COMPner-bert-base-spanish-wwm-cased

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

• Loss: 0.2793
• Body Part Precision: 0.6700
• Body Part Recall: 0.7186
• Body Part F1: 0.6934
• Body Part Number: 565
• Disease Precision: 0.6966
• Disease Recall: 0.7533
• Disease F1: 0.7238
• Disease Number: 1350
• Family Member Precision: 0.9
• Family Member Recall: 0.75
• Family Member F1: 0.8182
• Family Member Number: 24
• Medication Precision: 0.7143
• Medication Recall: 0.6190
• Medication F1: 0.6633
• Medication Number: 105
• Procedure Precision: 0.5233
• Procedure Recall: 0.5125
• Procedure F1: 0.5178
• Procedure Number: 439
• Overall Precision: 0.6640
• Overall Recall: 0.6971
• Overall F1: 0.6802
• Overall Accuracy: 0.9136

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: 8
• eval_batch_size: 8
• seed: 13
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

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
0.4741	1.0	703	0.2932	0.6449	0.6301	0.6374	565	0.6984	0.7170	0.7076	1350	0.9412	0.6667	0.7805	24	0.8551	0.5619	0.6782	105	0.5113	0.3599	0.4225	439	0.6674	0.6271	0.6466	0.9091
0.259	2.0	1406	0.2793	0.6700	0.7186	0.6934	565	0.6966	0.7533	0.7238	1350	0.9	0.75	0.8182	24	0.7143	0.6190	0.6633	105	0.5233	0.5125	0.5178	439	0.6640	0.6971	0.6802	0.9136

Framework versions

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