results

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0022
• Accuracy: 0.9994
• Precision: 0.9994
• Recall: 0.9993
• F1: 0.9994
• Classification Report: {'DebtInstrumentBasisSpreadOnVariableRate1': {'precision': 0.7067191945721164, 'recall': 0.9142129105322764, 'f1-score': 0.7971855326502901, 'support': 3532}, 'DebtInstrumentInterestRateStatedPercentage': {'precision': 0.9998381887971357, 'recall': 0.999405789408288, 'f1-score': 0.9996219423427282, 'support': 5174933}, 'LineOfCreditFacilityMaximumBorrowingCapacity': {'precision': 0.5497431106959365, 'recall': 0.87444279346211, 'f1-score': 0.6750788643533123, 'support': 1346}, 'micro avg': {'precision': 0.9993935596849445, 'recall': 0.9993152259802529, 'f1-score': 0.9993543912975653, 'support': 5179811}, 'macro avg': {'precision': 0.7521001646883961, 'recall': 0.9293538311342248, 'f1-score': 0.8239621131154435, 'support': 5179811}, 'weighted avg': {'precision': 0.99952135788135, 'recall': 0.9993152259802529, 'f1-score': 0.9993995712210777, 'support': 5179811}}

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
0.0073	0.7812	500	0.0021	0.9993	0.9993	0.9992	0.9992	{'DebtInstrumentBasisSpreadOnVariableRate1': {'precision': 0.6305549866885112, 'recall': 0.8717440543601359, 'f1-score': 0.7317884729649436, 'support': 3532}, 'DebtInstrumentInterestRateStatedPercentage': {'precision': 0.9997610581181664, 'recall': 0.9993501365138447, 'f1-score': 0.9995555550830959, 'support': 5174933}, 'LineOfCreditFacilityMaximumBorrowingCapacity': {'precision': 0.5428400239664469, 'recall': 0.6731054977711739, 'f1-score': 0.600995024875622, 'support': 1346}, 'micro avg': {'precision': 0.9992657391128399, 'recall': 0.9991783483991984, 'f1-score': 0.9992220418452484, 'support': 5179811}, 'macro avg': {'precision': 0.7243853562577082, 'recall': 0.8480665628817182, 'f1-score': 0.7774463509745537, 'support': 5179811}, 'weighted avg': {'precision': 0.9993905713269965, 'recall': 0.9991783483991984, 'f1-score': 0.9992694025945784, 'support': 5179811}}
0.0051	1.5625	1000	0.0024	0.9991	0.9991	0.9990	0.9991	{'DebtInstrumentBasisSpreadOnVariableRate1': {'precision': 0.5788912579957356, 'recall': 0.9224235560588901, 'f1-score': 0.711353711790393, 'support': 3532}, 'DebtInstrumentInterestRateStatedPercentage': {'precision': 0.9998106929296227, 'recall': 0.9991458826616693, 'f1-score': 0.999478177244797, 'support': 5174933}, 'LineOfCreditFacilityMaximumBorrowingCapacity': {'precision': 0.46706586826347307, 'recall': 0.7533432392273403, 'f1-score': 0.5766278077907308, 'support': 1346}, 'micro avg': {'precision': 0.9991299967505205, 'recall': 0.9990296943266849, 'f1-score': 0.9990798430211421, 'support': 5179811}, 'macro avg': {'precision': 0.681922606396277, 'recall': 0.8916375593159666, 'f1-score': 0.7624865656086403, 'support': 5179811}, 'weighted avg': {'precision': 0.9993852407310411, 'recall': 0.9990296943266849, 'f1-score': 0.9991718316639892, 'support': 5179811}}
