--- base_model: dmis-lab/biobert-v1.1 tags: - generated_from_trainer model-index: - name: pretoxtm-ner results: [] --- # pretoxtm-ner This model is a fine-tuned version of [dmis-lab/biobert-v1.1](https://huggingface.co/dmis-lab/biobert-v1.1) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1810 - Study Test: {'precision': 0.8215384615384616, 'recall': 0.8841059602649006, 'f1': 0.8516746411483254, 'number': 302} - Manifestation: {'precision': 0.8041958041958042, 'recall': 0.905511811023622, 'f1': 0.8518518518518519, 'number': 127} - Finding: {'precision': 0.6886657101865137, 'recall': 0.7570977917981072, 'f1': 0.7212622088655146, 'number': 634} - Specimen: {'precision': 0.7944162436548223, 'recall': 0.8236842105263158, 'f1': 0.8087855297157622, 'number': 380} - Dose: {'precision': 0.8647540983606558, 'recall': 0.9461883408071748, 'f1': 0.9036402569593148, 'number': 223} - Dose Qualification: {'precision': 0.65, 'recall': 0.8125, 'f1': 0.7222222222222223, 'number': 32} - Sex: {'precision': 0.9285714285714286, 'recall': 0.9285714285714286, 'f1': 0.9285714285714286, 'number': 84} - Group: {'precision': 0.5666666666666667, 'recall': 0.6938775510204082, 'f1': 0.6238532110091742, 'number': 49} ## 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 - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | Study Test | Manifestation | Finding | Specimen | Dose | Dose Qualification | Sex | Group | |:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:| | No log | 1.0 | 257 | 0.2005 | {'precision': 0.6658227848101266, 'recall': 0.8708609271523179, 'f1': 0.7546628407460545, 'number': 302} | {'precision': 0.7647058823529411, 'recall': 0.9212598425196851, 'f1': 0.8357142857142856, 'number': 127} | {'precision': 0.6425339366515838, 'recall': 0.6719242902208202, 'f1': 0.6569005397070162, 'number': 634} | {'precision': 0.7099767981438515, 'recall': 0.8052631578947368, 'f1': 0.75462392108508, 'number': 380} | {'precision': 0.8969957081545065, 'recall': 0.9372197309417041, 'f1': 0.9166666666666667, 'number': 223} | {'precision': 0.6764705882352942, 'recall': 0.71875, 'f1': 0.696969696969697, 'number': 32} | {'precision': 0.7448979591836735, 'recall': 0.8690476190476191, 'f1': 0.8021978021978022, 'number': 84} | {'precision': 0.3880597014925373, 'recall': 0.5306122448979592, 'f1': 0.4482758620689655, 'number': 49} | | 0.2932 | 2.0 | 514 | 0.1689 | {'precision': 0.8170347003154574, 'recall': 0.8576158940397351, 'f1': 0.8368336025848143, 'number': 302} | {'precision': 0.8226950354609929, 'recall': 0.9133858267716536, 'f1': 0.8656716417910448, 'number': 127} | {'precision': 0.6904400606980273, 'recall': 0.7176656151419558, 'f1': 0.7037896365042536, 'number': 634} | {'precision': 0.7746478873239436, 'recall': 0.868421052631579, 'f1': 0.8188585607940446, 'number': 380} | {'precision': 0.8870292887029289, 'recall': 0.9506726457399103, 'f1': 0.9177489177489178, 'number': 223} | {'precision': 0.7567567567567568, 'recall': 0.875, 'f1': 0.8115942028985507, 'number': 32} | {'precision': 0.8695652173913043, 'recall': 0.9523809523809523, 'f1': 0.909090909090909, 'number': 84} | {'precision': 0.6, 'recall': 0.673469387755102, 'f1': 0.6346153846153846, 'number': 49} | | 0.2932 | 3.0 | 771 | 0.1810 | {'precision': 0.8215384615384616, 'recall': 0.8841059602649006, 'f1': 0.8516746411483254, 'number': 302} | {'precision': 0.8041958041958042, 'recall': 0.905511811023622, 'f1': 0.8518518518518519, 'number': 127} | {'precision': 0.6886657101865137, 'recall': 0.7570977917981072, 'f1': 0.7212622088655146, 'number': 634} | {'precision': 0.7944162436548223, 'recall': 0.8236842105263158, 'f1': 0.8087855297157622, 'number': 380} | {'precision': 0.8647540983606558, 'recall': 0.9461883408071748, 'f1': 0.9036402569593148, 'number': 223} | {'precision': 0.65, 'recall': 0.8125, 'f1': 0.7222222222222223, 'number': 32} | {'precision': 0.9285714285714286, 'recall': 0.9285714285714286, 'f1': 0.9285714285714286, 'number': 84} | {'precision': 0.5666666666666667, 'recall': 0.6938775510204082, 'f1': 0.6238532110091742, 'number': 49} | ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2