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

Loss: 0.1165
Precision: 0.9468
Recall: 0.9626
F1: 0.9546
Accuracy: 0.9763

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.3684	1.0	612	0.1093	0.9356	0.9523	0.9438	0.9708
0.1191	2.0	1224	0.1026	0.9388	0.9674	0.9529	0.9746
0.0842	3.0	1836	0.1011	0.9394	0.9690	0.9539	0.9754
0.0657	4.0	2448	0.0986	0.9468	0.9682	0.9574	0.9779
0.0437	5.0	3060	0.0988	0.9499	0.9649	0.9573	0.9772
0.0395	6.0	3672	0.1070	0.9446	0.9645	0.9545	0.9757
0.0311	7.0	4284	0.1110	0.9459	0.9673	0.9565	0.9766
0.0302	8.0	4896	0.1141	0.9449	0.9635	0.9541	0.9763
0.023	9.0	5508	0.1133	0.9485	0.9641	0.9563	0.9770
0.0198	10.0	6120	0.1165	0.9468	0.9626	0.9546	0.9763

Framework versions

Transformers 4.45.1
Pytorch 2.4.0
Datasets 3.0.1
Tokenizers 0.20.0

Criser2013/NER-finetuning-BETO-UNCASED-BIOBERT

NER-finetuning-BETO-UNCASED-BIOBERT

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Criser2013/
NER-finetuning-BETO-UNCASED-BIOBERT