You can deploy this model and start earning money today!

alexd063/
bio-clinicalbert-finetuned-medmentions

Name: bio-clinicalbert-finetuned-medmentions
Availability: InStock

generated_from_trainer

emilyalsentzer/Bio_ClinicalBERT

finetune

mit

endpoints_compatible

Views

No views yet

bio-clinicalbert-finetuned-medmentions

This model is a fine-tuned version of emilyalsentzer/Bio_ClinicalBERT on the Ben10x/MedMentions-MTI881-NER dataset. It achieves the following results on the evaluation set:

Loss: 0.6913
Precision: 0.631
Recall: 0.673
F1: 0.652
Accuracy: 0.886

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: 16
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: 0.1
num_epochs: 20
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.9448	1.0	1463	0.6638	0.438	0.407	0.422	0.821
0.5448	2.0	2926	0.5070	0.515	0.547	0.531	0.845
0.4231	3.0	4389	0.4480	0.562	0.564	0.563	0.86
0.3301	4.0	5852	0.4261	0.578	0.604	0.591	0.866
0.2689	5.0	7315	0.4284	0.606	0.604	0.605	0.872
0.2147	6.0	8778	0.4410	0.607	0.632	0.62	0.875
0.1667	7.0	10241	0.4644	0.613	0.618	0.616	0.876
0.1304	8.0	11704	0.4982	0.61	0.646	0.627	0.878
0.1055	9.0	13167	0.5311	0.617	0.645	0.631	0.877
0.0826	10.0	14630	0.5643	0.629	0.64	0.635	0.88
0.0665	11.0	16093	0.5907	0.616	0.657	0.636	0.879
0.0537	12.0	17556	0.6218	0.629	0.653	0.64	0.882
0.0445	13.0	19019	0.6575	0.615	0.665	0.639	0.88
0.0375	14.0	20482	0.6699	0.621	0.66	0.64	0.881
0.0323	15.0	21945	0.6914	0.626	0.664	0.645	0.882
0.0275	16.0	23408	0.7028	0.628	0.665	0.646	0.882
0.0265	17.0	24871	0.7139	0.628	0.663	0.645	0.883
0.0242	18.0	26334	0.7184	0.629	0.662	0.645	0.882
0.0220	19.0	27797	0.7228	0.627	0.664	0.645	0.882

Framework versions

Transformers 5.8.1
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

alexd063/bio-clinicalbert-finetuned-medmentions

bio-clinicalbert-finetuned-medmentions

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

alexd063/
bio-clinicalbert-finetuned-medmentions