You can deploy this model and start earning money today!

alecocc/
modernbert-en-disease-10epochs-v1

Name: modernbert-en-disease-10epochs-v1
Availability: InStock

Views

No views yet

modernbert-en-disease-10epochs-v1

This model is a fine-tuned version of thomas-sounack/BioClinical-ModernBERT-base on the None dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 16
seed: 42
optimizer: Use 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_ratio: 0.1
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
0.1616	1.0	142	0.1914	0.5316	0.4216	0.4703
0.112	2.0	284	0.1102	0.6430	0.6691	0.6558
0.0758	3.0	426	0.1145	0.6584	0.6730	0.6656
0.0562	4.0	568	0.1226	0.6536	0.7041	0.6779
0.0343	5.0	710	0.1612	0.6669	0.6826	0.6747
0.0161	6.0	852	0.1856	0.6415	0.6933	0.6664
0.0074	7.0	994	0.2095	0.6350	0.6802	0.6568
0.0035	8.0	1136	0.2432	0.6399	0.6722	0.6557
0.0013	9.0	1278	0.2595	0.6389	0.6762	0.6570
0.0013	10.0	1420	0.2621	0.6401	0.6770	0.6580