jpherrerap/ner-roberta-es-clinical-trials-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. -->

ner-roberta-es-clinical-trials-ner

This model is a fine-tuned version of lcampillos/roberta-es-clinical-trials-ner on the jpherrerap/competencia2 dataset. It achieves the following results on the evaluation set:

• —Loss: 0.2661
• —Body Part Precision: 0.7124
• —Body Part Recall: 0.8173
• —Body Part F1: 0.7612
• —Body Part Number: 197
• —Disease Precision: 0.7712
• —Disease Recall: 0.7697
• —Disease F1: 0.7704
• —Disease Number: 521
• —Family Member Precision: 0.8462
• —Family Member Recall: 0.8462
• —Family Member F1: 0.8462
• —Family Member Number: 13
• —Medication Precision: 0.8378
• —Medication Recall: 0.8378
• —Medication F1: 0.8378
• —Medication Number: 37
• —Procedure Precision: 0.6510
• —Procedure Recall: 0.7239
• —Procedure F1: 0.6855
• —Procedure Number: 134
• —Overall Precision: 0.7418
• —Overall Recall: 0.7772
• —Overall F1: 0.7591
• —Overall Accuracy: 0.9238

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
• —trainbatchsize: 16
• —evalbatchsize: 16
• —seed: 13
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —num_epochs: 2

Training results

Framework versions

• —Transformers 4.30.2
• —Pytorch 2.0.1+cu118
• —Datasets 2.13.1
• —Tokenizers 0.13.3