This model is a fine-tuned version of dccuchile/bert-base-spanish-wwm-cased on the biobert_json dataset. It achieves the following results on the evaluation set:

Loss: 0.1258
Precision: 0.9472
Recall: 0.9603
F1: 0.9537
Accuracy: 0.9762

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 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.3733	1.0	612	0.1142	0.9382	0.9514	0.9447	0.9716
0.1116	2.0	1224	0.1143	0.9281	0.9695	0.9484	0.9725
0.079	3.0	1836	0.1006	0.9448	0.9699	0.9572	0.9778
0.0597	4.0	2448	0.1045	0.9501	0.9647	0.9574	0.9774
0.0422	5.0	3060	0.1064	0.9500	0.9635	0.9567	0.9764
0.0367	6.0	3672	0.1153	0.9430	0.9626	0.9527	0.9746
0.029	7.0	4284	0.1155	0.9457	0.9595	0.9526	0.9755
0.0294	8.0	4896	0.1221	0.9448	0.9628	0.9537	0.9761
0.0222	9.0	5508	0.1222	0.9483	0.9612	0.9547	0.9765
0.02	10.0	6120	0.1258	0.9472	0.9603	0.9537	0.9762

Framework versions

Transformers 4.46.2
Pytorch 2.5.1+cu121
Datasets 3.1.0
Tokenizers 0.20.3

stivenacua17/beto-biobert

beto-biobert

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

stivenacua17/
beto-biobert