BioClinical-ModernBERT-base-Symptom2Disease_WITHOUT-DROPOUT-42

This model is a fine-tuned version of thomas-sounack/BioClinical-ModernBERT-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4506
• Accuracy: 0.9773

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: 4.718960201365898e-05
• train_batch_size: 128
• eval_batch_size: 16
• 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: cosine
• lr_scheduler_warmup_steps: 2
• num_epochs: 8
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.4612	1.0	3	1.1750	0.6136
0.9587	2.0	6	0.6861	0.9091
0.5401	3.0	9	0.5511	0.9318
0.4878	4.0	12	0.4981	0.9545
0.44	5.0	15	0.5102	0.9091
0.4054	6.0	18	0.4674	0.9545
0.3942	7.0	21	0.4526	0.9773
0.3903	8.0	24	0.4506	0.9773

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.0