision: 0.9994
Recall: 0.9992
F1: 0.9993
Classification Report: {'DebtInstrumentBasisSpreadOnVariableRate1': {'precision': 0.4418954494170741, 'recall': 0.8729569093610698, 'f1-score': 0.5867665418227216, 'support': 1346}, 'DebtInstrumentFaceAmount': {'precision': 0.6829363529871144, 'recall': 0.9500271591526345, 'f1-score': 0.7946388005452066, 'support': 1841}, 'DebtInstrumentInterestRateStatedPercentage': {'precision': 0.9999559125095354, 'recall': 0.9992993145998219, 'f1-score': 0.9996275057343241, 'support': 5174933}, 'LineOfCreditFacilityMaximumBorrowingCapacity': {'precision': 0.7538389948813402, 'recall': 0.9619952494061758, 'f1-score': 0.8452908948604226, 'support': 1684}, 'micro avg': {'precision': 0.9994104930309579, 'recall': 0.9992368437106887, 'f1-score': 0.9993236608271996, 'support': 5179804}, 'macro avg': {'precision': 0.719656677448766, 'recall': 0.9460696581299255, 'f1-score': 0.8065809357406687, 'support': 5179804}, 'weighted avg': {'precision': 0.9996182079783044, 'recall': 0.9992368437106887, 'f1-score': 0.9993971885415519, 'support': 5179804}}

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: 192
eval_batch_size: 192
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Classification Report
0.0092	1.3514	500	0.0027	0.9991	0.9993	0.9991	0.9992	{'DebtInstrumentBasisSpreadOnVariableRate1': {'precision': 0.4453493356193742, 'recall': 0.7719167904903418, 'f1-score': 0.5648273987496603, 'support': 1346}, 'DebtInstrumentFaceAmount': {'precision': 0.581496325985304, 'recall': 0.9456816947311244, 'f1-score': 0.7201654601861428, 'support': 1841}, 'DebtInstrumentInterestRateStatedPercentage': {'precision': 0.9999340567367329, 'recall': 0.999195738379608, 'f1-score': 0.9995647612203504, 'support': 5174933}, 'LineOfCreditFacilityMaximumBorrowingCapacity': {'precision': 0.7285254937988057, 'recall': 0.9418052256532067, 'f1-score': 0.8215488215488216, 'support': 1684}, 'micro avg': {'precision': 0.999328198885571, 'recall': 0.9990990006571677, 'f1-score': 0.9992135866280765, 'support': 5179804}, 'macro avg': {'precision': 0.6888263030350542, 'recall': 0.9146498623135703, 'f1-score': 0.7765266104262438, 'support': 5179804}, 'weighted avg': {'precision': 0.9995529869285075, 'recall': 0.9990990006571677, 'f1-score': 0.9992946140399751, 'support': 5179804}}
0.0061	2.7027	1000	0.0022	0.9993	0.9995	0.9993	0.9994	{'DebtInstrumentBasisSpreadOnVariableRate1': {'precision': 0.4838709677419355, 'recall': 0.8246656760772659, 'f1-score': 0.6098901098901099, 'support': 1346}, 'DebtInstrumentFaceAmount': {'precision': 0.709504132231405, 'recall': 0.9326453014665942, 'f1-score': 0.8059141046702653, 'support': 1841}, 'DebtInstrumentInterestRateStatedPercentage': {'precision': 0.9999332961854311, 'recall': 0.9993893640748586, 'f1-score': 0.9996612561395511, 'support': 5174933}, 'LineOfCreditFacilityMaximumBorrowingCapacity': {'precision': 0.7698986975397974, 'recall': 0.9477434679334917, 'f1-score': 0.849614053766303, 'support': 1684}, 'micro avg': {'precision': 0.9994769164524161, 'recall': 0.999303448547474, 'f1-score': 0.9993901749725762, 'support': 5179804}, 'macro avg': {'precision': 0.7408017734246423, 'recall': 0.9261109523880526, 'f1-score': 0.8162698811165573, 'support': 5179804}, 'weighted avg': {'precision': 0.9996211843277153, 'recall': 0.999303448547474, 'f1-score': 0.9994423289451044, 'support': 5179804}}
0.0041	4.0541	1500	0.0027	0.9992	0.9994	0.9992	0.9993	{'DebtInstrumentBasisSpreadOnVariableRate1': {'precision': 0.4418954494170741, 'recall': 0.8729569093610698, 'f1-score': 0.5867665418227216, 'support': 1346}, 'DebtInstrumentFaceAmount': {'precision': 0.6829363529871144, 'recall': 0.9500271591526345, 'f1-score': 0.7946388005452066, 'support': 1841}, 'DebtInstrumentInterestRateStatedPercentage': {'precision': 0.9999559125095354, 'recall': 0.9992993145998219, 'f1-score': 0.9996275057343241, 'support': 5174933}, 'LineOfCreditFacilityMaximumBorrowingCapacity': {'precision': 0.7538389948813402, 'recall': 0.9619952494061758, 'f1-score': 0.8452908948604226, 'support': 1684}, 'micro avg': {'precision': 0.9994104930309579, 'recall': 0.9992368437106887, 'f1-score': 0.9993236608271996, 'support': 5179804}, 'macro avg': {'precision': 0.719656677448766, 'recall': 0.9460696581299255, 'f1-score': 0.8065809357406687, 'support': 5179804}, 'weighted avg': {'precision': 0.9996182079783044, 'recall': 0.9992368437106887, 'f1-score': 0.9993971885415519, 'support': 5179804}}

Framework versions

Transformers 4.46.3
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.20.3

martindevoto/finer_ner_finetuning_2330

finer_ner_finetuning_2330

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

martindevoto/
finer_ner_finetuning_2330