This model is a fine-tuned version of dmis-lab/biobert-base-cased-v1.1 on the ncbi_disease dataset. It achieves the following results on the evaluation set:

Loss: 0.0892
F1: 0.8376

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: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.9562	1.0	170	0.5053	0.0
0.3057	2.0	340	0.1515	0.4819
0.14	3.0	510	0.0960	0.6639
0.0865	4.0	680	0.0761	0.7515
0.0575	5.0	850	0.0725	0.7722
0.0418	6.0	1020	0.0730	0.7808
0.0297	7.0	1190	0.0741	0.8132
0.0211	8.0	1360	0.0745	0.8211
0.014	9.0	1530	0.0881	0.8285
0.0111	10.0	1700	0.0892	0.8376

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1

filippo-baglini/biobert_finetuned_ncbi_disease

biobert_finetuned_ncbi_disease

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

filippo-baglini/
biobert_finetuned_ncbi_disease