README.md

metadata

license: cc-by-nc-4.0
tags:
  - generated_from_trainer
model-index:
  - name: ner-roberta-es-clinical-trials-ner
    results: []

ner-roberta-es-clinical-trials-ner

This model is a fine-tuned version of lcampillos/roberta-es-clinical-trials-ner on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2811
• Body Part Precision: 0.6861
• Body Part Recall: 0.7766
• Body Part F1: 0.7286
• Body Part Number: 197
• Disease Precision: 0.7476
• Disease Recall: 0.7505
• Disease F1: 0.7490
• Disease Number: 521
• Family Member Precision: 0.8462
• Family Member Recall: 0.8462
• Family Member F1: 0.8462
• Family Member Number: 13
• Medication Precision: 0.8158
• Medication Recall: 0.8378
• Medication F1: 0.8267
• Medication Number: 37
• Procedure Precision: 0.6282
• Procedure Recall: 0.7313
• Procedure F1: 0.6759
• Procedure Number: 134
• Overall Precision: 0.7177
• Overall Recall: 0.7583
• Overall F1: 0.7375
• Overall Accuracy: 0.9174

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: 13
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Body Part Precision	Body Part Recall	Body Part F1	Body Part Number	Disease Precision	Disease Recall	Disease F1	Disease Number	Family Member Precision	Family Member Recall	Family Member F1	Family Member Number	Medication Precision	Medication Recall	Medication F1	Medication Number	Procedure Precision	Procedure Recall	Procedure F1	Procedure Number	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.3951	1.0	502	0.2831	0.6697	0.7513	0.7081	197	0.7314	0.7370	0.7342	521	1.0	0.8462	0.9167	13	0.625	0.6757	0.6494	37	0.5556	0.6716	0.6081	134	0.6861	0.7295	0.7071	0.9144
0.2123	2.0	1004	0.2912	0.6623	0.7665	0.7106	197	0.7389	0.7332	0.7360	521	0.7857	0.8462	0.8148	13	0.675	0.7297	0.7013	37	0.6289	0.7463	0.6826	134	0.7004	0.7439	0.7215	0.9132
0.1686	3.0	1506	0.2811	0.6861	0.7766	0.7286	197	0.7476	0.7505	0.7490	521	0.8462	0.8462	0.8462	13	0.8158	0.8378	0.8267	37	0.6282	0.7313	0.6759	134	0.7177	0.7583	0.7375	0.9174

Framework versions

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