BERT-full-finetuned-ner-pablo – AI Model by pabRomero | AlphaNeural AI

You can deploy this model and start earning money today!

pabRomero/
BERT-full-finetuned-ner-pablo

like

0

token-classification

generated_from_trainer

google-bert/bert-base-uncased

autotrain_compatible

endpoints_compatible

Views

No views yet

BERT-full-finetuned-ner-pablo

This model is a fine-tuned version of google-bert/bert-base-uncased on the n2c2 2018 dataset for the paper https://arxiv.org/abs/2409.19467. It achieves the following results on the evaluation set:

Loss: 0.0854
Precision: 0.7857
Recall: 0.7899
F1: 0.7878
Accuracy: 0.9747

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 4
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	231	0.1015	0.7485	0.7440	0.7462	0.9703
No log	2.0	462	0.0878	0.7618	0.7750	0.7684	0.9728
0.2646	3.0	693	0.0859	0.7759	0.7912	0.7835	0.9737
0.2646	4.0	924	0.0854	0.7857	0.7899	0.7878	0.9747

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 2.21.0
Tokenizers 0.19.1