StivenLancheros/mBERT-base-Biomedical-NER

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

bert-base-multilingual-cased-finetuned-ner-4

#This model is part of a test for creating multilingual BioMedical NER systems. Not intended for proffesional use now.

This model is a fine-tuned version of bert-base-multilingual-cased on the CRAFT+BC4CHEMD+BioNLP09 datasets concatenated. It achieves the following results on the evaluation set:

• —Loss: 0.1027
• —Precision: 0.9830
• —Recall: 0.9832
• —F1: 0.9831
• —Accuracy: 0.9799

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: 3e-05
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —num_epochs: 4

Training results

Framework versions

• —Transformers 4.16.2
• —Pytorch 1.10.0+cu111
• —Datasets 1.18.3
• —Tokenizers 0.11.0