README.md

metadata

library_name: transformers
base_model: dmis-lab/biobert-base-cased-v1.1
tags:
  - generated_from_trainer
model-index:
  - name: biobert-ner-model
    results: []

biobert-ner-model

This model is a fine-tuned version of dmis-lab/biobert-base-cased-v1.1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0386
• Compositemention: {'precision': 0.8, 'recall': 0.9142857142857143, 'f1': 0.8533333333333333, 'number': 35}
• Diseaseclass: {'precision': 0.5341614906832298, 'recall': 0.6825396825396826, 'f1': 0.5993031358885017, 'number': 126}
• Modifier: {'precision': 0.7014925373134329, 'recall': 0.8785046728971962, 'f1': 0.7800829875518672, 'number': 214}
• Specificdisease: {'precision': 0.8254716981132075, 'recall': 0.8495145631067961, 'f1': 0.8373205741626795, 'number': 412}
• Overall Precision: 0.7346
• Overall Recall: 0.8335
• Overall F1: 0.7810
• Overall Accuracy: 0.9934

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: 3e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Compositemention	Diseaseclass	Modifier	Specificdisease	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.005	1.0	359	0.0271	{'precision': 0.725, 'recall': 0.8285714285714286, 'f1': 0.7733333333333333, 'number': 35}	{'precision': 0.5263157894736842, 'recall': 0.7142857142857143, 'f1': 0.6060606060606061, 'number': 126}	{'precision': 0.7198443579766537, 'recall': 0.8644859813084113, 'f1': 0.7855626326963906, 'number': 214}	{'precision': 0.8103448275862069, 'recall': 0.7985436893203883, 'f1': 0.80440097799511, 'number': 412}	0.7243	0.8043	0.7622	0.9939
0.0049	2.0	718	0.0277	{'precision': 0.775, 'recall': 0.8857142857142857, 'f1': 0.8266666666666667, 'number': 35}	{'precision': 0.5891472868217055, 'recall': 0.6031746031746031, 'f1': 0.596078431372549, 'number': 126}	{'precision': 0.7195121951219512, 'recall': 0.8271028037383178, 'f1': 0.7695652173913042, 'number': 214}	{'precision': 0.7707423580786026, 'recall': 0.8567961165048543, 'f1': 0.8114942528735631, 'number': 412}	0.7297	0.8094	0.7675	0.9934
0.0031	3.0	1077	0.0330	{'precision': 0.7142857142857143, 'recall': 0.8571428571428571, 'f1': 0.7792207792207793, 'number': 35}	{'precision': 0.4939759036144578, 'recall': 0.6507936507936508, 'f1': 0.5616438356164383, 'number': 126}	{'precision': 0.7368421052631579, 'recall': 0.8504672897196262, 'f1': 0.789587852494577, 'number': 214}	{'precision': 0.8076923076923077, 'recall': 0.866504854368932, 'f1': 0.8360655737704917, 'number': 412}	0.7258	0.8272	0.7732	0.9935
0.0008	4.0	1436	0.0324	{'precision': 0.7567567567567568, 'recall': 0.8, 'f1': 0.7777777777777778, 'number': 35}	{'precision': 0.6014492753623188, 'recall': 0.6587301587301587, 'f1': 0.6287878787878789, 'number': 126}	{'precision': 0.746938775510204, 'recall': 0.8551401869158879, 'f1': 0.7973856209150327, 'number': 214}	{'precision': 0.8389423076923077, 'recall': 0.8470873786407767, 'f1': 0.8429951690821257, 'number': 412}	0.7691	0.8170	0.7924	0.9940
0.0019	5.0	1795	0.0314	{'precision': 0.7804878048780488, 'recall': 0.9142857142857143, 'f1': 0.8421052631578947, 'number': 35}	{'precision': 0.6356589147286822, 'recall': 0.6507936507936508, 'f1': 0.6431372549019608, 'number': 126}	{'precision': 0.7615062761506276, 'recall': 0.8504672897196262, 'f1': 0.8035320088300221, 'number': 214}	{'precision': 0.8148148148148148, 'recall': 0.8543689320388349, 'f1': 0.8341232227488151, 'number': 412}	0.7705	0.8234	0.7961	0.9939
0.0017	6.0	2154	0.0386	{'precision': 0.8, 'recall': 0.9142857142857143, 'f1': 0.8533333333333333, 'number': 35}	{'precision': 0.5341614906832298, 'recall': 0.6825396825396826, 'f1': 0.5993031358885017, 'number': 126}	{'precision': 0.7014925373134329, 'recall': 0.8785046728971962, 'f1': 0.7800829875518672, 'number': 214}	{'precision': 0.8254716981132075, 'recall': 0.8495145631067961, 'f1': 0.8373205741626795, 'number': 412}	0.7346	0.8335	0.7810	0.9934

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1