BioClinical-ModernBERT-base-Symptom2Disease_WITH-DROPOUT-123

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: 0.5898
• Accuracy: 0.9091

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: 3.545567008526446e-05
• train_batch_size: 128
• eval_batch_size: 16
• seed: 123
• 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
1.5403	1.0	3	1.3962	0.25
1.3735	2.0	6	1.3257	0.3864
1.1936	3.0	9	0.8816	0.8864
1.0227	4.0	12	0.7373	0.9318
0.9199	5.0	15	0.6575	0.9318
0.814	6.0	18	0.6167	0.9091
0.7644	7.0	21	0.5945	0.9091
0.7449	8.0	24	0.5898	0.9091

Framework versions

• Transformers 4.56.2
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1