--- library_name: transformers language: - eng license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer metrics: - accuracy - precision - recall - f1 model-index: - name: finer_ner_finetuning results: [] --- # finer_ner_finetuning This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/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: 0.9992 - Recall: 0.9991 - F1: 0.9991 - Classification Report: precision recall f1-score support DebtInstrumentBasisSpreadOnVariableRate1 0.63 0.92 0.75 3532 DebtInstrumentInterestRateStatedPercentage 1.00 1.00 1.00 5174933 LineOfCreditFacilityMaximumBorrowingCapacity 0.43 0.89 0.58 1346 micro avg 1.00 1.00 1.00 5179811 macro avg 0.69 0.94 0.78 5179811 weighted avg 1.00 1.00 1.00 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 | |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| | 0.0097 | 1.3514 | 500 | 0.0026 | 0.9991 | 0.9991 | 0.9990 | 0.9991 | precision recall f1-score support DebtInstrumentBasisSpreadOnVariableRate1 0.57 0.89 0.70 3532 DebtInstrumentInterestRateStatedPercentage 1.00 1.00 1.00 5174933 LineOfCreditFacilityMaximumBorrowingCapacity 0.45 0.79 0.57 1346 micro avg 1.00 1.00 1.00 5179811 macro avg 0.67 0.89 0.76 5179811 weighted avg 1.00 1.00 1.00 5179811 | | 0.0064 | 2.7027 | 1000 | 0.0026 | 0.9991 | 0.9991 | 0.9990 | 0.9990 | precision recall f1-score support DebtInstrumentBasisSpreadOnVariableRate1 0.59 0.92 0.72 3532 DebtInstrumentInterestRateStatedPercentage 1.00 1.00 1.00 5174933 LineOfCreditFacilityMaximumBorrowingCapacity 0.42 0.85 0.57 1346 micro avg 1.00 1.00 1.00 5179811 macro avg 0.67 0.92 0.76 5179811 weighted avg 1.00 1.00 1.00 5179811 | | 0.0044 | 4.0541 | 1500 | 0.0027 | 0.9992 | 0.9992 | 0.9991 | 0.9991 | precision recall f1-score support DebtInstrumentBasisSpreadOnVariableRate1 0.63 0.92 0.75 3532 DebtInstrumentInterestRateStatedPercentage 1.00 1.00 1.00 5174933 LineOfCreditFacilityMaximumBorrowingCapacity 0.43 0.89 0.58 1346 micro avg 1.00 1.00 1.00 5179811 macro avg 0.69 0.94 0.78 5179811 weighted avg 1.00 1.00 1.00 5179811 | ### Framework versions - Transformers 4.46.3 - Pytorch 2.5.1+cu124 - Datasets 3.2.0 - Tokenizers 0.20.3