DISO_bsc_test16

This model is a fine-tuned version of PlanTL-GOB-ES/bsc-bio-ehr-es on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1732
• Diso Precision: 0.7577
• Diso Recall: 0.7757
• Diso F1: 0.7666
• Diso Number: 4552
• Overall Precision: 0.7577
• Overall Recall: 0.7757
• Overall F1: 0.7666
• Overall Accuracy: 0.9732

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: 8e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Diso Precision	Diso Recall	Diso F1	Diso Number	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.0948	1.0	1400	0.0766	0.7157	0.7594	0.7369	4552	0.7157	0.7594	0.7369	0.9710
0.0631	2.0	2800	0.0818	0.7442	0.7599	0.7520	4552	0.7442	0.7599	0.7520	0.9726
0.0454	3.0	4200	0.0842	0.7544	0.7654	0.7599	4552	0.7544	0.7654	0.7599	0.9728
0.0311	4.0	5600	0.1113	0.7678	0.7700	0.7689	4552	0.7678	0.7700	0.7689	0.9732
0.0217	5.0	7000	0.1231	0.7745	0.7687	0.7716	4552	0.7745	0.7687	0.7716	0.9743
0.015	6.0	8400	0.1482	0.7651	0.7733	0.7691	4552	0.7651	0.7733	0.7691	0.9735
0.0101	7.0	9800	0.1498	0.7576	0.7709	0.7642	4552	0.7576	0.7709	0.7642	0.9730
0.0073	8.0	11200	0.1732	0.7577	0.7757	0.7666	4552	0.7577	0.7757	0.7666	0.9732

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu116
• Datasets 2.8.0
• Tokenizers 0.13.2