med-bert

NOTE: THE DATASET USED WAS JUST 31 ROWS AND HENCE THE MODEL DIDN'T ACHIEVE GOOD RESULTS. SPACY WAS ABLE TO PERFORM BETTER DUE TO LESS COMPLEXITY IN THE MODEL.

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.9379
• Precision: 0.0128
• Recall: 0.0794
• F1: 0.0221
• Accuracy: 0.1707
• All Metrics: {'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.03125, 'recall': 0.1875, 'f1': 0.05357142857142857, 'number': 16}, 'overall_precision': 0.01282051282051282, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02207505518763797, 'overall_accuracy': 0.17066290550070523}

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: 1e-08
• 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy	All Metrics
No log	1.0	3	1.9408	0.0128	0.0794	0.0220	0.1693	{'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.030927835051546393, 'recall': 0.1875, 'f1': 0.05309734513274336, 'number': 16}, 'overall_precision': 0.01278772378516624, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02202643171806167, 'overall_accuracy': 0.1692524682651622}
No log	2.0	6	1.9405	0.0128	0.0794	0.0220	0.1693	{'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.030927835051546393, 'recall': 0.1875, 'f1': 0.05309734513274336, 'number': 16}, 'overall_precision': 0.01278772378516624, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02202643171806167, 'overall_accuracy': 0.1692524682651622}
No log	3.0	9	1.9402	0.0128	0.0794	0.0220	0.1693	{'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.030927835051546393, 'recall': 0.1875, 'f1': 0.05309734513274336, 'number': 16}, 'overall_precision': 0.01278772378516624, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02202643171806167, 'overall_accuracy': 0.1692524682651622}
No log	4.0	12	1.9400	0.0128	0.0794	0.0220	0.1693	{'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.030927835051546393, 'recall': 0.1875, 'f1': 0.05309734513274336, 'number': 16}, 'overall_precision': 0.01278772378516624, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02202643171806167, 'overall_accuracy': 0.1692524682651622}
No log	5.0	15	1.9397	0.0128	0.0794	0.0220	0.1693	{'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.030927835051546393, 'recall': 0.1875, 'f1': 0.05309734513274336, 'number': 16}, 'overall_precision': 0.01278772378516624, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02202643171806167, 'overall_accuracy': 0.1692524682651622}
No log	6.0	18	1.9395	0.0128	0.0794	0.0220	0.1693	{'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.030927835051546393, 'recall': 0.1875, 'f1': 0.05309734513274336, 'number': 16}, 'overall_precision': 0.01278772378516624, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02202643171806167, 'overall_accuracy': 0.1692524682651622}
No log	7.0	21	1.9392	0.0128	0.0794	0.0220	0.1693	{'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.030927835051546393, 'recall': 0.1875, 'f1': 0.05309734513274336, 'number': 16}, 'overall_precision': 0.01278772378516624, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02202643171806167, 'overall_accuracy': 0.1692524682651622}
No log	8.0	24	1.9390	0.0128	0.0794	0.0221	0.1707	{'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.03125, 'recall': 0.1875, 'f1': 0.05357142857142857, 'number': 16}, 'overall_precision': 0.01282051282051282, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02207505518763797, 'overall_accuracy': 0.17066290550070523}
No log	9.0	27	1.9388	0.0128	0.0794	0.0221	0.1707	{'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.03125, 'recall': 0.1875, 'f1': 0.05357142857142857, 'number': 16}, 'overall_precision': 0.01282051282051282, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02207505518763797, 'overall_accuracy': 0.17066290550070523}
No log	10.0	30	1.9387	0.0128	0.0794	0.0221	0.1707	{'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.03125, 'recall': 0.1875, 'f1': 0.05357142857142857, 'number': 16}, 'overall_precision': 0.01282051282051282, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02207505518763797, 'overall_accuracy': 0.17066290550070523}
No log	11.0	33	1.9385	0.0128	0.0794	0.0221	0.1707	{'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.03125, 'recall': 0.1875, 'f1': 0.05357142857142857, 'number': 16}, 'overall_precision': 0.01282051282051282, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02207505518763797, 'overall_accuracy': 0.17066290550070523}
No log	12.0	36	1.9384	0.0128	0.0794	0.0221	0.1707	{'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.03125, 'recall': 0.1875, 'f1': 0.05357142857142857, 'number': 16}, 'overall_precision': 0.01282051282051282, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02207505518763797, 'overall_accuracy': 0.17066290550070523}
No log	13.0	39	1.9383	0.0128	0.0794	0.0221	0.1707	{'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.03125, 'recall': 0.1875, 'f1': 0.05357142857142857, 'number': 16}, 'overall_precision': 0.01282051282051282, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02207505518763797, 'overall_accuracy': 0.17066290550070523}
No log	14.0	42	1.9382	0.0128	0.0794	0.0221	0.1707	{'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.03125, 'recall': 0.1875, 'f1': 0.05357142857142857, 'number': 16}, 'overall_precision': 0.01282051282051282, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02207505518763797, 'overall_accuracy': 0.17066290550070523}
No log	15.0	45	1.9381	0.0128	0.0794	0.0221	0.1707	{'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.03125, 'recall': 0.1875, 'f1': 0.05357142857142857, 'number': 16}, 'overall_precision': 0.01282051282051282, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02207505518763797, 'overall_accuracy': 0.17066290550070523}
No log	16.0	48	1.9380	0.0128	0.0794	0.0221	0.1707	{'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.03125, 'recall': 0.1875, 'f1': 0.05357142857142857, 'number': 16}, 'overall_precision': 0.01282051282051282, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02207505518763797, 'overall_accuracy': 0.17066290550070523}
No log	17.0	51	1.9380	0.0128	0.0794	0.0221	0.1707	{'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.03125, 'recall': 0.1875, 'f1': 0.05357142857142857, 'number': 16}, 'overall_precision': 0.01282051282051282, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02207505518763797, 'overall_accuracy': 0.17066290550070523}
No log	18.0	54	1.9379	0.0128	0.0794	0.0221	0.1707	{'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.03125, 'recall': 0.1875, 'f1': 0.05357142857142857, 'number': 16}, 'overall_precision': 0.01282051282051282, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02207505518763797, 'overall_accuracy': 0.17066290550070523}
No log	19.0	57	1.9379	0.0128	0.0794	0.0221	0.1707	{'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.03125, 'recall': 0.1875, 'f1': 0.05357142857142857, 'number': 16}, 'overall_precision': 0.01282051282051282, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02207505518763797, 'overall_accuracy': 0.17066290550070523}
No log	20.0	60	1.9379	0.0128	0.0794	0.0221	0.1707	{'MedicalCondition': {'precision': 0.011428571428571429, 'recall': 0.05714285714285714, 'f1': 0.019047619047619046, 'number': 35}, 'Medicine': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}, 'Pathogen': {'precision': 0.03125, 'recall': 0.1875, 'f1': 0.05357142857142857, 'number': 16}, 'overall_precision': 0.01282051282051282, 'overall_recall': 0.07936507936507936, 'overall_f1': 0.02207505518763797, 'overall_accuracy': 0.17066290550070523}

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0