0.0038	2.3438	1500	0.0020	0.9994	0.9993	0.9993	0.9993	{'DebtInstrumentBasisSpreadOnVariableRate1': {'precision': 0.6898198393748644, 'recall': 0.8997734994337486, 'f1-score': 0.7809313183437769, 'support': 3532}, 'DebtInstrumentInterestRateStatedPercentage': {'precision': 0.9998283242552695, 'recall': 0.9993663686080574, 'f1-score': 0.9995972930594179, 'support': 5174933}, 'LineOfCreditFacilityMaximumBorrowingCapacity': {'precision': 0.5123626373626373, 'recall': 0.8313521545319466, 'f1-score': 0.6339943342776203, 'support': 1346}, 'micro avg': {'precision': 0.9993470201664963, 'recall': 0.9992547990650624, 'f1-score': 0.9993009074881091, 'support': 5179811}, 'macro avg': {'precision': 0.7340036003309237, 'recall': 0.9101640075245842, 'f1-score': 0.8048409818936051, 'support': 5179811}, 'weighted avg': {'precision': 0.9994902658235708, 'recall': 0.9992547990650624, 'f1-score': 0.999353185734804, 'support': 5179811}}
0.0028	3.125	2000	0.0022	0.9993	0.9993	0.9992	0.9993	{'DebtInstrumentBasisSpreadOnVariableRate1': {'precision': 0.6400077836154894, 'recall': 0.9312004530011325, 'f1-score': 0.7586206896551725, 'support': 3532}, 'DebtInstrumentInterestRateStatedPercentage': {'precision': 0.9998399151782452, 'recall': 0.9993230830234904, 'f1-score': 0.9995814322940401, 'support': 5174933}, 'LineOfCreditFacilityMaximumBorrowingCapacity': {'precision': 0.5529884480160723, 'recall': 0.8179791976225854, 'f1-score': 0.6598741384477075, 'support': 1346}, 'micro avg': {'precision': 0.9993111155217567, 'recall': 0.9992295085670114, 'f1-score': 0.9992703103782447, 'support': 5179811}, 'macro avg': {'precision': 0.7309453822699356, 'recall': 0.9161675778824027, 'f1-score': 0.8060254201323067, 'support': 5179811}, 'weighted avg': {'precision': 0.9994784368996982, 'recall': 0.9992295085670114, 'f1-score': 0.9993288517731452, 'support': 5179811}}
0.0025	3.9062	2500	0.0021	0.9994	0.9993	0.9993	0.9993	{'DebtInstrumentBasisSpreadOnVariableRate1': {'precision': 0.66721044045677, 'recall': 0.9263873159682899, 'f1-score': 0.7757230915125652, 'support': 3532}, 'DebtInstrumentInterestRateStatedPercentage': {'precision': 0.9998472649896363, 'recall': 0.9993495567961943, 'f1-score': 0.9995983489396741, 'support': 5174933}, 'LineOfCreditFacilityMaximumBorrowingCapacity': {'precision': 0.536096879366558, 'recall': 0.8551263001485884, 'f1-score': 0.659032350415116, 'support': 1346}, 'micro avg': {'precision': 0.999340079020614, 'recall': 0.9992623282973065, 'f1-score': 0.9993012021466097, 'support': 5179811}, 'macro avg': {'precision': 0.7343848616043215, 'recall': 0.9269543909710243, 'f1-score': 0.8114512636224518, 'support': 5179811}, 'weighted avg': {'precision': 0.9994999393278895, 'recall': 0.9992623282973065, 'f1-score': 0.9993571954992789, 'support': 5179811}}
0.0019	4.6875	3000	0.0022	0.9994	0.9994	0.9993	0.9994	{'DebtInstrumentBasisSpreadOnVariableRate1': {'precision': 0.7067191945721164, 'recall': 0.9142129105322764, 'f1-score': 0.7971855326502901, 'support': 3532}, 'DebtInstrumentInterestRateStatedPercentage': {'precision': 0.9998381887971357, 'recall': 0.999405789408288, 'f1-score': 0.9996219423427282, 'support': 5174933}, 'LineOfCreditFacilityMaximumBorrowingCapacity': {'precision': 0.5497431106959365, 'recall': 0.87444279346211, 'f1-score': 0.6750788643533123, 'support': 1346}, 'micro avg': {'precision': 0.9993935596849445, 'recall': 0.9993152259802529, 'f1-score': 0.9993543912975653, 'support': 5179811}, 'macro avg': {'precision': 0.7521001646883961, 'recall': 0.9293538311342248, 'f1-score': 0.8239621131154435, 'support': 5179811}, 'weighted avg': {'precision': 0.99952135788135, 'recall': 0.9993152259802529, 'f1-score': 0.9993995712210777, 'support': 5179811}}

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.20.3