my-symptom-checker-biobert

This model is a fine-tuned version of emilyalsentzer/Bio_ClinicalBERT on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1376

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: 32
• eval_batch_size: 32
• 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: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	30	2.9013
No log	2.0	60	2.4887
No log	3.0	90	2.0553
No log	4.0	120	1.6494
No log	5.0	150	1.3190
No log	6.0	180	1.0499
No log	7.0	210	0.8211
No log	8.0	240	0.6230
No log	9.0	270	0.4702
No log	10.0	300	0.3656
No log	11.0	330	0.2884
No log	12.0	360	0.2331
No log	13.0	390	0.1986
No log	14.0	420	0.1808
No log	15.0	450	0.1630
No log	16.0	480	0.1546
0.9873	17.0	510	0.1469
0.9873	18.0	540	0.1409
0.9873	19.0	570	0.1378
0.9873	20.0	600	0.1376

Framework versions

• Transformers 4.57.1
• Pytorch 2.9.1+cu128
• Datasets 4.4.1
• Tokenizers 0.22.1