clinicalbert-medical-doc-classifier

This model is a fine-tuned version of emilyalsentzer/Bio_ClinicalBERT on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0252
• Accuracy: 0.9953
• F1: 0.9948

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: 2e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.1238	0.1582	100	0.1158	0.9757	0.9679
0.0966	0.3165	200	0.0470	0.9924	0.9912
0.0269	0.4747	300	0.0364	0.9942	0.9931
0.0178	0.6329	400	0.0336	0.9947	0.9935
0.0428	0.7911	500	0.0327	0.9940	0.9933
0.0062	0.9494	600	0.0296	0.9949	0.9937
0.0370	1.1076	700	0.0262	0.9947	0.9935
0.0201	1.2658	800	0.0279	0.9947	0.9935
0.0231	1.4241	900	0.0252	0.9953	0.9948
0.0193	1.5823	1000	0.0249	0.9953	0.9942
0.0189	1.7405	1100	0.0263	0.9951	0.9941
0.0201	1.8987	1200	0.0256	0.9953	0.9947

Framework versions

• Transformers 5.4.0
• Pytorch 2.11.0+cu130
• Datasets 4.8.4
• Tokenizers 0.22.2